Semi-online machine-set multi-target tracking method

Abstract

The invention relates to a semi-online machine-set multi-target tracking method, which comprises the following steps of: obtaining a detection frame of a pedestrian or a moving target according to a pedestrian or moving target video, obtaining a Kalman sequence spectrum according to position change information between the detection frames in a period of time window, finding a pair of Kalman headsaccording to the Kalman sequence spectrum, and tracking the pedestrian or the moving target according to the pair of Kalman heads. obtaining a detection frame of a target or a moving object to be tracked in the next frame through the similarity of the appearance model, the moving model and the size change model, enabling the target or the moving object to be located in the detection frame in the frame, and otherwise, indicating that the target is lost; and splicing the detection frames of which the similarity is higher than a threshold value into the Kalman sequence spectrum, updating the motion model and the appearance model in the Kalman sequence spectrum, and tracking the pedestrian or moving object target in the next frame. The method is suitable for any trajectory splicing type multi-target tracking algorithm, that is, constraint of different trajectories generated by multiple targets such as pedestrians and moving objects is avoided, the tracking precision can be effectively improved, and the identity conversion value is reduced.

Description

technical field [0001] The invention relates to a tracking method, in particular to a semi-online multi-target tracking method. Background technique [0002] The multi-target tracking method is mainly applied to the trajectory tracking of multiple people or moving objects in the video sequence captured by the camera: in the unmanned vehicle driving scene, pedestrians or other vehicle targets on the road can be captured by the camera installed in the unmanned vehicle , to perform real-time trajectory tracking and predict its trajectory, so that unmanned vehicles can implement effective avoidance or automatic driving decisions based on the movement of these targets; in multiple cross-camera monitoring scenarios, multiple pedestrians in the camera can be monitored as needed Tracking, the trajectories and positioning of multiple pedestrian targets can be monitored through the videos captured by different cameras; in sports scenes captured by cameras, such as basketball games, mu...

AI Technical Summary

Problems solved by technology

[0004] The occlusion problem has always been one of the difficulties in MOT. Although the iterative updates of various algorithms are very fast, most of the algorithm performance is still difficult to maintain robustness when encountering severe occlusion.

But essentially by sacrificing real-time

Precision and accuracy are very important in actual tracking application scenarios. For example, the poor real-time performance of the tracking algorithm in driverless cars will cause the vehicle to judge lag, lead to misjudgment or delayed decision-making, and cause unnecessary traffic accidents; poor accuracy will lead to The tracking of multiple targets is disordered, leading to tracking failure. For example, the application of multiple target tracking algorithms in multiple smart cameras in cities will lead to lost pursuit when tracking criminal suspects, or tracking non-suspects, causing real suspects to escape, etc.

Images