A vehicle tracking method based on motion prediction and multi-feature fusion

Abstract

The invention discloses a vehicle tracking method based on motion prediction and multi-feature fusion. The method comprises the following steps: 1) traversing a tracking list to obtain the bounding frame of the tracking target vehicles in a prediction area from a video frame; 2) judging overlapping of all the tracking target vehicles, if so, entering step 3), or entering step 5); 3) calculating the multi-feature fusion similarity between the overlapping target vehicles and the original tracking target vehicle and performing target matching; if matching is successful, entering step 5); or counting the number of lost frames of the target and going to step 4); 4) if the number of lost frames of the target is great than the threshold value, the target vehicle is not added into the tracking list; or the target is added into the tracking list and the filter template is updated. 5) estimating the prediction area of the next frame based on motion prediction; and 6) after processing of all thetracking target vehicles is completed, reading the next video frame and going to step 1) until the end of video frame collection.

Description

technical field [0001] The invention relates to the technical fields of intelligent transportation systems, computer vision and target tracking, in particular to a vehicle tracking method based on motion prediction and multi-feature fusion. Background technique [0002] In order to observe and understand the traffic conditions of various roads in a more timely and comprehensive manner, the traffic police departments of most cities in my country have deployed real-time road video surveillance systems to achieve the purpose of deterring illegal driving, observing road conditions, and guiding traffic flow. However, most of the road video surveillance systems that have been deployed in large numbers can only display and record the video transmitted by the cameras at each monitoring point, and do not have intelligent analysis capabilities. Therefore, it is also necessary to arrange a large number of additional personnel to manually monitor the large amount of video streams obtain...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problem that the tracking accuracy and speed in the current traditional vehicle tracking methods are difficult to meet the application requirements. On the basis of the fast tracking method based on correlation filtering, a vehicle tracking method based on motion prediction and multi-feature fusion is proposed. , this method has high tracking accuracy while achieving fast tracking, and has a good tracking effect on fast-moving vehicles and mutual occlusion scenes

Images