Multi-pedestrian tracking method based on iterative filtering and observation discrimination

Abstract

The invention discloses a multi-pedestrian tracking method based on iterative filtering and observation discrimination. Iterative component combination detection is performed on a to-be-detected videoimage three times so as to reduce the omission ratio. A histogram area overlapping ratio is calculated between a newly added target head gray histogram reserved after the third iteration and an average gray histogram of the head image block after the second iteration. The target head detection frame of which the overlapping rate is smaller than a set threshold value is filtered out to effectivelyinhibit the influence of a false detection frame on the detection performance, reserve a reliable target detection frame, and facilitate the improvement of the detection accuracy. A local observablearea of the mutually-shielded or incomplete detection target is extracted. Center and scale information of the multi-target observable area is acquired., An observation data set is established and tracking is realized according to the observation data set and the target trajectory confidence. The method can be applied to the fields of artificial intelligence, intelligent robots, intelligent videomonitoring and the like.

Description

technical field [0001] The invention relates to a multi-pedestrian tracking method based on iterative filtering and observation discrimination, which belongs to the field of computer vision and is mainly used in artificial intelligence, intelligent robots and intelligent video monitoring. Background technique [0002] Multi-target tracking is one of the research hotspots in the field of computer vision and intelligent video information processing. It has a wide range of applications in public security monitoring and management, medical image analysis, behavior understanding, and visual navigation. At present, scholars at home and abroad are mainly concerned with tracking robustness and accuracy improvement in complex scenes such as similar feature interference between targets, blurred appearance and occlusion. [0003] In the article "Object Detection with Discriminatively Trained Part-Based Models" published by FelzenszwalbPF et al. in IEEE Transactions on Pattern Analysis ...

AI Technical Summary

Problems solved by technology

This method has a small amount of calculation and meets the real-time tracking requirements. However, after multiple targets are occluded and separated, there will be problems of target identity confusion and trajectory misjudgment.

In the article "Robust Online Multi-object Tracking Based on Tracklet Confidence and Online Discriminative Appearance Learning" (TC-ODAL) published in IEEE Conference on Computer Vision and Pattern Recognition (2014:1218-1225), Bae S H et al. The quantitative linear discriminant appearance algorithm solves the problem of identity confusion in the process of multi-target tracking and improves the performance of multi-target tracking. However, when the target is lost and reappears, the algorithm has the problem of reinitializing the new identity label.

In the article "High-Speed ​​Tracking-by-Detection Without Using Image Information" published by International Workshop on Traffic and Street Surveillance for Safety and Security at IEEE Avss (2017:1-6), Bochinski E et al. The change proposes a multi-target tracking algorithm based on the target region of interest. The algorithm can run at a rate of 100,000 frames per second, but in the case of missing detection, it will reduce the tracking performance

Images