Multi-scale structure relevance based pedestrian target identification method

Abstract

The invention discloses a multi-scale structure relevance based pedestrian target identification method. First, saliency bottom layer characteristics of a target are extracted in multiple scales according to different validness of the target bottom layer visual characteristics of different scales. Seconds, according to the geometric structure consistence of the same kind of targets in different scales, a local structure mode of different scales is constructed by using a local restriction uniform encoding method on the target characteristic vectors in different visual characteristic channels. Finally, according to the characteristic dimension difference of the target in different scales, the local structure characteristics of the target in different scales are converted to a characteristicsub space having identical geometric structural features so as to improve the pedestrian target identification performance. The multi-scale structure relevance based pedestrian target identification method provided by the invention is prior to related alike methods internationally and has especially distinctive performance in classification identification of pedestrian targets having comparativelylarge resolution ratio difference in a monitoring video.

Description

technical field [0001] The application relates to a pedestrian target recognition method based on multi-scale structural correlation in video surveillance, especially a pedestrian target detection and recognition method applied to large scene monitoring areas and pedestrian target scales with diverse dimensions, which belongs to the technical field of digital image processing. Background technique [0002] With the development of computer vision technology and the increase in the number of surveillance videos, intelligent video surveillance technology has received extensive attention and research, and intelligent video surveillance information is playing an increasingly important role in people's lifestyles and social development; target classification Recognition technology, as one of the key technologies of intelligent video surveillance, directly affects the real-time performance, robustness and accuracy of the intelligent visual surveillance system. Therefore, target cla...

AI Technical Summary

Problems solved by technology

[0006] On the other hand, the existing multi-scale pedestrian target recognition methods are all based on the multi-scale pyramid resampling technology to obtain the feature information of the target at different scales, but these different scale targets are independent of each other, ignoring the local Characterization of Scale-Related Structural Properties

In recent years, combined with the special nature of the scale, researchers have carried out a number of studies using it for image region description and feature similarity measurement, but these methods only use the scale factor as a supplement to other description methods, without considering the same The interrelated characteristics between different scale features in the region, did not effectively use scale factors for structural description

Images