Multiwavelet transform based license plate detection

The presented framework uses the localization concept of multiwavelet transform and empirical mode decomposition (EMD) to locate number plate from vehicle. Multiwavelet transform is similar to wavelet transform but unlike wavelet, it simultaneously provides orthogonality, symmetry, short-support and vanishing moment. Multiwavelet is used to decompose the image and EMD helps to find the actual wave crest from the projected information provided by multiwavelet transform. The effectiveness of the proposed algorithm is improvised using pre- and post-processing steps which include image enhancement and skew correction respectively. Proposed algorithm has also been tested on single and double line number plate. The performance of the proposed algorithm has been tested on various countries’ number plates like Croatia, Austria, France, India and Greece, and in various conditions like shadow, dirt and blurry. Proposed algorithm has detected number plate with high accuracy and in relatively less time.     

基于多尺度小波边缘检测的车牌定位研究

车辆牌照的准确定位是车牌识别系统中的关键步骤,利用车牌区域丰富的边缘和纹理信息以及车牌自身的特征,提出一种基于多尺度小波边缘检测的车牌定位方法.该方法能够更好地解决在复杂背景和复杂光照下的车牌定位.首先用图像增强和多尺度小波算子提取出车牌图像的边缘,然后利用数学形态学和连通区域标记的方法对车牌进行初步特征提取去除伪车牌区域,最后采用水平垂直投影法进行车牌的精确定位.实验结果表明,该方法能够实现车牌的快速准确定位,对复杂背景下的车牌具有很好的鲁棒性和实时性.     

汽车牌照自动识别系统的设计与研制

基于计算机图像处理技术的汽车牌照自动识别系统 ,要求能够将运动中汽车的牌照从复杂背景中准确地提取并识别出来。介绍了所研制的汽车牌照自动识别系统和关键技术 (图像分割与车牌定位、图像二值化和字符提取、车牌字符识别等 )。试验结果显示 ,系统在CeleronⅡ 6 33+12 8M的PC机上 ,对图像尺寸为 76 8× 5 74的 311幅试验图片的识别准确率达到 90 % ,识别时间≤1.5s。     

Temporal matching prior network for vehicle license plate detection and recognition in videos

In real‐world intelligent transportation systems, accuracy in vehicle license plate detection and recognition is considered quite critical. Many algorithms have been proposed for still images, but their accuracy on actual videos is not satisfactory. This stems from several problematic conditions in videos, such as vehicle motion blur, variety in viewpoints, outliers, and the lack of publicly available video datasets. In this study, we focus on these challenges and propose a license plate detection and recognition scheme for videos based on a temporal matching prior network. Specifically, to improve the robustness of detection and recognition accuracy in the presence of motion blur and outliers, forward and bidirectional matching priors between consecutive frames are properly combined with layer structures specifically designed for plate detection. We also built our own video dataset for the deep training of the proposed network. During network training, we perform data augmentation based on image rotation to increase robustness regarding the various viewpoints in videos.     

Automatic license plate detection in hazardous condition

Automatic detection of license plate (LP) is to localize a license plate region from an image without human involvement. So far a number of methods have been introduced for automatic license plate detection (ALPD), but most of them do not consider various hazardous image conditions that exist in many real driving situations. Hazardous image condition means an image can have rainy or foggy weather effects, low contrast environments, objects similar to LP in the background, and horizontally tilted LP area. All these issues create challenges in developing effective ALPD method. In this paper, we propose a new ALPD method which effectively detects LP area from an image in the hazardous conditions. For rain removal we apply a novel method that uses frequency domain mask to filter rain streaks from an image. A new contrast enhancement method with a statistical binarization approach is introduced in the proposed ALPD for handling low contrast indoor, night, blurry and foggy images. For correcting tilted LP, we apply Radon transform based tilt correction method for the first time. To filter non-LP regions, a new condition is used which is based on image entropy. We test the proposed ALPD method on 850 car images having different hazardous conditions, and achieve satisfactory results in LP detection.     

改进YOLOv5的车牌检测算法在林区中的应用北大核心CSCD

针对林区环境中现有的交通监控系统目标检测算法在雾、雨、雪等恶劣天气条件下车牌定位困难、精度低和检测速度慢等问题,提出了一种新的车牌检测方法。该方法以YOLOv5(you only look once v5)为基础模型,采用K-means++的方法对实例标签信息进行聚类分析获取新的初始化锚框尺寸,在特征提取网络中融入CBAM(convolutional block attention module)注意力机制提取到检测目标更多的特征信息,选取了CIoU作为损失函数提高检测框定位精度。在预处理方面,模拟摄像头在采集图像时可能产生的干扰,使用OpenCV-Python编写脚本对图像进行处理,增加算法在林区复杂环境下检测的鲁棒性。实验分析表明,该方法的均值平均精度@0.5(mean average precision@0.5,mAP@0.5)达99.5%、均值平均精度@0.5∶0.95(mAP@0.5∶0.95)达86.7%、检测速度达128帧/s、模型大小仅14 M,与YOLOv5以及其他主流目标检测算法相比有更好的准确性、实时性和广泛可部署性。