CN116228539A - A method for stitching remote sensing images of drones - Google Patents
A method for stitching remote sensing images of dronesDownload PDFInfo
- Publication number
- CN116228539A CN116228539ACN202310231460.4ACN202310231460ACN116228539ACN 116228539 ACN116228539 ACN 116228539ACN 202310231460 ACN202310231460 ACN 202310231460ACN 116228539 ACN116228539 ACN 116228539A
- Authority
- CN
- China
- Prior art keywords
- remote sensing
- image
- aerial vehicle
- unmanned aerial
- vehicle remote
- 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.)
- Pending
Links
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/80—Geometric correction
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/17—Terrestrial scenes taken from planes or by drones
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/32—Indexing scheme for image data processing or generation, in general involving image mosaicing
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Remote Sensing (AREA)
- Image Processing (AREA)
Abstract
Translated fromChinese
Description
Translated fromChinese技术领域technical field
本发明涉及图像处理技术领域，特别是涉及一种无人机遥感图像拼接的方法。The invention relates to the technical field of image processing, in particular to a method for mosaicing remote sensing images of drones.
背景技术Background technique
无人机作为一种新兴的航空遥感平台，具有高效、灵活、快速、低成本的特点，机上搭载的数码相机、数码摄像机可以获取高分辨率影像。无人机遥感是一种新的遥感手段，应用领域广泛，包括农业、林业、电力、国土资源、城市规划等,由于无人机遥感平台在航拍过程中，受到飞行高度和相机焦距等的限制，获取的影像存在航高低、像幅小的特点，无法反映拍摄区域的整体情况，往往不能满足地面对信息的需求和应用，特别是应急救灾时。As an emerging aerial remote sensing platform, UAV has the characteristics of high efficiency, flexibility, speed and low cost. The digital camera and digital video camera on board can obtain high-resolution images. UAV remote sensing is a new remote sensing method with a wide range of applications, including agriculture, forestry, electric power, land resources, urban planning, etc. Since the UAV remote sensing platform is limited by the flight height and camera focal length during the aerial photography process , the acquired images have the characteristics of low altitude and small image size, which cannot reflect the overall situation of the shooting area, and often cannot meet the needs and applications of information on the ground, especially in emergency disaster relief.
现在的无人机遥感图像拼接过程是先进行飞行轨迹规划，让无人机沿着规划的飞行轨迹采集图像，然后再对采集的图像序列进行拼接。当采集到的图像序列中有不符合拼接要求或图像序列并没有完全覆盖规划区域时，则利用无人机沿着以前规划的飞行轨迹再次采集图像，然后将两次采集的图像合并进行拼接，这导致工作量大，图像大量重复，拼接效率低。The current mosaic process of UAV remote sensing images is to plan the flight trajectory first, let the UAV collect images along the planned flight trajectory, and then stitch the collected image sequences. When the collected image sequence does not meet the splicing requirements or the image sequence does not completely cover the planned area, use the UAV to collect the image again along the previously planned flight trajectory, and then merge the two collected images for splicing. This results in a heavy workload, a large number of repeated images, and low stitching efficiency.
发明内容Contents of the invention
本发明的目的是提供一种无人机遥感图像拼接的方法，可精确地配准图像，减小拼接误差，做到无缝拼接，过渡自然。The purpose of the present invention is to provide a method for splicing remote sensing images of drones, which can accurately register images, reduce splicing errors, achieve seamless splicing, and transition naturally.
为实现上述目的，本发明提供了如下方案：To achieve the above object, the present invention provides the following scheme:
一种无人机遥感图像拼接的方法，包括：A method for mosaicing remote sensing images of drones, comprising:
采集无人机遥感图像，对所述无人机遥感图像进行预处理；Collecting UAV remote sensing images, and preprocessing the UAV remote sensing images;
对预处理后的所述无人机遥感图像进行特征提取，获取最优特征；Carrying out feature extraction to the preprocessed remote sensing image of the UAV to obtain optimal features;
对预处理后的所述无人机遥感图像进行图像配准，根据所述最优特征对匹配结果进行融合，并对融合结果进行质量评价。Perform image registration on the preprocessed UAV remote sensing images, fuse the matching results according to the optimal features, and evaluate the quality of the fusion results.
可选地，对所述无人机遥感图像进行预处理包括：Optionally, preprocessing the UAV remote sensing image includes:
基于直方图匹配法对所述无人机遥感图像进行辐射矫正，通过图像重采样对辐射校正后的所述无人机遥感图像进行几何矫正。Radiation correction is performed on the remote sensing image of the UAV based on a histogram matching method, and geometric correction is performed on the remote sensing image of the UAV after radiation correction by image resampling.
可选地，获取所述最优特征包括：Optionally, obtaining the optimal feature includes:
对预处理后的所述无人机遥感图像进行Harris角点检测，获得图像特征点，对所述图像特征点进行特征选择，获取所述最优特征，并剔除不相关或冗余的特征。Perform Harris corner detection on the preprocessed UAV remote sensing image to obtain image feature points, perform feature selection on the image feature points, obtain the optimal features, and eliminate irrelevant or redundant features.
可选地，对预处理后的所述无人机遥感图像进行图像配准包括：Optionally, performing image registration on the preprocessed UAV remote sensing image includes:
基于所述无人机遥感图像对应的经纬和偏航角信息，计算地理坐标投影信息，并按照拼接策略选取预处理后的所述无人机遥感图像，根据所述地理坐标投影信息进行图像配准，获取配准图像，即所述匹配结果。Based on the longitude, latitude and yaw angle information corresponding to the UAV remote sensing image, calculate the geographic coordinate projection information, and select the preprocessed UAV remote sensing image according to the splicing strategy, and perform image matching according to the geographic coordinate projection information. Acquire the registration image, that is, the matching result.
可选地，根据所述最优特征对匹配结果进行融合包括：Optionally, fusing the matching results according to the optimal features includes:
建立匹配数据集，基于所述最优特征构建相似性评估指标，筛选出所述匹配集中的匹配点，基于所述匹配点计算变换矩阵；Establishing a matching data set, constructing a similarity evaluation index based on the optimal feature, filtering out matching points in the matching set, and calculating a transformation matrix based on the matching points;
通过加权平均融合方法，结合所述变换矩阵对所述配准图像进行融合，实现无人遥感图像的拼接。By means of a weighted average fusion method, the registration image is fused in combination with the transformation matrix, so as to realize the splicing of unmanned remote sensing images.
可选地，建立所述匹配数据集包括：通过采用查询索引KD树方式，建立一对多的所述匹配数据集。Optionally, establishing the matching data set includes: establishing a one-to-many matching data set by using a query index KD tree.
可选地，对所述融合结果进行质量评价包括：Optionally, evaluating the quality of the fusion result includes:
基于所述边缘差分谱评价法对所述融合结果进行质量评价，获取质量评价结果，预设评价阈值，若所述质量评价结果小于评价阈值，则计算所述融合结果的重叠区域位置，并去除所述配准图像的重叠区域位置，将重叠区域位置后的所述配准图像再次进行融合，若所述质量评价结果大于评价阈值，则不做处理。Perform quality evaluation on the fusion result based on the edge difference spectrum evaluation method, obtain the quality evaluation result, preset the evaluation threshold, if the quality evaluation result is less than the evaluation threshold, calculate the overlapping area position of the fusion result, and remove For the overlapping area position of the registration image, the registration image after the overlapping area position is fused again, and if the quality evaluation result is greater than the evaluation threshold, no processing is performed.
可选地，对所述融合结果进行质量评价前包括：Optionally, before performing quality evaluation on the fusion result, it includes:
检测融合完成后的所述配准图像是否覆盖所有的规划区域，若存在未覆盖的空白区域，则在融合完成后的所述配准图像中将空白区域及其附近的部分遥感图像截取出来，基于截取出来的所述遥感图像与所述无人机遥感图像做匹配运算，找出匹配率最高的所述无人机遥感图像并计算截取出来的所述遥感图像的地理坐标投影信息，根据截取出来的所述遥感图像的地理坐标投影信息，对所述无人机遥感图像进行再次采集，将再次采集到的所述无人机遥感图像替换对应的所述无人机遥感图像，再次进行图像配准和融合。Detecting whether the registration image after fusion covers all the planned areas, if there is an uncovered blank area, intercepting the blank area and some remote sensing images near it from the registration image after fusion, Based on the matching operation between the intercepted remote sensing image and the UAV remote sensing image, find out the UAV remote sensing image with the highest matching rate and calculate the geographic coordinate projection information of the intercepted remote sensing image, according to the interception The geographical coordinate projection information of the remote sensing image is obtained, and the remote sensing image of the UAV is collected again, and the remote sensing image of the UAV collected again is replaced with the corresponding remote sensing image of the UAV, and the image is re-collected. Registration and Fusion.
本发明的有益效果为：The beneficial effects of the present invention are:
本发明通过无人机遥感图像拼接的方法，可精确地配准图像，减小拼接误差，做到无缝拼接，过渡自然，并通过对拼接结果进行检测与质量评价，避免了对有效图像的重复采集和拼接，减少工作量的同时提高图像的拼接效率。The present invention can accurately register images through the splicing method of remote sensing images of drones, reduce splicing errors, achieve seamless splicing, and transition naturally, and avoid damage to effective images by detecting and evaluating the splicing results. Repeated acquisition and stitching reduces the workload while improving the efficiency of image stitching.
附图说明Description of drawings
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the accompanying drawings required in the embodiments. Obviously, the accompanying drawings in the following description are only some of the present invention. Embodiments, for those of ordinary skill in the art, other drawings can also be obtained according to these drawings without paying creative labor.
图1为本发明实施例的一种无人机遥感图像拼接的方法流程图。Fig. 1 is a flow chart of a method for mosaicing remote sensing images of drones according to an embodiment of the present invention.
具体实施方式Detailed ways
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.
为使本发明的上述目的、特征和优点能够更加明显易懂，下面结合附图和具体实施方式对本发明作进一步详细的说明。In order to make the above objects, features and advantages of the present invention more comprehensible, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.
如图1所示，一种无人机遥感图像拼接的方法，包括：采集无人机遥感图像，对无人机遥感图像进行预处理；对预处理后的无人机遥感图像进行特征提取，获取最优特征；对预处理后的无人机遥感图像进行图像配准，根据最优特征对匹配结果进行融合，并对融合结果进行质量评价。As shown in Figure 1, a method for splicing UAV remote sensing images, including: collecting UAV remote sensing images, preprocessing the UAV remote sensing images; performing feature extraction on the preprocessed UAV remote sensing images, Obtain the optimal features; perform image registration on the preprocessed UAV remote sensing images, fuse the matching results according to the optimal features, and evaluate the quality of the fusion results.
对无人机遥感图像进行预处理包括：基于直方图匹配法对无人机遥感图像进行辐射矫正，通过图像重采样对辐射校正后的无人机遥感图像进行几何矫正，具体为：The preprocessing of UAV remote sensing images includes: radiometric correction of UAV remote sensing images based on the histogram matching method, and geometric correction of radiation-corrected UAV remote sensing images through image resampling, specifically:
由于无人机体积小，重量轻，受气流影响较大，稳定性和抗风能力较差，飞行姿态倾斜、抖动现象难以避免，这些都会对获取的遥感图像产生直接的影响，导致图像发生畸变。通过像点坐标变换、图像重采样等对畸变图像进行几何校正，以消除几何畸变对图像的影响，满足图像配准的需要。Due to the small size and light weight of the UAV, it is greatly affected by the airflow, its stability and wind resistance are poor, and the phenomenon of tilting and shaking of the flight attitude is unavoidable. These will have a direct impact on the acquired remote sensing images, resulting in image distortion. . Geometrically correct the distorted image through image point coordinate transformation, image resampling, etc. to eliminate the influence of geometric distortion on the image and meet the needs of image registration.
获取最优特征包括：对预处理后的无人机遥感图像进行Harris角点检测，获得图像特征点，对图像特征点进行特征选择，获取最优特征，并剔除不相关或冗余的特征，具体为：Harris角点检测利用移动的窗口在图像中计算灰度变化值，其中主要流程包括转化为灰度图像、计算差分图像、高斯平滑、计算局部极值、确认角点，进而得到图像特征点。Obtaining optimal features includes: performing Harris corner detection on preprocessed UAV remote sensing images, obtaining image feature points, performing feature selection on image feature points, obtaining optimal features, and eliminating irrelevant or redundant features, Specifically: Harris corner detection uses a moving window to calculate the grayscale change value in the image. The main process includes converting to grayscale image, calculating difference image, Gaussian smoothing, calculating local extremum, confirming corner point, and then obtaining image features. point.
对预处理后的无人机遥感图像进行图像配准包括：基于无人机遥感图像对应的经纬和偏航角信息，计算地理坐标投影信息，并按照拼接策略选取预处理后的无人机遥感图像，根据地理坐标投影信息进行图像配准，获取配准图像，即匹配结果；计算地理坐标投影信息包括：利用仿射矩阵参数对遥感图像坐标与地理坐标进行转换，其包括6个参数，分别为XE，Xpixel，Rγ，YE，Ypixel，Rγ，描述的是图像行列号和地理坐标之间的关系，其中，XE、YE表示图像左上角像元的地理投影坐标，Xpixel、Ypixel分别表示图像像元在经度、维度方向的地面分辨率，Rγ表示图像旋转角度的正弦值。The image registration of the preprocessed UAV remote sensing images includes: based on the longitude, latitude and yaw angle information corresponding to the UAV remote sensing images, calculating the geographic coordinate projection information, and selecting the preprocessed UAV remote sensing images according to the splicing strategy. Image, image registration is performed according to the geographic coordinate projection information, and the registered image is obtained, that is, the matching result; the calculation of the geographic coordinate projection information includes: using the affine matrix parameters to convert the remote sensing image coordinates and geographic coordinates, which includes 6 parameters, respectively XE, Xpixel, Rγ, YE, Ypixel, Rγ describe the relationship between image row and column numbers and geographic coordinates, where XE and YE represent the geographic projection coordinates of the upper left corner of the image, Xpixel and Ypixel respectively represent the image The ground resolution of the unit in the longitude and latitude direction, Rγ represents the sine value of the image rotation angle.
根据最优特征对匹配结果进行融合包括：建立匹配数据集，基于最优特征构建相似性评估指标，筛选出匹配集中的匹配点，基于匹配点计算变换矩阵；通过加权平均融合方法，结合变换矩阵对配准图像进行融合，实现无人遥感图像的拼接，具体为：The fusion of matching results according to the optimal features includes: establishing a matching data set, constructing a similarity evaluation index based on the optimal features, screening out the matching points in the matching set, and calculating the transformation matrix based on the matching points; through the weighted average fusion method, combined with the transformation matrix The registration images are fused to realize the splicing of unmanned remote sensing images, specifically:
计算匹配点对间的距离，将距离值的最大最小值均匀的分为10个区间，每个区间的频率为P＝{p1，…，p10}，则峰值区间的频率为max(P)，对应的区间为第i个，在区间[i-1，i+1]中的匹配点对是正确匹配点对，该匹配点对集为寻找的精确匹配点对；再根据随机抽样一致RANSAC算法消除错误特征点对，从而计算出变化矩阵，加权平均融合法的思想是对两幅图像的重叠部分的像素值，先进行加权计算，然后再进行叠加。结合变换矩阵对配准图像进行融合，实现无人遥感图像的拼接；Calculate the distance between matching point pairs, and evenly divide the maximum and minimum values of distance values into 10 intervals, the frequency of each interval is P={p1,...,p10}, then the frequency of the peak interval is max(P), The corresponding interval is the i-th, and the matching point pairs in the interval [i-1, i+1] are correct matching point pairs, and the matching point pair set is the exact matching point pair to be found; then, according to the random sampling consistent RANSAC algorithm Eliminate the wrong feature point pairs to calculate the change matrix. The idea of the weighted average fusion method is to perform weighted calculations on the pixel values of the overlapping parts of the two images, and then superimpose them. Combining the transformation matrix to fuse the registered images to realize the splicing of unmanned remote sensing images;
其中，图像融合的目的就是将配准后的图像基于一定的变换模型合并为一幅新的图像，在重叠区域不应该出现拼接痕迹，也就是要做到无缝拼接，过渡自然；Among them, the purpose of image fusion is to merge the registered images into a new image based on a certain transformation model, and there should be no splicing traces in the overlapping areas, that is, to achieve seamless splicing and natural transition;
匹配点的筛选方法为采用查询索引KD树方式为，通过空间距离选择与图像中每个特征点最接近的图像中的n个特征匹配点形成一对多的假设匹配集，并采取空间距离作为特征点相似性的评估指标，空间距离包括欧氏距离和像素坐标距离的加权和。The screening method of matching points is to use the query index KD tree method to select n feature matching points in the image closest to each feature point in the image through the spatial distance to form a one-to-many hypothetical matching set, and take the spatial distance as The evaluation index of feature point similarity, the spatial distance includes the weighted sum of Euclidean distance and pixel coordinate distance.
建立匹配数据集包括：通过采用查询索引KD树方式，建立一对多的匹配数据集。Establishing the matching data set includes: establishing a one-to-many matching data set by adopting a query index KD tree method.
对融合结果进行质量评价包括：基于边缘差分谱评价法对融合结果进行质量评价，获取质量评价结果，预设评价阈值，若质量评价结果小于评价阈值，则计算融合结果的重叠区域位置，并去除配准图像的重叠区域位置，将重叠区域位置后的配准图像再次进行融合，若质量评价结果大于评价阈值，则不做处理。Evaluating the quality of the fusion result includes: evaluating the quality of the fusion result based on the edge difference spectrum evaluation method, obtaining the quality evaluation result, and preset the evaluation threshold. If the quality evaluation result is less than the evaluation threshold, calculate the overlapping area position of the fusion result and remove The overlapping area position of the registration image is fused again with the registration image after the overlapping area position, and if the quality evaluation result is greater than the evaluation threshold, no processing is performed.
对融合结果进行质量评价前包括：检测融合完成后的配准图像是否覆盖所有的规划区域，若存在未覆盖的空白区域，则在融合完成后的配准图像中将空白区域及其附近的部分遥感图像截取出来，基于截取出来的遥感图像与无人机遥感图像做匹配运算，找出匹配率最高的无人机遥感图像并计算截取出来的遥感图像的地理坐标投影信息，根据截取出来的遥感图像的地理坐标投影信息，对无人机遥感图像进行再次采集，将再次采集到的无人机遥感图像替换对应的无人机遥感图像，再次进行图像配准和融合，具体为：Before evaluating the quality of the fusion results, it includes: detecting whether the registration image after fusion covers all the planning areas, and if there is an uncovered blank area, the blank area and its nearby parts will be included in the registration image after fusion. The remote sensing image is intercepted, and the matching operation is performed based on the intercepted remote sensing image and the UAV remote sensing image, and the UAV remote sensing image with the highest matching rate is found and the geographical coordinate projection information of the intercepted remote sensing image is calculated. The geographic coordinate projection information of the image is used to collect the UAV remote sensing image again, replace the corresponding UAV remote sensing image with the re-acquired UAV remote sensing image, and perform image registration and fusion again, specifically:
本实施例中，质量评价的结果在0～1之间，阈值采用0.7；如果质量评价的结果小于阈值，则计算融合结果的重叠区域位置，并去除配准图像的重叠区域位置，将重叠区域位置后的配准图像再次进行融合，若质量评价结果大于评价阈值，则不做处理；在融合结果进行质量评价前，检测融合完成后的配准图像是否覆盖所有的规划区域，若存在未覆盖的空白区域，则在融合完成后的配准图像中将空白区域及其附近的部分遥感图像截取出来，基于截取出来的遥感图像与无人机遥感图像做匹配运算，找出匹配率最高的无人机遥感图像并计算截取出来的遥感图像的地理坐标投影信息，根据截取出来的遥感图像的地理坐标投影信息，对无人机遥感图像进行再次采集，将再次采集到的无人机遥感图像替换对应的无人机数据，再次进行图像配准和融合，直到得到符合需求的拼接遥感图像。In this embodiment, the result of the quality evaluation is between 0 and 1, and the threshold value is 0.7; if the result of the quality evaluation is less than the threshold value, the position of the overlapping area of the fusion result is calculated, and the position of the overlapping area of the registration image is removed, and the overlapping area The registration image after the position is fused again. If the quality evaluation result is greater than the evaluation threshold, no processing is performed; In the blank area of the registration image after fusion, the blank area and some nearby remote sensing images are intercepted, based on the matching operation between the intercepted remote sensing image and the remote sensing image of the UAV, the remote sensing image with the highest matching rate is found. Man-machine remote sensing image and calculate the geographical coordinate projection information of the intercepted remote sensing image, according to the geographical coordinate projection information of the intercepted remote sensing image, re-collect the UAV remote sensing image, and replace the re-acquired UAV remote sensing image For the corresponding UAV data, image registration and fusion are performed again until the stitched remote sensing images that meet the requirements are obtained.
以上所述的实施例仅是对本发明优选方式进行的描述，并非对本发明的范围进行限定，在不脱离本发明设计精神的前提下，本领域普通技术人员对本发明的技术方案做出的各种变形和改进，均应落入本发明权利要求书确定的保护范围内。The above-mentioned embodiments are only descriptions of the preferred modes of the present invention, and do not limit the scope of the present invention. Variations and improvements should fall within the scope of protection defined by the claims of the present invention.
Claims (8)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310231460.4ACN116228539A (en) | 2023-03-10 | 2023-03-10 | A method for stitching remote sensing images of drones |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310231460.4ACN116228539A (en) | 2023-03-10 | 2023-03-10 | A method for stitching remote sensing images of drones |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116228539Atrue CN116228539A (en) | 2023-06-06 |
Family
ID=86574906
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310231460.4APendingCN116228539A (en) | 2023-03-10 | 2023-03-10 | A method for stitching remote sensing images of drones |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116228539A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117036666A (en)* | 2023-06-14 | 2023-11-10 | 北京自动化控制设备研究所 | Unmanned aerial vehicle low-altitude positioning method based on inter-frame image stitching |
| CN117499887A (en)* | 2024-01-02 | 2024-02-02 | 江西机电职业技术学院 | Data acquisition method and system based on multi-sensor fusion technology |
| CN118411380A (en)* | 2024-05-14 | 2024-07-30 | 浙江地信软件科技有限公司 | A method for extracting urban green areas based on drones |
| CN119228643A (en)* | 2024-12-03 | 2024-12-31 | 金华浙农信息技术有限公司 | Automatic mosaic method and device for unmanned aerial vehicle remote sensing images |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107146200A (en)* | 2017-04-25 | 2017-09-08 | 广西大学 | A mosaic method for UAV remote sensing images based on image mosaic quality evaluation |
| CN109584155A (en)* | 2017-09-29 | 2019-04-05 | 孙凯 | A kind of method that unmanned aerial vehicle remote sensing image quickly splices |
| CN110246082A (en)* | 2019-05-07 | 2019-09-17 | 华中科技大学 | A kind of remote sensing Panorama Mosaic method |
| CN110889818A (en)* | 2019-11-22 | 2020-03-17 | 华南农业大学 | Low-altitude unmanned aerial vehicle image splicing method and system, computer equipment and storage medium |
| CN114897705A (en)* | 2022-06-24 | 2022-08-12 | 徐州飞梦电子科技有限公司 | Unmanned aerial vehicle remote sensing image splicing method based on feature optimization |
| CN114936971A (en)* | 2022-06-08 | 2022-08-23 | 浙江理工大学 | A water-oriented UAV remote sensing multispectral image stitching method and system |
- 2023
- 2023-03-10CNCN202310231460.4Apatent/CN116228539A/enactivePending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107146200A (en)* | 2017-04-25 | 2017-09-08 | 广西大学 | A mosaic method for UAV remote sensing images based on image mosaic quality evaluation |
| CN109584155A (en)* | 2017-09-29 | 2019-04-05 | 孙凯 | A kind of method that unmanned aerial vehicle remote sensing image quickly splices |
| CN110246082A (en)* | 2019-05-07 | 2019-09-17 | 华中科技大学 | A kind of remote sensing Panorama Mosaic method |
| CN110889818A (en)* | 2019-11-22 | 2020-03-17 | 华南农业大学 | Low-altitude unmanned aerial vehicle image splicing method and system, computer equipment and storage medium |
| CN114936971A (en)* | 2022-06-08 | 2022-08-23 | 浙江理工大学 | A water-oriented UAV remote sensing multispectral image stitching method and system |
| CN114897705A (en)* | 2022-06-24 | 2022-08-12 | 徐州飞梦电子科技有限公司 | Unmanned aerial vehicle remote sensing image splicing method based on feature optimization |
Non-Patent Citations (1)
| Title |
|---|
| 林卉 等: "《数字摄影测量学》", 中国矿业大学出版社, pages: 112* |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117036666A (en)* | 2023-06-14 | 2023-11-10 | 北京自动化控制设备研究所 | Unmanned aerial vehicle low-altitude positioning method based on inter-frame image stitching |
| CN117036666B (en)* | 2023-06-14 | 2024-05-07 | 北京自动化控制设备研究所 | UAV low-altitude positioning method based on inter-frame image stitching |
| CN117499887A (en)* | 2024-01-02 | 2024-02-02 | 江西机电职业技术学院 | Data acquisition method and system based on multi-sensor fusion technology |
| CN117499887B (en)* | 2024-01-02 | 2024-03-19 | 江西机电职业技术学院 | Data acquisition method and system based on multi-sensor fusion technology |
| CN118411380A (en)* | 2024-05-14 | 2024-07-30 | 浙江地信软件科技有限公司 | A method for extracting urban green areas based on drones |
| CN119228643A (en)* | 2024-12-03 | 2024-12-31 | 金华浙农信息技术有限公司 | Automatic mosaic method and device for unmanned aerial vehicle remote sensing images |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116740288B (en) | A three-dimensional reconstruction method integrating lidar and oblique photography | |
| CN111583110B (en) | A Stitching Method of Aerial Images | |
| CN116228539A (en) | A method for stitching remote sensing images of drones | |
| CN110211043B (en) | A Registration Method Based on Grid Optimization for Panoramic Image Stitching | |
| CN112767391A (en) | Power grid line part defect positioning method fusing three-dimensional point cloud and two-dimensional image | |
| CN103927731B (en) | Low-altitude remote sensing image rapid and automatic splicing method without POS assisting | |
| CN114936971A (en) | A water-oriented UAV remote sensing multispectral image stitching method and system | |
| CN103822615B (en) | A kind of multi-control point extracts and the unmanned aerial vehicle target real-time location method be polymerized automatically | |
| CN104732482A (en) | Multi-resolution image stitching method based on control points | |
| CN114973028B (en) | A real-time change detection method and system for aerial video images | |
| CN113971768A (en) | A three-dimensional dynamic detection method for illegal buildings in transmission lines based on UAV | |
| CN110033407B (en) | Shield tunnel surface image calibration method, splicing method and splicing system | |
| CN107274380B (en) | A fast mosaic method for UAV multispectral images | |
| US12347189B2 (en) | Method for extracting forest parameters of wetland with high canopy density based on consumer-grade UAV image | |
| CN108320304A (en) | A kind of automatic edit methods and system of unmanned plane video media | |
| CN107527328A (en) | A kind of unmanned plane image geometry processing method for taking into account precision and speed | |
| CN111693025B (en) | Remote sensing image data generation method, system and equipment | |
| CN117423010B (en) | River and lake demarcation recognition monitoring method based on remote sensing data | |
| CN113793270A (en) | Aerial image geometric correction method based on unmanned aerial vehicle attitude information | |
| CN115511716B (en) | A multi-view global map stitching method based on calibration plate | |
| CN110246082B (en) | A remote sensing panorama image stitching method | |
| CN109961043B (en) | Single-tree height measuring method and system based on high-resolution image of unmanned aerial vehicle | |
| CN113313659A (en) | High-precision image splicing method under multi-machine cooperative constraint | |
| CN111861866A (en) | A panorama reconstruction method of substation equipment inspection image | |
| CN112907493A (en) | Multi-source battlefield image rapid mosaic fusion algorithm under unmanned aerial vehicle swarm cooperative reconnaissance |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | Application publication date:20230606 | |
| RJ01 | Rejection of invention patent application after publication |