A Pedestrian Analysis Method Based on Human Feature Distribution

Abstract

The invention relates to a pedestrian analysis method based on human body feature distribution. From the perspective of human body feature distribution, an intelligent pedestrian analysis method that combines a human body feature distribution model and a self-supervised structure-sensitive learning strategy is proposed. Using the self-supervised structure-sensitive learning method as the underlying framework, firstly, the candidate regions are generated by the method of superpixel segmentation, and the appearance model is established by extracting color and texture features for each region, and then the Gaussian function is used to establish the area ratio model. Finally, the two The model is superimposed to obtain the total human body characteristic distribution model. The final loss function is obtained by superimposing the analytical loss function, the joint structure loss function and the feature distribution loss function of the human body feature distribution model. The invention utilizes the self-supervised structure-sensitive learning method to make the generated analytical results have strong semantic consistency with the structure of the human body, which is more in line with the characteristics of human body feature distribution, and has invariance to occlusion, viewing angle and complex background.

Description

technical field [0001] The invention belongs to the technical field of image pedestrian analysis, uses a self-supervised structure-sensitive learning approach (Self-supervised Structure-sensitive Learning approach) as the underlying framework, and integrates a human body feature distribution model conforming to the human body feature distribution to perform human body analysis. The model first uses the superpixel segmentation method to generate candidate regions, and then calculates the similarity score between the candidate regions and the human body feature distribution model in the data set, so as to obtain the semantic labels of the joint points of each part of the human body. The present invention not only makes use of the self-supervised structure-sensitive learning method to make the generated analytical results have a strong semantic consistency with the structure of the human body, but also has characteristics that are more in line with the distribution of human body f...

AI Technical Summary

Problems solved by technology

However, due to the unavoidable complex factors such as illumination changes, partial occlusions, pose changes, and perspective changes in real scenes, pedestrian analysis research is challenging.

Images