Target detection method based on global convolution and local deep convolution fusion

Abstract

The invention discloses a target detection method based on global convolution and local deep convolution fusion, changes an original three-dimensional area suggestion network, and provides an ASD network structure based on asymmetric segmentation depth perception for target detection. By doing so, the features of each level and depth in the feature map can be extracted more fully. In addition, innovative technologies such as horizontal and vertical convolution fusion networks, a distillation network and an angle optimization algorithm are introduced, so that the detection effect is further improved.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a target detection method based on global convolution and local deep convolution fusion. Background technique [0002] Object detection is one of the classic problems in computer vision. Its task is to use a box to mark the position of the object in the image and give the category of the object. From the traditional framework of artificially designed features plus shallow classifiers to the end-to-end detection framework based on deep learning, object detection has become more and more mature step by step. Object detection is not difficult for the human eye, but the computer is faced with an RGB pixel matrix, it is difficult to directly obtain abstract concepts such as dogs and cats from images and locate their positions, plus object posture, lighting and complex backgrounds mixed together, making object detection more difficult. The detection algorithm usually includes three par...

AI Technical Summary

Problems solved by technology

[0007] The present invention proposes a target detection method based on global convolution and local deep convolution fusion, which is used to solve or at least partially solve the technical problem of poor detection effect existing in the methods in the prior art

Images