Movatterモバイル変換


[0]ホーム

URL:


CN117611987B - Automatic identification method, device and medium for aquaculture sea - Google Patents

Automatic identification method, device and medium for aquaculture sea
Download PDF

Info

Publication number
CN117611987B
CN117611987BCN202311335706.9ACN202311335706ACN117611987BCN 117611987 BCN117611987 BCN 117611987BCN 202311335706 ACN202311335706 ACN 202311335706ACN 117611987 BCN117611987 BCN 117611987B
Authority
CN
China
Prior art keywords
image
convolution
cultivation
sea
label
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202311335706.9A
Other languages
Chinese (zh)
Other versions
CN117611987A (en
Inventor
谢威夷
芮小平
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hohai University HHU
Original Assignee
Hohai University HHU
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hohai University HHUfiledCriticalHohai University HHU
Priority to CN202311335706.9ApriorityCriticalpatent/CN117611987B/en
Publication of CN117611987ApublicationCriticalpatent/CN117611987A/en
Application grantedgrantedCritical
Publication of CN117611987BpublicationCriticalpatent/CN117611987B/en
Activelegal-statusCriticalCurrent
Anticipated expirationlegal-statusCritical

Links

Classifications

Landscapes

Abstract

Translated fromChinese

本发明公开了一种养殖用海自动识别方法、装置及介质,所述方法通过构建自动识别模型,所述构建自动识别模型中设计了金字塔型尺度感知卷积模块与通道‑空间注意力双关注模块,并进行集成,可以有效增加特征的利用能力,捕获影像更多的全局信息。以高分一号影像为例,对两个模块进行消融实验证明了改进方式的有效性,同时将本方法的预测结果与现有模型的预测结果以及传统的支持向量机、随机森林方法进行对比,结果表明,所提出的改进模型泛化能力更强、识别精度更高,在3个测试区域识别养殖用海的总体精度、平均交并比以及F1分数分别达到了94.86%、87.23%、96.59%,精度明显高于其他方法,证明了该方法对于养殖用海识别的有效性,可以为养殖用海自动化识别提供新的技术支撑。

The present invention discloses a method, device and medium for automatic identification of aquaculture seas. The method constructs an automatic identification model, wherein a pyramid scale-aware convolution module and a channel-space attention dual attention module are designed and integrated, which can effectively increase the utilization capability of features and capture more global information of images. Taking the Gaofen-1 image as an example, ablation experiments on the two modules prove the effectiveness of the improved method. At the same time, the prediction results of the method are compared with the prediction results of the existing model and the traditional support vector machine and random forest methods. The results show that the proposed improved model has stronger generalization ability and higher recognition accuracy. The overall accuracy, average intersection-over-union ratio and F1 score of identifying aquaculture seas in three test areas reached 94.86%, 87.23% and 96.59% respectively, and the accuracy is significantly higher than other methods, which proves the effectiveness of the method for identifying aquaculture seas and can provide new technical support for the automatic identification of aquaculture seas.

Description

Automatic identification method, device and medium for sea for cultivation
Technical Field
The invention belongs to the technical field of processing of remote sensing data of geographic satellites, and particularly relates to an automatic identification method, device and medium for a sea for cultivation.
Background
The culture sea is an area where aquaculture is performed in a marine water area such as ocean, river bay, and gulf or in the vicinity of a coastal zone. As an important component of the aquaculture industry, the aquaculture sea has important significance for enriching the diversity of human consumption and promoting the development of marine economy. In addition, the sea for cultivation can promote the development of ocean technology, promote the protection of the marine ecological environment and the sustainable development. Due to the flexibility of the cultivation industry, the area and the type of the cultivation sea can be changed every year, so that the timely, accurate and efficient cultivation sea identification is important for scientifically and reasonably utilizing the sea resources and protecting the sea environment.
The common remote sensing image information extraction methods include manual visual interpretation classification, an object-oriented classification method, a classification method based on pixels and a classification method based on deep learning. The artificial visual interpretation method is the most common method in remote sensing information extraction, and mainly relies on manpower to identify the ground features according to regional data and artificial experience and by combining the features and spatial correlations of the ground features on remote sensing images or in the field. He Qiuhua and the like are based on high-resolution second-number remote sensing images, and cage culture information of inland water areas in Hunan province is extracted by using a man-machine interaction visual interpretation method; ji Luyan, designing a new purse seine extraction algorithm combining spectrum and texture features, and accurately extracting the space-time distribution information of the purse seine region of the Yangcheng lake. However, most of the culture sea areas in China have wide range and large area, and the traditional manual field interpretation has low information acquisition speed, high cost and strong subjectivity.
The object-oriented classification method mainly sets a segmentation parameter according to image information, segments a remote sensing image to form a plurality of objects, and takes the objects as a minimum processing unit for classification. Xu Jingping and the like to segment the SPOT5 satellite remote sensing image in different scales, and the identification and extraction of the culture pond are realized by combining the spectrum, the shape and the semantic features; wang Fang and the like are combined with association rule classification and object-oriented methods, so that four cultivation modes of ponds, net cages, beaches and floating rafts in complex coastal zone areas are accurately identified; a summary of the method is supplemented. The culture sea in the northern Bay coastal zone of Guangxi in 2019 is extracted by combining a thresholding method and an object-oriented classification method based on Google EARTH ENGINE (GEE) platform and annual Sentinel-1 and Sentinel-2 time sequence remote sensing data. The object-oriented classification method has a certain limitation, the precision of the method is seriously dependent on the segmentation scale and parameters, but the optimal value is difficult to determine, and the method needs repeated adjustment.
The classification method based on the pixels refers to that the smallest processing unit is the pixels when the ground feature is identified and classified, and the pixels are distinguished and classified one by utilizing the spectrum information, texture information, spatial association and other information of the images, and the common methods include an exponential method and a machine learning supervision classification method. Duan et al uses a traditional machine learning decision tree method to classify Landsat satellite images, obtain the space-time variation condition of the coastal zone cultivation sea area between 30 years in China, and analyze the development trend, geographical conditions, social and economic factors, development policies and other driving factors; kang et al extract the Liaoning province mariculture target of 2000-2018 by carrying out band ratio normalization calculation on Landsat data; wang et al identified and extracted Fuzhou Luoyuan bay raft culture based on the significance normalized vegetation index; hou Yingzhuo and the like, by combining a normalized vegetation index and a support vector machine classification method, monitoring the dynamic characteristics of the seaweed cultivation area in the wahai city of Shandong province; xing and the like extract seaweed culture areas by using differential vegetation indexes, and the formation of the seaweed culture areas and yellow sea green tide is revealed by remote sensing inversion space-time development process, so that the seaweed culture areas have important significance in guiding sea culture space planning and yellow sea green tide prevention and control; wang et al identified and extracted the aquaculture sea area based on the GEE framework and random forest model, and determined the dynamic mode and driving factors of mariculture. However, the traditional exponential method and the machine learning supervised classification method are difficult to avoid the phenomena of 'same-spectrum foreign matters', 'same-object foreign matters', the original characteristic information cannot be automatically extracted well, the accuracy of information acquisition is to be improved, and detailed reference and powerful support are difficult to provide for ocean resource management.
In recent years, technology has rapidly developed, and a plurality of emerging technologies are initiated. As a branch in machine learning, deep learning has been widely used in terms of object recognition, image segmentation, artificial intelligence, and the like. Chen et al extract and compare the multi-temporal high-resolution remote sensing image based on two neural network structures such as U-Net; zou et al construct a U2-Net network model, and extract the sea for cultivation in the island coastal zone of Zhejiang Zheshan from the remote sensing image; lu and the like improve the U-Net network by using a cavity space convolution pooling pyramid and an up-sampling structure, and reduce the phenomenon of edge adhesion of sea identification for medium-resolution remote sensing image cultivation. But in general, the deep learning has less application in the aspect of extracting sea information for cultivation, the used network model is simpler, a module which has higher performance and richer semantic information is not designed and integrated, the concerned information scale and detail are required to be promoted, the extraction of specific information such as a cultivation raft frame, a cultivation net cage and the like is more emphasized, the research result of automatically extracting the sea for cultivation in a large area is less, meanwhile, the existing method has certain limitation in the area with variable scale and uneven spatial distribution, and the problem of misidentification and missed identification exists in the area with large and dense sea area for cultivation and small area and scattered condition.
Disclosure of Invention
The present invention has been made to solve the above-mentioned problems occurring in the prior art. Therefore, an automatic identification method, device and medium for the sea for cultivation are needed, and an improved SegNet network model is constructed by introducing a pyramid-type scale-aware convolution module and a channel-space attention dual-focusing module so as to improve the automatic identification precision of the sea for cultivation, and provide technical support for scientific and reasonable monitoring and management work of the sea for cultivation.
According to a first aspect of the present invention, there is provided an automatic identification method for a sea for cultivation, the method comprising:
acquiring remote sensing image data, wherein the remote sensing image data comprises a multispectral image and a panchromatic image;
Preprocessing the remote sensing image data to obtain a data set;
Constructing an automatic recognition model, wherein the automatic recognition model takes remote sensing image data as an input feature map, and outputs a sea recognition result for cultivation; the automatic identification model comprises a pyramid scale perception convolution module and a channel-space attention double-focusing module, an input feature map is firstly matched to a first channel depth through a first standard convolution module and enters the scale perception convolution module to carry out grouping convolution, a plurality of first feature maps are generated, the plurality of first feature maps pass through the attention double-focusing module to improve the focusing acuity of extracted feature lifting information, a plurality of second feature maps are obtained, the plurality of second feature maps are matched to an initial channel depth through the second convolution module, a normalization layer and an activation function are added after each convolution, and finally the input feature maps and the second feature maps matched to the initial channel depth are added to be used as a sea identification result for cultivation;
and training the automatic identification model by using the data set, and realizing automatic identification of the sea for cultivation by using the trained automatic identification model.
Further, the preprocessing the remote sensing image data to obtain a data set specifically includes:
Performing atmospheric correction and orthographic correction on the multispectral image and the full-color image;
Carrying out image fusion on the corrected multispectral image and the full-color image to obtain a fusion image, wherein spectral characteristics are reserved in the fusion image, and extracting near infrared wave bands, green wave bands and blue wave bands of the fusion image are respectively corresponding to three channels of red, green and blue in sequence;
Labeling the fusion image by using a label to obtain a label image, wherein the label comprises a sea label for cultivation and a seamark label for non-cultivation;
cutting the fusion image and the corresponding label graph, and carrying out sample amplification on the cut image to obtain a plurality of groups of sample pairs, wherein each group of sample pairs consists of the fusion image and the corresponding label graph, and the sample pairs are divided into a training data set and a verification data set;
And extracting a plurality of test areas of the non-training image area based on the fusion image and the corresponding label image, respectively cutting the plurality of test areas to obtain test area comparison images, and drawing the label image of the corresponding test area comparison images to form a plurality of test area comparison sample pairs.
Further, labeling the fused image by using a label to obtain a label map specifically includes:
based on visual interpretation and manual annotation, the vector labels of the marked sample areas are endowed with field values of two different types of sea areas for cultivation and sea areas for non-cultivation, and converted into gray values of raster images,
Marking the sea area for cultivation and the sea area for non-cultivation as different colors;
and converting the vector label into raster data to finish the manufacture of the label graph.
Further, the cropping the fused image and the corresponding label graph specifically includes:
And carrying out overlapped sliding window cutting on the fusion image and the corresponding label image, and uniformly cutting the fusion image and the corresponding label image into images with the same pixel size.
Further, after performing sample amplification on the image after clipping to obtain a plurality of groups of sample pairs, the method further includes:
The data of the plurality of groups of sample pairs are enhanced by horizontal and vertical rotation, diagonal mirroring and addition of salt and pepper noise or Gaussian noise, the generation of an countermeasure network is introduced more innovatively to carry out large-scale automatic sample amplification, the simulated sample pairs have extremely high similarity, and the sample diversity is widened.
Further, the scale-aware convolution module comprises four convolution layers with different convolution kernel sizes, and the four convolution layers are used for carrying out grouping convolution on the input feature images matched to the first channel depth to generate a plurality of first feature images.
Further, the convolution kernel sizes of the four layer-different convolution layers are 9×9, 7×7, 5×5, and 3×3, respectively.
Further, the attention dual-closure injection molding block comprises a channel attention and spatial attention module;
The channel attention module extracts the information of the characteristics of each channel of the first characteristic diagram through global maximum pooling and global average pooling operation, and learns the channel attention weight through using a shared full-connection layer and a Sigmoid activation function;
The spatial attention module calculates spatial attention by carrying out maximum pooling and average pooling on the features of each spatial position of the first feature map, stacks the spatial attention of each spatial position, connects the spatial attention by utilizing standard convolution, and obtains spatial attention weight by Sigmoid activation function;
And multiplying the channel attention weight and the space attention weight, and then weighting the first feature map to obtain a second feature map.
According to a second aspect of the present invention, there is provided an automatic identification device for a sea for cultivation, the device comprising:
The data acquisition module is configured to acquire remote sensing image data, wherein the remote sensing image data comprises a multispectral image and a panchromatic image;
the data preprocessing module is configured to preprocess the remote sensing image data to obtain a data set;
The model construction module is configured to construct an automatic identification model, and the automatic identification model takes remote sensing image data as an input feature map and outputs a sea identification result for cultivation; the automatic identification model comprises a pyramid convolution module and a convolution attention module, an input feature map is firstly adapted to a first channel depth through a first standard convolution module and enters the pyramid convolution module to carry out grouping convolution, a plurality of first feature maps are generated, the plurality of first feature maps pass through the convolution attention module to improve the acuity of focusing on extracted feature lifting information, a plurality of second feature maps are obtained, the plurality of second feature maps are adapted to an initial channel depth through the second convolution module, a normalization layer and an activation function are added after each convolution, and finally the input feature map and the second feature map adapted to the initial channel depth are added to be used as a sea identification result for cultivation;
And the automatic identification module is configured to train the automatic identification model by utilizing the data set, and realize automatic identification of the sea for cultivation by the trained automatic identification model.
According to a third aspect of the present invention, there is provided a readable storage medium storing one or more programs executable by one or more processors to implement the method as described above.
The invention has at least the following beneficial effects:
The invention obtains multi-scale information by adding the pyramid-type scale sensing convolution module without additionally adding network parameters and adding the channel-space attention double-relation injection molding block, thereby enhancing the utilization of effective information. The effectiveness of the module is verified through an ablation experiment, and the improvement mode of combined use is helpful to precision improvement, and the overall precision, average intersection ratio and F1 fraction of the culture sea are identified in 3 test areas by the proposed model, and are improved by 2.83%, 6.67% and 1.8% respectively compared with the original model. By carrying out comparison experiments with UNet, segNet, denseNet models and traditional machine learning SVM and RF methods, the effectiveness of the proposed models is verified, and the overall accuracy, average cross-over ratio and F1 score of the proposed models for identifying the sea for cultivation in 3 test areas respectively reach 94.86%, 87.23% and 96.59%, which are improved compared with the comparison methods. Experimental results show that the network model provided by the method can automatically and accurately identify the sea area for cultivation, and can provide technical support for monitoring and management of the sea for cultivation.
Drawings
FIG. 1 is a schematic diagram of a geographical location and a remote sensing image of a region of a selected application scene according to an embodiment of the present invention, wherein (a) is the geographical location of the application scene, (b) is the location of a target region in the application scene, and (c) is the remote sensing image of the target region;
FIG. 2 is a flowchart of a method for automatically identifying a sea for farming according to an embodiment of the present invention;
FIG. 3 is a diagram of GF-1D sample set images and labels according to an embodiment of the present invention;
FIG. 4 is a diagram of a structure of an improvement SegNet according to an embodiment of the present invention;
FIG. 5 is a diagram of a pyramid-type scale-aware convolution architecture in accordance with an embodiment of the present invention;
FIG. 6 is a diagram of a channel-space attention dual-closure injection-molded block architecture according to an embodiment of the present invention;
FIG. 7 is a comparison chart of test area identification results (comparison experiment) according to an embodiment of the present invention;
FIG. 8 is a comparison graph of test zone identification results (ablation experiments) according to an embodiment of the present invention;
fig. 9 is a structural view of an automatic marine identification device for cultivation according to an embodiment of the present invention.
Detailed Description
The present invention will be described in detail below with reference to the drawings and detailed description to enable those skilled in the art to better understand the technical scheme of the present invention. Embodiments of the present invention will be described in further detail below with reference to the drawings and specific examples, but not by way of limitation. The order in which the steps are described herein by way of example should not be construed as limiting if there is no necessity for a relationship between each other, and it should be understood by those skilled in the art that the steps may be sequentially modified without disrupting the logic of each other so that the overall process is not realized.
The embodiment of the invention provides an automatic identification method for a sea for cultivation, which firstly provides an application scene of the method, as shown in fig. 1, wherein the application scene is a geographical position and region remote sensing image schematic diagram of a selected application scene, the application scene is 34 degrees 18 '21' -35 degrees 1 '3', and the geographical coordinate range is 118 degrees 41 '38' -119 degrees 33 '44', in the Jiangsu province, and the sea for cultivation is the remote sensing image schematic diagram of the region. The Lianyuangang is an important ocean fishery area in Jiangsu province, the ocean economy is developed, the ocean resources are abundant, the area of the ocean is 6677 square kilometers, the shallow sea beach is 11 ten thousand hectares, 17 large rivers flow into the sea along the coast, the water quality of the sea area is rich, and the national north salt farm is one of the sea state bay fishery of one of the national eight-big fishery and one of the four national sea salt production areas. The main cultivated crop is laver, the largest national laver cultivation processing base is located at the place, and the national fishery association organization in 2021 also examines and approves the name of' Chinese laver. The sea for cultivation is mainly distributed in coast county city of east coast, such as Guanyun, east sea, sea state, etc., wherein the sea for cultivation is the largest in Guanyun county.
As shown in fig. 2, which is a flow chart of the method, the method comprises the following steps:
Step S100, remote sensing image data is obtained, wherein the remote sensing image data comprises a multispectral image and a full-color image.
In the embodiment, the experimental data adopts GF-1D satellite L1A remote sensing image data of Lianghong Kong city, and the shooting time is 2022, 5, 24, 11 and 39 minutes. The high-resolution one-size-D satellite is jointly emitted by 2018 and the B, C satellite in a three-star-with-arrow mode, the full-color image spatial resolution is 2 meters, the multispectral image spatial resolution is better than 8 meters, the single-star imaging breadth is more than 60 kilometers, and the all-weather and full-coverage real-time monitoring capability of natural resources is greatly improved.
Step S200, preprocessing the remote sensing image data to obtain a data set.
In this embodiment, the software ENVI5.3 is used to perform atmospheric correction and orthographic correction on the high-resolution first-order multispectral image and the full-color image of the research area, then perform image fusion on the corrected first-order multispectral image and the full-color image to improve the resolution of the corrected first-order multispectral image and keep the spectral characteristics, and extract the fused high-resolution multispectral image in a band 4 (near infrared band), a band 2 (green band) and a band 1 (blue band) respectively corresponding to three red, green and blue channels in sequence. And then, by combining visual interpretation and manual annotation with the vector labels of the marked sample areas through ArcGIS10.8 software, the field values of two different types of the sea for cultivation and other land features are given, and converted into gray values of raster images, wherein the sea for cultivation is1, and the other land features are 0. Meanwhile, the sea area for cultivation is marked as white, and RGB is (255 ); the other feature areas are marked black, and RGB is (0, 0). And finally, converting the vector label into raster data to finish the production of the seamark signature data set for cultivation.
After the marking is completed, the whole image and the label are cut into sliding windows overlapped by using Python codes, and the size of 256 multiplied by 256 pixels is uniformly cut. Sample amplification is carried out after cutting to avoid the condition of over-fitting of network training, a data set is enhanced through traditional amplification and generation of countermeasure network amplification, and finally 10000 groups of 256 multiplied by 256 pixel sample pairs are obtained, wherein 7500 groups of training data sets and 2500 groups of verification data sets. Each set of sample pairs in the marine culture dataset consists of an image map and a corresponding label map, as shown in fig. 3. In addition, three test areas of the non-training image area are selected, cut into remote sensing images of 1000 multiplied by 1000 pixels, and corresponding sea labels for cultivation are drawn to form three groups of test area comparison.
Step S300, an automatic recognition model is constructed, remote sensing image data is used as an input feature map by the automatic recognition model, and a sea recognition result for cultivation is output; the automatic identification model comprises a pyramid scale perception convolution module and a channel-space attention dual-attention module, an input feature map is firstly matched to a first channel depth through a first standard convolution module and enters the pyramid convolution module to carry out grouping convolution, a plurality of first feature maps are generated, the plurality of first feature maps pass through the convolution attention module to improve the acuity of attention to extracted feature lifting information, a plurality of second feature maps are obtained, the plurality of second feature maps are matched to an initial channel depth through the second convolution module, a normalization layer and an activation function are added after each convolution, and finally the input feature maps are added with the second feature maps matched to the initial channel depth to serve as a sea identification result for cultivation.
The present embodiment improves upon the underlying SegNet network. SegNet the network is a basic convolutional neural network of classical encoder-decoder architecture, published by Vijay, alex equal to 2017 under IEEE. The network structure is clear, and can be quickly applied to real-time application with small storage space. The study redesigns the classical SegNet network structure, adds PyConv module (pyramid scale-aware convolution module) and CBAM module (channel-space attention dual-focus module), as shown in fig. 4, and strengthens the utilization of characteristic information.
First, the first standard convolution of each layer SegNet of the network is replaced with a scale-aware convolution, and a portion of the pyramid-type scale-aware convolution is designed, as shown in FIG. 4. In the convolution process, taking the input feature map depth of 256 as an example, the input feature map is designed to be firstly matched to the channel depth of 64 through standard convolution of 1×1, and then is subjected to feature pyramid convolution with 4 layers of different convolution kernel sizes. According to the traditional experience and parameter debugging, four layers of convolution kernels in the pyramid are respectively set to 9×9, 7×7, 5×5 and 3×3, groups are set to 16, 8, 4 and 1 to carry out grouping convolution, 16 feature maps are generated in each layer, 64 feature maps are generated by four layers as output, and then channel depth with the size of 256 is adapted by standard convolution of 1×1. At the same time, BN normalization and ReLU activation functions are added after each convolution. And finally, adding the output characteristic diagram and the input characteristic diagram through quick connection to obtain final output.
Secondly, the encoder part of SegNet networks is improved, a channel-space attention dual attention module is added before the pooling operation of the fifth-layer network, and the input feature map sequentially passes through the channel attention module and the space attention module, so that the information attention acuity of the features extracted by the encoder is improved. According to experience principle and debugging, the fifth layer network belongs to the encoder part, the attention double-attention module is added, excessive semantic information is not added, the phenomenon of overfitting can be reduced to a certain extent, the current more key information can be focused, the attention to other information is reduced, more information related to the identification target is acquired, and the utilization efficiency of the characteristic information is improved.
It should be noted that, the core idea of the pyramid scale-aware convolution module described herein is to use convolution kernels of different levels, that is, different sizes and depths, to process an input image, so as to better capture details of different levels and different scales, so as to solve the problem that standard convolution lacks the capability of processing the input image in multiple scales. As shown in fig. 5, the pyramid scale-aware convolution includes n-level pyramids of different convolution kernels, which increase in size from the bottom (level 1) to the top (level n) of the pyramid, while the depth of the convolution kernels decreases.
Thanks to this, the biggest advantage of scale-aware convolution is that multi-scale processing can be achieved by diversified combinations, different convolution kernels can contain both larger and smaller receptive fields, and can focus on larger objects as well as on details. At the same time, no additional network parameters are added, and similar number of levels of model parameters and requirements are maintained by default in the computing resources as compared to standard convolution.
The channel-space attention dual attention module is a module which is often added in a convolutional neural network, and the core of the module is to focus the network on more important information, and generally comprises two types of space attention mechanisms and channel attention mechanisms. As shown in fig. 6, the feature map of the input network is sequentially processed by the channel attention module and the spatial attention module. The channel attention module extracts information of the characteristics of each channel through global maximum pooling and global average pooling operation, and learns the channel attention weight by using a shared full connection layer and a Sigmoid activation function; additionally, the spatial attention module calculates spatial attention by max pooling and average pooling features of each spatial location and stacks them together, then connects with a standard convolution of channel number 1, and gets spatial attention weights by Sigmoid activation function. And finally multiplying the outputs of the two modules, and weighting the feature map to obtain the final output.
And finally, in step S400, training the automatic identification model by using the data set, and realizing automatic identification of the sea for cultivation by using the trained automatic identification model.
According to the steps, the method provided by the invention is operated on an experimental platform, the experimental platform selected by the embodiment adopts a Windows 10 professional 64-bit system, the processor is Intel Rui 12-generation Inter Core i7-12700 twelve-Core processor, 48G memory (DDR 43200 MHz) is configured, and the built-in display card is NVIDIA GeForce RTX 3060. The experimental environment is configured by taking Anaconda3 software as a carrier, an experiment is carried out by creating a virtual environment of Python3.6 version, and a deep learning framework selects TensorFlow 2.4.4 and an integrated Keras 2.4.4 interface thereof. Secondly, by configuring the corresponding CUDA 11.1 as an operation platform and carrying cuDNN 8.0.0 as a neural network acceleration library, the capability of the GPU for solving the complex calculation problem is improved. Finally, software PyCharm 2022 is installed as an integrated development environment to write, debug and develop programs so as to ensure that experiments can be successfully developed.
Finally, the super-parameter setting for training the improved network is shown in table 1 through multiple parameter adjustment experiment optimization.
Table 1 network training parameter settings
The precision evaluation refers to comparing the breeding sea identified by the three test areas with the real labels thereof, so as to judge the effectiveness and the accuracy of the method. The evaluation index quantitatively analyzes the sea for cultivation by relying on the confusion matrix. The images predicted into the map are divided into two categories of sea for cultivation and other ground features, so that the confusion matrix is in a matrix form of 2 rows and 2 columns. Combining the predicted and real results in a matrix has four cases: TP, FP, FN, TN, T and F represent correct or incorrect, P and N represent 1 or 0. Wherein TP represents the correct marine pixel for cultivation, FP represents the wrong marine pixel for cultivation, TN represents the correct other ground object pixel for cultivation, FN represents the wrong other ground object pixel for cultivation, n is the number of categories, and n is 2 herein.
Five evaluation factors of accuracy (precision), recall (recall), overall Accuracy (OA), F1-Score (F1-Score), average cross ratio (mIoU) are selected, and the calculation formulas are shown in formulas (1) to (5), respectively. Accuracy represents the probability that all samples predicted as sea for farming are correctly identified; recall represents the probability of being correctly identified in all samples that are truly marine for farming; the total precision OA represents the probability that each random sample, the predicted result is the same as the real type; f1-score is the balance value with highest classification model accuracy and recall; the intersection ratio represents the ratio of the intersection and union of the predicted class sample and the actual class sample, and the average intersection ratio is the result of averaging all classes.
The calculation formula of the five evaluation factors is as follows:
In order to verify the performance of the improved model and prove the superiority of the improved model, the best improved SegNet model after training is stored, the three selected test areas are predicted and identified, and the visual analysis and quantitative accuracy evaluation are carried out on the predicted image and the real label image of the test areas. The proposed improved method is compared with the classification results of classical SegNet, UNet, denseNet networks and traditional machine learning support vector machines, random forest methods. The comparison diagrams of the identification results generated by the original images, the real labels and the various methods of the three test areas are shown in fig. 7, wherein white represents the sea for cultivation and black represents other ground objects.
As can be seen by visual comparison, the model provided by the method has the best visual effect, and the situations of wrong separation and missing separation are greatly reduced compared with other models. In other models, the condition of the sea leakage for cultivation is in the green frame, and the condition of the omission of other models is serious in the sea area of a large area; the yellow frame is internally provided with a situation that other ground objects are wrongly identified as the sea for cultivation, and the model proposed herein is also an optimal model for avoiding the situation; in addition, the red frame is a drain sea channel of the culture sea area which is missed, and the recognition capability of the model provided herein on finer river channels is improved compared with other models. In addition, the method of identification by using the traditional machine learning method obviously produces broken blocks, the identification result of the sea for cultivation is scattered and finely divided, the extraction effect is poor, and the region integrity and the integrity are poor. According to analysis, the traditional machine learning only depends on single information such as spectrum information, only focuses on features of single dimension to judge pixel by pixel, lacks grasp of global information of an image, cannot link the global information to strengthen utilization of the features like deep learning, cannot continuously learn and utilize other feature information in classification, and therefore the situation of breaking plaques is generated. In a comprehensive view, the model provided by the method is accurate in identifying the sea for cultivation, can accurately distinguish other ground objects, and has the highest identification integrity on a large area.
In addition, quantitative analysis is also carried out on the model performance based on the evaluation index, and the results are shown in table 2, and the optimal values are shown in a rough scale. It can be seen that the method provided by the invention has the best indexes, the accuracy reaches 96.17%, and the accuracy is improved by 1.41% compared with other best methods; the recall rate reaches 97.02%, and is improved by 0.2% compared with other optimal methods; the overall precision reaches 94.86%, and is improved by 2.77% compared with other optimal methods; the average cross ratio reaches 87.23%, and is improved by 6.67% compared with other optimal methods; the F1 fraction reaches 96.56%, and is improved by 1.66% compared with other optimal methods. The data fully prove the superior performance of the method in the aspect of automatic identification of the sea for cultivation, so that the improved SegNet model provided herein can accurately identify the sea for cultivation through comprehensive visual comparison results and accuracy evaluation result analysis, and has high information mining capability for the sea for cultivation, and good identification capability in areas with large and dense sea areas for cultivation or small and dispersed areas.
TABLE 2 evaluation results of precision of test areas (comparative experiments)
In order to verify the effectiveness of different modules in the improved network proposed herein, a series of experiments were performed on the marine culture dataset, including the use of different modules, respectively adding Pyconv and CBAM modules separately to the original SegNet and SegNet networks, respectively, and four models of the improved SegNet networks. Performance of the four models on the three test zones can be determined by comparing the graphs, see fig. 8. Through visual comparison, the combination of CBAM and Pyconv enables the visual effect to be optimal, and compared with the original SegNet model or the addition of a single module, the capability of identifying the whole area of the sea for cultivation is improved, as shown by a green frame in the figure; meanwhile, the capability of identifying a thinner drainage sea channel is obviously improved, as shown by a red frame in the figure; in addition, the error division is reduced, as shown by the yellow box in the figure.
And (3) analyzing according to quantitative precision evaluation indexes, wherein the analysis is shown in a table 3, and the optimal values are shown in a rough scale. The data strongly demonstrate that CBAM and Pyconv modules, when used alone, both improve accuracy over the original model. The method has the advantages that the method can be improved to the optimal performance when the method is combined and added, the accuracy of automatic identification of the sea for cultivation is remarkably improved, the overall accuracy of an improved model is improved by 2.83%, 2% and 0.46% respectively compared with that of an original model, a CBAM module is added singly, a Pyconv module is added singly, the average cross ratio is improved by 6.67%, 6.48% and 1.33% respectively, and the F1 fraction is improved by 1.8% and 1.07% and 0.26% respectively.
Table 3 evaluation results of accuracy of test area (ablation experiment)
In summary, the method provided by the invention can realize rapid and accurate large-area automatic extraction of the culture sea, multi-scale information is obtained by adding PyConv pyramid convolution modules, network parameters are not additionally added, and the utilization of effective information is enhanced by adding CBAM attention mechanism modules. The effectiveness of the module is verified through an ablation experiment, and the improvement mode of combined use is helpful to precision improvement, and the overall precision, average intersection ratio and F1 fraction of the culture sea are identified in 3 test areas by the proposed model, and are improved by 2.83%, 6.67% and 1.8% respectively compared with the original model. By carrying out comparison experiments with UNet, segNet, denseNet models and traditional machine learning SVM and RF methods, the effectiveness of the proposed models is verified, and the overall accuracy, average cross-over ratio and F1 score of the proposed models for identifying the sea for cultivation in 3 test areas respectively reach 94.86%, 87.23% and 96.59%, which are improved compared with the comparison methods. Experimental results show that the improved SegNet model provided by the method can automatically and accurately identify the sea area for cultivation, and can provide technical support for monitoring and management of the sea for cultivation.
An embodiment of the present invention provides an automatic identification device for a sea for cultivation, as shown in fig. 9, the device 900 includes:
A data acquisition module 901 configured to acquire remote sensing image data including a multispectral image and a panchromatic image;
the data preprocessing module 902 is configured to preprocess the remote sensing image data to obtain a data set;
The model construction module 903 is configured to construct an automatic recognition model, and the automatic recognition model uses remote sensing image data as an input feature map and outputs a sea recognition result for cultivation; the automatic identification model comprises a pyramid scale perception convolution module and a channel-space attention dual-attention module, an input feature map is firstly matched to a first channel depth through a first standard convolution module and enters the pyramid convolution module to carry out grouping convolution, a plurality of first feature maps are generated, the plurality of first feature maps pass through the convolution attention module to improve the acuity of attention to extracted feature lifting information, a plurality of second feature maps are obtained, the plurality of second feature maps are matched to an initial channel depth through the second convolution module, a normalization layer and an activation function are added after each convolution, and finally the input feature maps are added with the second feature maps matched to the initial channel depth to serve as a sea identification result for cultivation;
An automatic recognition module 904 configured to train the automatic recognition model using the data set, and to implement automatic recognition of the sea for farming by the trained automatic recognition model.
In some embodiments, the data preprocessing module is further configured to:
Performing atmospheric correction and orthographic correction on the multispectral image and the full-color image;
Carrying out image fusion on the corrected multispectral image and the full-color image to obtain a fusion image, wherein spectral characteristics are reserved in the fusion image, and extracting near infrared wave bands, green wave bands and blue wave bands of the fusion image are respectively corresponding to three channels of red, green and blue in sequence;
Labeling the fusion image by using a label to obtain a label image, wherein the label comprises a sea label for cultivation and a seamark label for non-cultivation;
cutting the fusion image and the corresponding label graph, and carrying out sample amplification on the cut image to obtain a plurality of groups of sample pairs, wherein each group of sample pairs consists of the fusion image and the corresponding label graph, and the sample pairs are divided into a training data set and a verification data set;
And extracting a plurality of test areas of the non-training image area based on the fusion image and the corresponding label image, respectively cutting the plurality of test areas to obtain test area comparison images, and drawing the label image of the corresponding test area comparison images to form a plurality of test area comparison sample pairs.
In some embodiments, the data preprocessing module is further configured to:
based on visual interpretation and manual annotation, the vector labels of the marked sample areas are endowed with field values of two different types of sea areas for cultivation and sea areas for non-cultivation, and converted into gray values of raster images,
Marking the sea area for cultivation and the sea area for non-cultivation as different colors;
and converting the vector label into raster data to finish the manufacture of the label graph.
In some embodiments, the data preprocessing module is further configured to:
And carrying out overlapped sliding window cutting on the fusion image and the corresponding label image, and uniformly cutting the fusion image and the corresponding label image into images with the same pixel size.
In some embodiments, the data preprocessing module is further configured to:
The plurality of sets of sample pairs are data enhanced by combining conventional amplification steps to generate a method of automatically amplifying samples substantially against a network.
In some embodiments, the pyramid convolution module includes four different convolution layers with different convolution kernel sizes, and the four convolution layers group-convolve the input feature map adapted to the first channel depth to generate a plurality of first feature maps.
In some embodiments, the convolution kernel sizes of the four layer-specific convolution layers are 9×9, 7×7, 5×5, 3×3, respectively.
In some embodiments, the convolution attention module includes a channel attention module and a spatial attention module;
The channel attention module extracts the information of the characteristics of each channel of the first characteristic diagram through global maximum pooling and global average pooling operation, and learns the channel attention weight through using a shared full-connection layer and a Sigmoid activation function;
The spatial attention module calculates spatial attention by carrying out maximum pooling and average pooling on the features of each spatial position of the first feature map, stacks the spatial attention of each spatial position, connects the spatial attention by utilizing standard convolution, and obtains spatial attention weight by Sigmoid activation function;
And multiplying the channel attention weight and the space attention weight, and then weighting the first feature map to obtain a second feature map.
It should be noted that, the device in this embodiment and the method described in the foregoing belong to the same technical idea, and the same technical effects can be achieved, which are not repeated here.
Embodiments of the present invention provide a readable storage medium storing one or more programs executable by one or more processors to implement the methods described in the above embodiments.
The above description is intended to be illustrative and not restrictive. For example, the above-described examples (or one or more aspects thereof) may be used in combination with each other. For example, other embodiments may be used by those of ordinary skill in the art upon reading the above description. In addition, in the above detailed description, various features may be grouped together to streamline the invention. This is not to be interpreted as an intention that the features of the claimed invention are essential to any of the claims. Rather, inventive subject matter may lie in less than all features of a particular inventive embodiment. Thus, the following claims are hereby incorporated into the detailed description as examples or embodiments, with each claim standing on its own as a separate embodiment, and it is contemplated that these embodiments may be combined with one another in various combinations or permutations. The scope of the invention should be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled.

Claims (9)

Constructing an automatic recognition model, wherein the automatic recognition model takes remote sensing image data as an input feature map, and outputs a sea recognition result for cultivation; the automatic identification model comprises a pyramid scale perception convolution module and a convolution channel-space double-relation attention module, wherein n-level pyramids with different convolution kernels are contained in the pyramid scale perception convolution, the size of the convolution kernels is continuously increased from 1 level to n levels of pyramids, and meanwhile, the depth of the convolution kernels is continuously reduced; the automatic identification model is that the first standard convolution of each layer SegNet of network is replaced by pyramid scale-aware convolution, and the channel-space attention double-closure injection molding block is positioned before pooling operation of a fifth layer network of SegNet network; the input feature images are matched to the depth of a first channel through standard convolution and then are subjected to pyramid scale perception convolution to obtain a plurality of feature images, then the initial channel depth is matched back through standard convolution, a BN return layer and a ReLU activation function are added after each convolution, finally the output feature images and the input feature images are added through quick connection to be used as a sea identification result for cultivation, and as the channel-space attention double-closure injection molding block is positioned before pooling operation of a SegNet fifth layer network, only the feature images output after passing through a fourth layer pass through the channel-space attention double-closure injection molding block;
A model building module configured to build an automatic recognition model; the automatic identification model comprises a pyramid scale perception convolution module and a convolution channel-space double-relation attention module, wherein n-level pyramids with different convolution kernels are contained in the pyramid scale perception convolution, the size of the convolution kernels is continuously increased from 1 level to n levels of pyramids, and meanwhile, the depth of the convolution kernels is continuously reduced; the automatic identification model is that the first standard convolution of each layer SegNet of network is replaced by pyramid scale-aware convolution, and the channel-space attention double-closure injection molding block is positioned before pooling operation of a fifth layer network of SegNet network; the input feature images are matched to the depth of a first channel through standard convolution and then are subjected to pyramid scale perception convolution to obtain a plurality of feature images, then the initial channel depth is matched back through standard convolution, a BN return layer and a ReLU activation function are added after each convolution, finally the output feature images and the input feature images are added through quick connection to be used as a sea identification result for cultivation, and as the channel-space attention double-closure injection molding block is positioned before pooling operation of a SegNet fifth layer network, only the feature images output after passing through a fourth layer pass through the channel-space attention double-closure injection molding block;
CN202311335706.9A2023-10-132023-10-13 Automatic identification method, device and medium for aquaculture seaActiveCN117611987B (en)

Priority Applications (1)

Application NumberPriority DateFiling DateTitle
CN202311335706.9ACN117611987B (en)2023-10-132023-10-13 Automatic identification method, device and medium for aquaculture sea

Applications Claiming Priority (1)

Application NumberPriority DateFiling DateTitle
CN202311335706.9ACN117611987B (en)2023-10-132023-10-13 Automatic identification method, device and medium for aquaculture sea

Publications (2)

Publication NumberPublication Date
CN117611987A CN117611987A (en)2024-02-27
CN117611987Btrue CN117611987B (en)2024-06-28

Family

ID=89952242

Family Applications (1)

Application NumberTitlePriority DateFiling Date
CN202311335706.9AActiveCN117611987B (en)2023-10-132023-10-13 Automatic identification method, device and medium for aquaculture sea

Country Status (1)

CountryLink
CN (1)CN117611987B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN117975282B (en)*2024-03-292024-06-11山东大学 Remote sensing extraction method and system of laver cultivation area based on multivariate optical feature fusion
CN119992347A (en)*2025-04-152025-05-13武汉纺织大学 An improved method for target detection in remote sensing images

Citations (2)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN113516012A (en)*2021-04-092021-10-19湖北工业大学Pedestrian re-identification method and system based on multi-level feature fusion
CN114565655A (en)*2022-02-282022-05-31上海应用技术大学 A Pyramid Segmentation Attention-Based Depth Estimation Method and Device

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN113486851B (en)*2021-07-282023-04-18齐齐哈尔大学Hyperspectral image classification method based on double-branch spectrum multi-scale attention network
CN116052016B (en)*2023-01-142025-09-30南京信息工程大学 Fine segmentation and detection method of clouds and cloud shadows in remote sensing images based on deep learning
CN115965874A (en)*2023-01-182023-04-14华南理工大学 A crop disease identification method, system, device and storage medium
CN116863345A (en)*2023-05-302023-10-10浙江大学High-resolution image farmland recognition method based on dual attention and scale fusion
CN116452901B (en)*2023-06-192023-09-15中国科学院海洋研究所 Automatic extraction method of marine breeding areas from remote sensing images based on deep learning

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN113516012A (en)*2021-04-092021-10-19湖北工业大学Pedestrian re-identification method and system based on multi-level feature fusion
CN114565655A (en)*2022-02-282022-05-31上海应用技术大学 A Pyramid Segmentation Attention-Based Depth Estimation Method and Device

Also Published As

Publication numberPublication date
CN117611987A (en)2024-02-27

Similar Documents

PublicationPublication DateTitle
CN117611987B (en) Automatic identification method, device and medium for aquaculture sea
CN102054274B (en)Method for full automatic extraction of water remote sensing information in coastal zone
CN108596248A (en)A kind of classification of remote-sensing images model based on improvement depth convolutional neural networks
CN108875659A (en)A kind of sea chart culture zone recognition methods based on multi-spectrum remote sensing image
CN115452759B (en)River and lake health index evaluation method and system based on satellite remote sensing data
ElawadySparse coral classification using deep convolutional neural networks
CN113963222A (en) A Multi-Strategy Combination-Based Change Detection Method for High Resolution Remote Sensing Imagery
CN109740460A (en) Optical remote sensing image ship detection method based on deep residual dense network
Zheng et al.Underwater sonar target detection based on improved ScEMA-YOLOv8
CN106650812A (en)City water body extraction method for satellite remote sensing image
CN107992818A (en)A kind of detection method of remote sensing image sea ship target
Zhang et al.Coastal oyster aquaculture area extraction and nutrient loading estimation using a GF-2 satellite image
Yuan et al.A low-cost edge AI-chip-based system for real-time algae species classification and HAB prediction
CN109359533A (en) A coastline extraction method based on multi-band remote sensing images
CN117611991A (en)Remote sensing image urban green land information extraction method, device and medium
CN115439689A (en)Near-shore visual ship target detection method based on direct guide mask detection network
Cui et al.Reverse attention dual-stream network for extracting laver aquaculture areas from GF-1 remote sensing images
CN117152616A (en)Remote sensing image typical object extraction method based on spectrum enhancement and double-path coding
Wang et al.QTU-Net: quaternion transformer-based U-Net for water body extraction of RGB satellite image
Dong et al.Detection of pine wilt disease infected pine trees using YOLOv5 optimized by attention mechanisms and loss functions
Ge et al.MARFPNet: Multi-attention and Adaptive Reparameterized Feature Pyramid Network for Small Target Detection on Water Surfaces
Sun et al.Annual change in the distribution and landscape health of mangrove ecosystems in China from 2016 to 2023 with Sentinel imagery
Hu et al.Spectral-Spatial Features Extraction of Hyperspectral Remote Sensing Oil Spill Imagery Based on Convolutional Neural Networks
CN118521901A (en)Remote sensing interpretation method for sea elements for cultivation
Hu et al.Tree species identification method based on improved YOLOv7

Legal Events

DateCodeTitleDescription
PB01Publication
PB01Publication
SE01Entry into force of request for substantive examination
SE01Entry into force of request for substantive examination
GR01Patent grant
GR01Patent grant

[8]ページ先頭

©2009-2025 Movatter.jp