A traffic incident detection method based on depth learning and entropy model

Abstract

A traffic incident detection method based on depth learning and entropy model relates to the technical field of intelligent traffic. The traffic incident detection method based on depth learning and entropy model includes the following steps: 1) training a convolutional neural network model for traffic incident classification; 2) performing incident classification on input video stream images or video subsegments according to the convolutional neural network model; 3) calculating the entropy value in a period of time according to the result of the incident classification; 4) judging whether atraffic incident occur according to the entropy value. Compared with the prior art, the reliability parameter is calculated according to the proportional and inverse relation between different incident probability, the entropy value and stability. The mutation of the image is analyzed from the global and local characteristics of video images, the occurrence of traffic incidents is detected with the advantages and methods of CNN and the characteristics of mutation detection by entropy model, and the method has characteristics of fast speed and accurate detection.

Description

technical field [0001] The invention relates to the technical field of intelligent transportation, in particular to a traffic event detection method based on deep learning and an entropy model. Background technique [0002] The traffic incident detection method based on video analysis is gradually becoming a research hotspot at home and abroad because of its fast detection speed and rich detection information. Since the mid-1990s, the United States, Britain, Japan and other countries have begun to study the rapid automatic event detection system based on image processing, simulating the method of manual identification of traffic anomalies to achieve rapid event detection, such traditional methods are usually from video images Detect vehicles in the system, track moving vehicles, extract features such as speed change rate, position, area, direction, etc. According to these feature models, traffic events can be judged. Technical points include moving target detection, vehicle...

AI Technical Summary

Problems solved by technology

[0019] In the prior art, the detection method based on image processing and artificial discrimination of traffic anomalies still has the following disadvantages: being interfered by factors such as image quality, scene diversification, camera focal length, occlusion, adhesion, etc., it will often be seriously affected in the detection process , resulting in false and missed detection of traffic incidents

The application of traditional algorithms in the above scenarios will be greatly restricted

[0020] There are also some deficiencies in deep learning in the prior art: relying only on deep learning methods, there are challenges in the construction of sample libraries, network model design, training methods, network parameters, and classification methods, and traditional static images The training model used as a sample library can only obtain the static features of the image

The detection of traffic incidents often requires dynamic feature analysis in the time domain. Therefore, the method that relies solely on deep learning has the problems of low accuracy and many false detections and missed detections in the detection of traffic incidents.

Images