Pedestrian trajectory tracking method, system and related device

Abstract

The invention provides a pedestrian trajectory tracking method, and relates to the field of image processing, and the method comprises the steps: obtaining image data; performing feature extraction on the image data, and constructing a candidate relation mask; extracting a historical frame feature set of the pedestrian trajectory library, and performing feature calculation on the historical frame feature set and the candidate frames in the candidate frame relation mask to obtain a person frame feature distance matrix and a frame person feature distance matrix; calculating the feature distance between the target pedestrian and the candidate box, and classifying the target candidate box, the feature distance between which and the target pedestrian satisfies the minimum distance, into the trajectory of the target pedestrian until no detection box satisfying the condition exists in the current frame detection box; and updating the pedestrian trajectory library, and outputting the pedestrian index set of the target pedestrian and the corresponding position trajectory. The problem of insufficient feature richness in the pedestrian tracking process can be effectively solved, and the pedestrian tracking detection precision is improved. The invention also provides a pedestrian trajectory tracking system, a computer readable storage medium and electronic equipment, which have the above beneficial effects.

Description

technical field [0001] The present application relates to the field of image processing, and in particular, to a pedestrian trajectory tracking method, system and related device. Background technique [0002] Pedestrian target tracking has always been one of the most important research directions in the field of computer vision. Due to its high landing value and practicability, pedestrian target tracking has received attention from researchers in various fields. [0003] Multiple Object Tracking (MOT, Multiple Object Tracking) is a difficult subject in the field of object tracking. At this stage, practitioners in this field usually combine object detection and metric learning to achieve it. Usually, we use object detection algorithms to detect pedestrians. It locates, and uses metric learning to extract the features of the located pedestrians, and then realizes the calculation of the same pedestrian trajectory through the feature matching strategy. However, due to the large...

AI Technical Summary

Problems solved by technology

However, due to the large number of tracking targets, the existing strategy will cause more False Negative and ID-Switch phenomena.

Images