Stereoscopic vision comfort level evaluation method based on motion features inside area of interest

Abstract

The invention discloses a stereoscopic vision comfort level evaluation method based on motion features inside an area of interest. The stereoscopic vision comfort level evaluation method based on the motion features inside the area of interest includes the steps: formulating a strategy of computing motion feature vectors inside a stereoscopic vision interest area, building a stereoscopic vision model which represents a non-liner relationship between stereoscopic video motion features and a stereoscopic vision comfort level through subjective testing, selecting a spatial domain mean value strategy, a minimum value integration strategy and a time domain mid-value strategy based on the motion feature vectors inside the stereoscopic vision interest area and a nonlinearity stereoscopic vision model, and formulating the stereoscopic vision comfort level evaluation method. Uniformity of between evaluation results provided and results of human-eye subjective stereoscopic comfort is good.

Description

technical field [0001] The invention relates to the field of binocular stereo vision, in particular to a method for evaluating comfort of stereo vision based on motion characteristics in a region of interest of a stereo video. Background technique [0002] The evaluation standard of stereoscopic vision comfort is based on the visual characteristics of stereoscopic video (such as parallax features, motion characteristics, etc.), and establishes corresponding standards to judge and predict the stereoscopic comfort degree of stereoscopic video to observers. With the rapid development of stereoscopic TV technology, the evaluation standard of stereoscopic visual comfort has gradually attracted people's attention. Because in the field of stereo vision safety, the stereo vision comfort evaluation standard plays a key role in predicting stereo vision fatigue and discomfort. In the analysis process of preventing stereoscopic vision fatigue and discomfort, the convergence-accommodati...

AI Technical Summary

Problems solved by technology

[0006] However, there are certain problems with the above three evaluation criteria: First, the first and second evaluation criteria mentioned above are analyzed and judged based on the global disparity information; according to the human eye attention model, compared with the global disparity information, interested The disparity information in the area plays a more significant and important role in the evaluation standard of stereoscopic vision comfort, thereby improving the accuracy of judgment of stereoscopic vision comfort; secondly, the third evaluation standard mentioned above is based on the Block-level motion features; compared to pixel-level motion features, it cannot accurately reflect changes in motion features of stereoscopic video in the temporal and spatial domains; at the same time, the third evaluation standard uses dense optical flow tracking methods to obtain motion information ; Compared with the sparse optical flow tracking method, its robustness is not good, and it needs to consume a lot of computing time; in addition, in the process of extracting the region of interest, it does not combine the depth spatial information to further improve the region of interest extraction the accuracy of

Images