Method and system for full-time vehicle detection and tracking in video based on Kalman filter and deep learning

Abstract

The invention provides a method and system for full-time vehicle detection and tracking in video based on Kalman filter and deep learning, and the method comprises the steps: firstly carrying out theoffline training of a CNN model, and building vehicle daytime and nighttime infrared classifiers; secondly collecting an image frame through the system, detecting a vehicle: obtaining moving and stationary targets during daytime through a moving and stationary target detection method and carrying out the classifying of the vehicle through the daytime classifier, detecting the position of a vehiclelamp during daytime through a vehicle lamp detection method, and detecting the position of the vehicle through the nighttime classifier; thirdly initializing a Kalman filter for each detected vehicletarget; fourthly switching to a next frame, detecting the position of the vehicle in the current frame, and predicting the position through the Kalman filter used for the vehicle target in a former frame; fifthly comparing a detected position and a predicted position, connecting the vehicle target in the former frame and the position of the vehicle in the current frame, and obtaining the trackingpath of the vehicle; and finally drawing a continuous frame path of the vehicle in the video through the system.

Description

technical field [0001] The invention belongs to the fields of image recognition, video analysis and vehicle recognition, and in particular relates to a full-time vehicle detection and tracking method and system in video based on Kalman filtering and deep learning. Background technique [0002] With the development of society and the continuous improvement of people's living standards, automobiles have gradually become popular. But what follows is traffic accidents, especially the trend of vicious traffic accidents continues to rise. In recent years, the growth rate of vehicles has been far higher than that of roads and other traffic facilities. Therefore, traffic accidents continue to occur, casualties are increasing day by day, and property losses are serious. The main causes of traffic accidents are speeding, lane-occupied driving, drunk driving, and fatigue driving. Therefore, for the traffic management department, video surveillance is used to monitor the running statu...

AI Technical Summary

Problems solved by technology

[0013] Patent CN201220337489 "Intelligent traffic control device based on image processing" is based on the method of motion detection. When the vehicle stops, the vehicle will blend into the background. If the motion method cannot detect the vehicle, it cannot be tracked; at the same time, it does not describe the situation of night detection

[0014] Patent CN201210357874 "A Vehicle Tracking Method and System" is a method based on feature detection. This method traverses the entire image or a partial image. The search strategy requires a large amount of calculation, and the target features cannot be updated in time. Changes in posture can easily lead to tracking loss , at the same time, due to occlusion, error elimination, etc., the temporarily lost target cannot continue to track; at the same time, the situation of night detection is not described

Images