技术领域Technical Field
本发明涉及道路停车技术领域，具体为一种基于5G神经网络的道路停车车牌识别方法及系统。The present invention relates to the field of road parking technology, and specifically to a road parking license plate recognition method and system based on 5G neural network.
背景技术Background Art
在车辆进出频繁的道路停车场景中，道路停车管理人员通常配备手持PDA（Personal Digital Assistant，掌上电脑）设备，用于车牌信息的采集、处理和上传。车牌识别的算法原理是通过图像处理技术和模式识别方法，对车辆牌照进行定位、分割、识别和验证。首先，通过摄像头采集车辆图像，并对图像进行预处理，去除噪声、增强图像质量；其次，通过边缘检测、颜色分割等技术对车牌进行定位，将其从背景中分离出来；然后，对分离出来的车牌进行字符分割，并对每个字符进行识别；最后，将识别出的车牌信息与数据库中的标准车牌进行比对，实现车辆的自动识别和身份验证。In road parking scenarios where vehicles frequently enter and exit, road parking managers are usually equipped with handheld PDA (Personal Digital Assistant) devices for collecting, processing and uploading license plate information. The algorithm principle of license plate recognition is to locate, segment, identify and verify vehicle license plates through image processing technology and pattern recognition methods. First, the vehicle image is collected through the camera, and the image is preprocessed to remove noise and enhance image quality; secondly, the license plate is located and separated from the background through edge detection, color segmentation and other technologies; then, the separated license plate is segmented and each character is recognized; finally, the recognized license plate information is compared with the standard license plate in the database to achieve automatic recognition and identity authentication of the vehicle.
车牌区域在整幅图像中所占比例很小，车牌的颜色、大小、位置等也不确定，识别距离要兼顾收费员的安全拍摄距离(3米左右)和部分车位紧张路段的近距离识别要求(1米左右)，定位算法要能够克服复杂环境（如夜晚、雨天、弱光、强光、车牌污损、遮挡、变形等）的影响，还要兼顾准确性和实时性。然而，PDA设备硬件资源有限，传统的车牌识别算法在这些设备上运行效率较低，识别速度和准确率难以满足实际需求，导致停车管理效率低下，且容易产生争议和管理漏洞。因此在PDA设备上实现快速准确的定位车牌是比较困难的。The license plate area accounts for a very small proportion of the entire image, and the color, size, and position of the license plate are uncertain. The recognition distance must take into account the safe shooting distance of the toll collector (about 3 meters) and the close-range recognition requirements of some sections with tight parking spaces (about 1 meter). The positioning algorithm must be able to overcome the influence of complex environments (such as night, rainy days, weak light, strong light, license plate damage, occlusion, deformation, etc.), and must also take into account accuracy and real-time performance. However, PDA equipment has limited hardware resources, and traditional license plate recognition algorithms have low operating efficiency on these devices. The recognition speed and accuracy are difficult to meet actual needs, resulting in low parking management efficiency and prone to disputes and management loopholes. Therefore, it is difficult to quickly and accurately locate license plates on PDA devices.
近年来，神经网络技术特别是深度学习的发展为车牌识别带来了新的解决方案。深度学习模型可以通过多层神经网络结构自动学习并提取车牌的复杂特征，具有较高的识别准确率和泛化能力。然而，深度学习模型的高效运行通常需要强大的计算资源和高速数据传输，而手持PDA设备由于硬件性能的限制，难以在传统网络环境下满足这些要求，导致车牌识别速度和准确率大幅降低。In recent years, the development of neural network technology, especially deep learning, has brought new solutions to license plate recognition. Deep learning models can automatically learn and extract complex features of license plates through multi-layer neural network structures, and have high recognition accuracy and generalization capabilities. However, the efficient operation of deep learning models usually requires powerful computing resources and high-speed data transmission. Due to the limitations of hardware performance, handheld PDA devices are difficult to meet these requirements in traditional network environments, resulting in a significant reduction in license plate recognition speed and accuracy.
随着5G通信技术的普及，其高带宽、低延迟和大规模连接的特点为手持PDA终端在车牌识别中的应用提供了技术支持。5G网络的高速率和低延迟特性，使得手持PDA设备能够实时接收、处理和上传大量图像数据，同时利用远程服务器的强大计算能力，进行复杂的神经网络模型推理和训练，从而大幅提升车牌识别的速度和准确率。With the popularization of 5G communication technology, its high bandwidth, low latency and large-scale connection characteristics provide technical support for the application of handheld PDA terminals in license plate recognition. The high speed and low latency characteristics of the 5G network enable handheld PDA devices to receive, process and upload large amounts of image data in real time, while using the powerful computing power of remote servers to perform complex neural network model reasoning and training, thereby greatly improving the speed and accuracy of license plate recognition.
因此，如何在手持PDA设备上结合5G通信技术和神经网络技术，开发出一种灵活、高效的车牌识别系统，以提高车牌识别的速度与准确率，成为亟需解决的问题。Therefore, how to combine 5G communication technology and neural network technology on handheld PDA devices to develop a flexible and efficient license plate recognition system to improve the speed and accuracy of license plate recognition has become an urgent problem to be solved.
发明内容Summary of the invention
针对手持PDA设备硬件资源有限、车牌识别算法对环境适应性差等问题，本发明提出一种基于5G神经网络的道路停车车牌识别方法及系统，不仅可以提高识别的准确率和实时性，还能减少传统固定设备的部署成本和运维难度，特别适用于道路停车场景。In view of the problems of limited hardware resources of handheld PDA devices and poor environmental adaptability of license plate recognition algorithms, the present invention proposes a road parking license plate recognition method and system based on 5G neural network, which can not only improve the accuracy and real-time performance of recognition, but also reduce the deployment cost and operation and maintenance difficulty of traditional fixed equipment, and is particularly suitable for road parking scenarios.
为了实现上述目的，本发明提供如下技术方案：In order to achieve the above object, the present invention provides the following technical solutions:
一种基于5G神经网络的道路停车车牌识别方法，所述方法包括：A method for road parking license plate recognition based on 5G neural network, the method comprising:
通过手持PDA终端的摄像头对车辆车牌进行拍照或视频扫描，以采集车牌图像；The vehicle license plate is photographed or video scanned by the camera of the handheld PDA terminal to collect the license plate image;
将所述车牌图像通过5G网络传输到部署在5G基站中的边缘计算节点；Transmitting the license plate image to an edge computing node deployed in a 5G base station via a 5G network;
在边缘计算节点通过超分辨率模型对所述车牌图像进行清晰度增强，并将处理后的车牌图像输入训练好的车牌识别模型进行识别，得到识别后的车牌信息；At the edge computing node, the license plate image is enhanced in clarity by using a super-resolution model, and the processed license plate image is input into a trained license plate recognition model for recognition to obtain recognized license plate information;
将所述车牌信息通过5G网络传输回手持PDA终端进行可视化显示，人工确认车牌识别是否正确，若识别错误则重新进行识别，并将错误信息上报云端，用于后续的模型训练和优化。The license plate information is transmitted back to the handheld PDA terminal via the 5G network for visual display, and manual confirmation is made as to whether the license plate recognition is correct. If the recognition is wrong, the recognition is performed again, and the error information is reported to the cloud for subsequent model training and optimization.
作为本发明的一种优选方案，所述采集车牌图像的方法包括：As a preferred solution of the present invention, the method for collecting license plate images includes:
启用低光增强、自动对焦和抗抖动功能，在动态场景中连续拍摄多帧包含车牌信息的车辆图像，并使用图像去噪和多帧合成算法生成单帧的车辆图像；Enable low-light enhancement, autofocus, and anti-shake functions, continuously capture multiple frames of vehicle images containing license plate information in dynamic scenes, and use image denoising and multi-frame synthesis algorithms to generate a single-frame vehicle image;
使用预训练的YOLO模型在车辆图像上实时检测车牌位置，自动标记并输出车牌的边界框坐标，公式为：Use the pre-trained YOLO model to detect the license plate position in real time on the vehicle image, automatically mark and output the bounding box coordinates of the license plate. The formula is:
； ;
式中，(x,y)为边界框的实际中心坐标，w、h分别为边界框的实际宽度和高度；为YOLO模型的输出值，表示边界框中心点相对于网格单元左上角的偏移量，以及预测框的宽度和高度相对于锚框的对数偏移量；、为指数函数，用于将模型预测的对数偏移量转换为正数比例因子；表示预定义的锚框的宽度和高度；表示网格单元左上角的绝对坐标，用于确定预测的边界框相对于整个图像的位置；为使用Sigmoid函数将预测偏移限制在0到1之间；Where (x, y) is the actual center coordinate of the bounding box, w and h are the actual width and height of the bounding box respectively; is the output value of the YOLO model, indicating the offset of the center point of the bounding box relative to the upper left corner of the grid cell , and the logarithmic offset of the width and height of the predicted box relative to the anchor box ; , is an exponential function used to convert the logarithmic offset of the model prediction into a positive scaling factor; Represents the width and height of the predefined anchor box; Represents the absolute coordinates of the upper left corner of the grid cell, which is used to determine the position of the predicted bounding box relative to the entire image; To use the Sigmoid function to limit the prediction offset between 0 and 1;
将所述车牌的边界框坐标作为输入数据，使用基于MobileNetV2的U-Net分割模型从单帧的车辆图像中裁剪出车牌图像。The bounding box coordinates of the license plate are used as input data, and the license plate image is cropped from the single-frame vehicle image using a U-Net segmentation model based on MobileNetV2.
作为本发明的一种优选方案，所述通过超分辨率模型对所述车牌图像进行清晰度增强，实现方法包括：As a preferred solution of the present invention, the definition of the license plate image is enhanced by a super-resolution model, and the implementation method includes:
对采集的车牌图像进行标准化和尺度归一化处理，使用卷积神经网络对预处理后的车牌图像ILR进行特征提取，生成初始特征图FLR，公式为：The collected license plate image is standardized and scaled, and the convolutional neural network is used to extract features from the preprocessed license plate image ILR to generate the initial feature map FLR . The formula is:
； ;
式中，为卷积核权重，为偏置项，表示卷积操作，为激活函数；In the formula, is the convolution kernel weight, is the bias term, represents the convolution operation, is the activation function;
将特征图FLR输入到包含通道注意力、空间注意力、像素注意力的三重注意力和残差连接块的特征增强模块，通过自注意机制以及残差连接增强车牌图像中的字符和布局特征，并集成可变卷积层，根据特征图FLR的内容动态调整卷积核的形状和位置，输出增强后的特征图FLA；The feature map FLR is input into the feature enhancement module which includes triple attention of channel attention, spatial attention, pixel attention and residual connection block. The character and layout features in the license plate image are enhanced through self-attention mechanism and residual connection. The variable convolution layer is integrated to dynamically adjust the shape and position of the convolution kernel according to the content of the feature map FLR , and the enhanced feature map FLA is output.
将增强后的特征图FLA输入字符特征上采样模块，使用反卷积操作进行上采样，输出超分辨率的车牌图像ISR，公式为：The enhanced feature map FLA is input into the character feature upsampling module, and upsampled using the deconvolution operation to output the super-resolution license plate image ISR . The formula is:
； ;
式中，为反卷积核权重，为偏置项；In the formula, is the deconvolution kernel weight, is the bias term;
采用生成对抗网络的训练策略，生成器用于生成超分辨率的车牌图像，判别器是一个OCR模型，逐步调整和更新卷积核权重、自主力权重和反卷积核权重，对超分辨率模型进行优化。The training strategy of generative adversarial network is adopted. The generator is used to generate super-resolution license plate images. The discriminator is an OCR model that gradually adjusts and updates the convolution kernel weights. , autonomy weights and deconvolution kernel weights , optimize the super-resolution model.
作为本发明的一种优选方案，对所述超分辨率模型定义复合损失函数L总，直至复合损失函数L总收敛到预设的阈值范围内，复合损失函数L总的计算公式为：As a preferred solution of the present invention, a composite loss functionLtotal is defined for the super-resolution model until the composite loss function Ltotalconverges to a preset threshold range. The calculation formula of the composite loss functionLtotal is:
； ;
其中，in,
； ;
； ;
； ;
式中，为字符分类的交叉熵损失，用于表示模型对车牌字符的分类误差；N表示车牌图像中包含的字符总数；为第n个字符的权重；为输入特征，为第n个字符的真实标签；为给定输入时，第n个字符的预测概率；In the formula, is the cross entropy loss of character classification, which is used to represent the classification error of the model for license plate characters; N represents the total number of characters contained in the license plate image; is the weight of the nth character; is the input feature, is the true label of the nth character; For a given input When the nth character The predicted probability of
为字符定位损失，用于表示模型在字符位置定位上的误差；其中，函数和分别用于计算字符类型是否为数字或字母，若为数字或字母，则取值为，否则取值为0；为预定义的惩罚系数； is the character positioning loss, which is used to represent the error of the model in character positioning; among them, the function and They are used to calculate whether the character type is a number or a letter. If it is a number or a letter, the value is , otherwise the value is 0; is a predefined penalty coefficient;
为结构相似性损失，用于表示生成图像与真实图像之间的结构相似度误差；和分别为生成图像和真实图像的像素块；为结构相似性指数，用于衡量生成图像与真实图像之间的结构相似度。 is the structural similarity loss, which is used to represent the structural similarity error between the generated image and the real image; and are the pixel blocks of the generated image and the real image respectively; is the structural similarity index used to measure the generated image With real image The structural similarity between them.
作为本发明的一种优选方案，所述车牌识别模型在云端进行训练和更新，边缘计算节点从云端下载所述车牌识别模型用于车牌识别；所述车牌识别模型的构建过程包括：As a preferred solution of the present invention, the license plate recognition model is trained and updated in the cloud, and the edge computing node downloads the license plate recognition model from the cloud for license plate recognition; the construction process of the license plate recognition model includes:
从多个数据源收集车辆图像数据构成数据集，在联邦学习的环境下，将总图像数按客户端数量进行数据划分，以确保每个客户端在本地训练过程中使用不同的数据子集，客户端数量表示参与联邦学习训练的设备或节点数量；Vehicle image data is collected from multiple data sources to form a dataset. In the federated learning environment, the total number of images is divided according to the number of clients to ensure that each client uses a different data subset during local training. The number of clients represents the number of devices or nodes participating in the federated learning training.
使用数据增强技术扩展每个客户端的数据集，对数据集中的原始图像进行缩放、特征标准化、水平和垂直偏移以及特征居中处理；Use data augmentation techniques to expand each client’s dataset by scaling, normalizing, horizontally and vertically offsetting, and centering the original images in the dataset.
通过超分辨率模型对扩展后的图像进行清晰度增强，生成高分辨率图像；The definition of the expanded image is enhanced through a super-resolution model to generate a high-resolution image;
使用U-Net模型从高分辨率图像中分割出车牌图像，通过Tesseract OCR模型对已分割出的车牌图像中的每个字符进行二值化和特征提取，通过卷积神经网络实现字符分类；Use the U-Net model to segment the license plate image from the high-resolution image, use the Tesseract OCR model to binarize and extract features for each character in the segmented license plate image, and use the convolutional neural network to achieve character classification;
采用Dice相似系数作为评估图像分割性能的度量，公式为：The Dice similarity coefficient is used as a metric to evaluate image segmentation performance, and the formula is:
； ;
式中，为Dice相似系数；为真实掩模像素，为预测掩模像素，为常数，防止分母为0；In the formula, is the Dice similarity coefficient; is the real mask pixel, To predict the mask pixels, is a constant to prevent the denominator from being 0;
使用F1分数评估分类结果，公式为：The F1 score is used to evaluate the classification results. The formula is:
； ;
式中，P为精确度，R为召回率。In the formula, P is the precision and R is the recall.
作为本发明的一种优选方案，所述对数据集中的原始图像进行缩放、特征标准化、水平和垂直偏移以及特征居中处理，具体为：As a preferred solution of the present invention, the scaling, feature normalization, horizontal and vertical offset, and feature centering of the original image in the data set are specifically:
缩放：定义缩放因子s∈[0.8,1.2]，对图像尺寸进行随机缩放；Scaling: Define the scaling factor s∈[0.8,1.2] to randomly scale the image size;
特征标准化：使用均值μ和标准差δ对图像像素值进行标准化处理；Feature standardization: Use mean μ and standard deviation δ to standardize the image pixel values;
偏移：随机生成偏移值(Δx,Δy)，应用于图像坐标以实现随机裁剪；Offset: Randomly generate offset values (Δx, Δy) and apply them to image coordinates to achieve random cropping;
特征居中：对每个图像进行对称性调整，使每个图像的中心对齐于固定参考点。Feature Centering: Symmetrically adjust each image so that the center of each image is aligned to a fixed reference point.
作为本发明的一种优选方案，所述U-Net模型包括编码器和解码器，具体实现步骤为：As a preferred solution of the present invention, the U-Net model includes an encoder and a decoder, and the specific implementation steps are:
编码器部分通过卷积层和池化层逐步下采样输入图像，生成一组特征图；The encoder part gradually downsamples the input image through convolutional layers and pooling layers to generate a set of feature maps;
解码器部分通过上采样层和跳跃连接逐步恢复图像空间分辨率，并生成分割掩模；The decoder part gradually restores the image spatial resolution through upsampling layers and skip connections and generates segmentation masks;
采用联邦学习方法进行去中心化训练，通过对多个客户端的局部模型Wi聚合更新全局模型 W，公式为：The federated learning method is used for decentralized training. The global model W is updated by aggregating the local modelsWi of multiple clients. The formula is:
； ;
式中，G是参与训练的客户端数量，Wj表示第j个客户端的局部模型参数。Where G is the number of clients participating in the training, andWj represents the local model parameters of the jth client.
作为本发明的一种优选方案，所述5G网络中，使用HEVC/H.265或JPEG XL对车牌图像进行压缩，通过TLS/SSL加密协议确保数据在传输过程中的安全性，使用QUIC或HTTP/3高效传输协议降低传输延迟。As a preferred solution of the present invention, in the 5G network, HEVC/H.265 or JPEG XL is used to compress the license plate image, the TLS/SSL encryption protocol is used to ensure the security of data during transmission, and the QUIC or HTTP/3 efficient transmission protocol is used to reduce transmission delay.
作为本发明的一种优选方案，所述手持PDA终端设有本地缓存机制，当网络不稳定或断网时，暂时将采集到的车牌图像保存在本地，自动切换到离线识别模式，通过轻量型离线识别模型对本地缓存的车牌图像进行离线识别；当网络恢复时，自动或手动触发重试机制，将缓存的车牌图像上传到边缘计算节点进行处理。As a preferred solution of the present invention, the handheld PDA terminal is provided with a local caching mechanism. When the network is unstable or disconnected, the collected license plate image is temporarily saved locally, and the mode is automatically switched to offline recognition mode. The locally cached license plate image is recognized offline through a lightweight offline recognition model. When the network is restored, the retry mechanism is automatically or manually triggered to upload the cached license plate image to the edge computing node for processing.
一种基于5G神经网络的道路停车车牌识别系统，基于如上所述的一种基于5G神经网络的道路停车车牌识别方法，所述系统包括：A road parking license plate recognition system based on a 5G neural network, based on the road parking license plate recognition method based on a 5G neural network as described above, the system comprises:
摄像头，用于对车辆车牌进行拍照或视频扫描，以采集车牌图像；A camera is used to take a photo or video scan of the vehicle license plate to collect the license plate image;
5G通信模块，用于手持PDA终端和边缘计算节点间的数据通信；5G communication module, used for data communication between handheld PDA terminals and edge computing nodes;
边缘计算节点，用于通过超分辨率模型对所述车牌图像进行清晰度增强，并将处理后的车牌图像输入训练好的车牌识别模型进行识别，得到识别后的车牌信息；The edge computing node is used to enhance the clarity of the license plate image by using a super-resolution model, and input the processed license plate image into a trained license plate recognition model for recognition to obtain recognized license plate information;
云端服务器，用于执行车牌识别模型的训练和更新；A cloud server for training and updating the license plate recognition model;
本地缓存模块，用于当网络不稳定或断网时，暂时将采集到的车牌图像保存在本地；The local cache module is used to temporarily save the collected license plate images locally when the network is unstable or disconnected;
离线识别模块，用于离线识别模式下，通过轻量型离线识别模型对本地缓存的车牌图像进行离线识别。The offline recognition module is used in offline recognition mode to perform offline recognition on the locally cached license plate images through a lightweight offline recognition model.
与现有技术相比，本发明所取得的有益效果是：利用5G通信技术和边缘计算节点，实现了车牌图像数据的实时获取和快速传输，同时在边缘计算节点上进行初步处理（如超分辨率增强和YOLO模型检测），降低了对云端的依赖，减少了数据传输的延迟和带宽消耗；通过在边缘计算节点和云端服务器之间协同工作，使用U-Net分割模型对车牌区域进行精确分割和识别，提高了识别的准确性；通过引入联邦学习模块，在分布式环境中实现数据隐私保护，避免数据泄露的风险，同时保证了识别模型的持续优化；设计本地缓存模块用于存储车牌图像数据及其识别结果，同时引入一个轻量型的离线识别模型，在网络不可用时使用该模型进行离线识别，从而保证系统的连续性和可靠性。Compared with the prior art, the beneficial effects achieved by the present invention are as follows: by utilizing 5G communication technology and edge computing nodes, real-time acquisition and rapid transmission of license plate image data are realized, and preliminary processing (such as super-resolution enhancement and YOLO model detection) is performed on the edge computing nodes, reducing dependence on the cloud, reducing data transmission delays and bandwidth consumption; by working together between edge computing nodes and cloud servers, the U-Net segmentation model is used to accurately segment and identify the license plate area, thereby improving recognition accuracy; by introducing a federated learning module, data privacy protection is achieved in a distributed environment, the risk of data leakage is avoided, and continuous optimization of the recognition model is ensured; a local cache module is designed to store license plate image data and its recognition results, and a lightweight offline recognition model is introduced, which is used for offline recognition when the network is unavailable, thereby ensuring the continuity and reliability of the system.
附图说明BRIEF DESCRIPTION OF THE DRAWINGS
为了更清楚地说明本发明实施例的技术方案，下面将对实施例描述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。其中：In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:
图1为本发明的方法流程图；Fig. 1 is a flow chart of the method of the present invention;
图2为本发明的系统模块化结构图。FIG. 2 is a diagram showing a modular structure of the system of the present invention.
具体实施方式DETAILED DESCRIPTION
为使本发明实施例的目的、技术方案和优点更加清楚，下面将结合本发明实施例的附图，对本发明实施例的技术方案进行清楚、完整地描述。显然，所描述的实施例是本发明的一部分实施例，而不是全部的实施例。基于所描述的本发明的实施例，本领域普通技术人员所获得的所有其他实施例，都属于本发明保护的范围。In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the described embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the present invention.
如图1所示，为本发明的一个实施例，该实施例提供了一种基于5G神经网络的道路停车车牌识别方法，包括以下步骤：As shown in FIG1 , it is an embodiment of the present invention, which provides a method for road parking license plate recognition based on a 5G neural network, including the following steps:
S1：通过手持PDA终端的摄像头对车辆车牌进行拍照或视频扫描，以采集车牌图像；S1: Take a photo or video scan of the vehicle license plate through the camera of the handheld PDA terminal to collect the license plate image;
在其中一个实施例中，步骤S1包括：In one embodiment, step S1 comprises:
S11：启用低光增强、自动对焦和抗抖动功能，在动态场景中连续拍摄多帧包含车牌信息的车辆图像，并使用图像去噪和多帧合成算法生成单帧的车辆图像；S11: Enables low-light enhancement, autofocus, and anti-shake functions, continuously captures multiple frames of vehicle images containing license plate information in dynamic scenes, and uses image denoising and multi-frame synthesis algorithms to generate a single-frame vehicle image;
低光增强功能可以提高在低照明条件下的图像质量，确保车牌信息清晰可见；自动对焦和抗抖动功能保证图像清晰，减少由于手持设备震动引起的模糊；动态场景中，连续拍摄可以捕捉到最佳的车牌图像帧，增加了捕获清晰车牌图像的机会，尤其是在移动条件下；图像去噪和多帧合成算法使得生成的单帧图像更加清晰，有助于后续的车牌检测和识别准确性；The low-light enhancement function can improve the image quality in low-light conditions, ensuring that the license plate information is clearly visible; the autofocus and anti-shake functions ensure clear images and reduce blur caused by vibration of the handheld device; in dynamic scenes, continuous shooting can capture the best license plate image frames, increasing the chance of capturing clear license plate images, especially under moving conditions; image denoising and multi-frame synthesis algorithms make the generated single-frame images clearer, which helps the subsequent license plate detection and recognition accuracy;
S12：使用预训练的YOLO模型在车辆图像上实时检测车牌位置，自动标记并输出车牌的边界框坐标，公式为：S12: Use the pre-trained YOLO model to detect the license plate position in real time on the vehicle image, automatically mark and output the bounding box coordinates of the license plate. The formula is:
； ;
式中，(x,y)为边界框的实际中心坐标，w、h分别为边界框的实际宽度和高度；为YOLO模型的输出值，表示边界框中心点相对于网格单元左上角的偏移量，以及预测框的宽度和高度相对于锚框的对数偏移量；、为指数函数，用于将模型预测的对数偏移量转换为正数比例因子；表示预定义的锚框的宽度和高度；表示网格单元左上角的绝对坐标，用于确定预测的边界框相对于整个图像的位置；为使用Sigmoid函数将预测偏移限制在0到1之间；Where (x, y) is the actual center coordinate of the bounding box, w and h are the actual width and height of the bounding box respectively; is the output value of the YOLO model, indicating the offset of the center point of the bounding box relative to the upper left corner of the grid cell , and the logarithmic offset of the width and height of the predicted box relative to the anchor box ; , is an exponential function used to convert the logarithmic offset of the model prediction into a positive scaling factor; Represents the width and height of the predefined anchor box; Represents the absolute coordinates of the upper left corner of the grid cell, which is used to determine the position of the predicted bounding box relative to the entire image; To use the Sigmoid function to limit the prediction offset between 0 and 1;
S13：将车牌的边界框坐标作为输入数据，使用基于MobileNetV2的U-Net分割模型从单帧的车辆图像中裁剪出车牌图像；S13: Using the bounding box coordinates of the license plate as input data, a U-Net segmentation model based on MobileNetV2 is used to crop the license plate image from a single frame of the vehicle image;
MobileNetV2是一种轻量级的网络，适合在移动设备上运行；U-Net则是一种有效的图像分割网络，结合两者可以在保持高效运算的同时，精确分割车牌图像，适合在资源受限的PDA设备上运行。MobileNetV2 is a lightweight network suitable for running on mobile devices; U-Net is an effective image segmentation network. Combining the two can accurately segment license plate images while maintaining efficient computing, and is suitable for running on resource-constrained PDA devices.
S2：将车牌图像通过5G网络传输到部署在5G基站中的边缘计算节点；S2: Transmit the license plate image to the edge computing node deployed in the 5G base station through the 5G network;
具体地，5G网络中，使用HEVC/H.265或JPEG XL对车牌图像进行压缩，通过TLS/SSL加密协议确保数据在传输过程中的安全性，使用QUIC或HTTP/3高效传输协议降低传输延迟；Specifically, in 5G networks, HEVC/H.265 or JPEG XL is used to compress license plate images, TLS/SSL encryption protocols are used to ensure data security during transmission, and QUIC or HTTP/3 efficient transmission protocols are used to reduce transmission delays;
考虑到手持PDA终端的设备性能可能有限，而清晰度增强通常需要较强的计算能力，因此将清晰度增强设置在部署在5G基站的边缘计算节点更为合适，这样可以利用边缘计算节点的高效计算能力对车牌图像进行清晰度增强处理，同时避免了对PDA终端的过高性能要求。Considering that the device performance of handheld PDA terminals may be limited, and clarity enhancement usually requires strong computing power, it is more appropriate to set the clarity enhancement on the edge computing nodes deployed in the 5G base stations. In this way, the efficient computing power of the edge computing nodes can be used to enhance the clarity of the license plate images, while avoiding excessive high performance requirements for the PDA terminals.
S3：在边缘计算节点通过超分辨率模型对车牌图像进行清晰度增强，并将处理后的车牌图像输入训练好的车牌识别模型进行识别，得到识别后的车牌信息；S3: At the edge computing node, the license plate image is enhanced in clarity through a super-resolution model, and the processed license plate image is input into a trained license plate recognition model for recognition to obtain the recognized license plate information;
车牌识别模型在云端进行训练和更新，边缘计算节点从云端下载车牌识别模型用于车牌识别；The license plate recognition model is trained and updated in the cloud, and the edge computing node downloads the license plate recognition model from the cloud for license plate recognition;
具体地，通过超分辨率模型对车牌图像进行清晰度增强，实现方法包括：Specifically, the clarity of the license plate image is enhanced by a super-resolution model, and the implementation method includes:
S31：对采集的车牌图像进行标准化和尺度归一化处理，消除图像在不同捕获条件下的变异，确保模型的泛化能力；使用卷积神经网络对预处理后的车牌图像ILR进行特征提取，深入挖掘图像的本质特征，生成初始特征图FLR，公式为：S31: Standardize and scale the collected license plate images to eliminate image variations under different capture conditions and ensure the generalization ability of the model; use a convolutional neural network to extract features from the preprocessed license plate image ILR , deeply explore the essential features of the image, and generate an initial feature map FLR , the formula is:
； ;
式中，为卷积核权重，为偏置项，表示卷积操作，为激活函数；In the formula, is the convolution kernel weight, is the bias term, represents the convolution operation, is the activation function;
S32：将特征图FLR输入到包含通道注意力、空间注意力、像素注意力的三重注意力和残差连接块的特征增强模块，通过自注意机制以及残差连接增强车牌图像中的字符和布局特征，如字符边缘和对比度，并集成可变卷积层，根据特征图FLR的内容动态调整卷积核的形状和位置，输出增强后的特征图FLA；S32: Input the feature map FLR into the feature enhancement module including triple attention of channel attention, spatial attention, pixel attention and residual connection block, enhance the characters and layout features in the license plate image, such as character edges and contrast, through the self-attention mechanism and residual connection, and integrate the variable convolution layer, dynamically adjust the shape and position of the convolution kernel according to the content of the feature map FLR , and output the enhanced feature map FLA ;
S33：将增强后的特征图FLA输入字符特征上采样模块，使用反卷积操作进行上采样，反卷积可以有效地放大图像尺寸的同时增加图像的细节和清晰度，使得车牌上的字符更容易被后续的OCR模型准确识别，从低分辨率的车牌图像中恢复出高分辨率细节，输出超分辨率的车牌图像ISR，公式为：S33: The enhanced feature map FLA is input into the character feature upsampling module and upsampled using the deconvolution operation. Deconvolution can effectively enlarge the image size while increasing the image details and clarity, making the characters on the license plate easier to be accurately recognized by the subsequent OCR model, recovering high-resolution details from the low-resolution license plate image, and outputting the super-resolution license plate image ISR . The formula is:
； ;
式中，为反卷积核权重，为偏置项；In the formula, is the deconvolution kernel weight, is the bias term;
S34：采用生成对抗网络的训练策略，生成器用于生成超分辨率的车牌图像，判别器是一个OCR模型，逐步调整和更新卷积核权重、自主力权重和反卷积核权重，对超分辨率模型进行优化；S34: Using the training strategy of generative adversarial network, the generator is used to generate super-resolution license plate images, and the discriminator is an OCR model that gradually adjusts and updates the convolution kernel weights. , autonomy weights and deconvolution kernel weights , optimize the super-resolution model;
GAN能够生成与真实车牌非常接近的高质量图像，同时训练过程中的对抗性使模型在性能上持续进步，提高了超分辨率图像的真实感和实用性；GAN can generate high-quality images that are very close to real license plates. At the same time, the adversarial nature of the training process enables the model to continuously improve its performance, improving the realism and practicality of super-resolution images.
S35：对超分辨率模型定义复合损失函数L总，直至复合损失函数L总收敛到预设的阈值范围内，复合损失函数L总的计算公式为：S35: defining a composite loss functionLtotal for the super-resolution model until the composite loss function Ltotalconverges to within a preset threshold range. The calculation formulaof the composite loss function Ltotal is:
； ;
其中，in,
； ;
； ;
； ;
式中，为字符分类的交叉熵损失，用于表示模型对车牌字符的分类误差；N表示车牌图像中包含的字符总数；为第n个字符的权重；为输入特征，为第n个字符的真实标签；为给定输入时，第n个字符的预测概率；In the formula, is the cross entropy loss of character classification, which is used to represent the classification error of the model for license plate characters; N represents the total number of characters contained in the license plate image; is the weight of the nth character; is the input feature, is the true label of the nth character; For a given input When the nth character The predicted probability of
为字符定位损失，用于表示模型在字符位置定位上的误差；其中，函数和分别用于计算字符类型是否为数字或字母，若为数字或字母，则取值为，否则取值为0；为预定义的惩罚系数； is the character positioning loss, which is used to represent the error of the model in character positioning; among them, the function and They are used to calculate whether the character type is a number or a letter. If it is a number or a letter, the value is , otherwise the value is 0; is a predefined penalty coefficient;
为结构相似性损失，用于表示生成图像与真实图像之间的结构相似度误差；和分别为生成图像和真实图像的像素块；为结构相似性指数，用于衡量生成图像与真实图像之间的结构相似度，值越接近1表示越相似。通过计算1-SSIM来获取结构差异，再除以2以确保损失范围在[0, 0.5]之间。 is the structural similarity loss, which is used to represent the structural similarity error between the generated image and the real image; and are the pixel blocks of the generated image and the real image respectively; is the structural similarity index used to measure the generated image With real image The closer the value is to 1, the more similar it is. The structural difference is obtained by calculating 1-SSIM and then divided by 2 to ensure that the loss range is between [0, 0.5].
进一步地，车牌识别模型的构建过程包括：Furthermore, the construction process of the license plate recognition model includes:
从多个数据源收集车辆图像数据构成数据集，在联邦学习的环境下，将总图像数按客户端数量进行数据划分，以确保每个客户端在本地训练过程中使用不同的数据子集，客户端数量表示参与联邦学习训练的设备或节点数量；通过在联邦学习环境下将数据按客户端数量划分，确保各客户端训练数据的多样性和独立性，减少信息泄露风险。通过多节点协同学习，提高了模型的泛化能力。The vehicle image data is collected from multiple data sources to form a data set. In the federated learning environment, the total number of images is divided according to the number of clients to ensure that each client uses a different data subset during local training. The number of clients represents the number of devices or nodes participating in the federated learning training. By dividing the data according to the number of clients in the federated learning environment, the diversity and independence of each client's training data are ensured, reducing the risk of information leakage. Through multi-node collaborative learning, the generalization ability of the model is improved.
为了提高模型的准确性并防止过拟合，使用数据增强技术扩展每个客户端的数据集，对数据集中的原始图像进行缩放、特征标准化、水平和垂直偏移以及特征居中处理，具体为：In order to improve the accuracy of the model and prevent overfitting, data augmentation techniques are used to expand the dataset of each client. The original images in the dataset are scaled, feature normalized, horizontally and vertically offset, and feature centered. Specifically:
缩放：定义缩放因子s∈[0.8,1.2]，对图像尺寸进行随机缩放；Scaling: Define the scaling factor s∈[0.8,1.2] to randomly scale the image size;
特征标准化：使用均值μ和标准差δ对图像像素值进行标准化处理；Feature standardization: Use mean μ and standard deviation δ to standardize the image pixel values;
偏移：随机生成偏移值(Δx,Δy)，应用于图像坐标以实现随机裁剪；Offset: Randomly generate offset values (Δx, Δy) and apply them to image coordinates to achieve random cropping;
特征居中：对每个图像进行对称性调整，使每个图像的中心对齐于固定参考点；Feature centering: symmetrically adjust each image so that the center of each image is aligned with a fixed reference point;
通过超分辨率模型对扩展后的图像进行清晰度增强，生成高分辨率图像；The definition of the expanded image is enhanced through a super-resolution model to generate a high-resolution image;
使用U-Net模型从高分辨率图像中分割出车牌图像，U-Net在处理低光和不规则车牌图像方面表现突出，显著提高了识别精度；为了保护隐私，采用联邦学习（FL）方法，该方法在客户设备上进行去中心化的模型训练，数据不会离开设备，从而保证数据隐私；The U-Net model is used to segment the license plate image from the high-resolution image. U-Net performs well in processing low-light and irregular license plate images, significantly improving the recognition accuracy. In order to protect privacy, the Federated Learning (FL) method is used. This method performs decentralized model training on the customer device, and the data does not leave the device, thus ensuring data privacy.
U-Net模型包括编码器和解码器，具体实现步骤为：The U-Net model includes an encoder and a decoder. The specific implementation steps are as follows:
编码器部分通过卷积层和池化层逐步下采样输入图像，生成一组特征图；The encoder part gradually downsamples the input image through convolutional layers and pooling layers to generate a set of feature maps;
解码器部分通过上采样层和跳跃连接逐步恢复图像空间分辨率，并生成分割掩模；The decoder part gradually restores the image spatial resolution through upsampling layers and skip connections and generates segmentation masks;
采用联邦学习方法进行去中心化训练，通过对多个客户端的局部模型Wi聚合更新全局模型 W，公式为：The federated learning method is used for decentralized training. The global model W is updated by aggregating the local modelsWi of multiple clients. The formula is:
； ;
式中，G是参与训练的客户端数量，Wj表示第j个客户端的局部模型参数。Where G is the number of clients participating in the training, andWj represents the local model parameters of the jth client.
编码器通过卷积层和池化层提取图像特征，而解码器通过上采样和跳跃连接恢复图像的详细信息，这种结构可以有效捕捉车牌图像的重要特征并在图像分割时保持边界清晰。The encoder extracts image features through convolutional layers and pooling layers, while the decoder restores detailed information of the image through upsampling and skip connections. This structure can effectively capture the important features of the license plate image and keep the boundaries clear during image segmentation.
通过U-Net模型和联邦学习方法的结合，克服了YOLO V3和YOLO V4存在的局部化和内存分配问题，特别是改善了夜间条件下车牌识别的准确性；By combining the U-Net model with the federated learning method, the localization and memory allocation problems existing in YOLO V3 and YOLO V4 are overcome, especially the accuracy of license plate recognition under night conditions is improved;
通过OCR模型对已分割出的车牌图像中的每个字符进行二值化和特征提取，通过卷积神经网络实现字符分类；Binarize and extract features of each character in the segmented license plate image through the OCR model, and classify the characters through the convolutional neural network.
采用Dice相似系数作为评估图像分割性能的度量，公式为：The Dice similarity coefficient is used as a metric to evaluate image segmentation performance, and the formula is:
； ;
式中，为Dice相似系数；为真实掩模像素，为预测掩模像素，为常数，防止分母为0；In the formula, is the Dice similarity coefficient; is the real mask pixel, To predict the mask pixels, is a constant to prevent the denominator from being 0;
DSC常用于衡量图像分割的重叠精度，适用于不均匀大小对象的分割任务。DSC is often used to measure the overlap accuracy of image segmentation and is suitable for segmentation tasks of objects of uneven sizes.
使用F1分数评估分类结果，公式为：The F1 score is used to evaluate the classification results. The formula is:
； ;
式中，P为精确度，R为召回率。In the formula, P is the precision and R is the recall.
综合考虑了精确度和召回率，帮助优化模型性能，平衡漏检与误检，提高识别的准确性。Comprehensive consideration of precision and recall helps optimize model performance, balance missed detections and false detections, and improve recognition accuracy.
S4：将车牌信息通过5G网络传输回手持PDA终端进行可视化显示，人工确认车牌识别是否正确；S4: The license plate information is transmitted back to the handheld PDA terminal via the 5G network for visual display, and manual confirmation is made as to whether the license plate recognition is correct;
若识别错误则重新进行识别，并将错误信息上报云端，用于后续的模型训练和优化。If there is a recognition error, the recognition will be performed again and the error information will be reported to the cloud for subsequent model training and optimization.
优选地，本实施例中的手持PDA终端设有本地缓存机制，当网络不稳定或断网时，暂时将采集到的车牌图像保存在本地，自动切换到离线识别模式，通过轻量型离线识别模型对本地缓存的车牌图像进行离线识别；该模型相较于主要识别模型（如YOLO模型）而言，具有计算量小、资源消耗少的特点，因此能够在网络不可用的情况下，利用本地设备的有限计算资源进行车牌识别，确保系统的连续运行；Preferably, the handheld PDA terminal in this embodiment is provided with a local cache mechanism. When the network is unstable or disconnected, the collected license plate image is temporarily saved locally, and the mode is automatically switched to offline recognition mode. The locally cached license plate image is offline recognized by a lightweight offline recognition model. Compared with the main recognition model (such as the YOLO model), the model has the characteristics of small computational complexity and low resource consumption. Therefore, when the network is unavailable, the limited computing resources of the local device can be used for license plate recognition to ensure the continuous operation of the system.
当网络恢复时，自动或手动触发重试机制，将缓存的车牌图像上传到边缘计算节点进行处理，确保在网络恢复时可以继续使用缓存的数据，减少数据的重复获取和处理。When the network is restored, the retry mechanism is triggered automatically or manually to upload the cached license plate image to the edge computing node for processing, ensuring that the cached data can continue to be used when the network is restored, reducing repeated acquisition and processing of data.
如图2所示，为本发明的另一实施例，该实施例提供了一种基于5G神经网络的道路停车车牌识别系统，基于如上所述的一种基于5G神经网络的道路停车车牌识别方法，具体包括：As shown in FIG. 2 , another embodiment of the present invention provides a road parking license plate recognition system based on a 5G neural network, based on the above-mentioned road parking license plate recognition method based on a 5G neural network, specifically including:
摄像头，用于对车辆车牌进行拍照或视频扫描，以采集车牌图像；A camera is used to take a photo or video scan of the vehicle license plate to collect the license plate image;
5G通信模块，用于手持PDA终端和边缘计算节点间的数据通信；5G communication module, used for data communication between handheld PDA terminals and edge computing nodes;
边缘计算节点，用于通过超分辨率模型对所述车牌图像进行清晰度增强，并将处理后的车牌图像输入训练好的车牌识别模型进行识别，得到识别后的车牌信息；The edge computing node is used to enhance the clarity of the license plate image by using a super-resolution model, and input the processed license plate image into a trained license plate recognition model for recognition to obtain recognized license plate information;
云端服务器，用于执行车牌识别模型的训练和更新；A cloud server for training and updating the license plate recognition model;
本地缓存模块，用于当网络不稳定或断网时，暂时将采集到的车牌图像保存在本地；The local cache module is used to temporarily save the collected license plate images locally when the network is unstable or disconnected;
离线识别模块，用于离线识别模式下，通过轻量型离线识别模型对本地缓存的车牌图像进行离线识别。The offline recognition module is used in offline recognition mode to perform offline recognition on the locally cached license plate images through a lightweight offline recognition model.
综上所述，本发明利用5G通信技术和边缘计算节点，实现了车牌图像数据的实时获取和快速传输，同时在边缘计算节点上进行初步处理（如超分辨率增强和YOLO模型检测），降低了对云端的依赖，减少了数据传输的延迟和带宽消耗；通过在边缘计算节点和云端服务器之间协同工作，使用U-Net分割模型对车牌区域进行精确分割和识别，提高了识别的准确性；通过引入联邦学习模块，在分布式环境中实现数据隐私保护，避免数据泄露的风险，同时保证了识别模型的持续优化；设计本地缓存模块用于存储车牌图像数据及其识别结果，同时引入一个轻量型的离线识别模型，在网络不可用时使用该模型进行离线识别，从而保证系统的连续性和可靠性。In summary, the present invention utilizes 5G communication technology and edge computing nodes to realize real-time acquisition and rapid transmission of license plate image data, and performs preliminary processing (such as super-resolution enhancement and YOLO model detection) on the edge computing nodes, thereby reducing dependence on the cloud, reducing data transmission delays and bandwidth consumption; by working together between edge computing nodes and cloud servers, the U-Net segmentation model is used to accurately segment and identify the license plate area, thereby improving recognition accuracy; by introducing a federated learning module, data privacy protection is achieved in a distributed environment, the risk of data leakage is avoided, and continuous optimization of the recognition model is ensured; a local cache module is designed to store license plate image data and its recognition results, and a lightweight offline recognition model is introduced, which is used for offline recognition when the network is unavailable, thereby ensuring the continuity and reliability of the system.
在上述实施例中，可以全部或部分地通过软件、硬件、固件或者其他任意组合来实现。当使用软件实现时，可以全部或部分地以计算机程序产品的形式实现，计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行计算机程序指令时，全部或部分地产生按照本申请的流程或功能。计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。计算机指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输。In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or other arbitrary combinations. When implemented using software, it can be implemented in whole or in part in the form of a computer program product, which includes one or more computer instructions. When loading and executing computer program instructions on a computer, the process or function according to the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.
此外，在本申请各个实施例中的各功能单元可以集成在一个处理模块中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。上述集成的模块如果以软件功能模块的形式实现并作为独立的产品销售或使用时，也可以存储在一个计算机可读存储介质中。该存储介质可以是只读存储器，磁盘或光盘等。In addition, each functional unit in each embodiment of the present application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. If the above-mentioned integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The storage medium can be a read-only memory, a disk or an optical disk, etc.
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到其各种变化或替换，这些都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以权利要求的保护范围为准。The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411328443.3ACN118865351B (en) | 2024-09-24 | 2024-09-24 | A road parking license plate recognition method and system based on 5G neural network |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411328443.3ACN118865351B (en) | 2024-09-24 | 2024-09-24 | A road parking license plate recognition method and system based on 5G neural network |
| Publication Number | Publication Date |
|---|---|
| CN118865351Atrue CN118865351A (en) | 2024-10-29 |
| CN118865351B CN118865351B (en) | 2024-11-29 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411328443.3AActiveCN118865351B (en) | 2024-09-24 | 2024-09-24 | A road parking license plate recognition method and system based on 5G neural network |
| Country | Link |
|---|---|
| CN (1) | CN118865351B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119292073A (en)* | 2024-12-09 | 2025-01-10 | 上海申茂电磁线有限公司 | Automatic control system for the stacking rate of polyimide sintering lines |
| CN119723892A (en)* | 2025-02-27 | 2025-03-28 | 济南红旗信息科技有限公司 | A vehicle height limit warning system and device based on intelligent video recognition technology |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106251416A (en)* | 2016-07-25 | 2016-12-21 | 苏州爱开客信息技术有限公司 | The wagon control turnover system of customizable rule |
| CN109829450A (en)* | 2019-03-08 | 2019-05-31 | 中国联合网络通信有限公司广州市分公司 | A kind of building site dump truck intelligent monitoring system and monitoring and managing method |
| US20190251369A1 (en)* | 2018-02-11 | 2019-08-15 | Ilya Popov | License plate detection and recognition system |
| CN110781882A (en)* | 2019-09-11 | 2020-02-11 | 南京钰质智能科技有限公司 | License plate positioning and identifying method based on YOLO model |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106251416A (en)* | 2016-07-25 | 2016-12-21 | 苏州爱开客信息技术有限公司 | The wagon control turnover system of customizable rule |
| US20190251369A1 (en)* | 2018-02-11 | 2019-08-15 | Ilya Popov | License plate detection and recognition system |
| CN109829450A (en)* | 2019-03-08 | 2019-05-31 | 中国联合网络通信有限公司广州市分公司 | A kind of building site dump truck intelligent monitoring system and monitoring and managing method |
| CN110781882A (en)* | 2019-09-11 | 2020-02-11 | 南京钰质智能科技有限公司 | License plate positioning and identifying method based on YOLO model |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119292073A (en)* | 2024-12-09 | 2025-01-10 | 上海申茂电磁线有限公司 | Automatic control system for the stacking rate of polyimide sintering lines |
| CN119723892A (en)* | 2025-02-27 | 2025-03-28 | 济南红旗信息科技有限公司 | A vehicle height limit warning system and device based on intelligent video recognition technology |
| Publication number | Publication date |
|---|---|
| CN118865351B (en) | 2024-11-29 |
| Publication | Publication Date | Title |
|---|---|---|
| KR102319177B1 (en) | Method and apparatus, equipment, and storage medium for determining object pose in an image | |
| CN111754394B (en) | Method and device for detecting object in fisheye image and storage medium | |
| US12293581B2 (en) | Information pushing method in vehicle driving scene and related apparatus | |
| CN118865351A (en) | A road parking license plate recognition method and system based on 5G neural network | |
| CN115205264A (en) | A high-resolution remote sensing ship detection method based on improved YOLOv4 | |
| CN113192646B (en) | Target detection model construction method and distance monitoring method and device between different targets | |
| CN108109385A (en) | A kind of vehicle identification of power transmission line external force damage prevention and hazardous act judgement system and method | |
| CN115240089A (en) | A vehicle detection method for aerial remote sensing images | |
| US11605220B2 (en) | Systems and methods for video surveillance | |
| Balchandani et al. | A deep learning framework for smart street cleaning | |
| US20230053952A1 (en) | Method and apparatus for evaluating motion state of traffic tool, device, and medium | |
| CN112967341A (en) | Indoor visual positioning method, system, equipment and storage medium based on live-action image | |
| CN115115713A (en) | Unified space-time fusion all-around aerial view perception method | |
| CN112115737B (en) | Vehicle orientation determining method and device and vehicle-mounted terminal | |
| CN117455762B (en) | Method and system for improving recording image resolution based on panoramic driving recorder | |
| CN117288168B (en) | Unmanned aerial vehicle city building system of taking photo by plane of low-power consumption | |
| CN110503049B (en) | A method for estimating the number of vehicles in satellite video based on generative adversarial network | |
| CN119399379A (en) | A centimeter-level three-dimensional reconstruction method and system for wind farm equipment | |
| CN112926588A (en) | Large-angle license plate detection method based on convolutional network | |
| CN114120056B (en) | Small target identification method, device, electronic equipment, medium and product | |
| CN115358937B (en) | Image de-reflection method, medium and electronic device | |
| CN118172741A (en) | Image aggregation method, device, electronic equipment and storage medium | |
| CN119600031B (en) | Transmission line insulator chain defect positioning system and method based on cascade detection strategy | |
| CN119863638A (en) | Large-scene-oriented cross-view image template matching and positioning method | |
| Rohithaksha et al. | Road Accident Data Annotation and Reporting (RADAR)-A Comprehensive Approach to Automate Accident Images Analysis Using Deep Learning Algorithms |
| 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |