Rapid saliency object detection method of multi-scale neural network based on stereo attention control

Abstract

The invention discloses a rapid saliency object detection method of a multi-scale neural network based on stereo attention control. The objective of the method is to design a lightweight convolutionalneural network for salient object detection. The method includes: extracting multi-scale convolution features through a multi-branch structure, wherein each branch is a depth separable convolution with different expansion rates; adding the convolution features of all the branches, and calculating an attention graph for each branch by using a three-dimensional attention unit; multiplying the attention map obtained by calculation by the features of each branch, adding the multiplied results of each branch, and adding residual connection to form a multi-scale convolution module controlled by three-dimensional attention; and finally, stacking the multi-scale modules to form a deep convolutional neural network, and performing saliency object detection on a natural image. Experiments show thatcompared with an existing method, the method is higher in speed, fewer in parameters, less in calculated amount and similar in precision.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and in particular relates to a fast salient object detection method based on a multi-scale neural network controlled by stereo attention. Background technique [0002] Salient object detection, also known as saliency detection, is dedicated to detecting the most visually distinctive objects or regions in natural images. Saliency detection techniques have many applications in computer vision, such as image retrieval, image segmentation, object detection, object tracking, scene classification, content-based image editing, etc. Traditional salient object detection methods mainly rely on hand-designed features and prior knowledge, such as image contrast, texture features, and the characteristic that salient objects often appear in the center of the image, but these methods usually lack high-level semantic information. Recently, great advances in deep learning have led to continuous improveme...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problems of the existing salient object detection method based on convolutional neural network, such as too high computer complexity, too slow speed, and too many parameters, and propose a multi-scale neural network based on three-dimensional attention control. Fast salient object detection method

Images