A multi-target tracking method and system based on depth features

Abstract

The embodiment of the invention provides a multi-target tracking method and system based on depth features. The method comprises the following steps: obtaining detection frame positions correspondingto targets detected in a current frame image and the depth features of the targets; based on the position of the detection frame corresponding to each target in the previous frame of image, obtainingthe prediction position of each target in the current frame by using a Kalman filter; according to the detection frame position corresponding to each target, the prediction position of each target inthe current frame, the depth feature of each target and the depth feature set of each tracker, performing cascade matching on the detection frame corresponding to each target and the tracker by usinga Hungarian algorithm; And calculating an IOU distance matrix between the detection frame on the non-cascade matching and the tracker to be matched, and performing IOU matching between the detection frame and the tracker by using a Hungarian algorithm based on the IOU distance matrix to obtain a final matching set. According to the embodiment of the invention, the target tracking effect under theshielding condition can be effectively improved, and the number of times of ID switching is reduced.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of deep learning, and more specifically, to a multi-target tracking method and system based on deep features. Background technique [0002] The main task of multi-object tracking is to simultaneously locate multiple objects of interest in a given video, maintain their IDs, and record their trajectories. [0003] With the rapid development of target detection technology, tracking by detection (Tracking by detection) has become the mainstream in multi-target tracking. In this processing mode, target trajectories are computed by globally optimized processing of the entire video stream, such as flow networks, probabilistic graphical models, etc. However, batch processing makes these methods unsuitable for online scenarios that require real-time object detection. More traditional methods are Multiple Hypothesis Tracking and Joint Probabilistic Data Association Filter. Another method is th...

AI Technical Summary

Problems solved by technology

[0004] The existing multi-target tracking methods have the problems of ID switching, large calculation and implementation complexity, and low tracking performance when there is occlusion

Images