A Salient Object Detection Method Based on Center Rectangle Composition Prior

Abstract

The present invention provides a salient object detection method based on the composition prior of the central rectangle. The central rectangle refers to the rectangle surrounded by the four composition intersection points of the third composition line. Assuming that the salient objects are arranged along the central rectangular composition line, perform correlation sorting on the superpixels on the four sides of the central rectangle to obtain the saliency map of the central rectangular composition line; assuming that the salient objects are located at the intersection of the central rectangular composition line, according to the saliency of the central rectangular composition line The graph removes the compositional intersection points that are unlikely to become salient objects, and then takes the remaining compositional intersection points as the central nodes to calculate the spatial distances between all superpixel nodes and the central node in the image to form a corresponding saliency graph, and finally add and fuse them to form The intersection point saliency map of the central rectangle composition; then the compactness relationship saliency map is obtained by using the compactness relationship; finally, the three are fused to obtain the final saliency map. The method follows the rules of photographic composition and conforms to the visual attention mechanism of human eyes.

Description

technical field [0001] The invention belongs to the field of computer vision, and in particular relates to a salient target detection method. Background technique [0002] Salient object detection in computer vision has attracted increasing attention in recent years. Salient target detection is mostly used in image segmentation, target recognition, video tracking, image classification, image compression, etc., and belongs to the basic research work in computer vision. Researchers have also proposed many algorithms for salient object detection. [0003] In 2013, Yang et al. proposed the MR method in the paper Saliency Detection via Graph-Based ManifoldRanking to perform superpixel segmentation on the image, set the superpixel nodes where the four boundaries of the image are located as the background, and search for the target background distribution map according to the feature correlation ranking. , and then starting from the found target, the saliency map is refined by fe...

AI Technical Summary

Problems solved by technology

[0006] In order to overcome the noise caused by the initialization of the composition line near the image boundary as the target in the method of calculating the salient value of the image with the composition line as the target and the error problem caused by assuming that the image center is the salient target, the present invention provides a composition based on a center rectangle A priori salient object detection methods

Images