A feature description method of target detection area based on first-order and second-order merging

Abstract

The invention provides a method for describing target detection region features based on merging between a first order and a second order. The method comprises the following steps: firstly, extracting features of a HOG inside a target detection rectangular region img1, and obtaining a feature vector hog; secondly, extracting a combination feature vector of a real target region in the target detection rectangular region img1; thirdly, conducting combination on the feature vectors and the merging between the first order and the second order, and obtaining the final feature vector of the target detection region. According to the method, firstly, interference from non-target regions is removed, a position feature vector is introduced to describe the relation between the image texture and the position, the merging between the first order and the second order is carried out on the position feature, the color feature and the texture feature to obtain the final feature description vector, the relevance between different feature dimensions is reserved, therefore, the better target feature description is obtained, and the method is suitable for various targets.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a target detection area feature description technology in the joint target detection and semantic segmentation technology. Background technique [0002] How to make computers have cognitive abilities similar to humans and automatically complete scene understanding is an extremely important basic problem in the field of computer vision research. Scene understanding is to let the computer understand the content of a picture, such as image segmentation, object recognition and other research. With the rapid development of electronic products and Internet technology in recent years, the content of pictures has become more and more diverse, which leads to a broad sense of scene understanding: the understanding of the subject of pictures. Among them, the joint target detection and semantic segmentation technology research how to jointly solve the two sub-tasks in s...

AI Technical Summary

Problems solved by technology

However, the object area (usually a rectangular area) obtained by target detection often contains non-target areas, and the features extracted from it will inevitably affect the feature expression of the real target area; secondly, the existing joint target detection and semantic segmentation systems often use a single The feature description method to express the target detection area cannot be applied to various target types

Images