Stereo image quality evaluation method based on stereo perception characteristics
A stereoscopic perception and stereoscopic image technology, applied in the field of image processing, can solve the problems of inaccurate parallax and depth information acquisition, insufficient consideration of binocular characteristics, etc., and achieve accurate reflection and high consistency effect
Active Publication Date: 2021-11-02
TIANJIN UNIV
View PDF14 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The above evaluation methods have achieved good results in different development stages of stereoscopic image quality evaluation. However, due to the inaccurate acquisition of disparity and depth information, and insufficient consideration of binocular characteristics, stereoscopic image quality evaluation is still a hot and difficult point in current research.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0051] The present invention will be further described below in conjunction with the accompanying drawings.
[0052] The invention relates to the synthesis of stereoscopic images to depth perception images, the extraction of frequency domain information and the prediction of its statistical characteristics. A method is proposed to describe the image quality through the influence of distortion on the statistical characteristics of the frequency domain information by using the frequency domain information of both the depth perception image and the image content. Such as figure 1 with figure 2As shown in the stereoscopic image quality evaluation method based on stereoscopic perception characteristics, each distorted stereo image pair is composed of a left view and a right view, and the distorted image pair is (D l ,D r ), including the following steps:
[0053] Step 1: Simulate the characteristics of human stereo vision, and calculate the disparity maps of the left and right...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a stereoscopic image quality evaluation method based on stereoscopic perception characteristics: calculate the parallax maps of the left and right viewpoints according to the parallax matching algorithm; respectively use the left and right views as reference images to obtain the relative parallax map; according to the parallax and depth formula to obtain the depth perception map; use db7 to do four-layer wavelet decomposition for the depth perception map, left view, and right view respectively; extract the coefficients of three subbands in each layer; solve the amplitude, variance and sum of each subband in the first layer Entropy features; perform the above processing on the coefficients of the remaining three layers; calculate the frequency domain statistical characteristics of the depth perception map, left view, and right view; train 80% distorted stereo image pairs, and predict 20% distorted image pairs to obtain stereo images quality. The invention simulates the depth visual perception image formed in the brain, combines the image content, and uses the frequency domain information of the image as a means to describe the quality of the stereoscopic image through the statistical characteristics of the frequency domain information, so as to make a more comprehensive and accurate objective evaluation.
Description
technical field [0001] The present invention relates to the field of image processing, and more specifically, relates to a stereoscopic image quality evaluation method based on stereoscopic perception characteristics. Background technique [0002] Stereoscopic images / videos can enable people to experience the stereoscopic and telepresence, and gradually become the mainstream direction of multimedia research, and the demand for development and application in the market is becoming more and more urgent, such as stereoscopic digital TV, 3D movies, virtual Realistic systems, etc. However, due to the limitation and influence of stereoscopic video acquisition system, storage medium, compression coding and transmission equipment in the collection, storage, processing and transmission of stereoscopic video, it is inevitable to introduce noise or interference, which will cause the quality of stereoscopic video image on the display terminal to deteriorate. decline. Therefore, the st...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00G06T7/42
CPCG06T7/0002G06T2207/10012G06T2207/30168G06T7/42
Inventor 杨嘉琛汪亚芳姜斌朱英豪计春祺
Owner TIANJIN UNIV