Method for detecting significance of stereo image based on human eye stereo visual characteristics

Abstract

The invention particularly relates to a method for detecting significance of a stereo image based on human eye stereo visual characteristics. The method comprises the following steps of calculating the significance of view information of two different dimensions (space and depth) of a stereo image; firstly, using an SLIC (simple linear iterative clustering) algorithm to perform ultrapixel segmentation on a single-viewpoint view, and combining similarity of areas; then, using a GBVS (graph-based visual saliency) algorithm to calculate a two-dimensional space significance map; combining the absolute parallax feature, local parallax feature and depth contrast feature in a parallax map to perform depth significant calculation; finally, combining with human eye visual fatigue characteristics to reasonably process the parallax distribution, clustering the significance of the two different dimensions of significance maps by a linear weighting type, and generating a stereo image significance map. The method can be used for effectively detecting the significance area of the stereo image under different scenes, and is suitable for the fields of doubtful object calculation, image searching and the like.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a method for detecting the saliency of a stereoscopic image based on binocular stereovision of human eyes. Background technique [0002] Saliency detection technology is an important part of stereoscopic video processing technology and is also the basis of many different applications in image processing, especially in important applications such as object detection and recognition, image compression, visual navigation and image quality assessment. For example, it can be obtained by The salient detection technology obtains the visually salient areas of the stereoscopic video, further improves the video image quality of the visually salient areas, and reduces the processing time of the non-salient areas (that is, areas that have less impact on the human visual system). [0003] Most of the current saliency calculation models only use spatial two-dimensional inf...

AI Technical Summary

Problems solved by technology

[0003] Most of the current saliency calculation models only use spatial two-dimensional information such as image color, brightness, shape, and texture as input, and then perform saliency calculations based on pixel points by downsampling or multi-scale transformation. However, these The calculation model does not consider the distance information of the object in most cases, and is not suitable for the saliency detection of the stereo image

Images