Multi-feature fusion multi-target tracking method based on Kalman filtering assistance

Abstract

The invention discloses a multi-feature fusion multi-target tracking method based on Kalman filtering assistance, and the method comprises the steps: firstly, reading any two frames of images in a video frame, inputting a preprocessed image into a multi-target detector, and obtaining a detection result of each frame in a video; introducing a target occlusion mechanism, enabling the judgment mechanism to carry out judgment according to coordinates of a target center point and the size of a target, and if the occluded part is small or no occlusion exists, enabling the detector to input the masscenter coordinates of the detection frame and the preprocessed video frame into a pre-trained convolutional neural network, extract the semantic information of the shallow layer and the deep layer ofthe target, perform cascading to form a feature matrix, and then perform similarity estimation on the feature matrixes of the two frames to obtain an optimal track; and if the detected target occlusion condition is serious, inputting the mass center coordinates of the detection frame into a Kalman filter, estimating the position information of the target in the next frame according to the previousmotion state of the target, and comparing the estimated coordinate information with an actual detection result to obtain an optimal track.

Description

technical field [0001] The invention belongs to the technical field of intelligent video multi-target tracking, and in particular relates to a multi-target tracking method based on Kalman filter-assisted multi-feature fusion. Background technique [0002] How to build a safe and harmonious social security environment, so as to effectively protect the lives and property of the country and the people, is a difficult and important issue that needs to be solved urgently before the governments of all countries. The video surveillance system is an important part of the security system. It first obtains real-time video frames through the front-end video acquisition equipment (such as a camera), and then performs real-time monitoring of the monitoring scene through manual browsing or intelligent video analysis technologies. It is a preventive capability. Strong integrated system. The multi-target detection and tracking system, as the core part of video analysis technology, uses com...

AI Technical Summary

Problems solved by technology

[0003] At the same time, the current target tracking technology mainly has the following deficiencies: (1) Most of them are semi-automatic single target tracking systems, which also require manual participation, which is inefficient and cannot meet the tracking requirements of multiple targets; (2) Even at present There are a small number of multi-target tracking systems, but the computational complexity of these systems is too high, it is difficult to meet the real-time requirements of video surveillance and it is difficult to ensure the accuracy of tracking results

Images