A multi-body tracking method based on human body part model

Abstract

The invention provides a multi-body tracking method based on a human body part model, and relates to the technical field of video monitoring. It includes: acquiring image data, extracting the human body part model of each person and calculating color features, obtaining each person's part feature set, and assembling to obtain a list of multiple human body part feature sets. Then calculate the similarity between each person's part feature set obtained in the current frame and each person in the multi-body part feature set list obtained in the previous frame to obtain a matching matrix. Then, according to the matching matrix, calculate the similarity confidence of each person obtained in the current frame to each person obtained in the previous frame, and match the target obtained in the current frame with the target in the previous frame according to the similarity and similarity confidence to obtain the tracking result . This method can accurately match the detection target of the current frame to the position of the previous frame and discover a new target, effectively solving the problem of tracking failure due to feature differences caused by human body deformation in the process of multi-body tracking.

Description

technical field [0001] The invention relates to the technical field of video monitoring, and in particular to a multi-body tracking method based on a human body part model. Background technique [0002] Smart society and smart city have become a main direction of domestic urban construction. With the explosion of artificial intelligence technology, artificial intelligence has become a national strategy and policy. The retail industry has also proposed the concept and measures of new retail, which will be highly intelligent, convenient, automated, and professional, greatly reducing intermediate links and liberating manpower. Among them, smart unmanned stores have become the most emerging market in the current retail industry. The smart unmanned store is the product of the combination of artificial intelligence and new retail. It is a 7x24 unattended store that realizes the entire shopping process through artificial intelligence. This kind of store is connected with the arti...

AI Technical Summary

Problems solved by technology

[0004] Although there are many different tracking methods, the most important thing in the tracking process is the characteristics of the target, and the main reason for the tracking failure is the feature change during the tracking process.

At present, the problems of multi-body tracking technology are as follows: due to the difference in features caused by the change of human scale, the tracking fails; compared with other targets, human targets will undergo more deformation during the movement process, and the resulting features Changes; changes in target features due to partial occlusion

Images