Neural network system, as well as image analysis method and device based on neural network system

Abstract

Provided are a neural network system, and an image parsing method and device based on same. The method comprises: acquiring, by a neural network system, a first visual feature vector x of a target object; according to the first visual feature vector x of the target object, determining, by a shielding estimation sub-network of the neural network system, a shielding mark vector xo of a shielded portion of the target object; according to the first visual feature vector x and the shielding mark vector xo, determining, by a shielding completion sub-network, a third visual feature xc of the target object after complementing the shielded portion; and according to the third visual feature vector xc, determining, by a resolution sub-network, class mark images of all the parts of the target object, and combining the class mark images of all the parts to obtain a parsing result of the target object. The method can solve the image parsing problem when a target object is shielded, and can accurately obtain the parsing result of the target object even if the target object is shielded.

Description

technical field [0001] The invention relates to data communication technology, in particular to a neural network system, an image analysis method and device based on the neural network system. Background technique [0002] Pedestrian target parsing is to decompose a pedestrian image into regions with specific semantics, such as hair, torso, arms, legs, etc. After the pedestrian target is analyzed, it can be conveniently used in various pedestrian target analysis and understanding tasks such as pedestrian pose estimation and behavior analysis. It has important application value in image and video search, video surveillance and other methods. The problem of pedestrian target analysis is very challenging, not only because pedestrians have great changes in appearance, posture, shape, etc., but also pedestrian images captured in real environments such as video surveillance often have large occlusions and clutter. background. [0003] The existing pedestrian target analysis meth...

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a neural network system, an image analysis method and device based on the neural network system, which can solve the analysis problem when the target object is blocked, and make the analysis result more accurate

Images