Method for detecting region of interest in complicated natural environment

Abstract

The invention relates to a method for detecting a region of interest, called ROI for short, from bottom to top based on combination of low-level image information and middle-level image information. The method for detecting the region of interest comprises the steps that firstly, an angular point is detected through the Harris operator, so that a convex hull boundary is obtained, and a middle-level information saliency map is calculated according to a convex hull area and a superpixel clustering result; secondly, an image which is originally in the RGB space is converted into the CIELab space, and filtering is conducted on the image through a Gaussian difference filter, so that a low-level information saliency map is obtained; finally, weight fusion is conducted on the low-level image information and the middle-level image information so that a saliency map of the image can be obtained. According to the method for detecting the region of interest, through the combination of the middle-level image information calculated through superpixel clustering and the low-level image information calculated through filtration of the difference filter, accurate positioning of the region of interest in the complicated natural environment is achieved, and the edge of a detected object of interest is clear; meanwhile, background noise can be effectively restrained, and the applicability is high.

Description

technical field [0001] The invention relates to a method for detecting a region of interest in a complex natural environment. The method has a good detection effect on the region of interest with different background contrast and background complexity and the images of the region of interest with different areas. It is used in multiple image processing fields such as image compression and coding, target detection and recognition, image retrieval, and robot active vision. Background technique [0002] At present, people are in the era of information explosion, accepting a large amount of visual information flow every second (10 8 -10 9 bits), so how to analyze and process massive image information more effectively has become one of the important research contents. Research has found that when the Human Visual System (HVS) deals with a relatively complex scene, it first focuses its visual attention on a few objects in the scene, namely the region of interest. This processin...

AI Technical Summary

Problems solved by technology

The saliency map obtained by this biological structure-based method has reduced resolution, with inaccurate localization of regions of interest and unclear edges

[0004] The main defects of existing methods are that the saliency of the region of interest is not prominent, the edges of salient objects are not clear, and there is noise in the background of the saliency map.

Images