Salient object detection method based on cascade improved network

Abstract

The invention discloses an RGB-D saliency object detection method based on a cascade improved network, and belongs to the technical field of image processing. Most existing RGB-D models directly aggregate the features from the CNN networks of different levels, and the noise and interference information contained in low-level features are easily introduced. The invention creatively provides a cascade improved structure, a saliency map generated by the features of a high-level part is used as a mask to improve the features of a low-level part, and then a final saliency map is generated by aggregating the improved low-level features. In addition, in order to eliminate the interference information of the depth map, the invention provides a depth enhancement module for preprocessing before thedepth features and the RGB features are mixed. According to the method, four evaluation indexes are used for carrying out experiments on seven data sets, and the results show that the method surpassesall current most advanced RGB-D saliency object detection methods.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to an RGB-D salient object detection method based on a cascaded improved network. [0002] technical background [0003] The purpose of RGB-D saliency detection is to combine RGB images with depth information to find the most salient objects in a scene. In recent years, various smart devices capable of capturing depth information (such as smart phones, somatosensory peripherals, etc.) have been popularized and widely used, so a large number of RGB-D saliency algorithms have been proposed. [0004] Early RGB-D saliency detection algorithms mainly used manual features, and these methods greatly relied on specific knowledge, such as local area comparison, global area comparison, background prior knowledge, spatial prior knowledge, and channel prior knowledge. In order to effectively use manual features, researchers have used various classic tools such as support vector machine...

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to solve the problem of background interference caused by the noise contained in low-level partial features by direct aggregation of features of each level without distinction in the existing RGB-D saliency detection method, and to improve depth features and RGB feature models. Aiming at the problem of state matching ability, a RGB-D salient object detection method based on cascaded improved network is designed.

Images