Deep license plate detection method based on thermodynamic diagram and key point regression

Abstract

The invention relates to a deep license plate detection method based on a thermodynamic diagram and key point regression. The method includes an off-line learning phase and a detection phase. The off-line learning phase includes the following four steps of: (1) designing network depth; (2) preparing a training sample set; (3) performing sample labeling; and (4) performing training. According to the step (1), a deep learning network structure is designed, inputted images are adjusted and unified, first-layer convolution and activation function operation are performed on the images, second-layerconvolution and activation function and pooling operation are performed, and third-layer convolution and activation function and pooling operation are performed, and a plurality of task branches areformed, one branch learns the coordinates of plate number plates through one convolutional layer, another branch learns the thermodynamic diagram of the license number plates through another convolutional layer. According to step (2), a batch of vehicle front or rear images is obtained and adopted as a sample set for offline learning, and the larger the total number of the classes of samples is, the better a training effect is, and the sizes of the samples are normalized. According to the method, the offline trained deep network is adopted to characterize a target, and therefore, license platedetection can be performed on the target quickly and steadily.

Description

technical field [0001] The invention relates to the field of intelligent transportation, and relates to a deep license plate detection method based on a heat map and key point regression. Background technique [0002] In recent years, the importance of video-based license plate detection and recognition technology in the field of intelligent transportation has been increasing, and the accuracy of license plate detection and recognition is an important indicator for judging the development of license plate recognition technology. License plate recognition technology can be applied to many fields such as residential parking management system, "electronic eye" system at important transportation hubs, expressway speed management system, etc., which brings a lot of convenience and guarantee to public safety and national development. With the continuous complexity of the traffic environment, some license plate recognition related products have gradually failed to meet the real-tim...

AI Technical Summary

Problems solved by technology

[0003] 1. The target detection method has the requirement to deal with multiple target scales, so it is usually time-consuming;

[0004] 2. Conventional detection methods usually use a sliding window combined with a target classifier method for target detection. Since the classifier will always make judgment errors, it is easy to miss the real license plate when using conventional detection methods in license plate detection. It is also easy to cause large number of false positives

Images