Saliency detection method for color-thermal infrared image

Abstract

The invention discloses a saliency detection method for a color-thermal infrared image, and belongs to the field of computer vision image detection. The method comprises the following steps of: combining a thermal infrared image serving as an image channel with a color image, and performing super-pixel segmentation on the thermal infrared image by using a super-pixel segmentation method; extracting multiple types of feature vectors from each superpixel, establishing a graph model, and calculating an original graph adjacency matrix; stacking the multi-modal multi-feature graph adjacency matrixinto the tensor, and performing graph learning of a low-rank tensor; and finally, performing adaptive learning on the plurality of image adjacency matrixes by using an adaptive collaborative sorting algorithm to obtain an optimal image adjacency matrix, and performing superpixel saliency sorting by using background and foreground seed points respectively to obtain a final saliency map. According to the invention, image information of a color mode and a thermal infrared mode can be adaptively combined, and the robustness and accuracy of saliency detection are greatly improved.

Description

technical field [0001] The invention belongs to the field of computer vision image detection, and in particular relates to a saliency detection method for color-thermal infrared images based on low-rank tensor learning and cooperative sorting algorithm. Background technique [0002] Saliency detection, which aims to automatically locate the most attractive part from an image, has been widely used in various computer vision tasks. Over the past few decades, image saliency detection has been extensively explored by researchers. According to whether prior knowledge is applied to the saliency algorithm, saliency detection models can be divided into two categories: bottom-up model and top-down model. Among them, the bottom-up model is mainly driven by sensory stimuli and relies on low-level image features, such as color, texture, position, etc. The main disadvantage of this saliency detection method is that the detection results cannot contain all saliency regions and are easily...

AI Technical Summary

Problems solved by technology

These algorithms usually have the following problems: 1. The multi-type features extracted from a pair of color-thermal infrared images usually contain the same image information, and the interaction of these same information may produce information redundancy, making useful The information becomes blurred and will greatly increase the computational complexity; 2. When the image of one of the two modalities is severely disturbed, the algorithms of Li, Tu and Tang et al. often cannot achieve good detection results, because they cannot Nicely adaptive combining images from both modalities

Images