Dual-mode image saliency detection method based on node classification and sparse graph learning

Abstract

The invention discloses a bimodal image saliency detection method based on node classification and sparse graph learning, and belongs to the technical field of computer vision. According to the invention, the method comprises the steps: taking a thermal infrared image as an image channel of a color image to carry out superpixel segmentation, extracting color features and multilayer semantic features of each superpixel in a bimodal image, establishing a graph model, and then carrying out low-rank matrix decomposition on the color features of the two modal images, generating a corresponding low-rank matrix and a sparse matrix, and classifying graph model nodes; calculating an initial adjacency matrix according to a node classification distance and an Euclidean distance, and then carrying out sparse graph learning saliency sorting by using the initial adjacency matrix and an indication vector for many times to obtain a saliency graph. Compared with an existing saliency detection method, the method has the advantages that the detection precision is remarkably improved, the image saliency region can be well separated from the background, and the method still has good performance on images shot in a rain and fog environment and an environment with insufficient light.

Description

technical field [0001] The invention relates to an image saliency detection method, in particular to a dual-mode image saliency detection method based on node classification and sparse graph learning. Background technique [0002] Saliency detection is to identify the most attractive objects or regions in an image by simulating the attention mechanism of the human eye. As a key step in image processing, salient object detection plays an important role in computer vision tasks such as image segmentation, object tracking, and image fusion. [0003] Most of the current saliency detection methods are mainly designed for visible light images, that is, RGB images. When exposed to challenging environments such as poor lighting conditions or complex backgrounds, methods designed for RGB images may not be able to accurately distinguish salient objects from the image background. Therefore, some researchers have begun to use multiple sensors to acquire images of different modalities,...

AI Technical Summary

Problems solved by technology

The above saliency detection methods for RGB images and thermal infrared images usually have the following problems: 1. The graph learning used in the above methods is graph learning with complete information, which will cause repeated learning of information, increase the amount of calculation and cause information loss. Redundancy; 2. The above methods all use Euclidean distance to calculate the adjacency matrix. This calculation method only considers the local relationship between nodes, and does not consider its global relationship, which leads to low accuracy of saliency detection.

Images