Salient object detection method based on central rectangular composition prior

Abstract

The invention provides a salient object detection method based on a central rectangular composition prior. The central rectangle refers to a rectangle surrounded by four composition intersections of thirds of the composition line. The method comprises steps of: supposing that a salient object is arranged along the composition line of the central rectangle, performing correlation ordering on the super-pixels on the four sides of the central rectangle to obtain a central rectangle composition line salient map; supposing that the salient target is located at the intersection of the center rectangle composition, removing composition intersections unlikely to be the salient object according to the central rectangle composition line salient map, and then computing the spatial distance between all the super-pixel nodes and a center node in an image by using the rest composition intersections as the center node to form a corresponding salient map, and finally adding and fusing the salient maps to form a central rectangle composition intersection salient map; then acquiring a compactness relation salient map by using a compactness relation; and finally, fusing the three maps to obtain a final salient map. The method conforms to the principle of photographic composition and conforms to the human visual attention mechanism.

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