CN103686161B - The quality evaluating method of disparity map and 3D video and device - Google Patents
The quality evaluating method of disparity map and 3D video and device Download PDFInfo
- Publication number
- CN103686161B CN103686161B CN201210349352.9A CN201210349352A CN103686161B CN 103686161 B CN103686161 B CN 103686161B CN 201210349352 A CN201210349352 A CN 201210349352A CN 103686161 B CN103686161 B CN 103686161B
- Authority
- CN
- China
- Prior art keywords
- disparity map
- quality
- video
- quality evaluating
- bias
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Abstract
The invention provides a kind of quality evaluating method of disparity map, comprising: determine the average of disparity map, the degree of bias and kurtosis; The quality of disparity map is evaluated according to average, the degree of bias and kurtosis.Present invention also offers a kind of quality evaluating method of 3D video, comprising: from 3D video, obtain piece image; Convert image to disparity map; The quality evaluating method of above-mentioned disparity map is utilized to evaluate the quality of disparity map; The quality evaluating disparity map is better, then the quality evaluating 3D video is better; The quality evaluating disparity map is poorer, then the quality evaluating 3D video is poorer.Present invention also offers the quality evaluation device of a kind of disparity map and 3D video.Invention increases evaluation quality.
Description
Technical field
The present invention relates to image domains, in particular to quality evaluating method and the device of disparity map and 3D video.
Background technology
Three-dimensional (three-dimensional 3D) Display Technique has become current noticeable frontier science and technology.Having the disparity map that the left eye of parallax and eye image are called stereo display, is placed at a certain distance by two cameras with identical parameters to take Same Scene and the two width images that obtain.In actual life, during human eye viewing jobbie, convergent point and focusing are consistent, and the distance namely from convergent point to eyes equals diopter adjustment distance.
The rating quality how improving three-dimensional 3D program is an important topic, and video quality detection supporting with it and objective evaluation are key factors wherein.Image quality evaluating method refers to by design mathematic model, carries out intellectual analysis to image, and carries out the method for objectively evaluating of automatic scoring according to the quality yardstick of design.Image quality evaluating method be analysis image compression and treatment effect, feedback image transmission quality key technology, be important component part indispensable in multimedia system.
The subjective method of traditional dependence manual observation carries out quality evaluation to disparity map not only wastes time and energy, and the impact that the result evaluated is subject to evaluating environment, evaluates the factors such as person works's background, cannot objectively respond the quality of disparity map.
Summary of the invention
The present invention aims to provide quality evaluating method and the device of disparity map and 3D video, to solve the above problems.
In an embodiment of the present invention, provide a kind of quality evaluating method of disparity map, comprising: determine the average of disparity map, the degree of bias and kurtosis; The quality of disparity map is evaluated according to average, the degree of bias and kurtosis.
In an embodiment of the present invention, provide a kind of quality evaluating method of 3D video, comprising: from 3D video, obtain piece image; Convert image to disparity map; The quality evaluating method of above-mentioned disparity map is utilized to evaluate the quality of disparity map; The quality evaluating disparity map is better, then the quality evaluating 3D video is better; The quality evaluating disparity map is poorer, then the quality evaluating 3D video is poorer.
In an embodiment of the present invention, provide a kind of quality evaluation device of disparity map, comprising: parameter module, for determining the average of disparity map, the degree of bias and kurtosis; Evaluation module, for evaluating the quality of disparity map according to average, the degree of bias and kurtosis.
In an embodiment of the present invention, provide a kind of quality evaluation device of 3D video, comprising: acquisition module, for obtaining piece image from 3D video; Modular converter, for converting image to disparity map; Above-mentioned disparity map quality evaluation device; Video evaluation module, better for the quality evaluating disparity map, then the quality evaluating 3D video is better; The quality evaluating disparity map is poorer, then the quality evaluating 3D video is poorer.
The disparity map of the above embodiment of the present invention and the quality evaluating method of 3D video and device, because adopt parameter to carry out evaluation quality, so overcome the artificial subjective bias evaluated, improve evaluation quality.
Accompanying drawing explanation
Accompanying drawing described herein is used to provide a further understanding of the present invention, and form a application's part, schematic description and description of the present invention, for explaining the present invention, does not form inappropriate limitation of the present invention.In the accompanying drawings:
Fig. 1 shows the flow chart of the quality evaluating method of the disparity map according to the embodiment of the present invention;
Fig. 2 shows the flow chart of the quality evaluating method of the 3D video according to the embodiment of the present invention;
Fig. 3 shows the schematic diagram of the quality evaluation device of the disparity map according to the embodiment of the present invention;
Fig. 4 shows the schematic diagram of the quality evaluating method of the 3D video according to the embodiment of the present invention.
Embodiment
Below with reference to the accompanying drawings and in conjunction with the embodiments, describe the present invention in detail.
Fig. 1 shows the flow chart of the quality evaluating method of the disparity map according to the embodiment of the present invention, comprising:
Step S10, determines the average of disparity map, the degree of bias and kurtosis;
Step S20, evaluates the quality of disparity map according to average, the degree of bias and kurtosis.
This method, because adopt parameter to carry out evaluation quality, so overcome the artificial subjective bias evaluated, improves the evaluation quality of disparity map.In addition, adopting parameter to carry out evaluation quality can realize with computer programming easily, thus can realize the automation of quality evaluation, it also improves the assess effectiveness of disparity map, saves hand labor.
Preferably, step S20 comprises: quality and the average of evaluating disparity map are inversely proportional to, and with the degree of bias and kurtosis be inversely proportional to.
Preferably, step 10 comprises:
Average MU=E [D] is set;
Degree of bias SK=E [(D-μ) is set
3]/(E [(D-μ)
2])
3/2;
Kurtosis KU=E [(D-μ) is set
4]/(E [(D-μ)
2])
2;
Wherein, E [] refers to and asks desired value, and D is the image value of each pixel in disparity map, μ=MU.
If disparity map is gray-scale map, image value can be gray value.
Preferably, step S20 comprises: arrange quality coefficient INDEX=MU* (SK+KU); If INDEX is less, then the quality evaluating disparity map is better; If INDEX is larger, then the quality evaluating disparity map is poorer.
Fig. 2 shows the flow chart of the quality evaluating method of the 3D video according to the embodiment of the present invention, comprising:
Step S15, obtains piece image from 3D video;
Step S25, converts image to disparity map;
Step S35, utilizes the quality evaluating method of above-mentioned disparity map to evaluate the quality of disparity map;
Step S45, the quality evaluating disparity map is better, then the quality evaluating 3D video is better; The quality evaluating disparity map is poorer, then the quality evaluating 3D video is poorer.
Wherein now can convert image to gray-scale map, then convert disparity map to.
This method, because adopt parameter to carry out evaluation quality, so overcome the artificial subjective bias evaluated, improves the evaluation quality of 3D video.In addition, adopting parameter to carry out evaluation quality can realize with computer programming easily, thus can realize the automation of quality evaluation, it also improves the assess effectiveness of 3D video, saves hand labor.
Fig. 3 shows the schematic diagram of the quality evaluation device of the disparity map according to the embodiment of the present invention, comprising:
Parameter module 10, for determining the average of disparity map, the degree of bias and kurtosis;
Evaluation module 20, for evaluating the quality of disparity map according to average, the degree of bias and kurtosis.
This device improves evaluation quality and the assess effectiveness of disparity map.
Preferably, evaluation module 20 evaluates the quality of disparity map and average is inversely proportional to, and with the degree of bias and kurtosis and be inversely proportional to.
Preferably, parameter module 10 comprises:
MU module, for arranging average MU=E [D];
SK module, for arranging degree of bias SK=E [(D-μ)
3]/(E [(D-μ)
2])
3/2;
KU arranges kurtosis KU=E [(D-μ)
4]/(E [(D-μ)
2])
2;
Wherein, E [] refers to and asks desired value, and D is the image value of each pixel in disparity map, μ=MU.
Preferably, evaluation module 20 arranges quality coefficient INDEX=MU* (SK+KU); If INDEX is less, then the quality evaluating disparity map is better; If INDEX is larger, then the quality evaluating disparity map is poorer.
Fig. 4 shows the schematic diagram of the quality evaluating method of the 3D video according to the embodiment of the present invention, comprising:
Acquisition module 15, for obtaining piece image from 3D video;
Modular converter 25, for converting image to disparity map;
Above-mentioned disparity map quality evaluation device 35;
Video evaluation module 45, better for the quality evaluating disparity map, then the quality evaluating 3D video is better; The quality evaluating disparity map is poorer, then the quality evaluating 3D video is poorer.
This device improves evaluation quality and the assess effectiveness of 3D video.
Obviously, those skilled in the art should be understood that, above-mentioned of the present invention each module or each step can realize with general calculation element, they can concentrate on single calculation element, or be distributed on network that multiple calculation element forms, alternatively, they can realize with the executable program code of calculation element, thus, they can be stored and be performed by calculation element in the storage device, or they are made into each integrated circuit modules respectively, or the multiple module in them or step are made into single integrated circuit module to realize.Like this, the present invention is not restricted to any specific hardware and software combination.
The foregoing is only the preferred embodiments of the present invention, be not limited to the present invention, for a person skilled in the art, the present invention can have various modifications and variations.Within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (8)
1. a quality evaluating method for disparity map, is characterized in that, comprising:
Determine the average of disparity map, the degree of bias and kurtosis;
The quality of described disparity map is evaluated according to described average, the degree of bias and kurtosis;
Wherein, the quality evaluating described disparity map according to described average, the degree of bias and kurtosis comprises:
Quality and the described average of evaluating described disparity map are inversely proportional to, and with the described degree of bias and kurtosis and be inversely proportional to.
2. method according to claim 1, is characterized in that, determines that the average of disparity map, the degree of bias and kurtosis comprise:
Average MU=E [D] is set;
Degree of bias SK=E [(D-μ) is set
3]/(E [(D-μ)
2])
3/2;
Kurtosis KU=E [(D-μ) is set
4]/(E [(D-μ)
2])
2;
Wherein, E [] refers to and asks desired value, and D is the image value of each pixel in described disparity map, μ=MU.
3. method according to claim 2, is characterized in that, the quality evaluating described disparity map according to described average, the degree of bias and kurtosis comprises:
Quality coefficient INDEX=MU* (SK+KU) is set;
If INDEX is less, then the quality evaluating described disparity map is better; If INDEX is larger, then the quality evaluating described disparity map is poorer.
4. a quality evaluating method for 3D video, is characterized in that, comprising:
Piece image is obtained from described 3D video;
Convert described image to disparity map;
The quality evaluating method of the disparity map described in any one of claim 1-3 is utilized to evaluate the quality of described disparity map;
The quality evaluating described disparity map is better, then the quality evaluating described 3D video is better; The quality evaluating described disparity map is poorer, then the quality evaluating described 3D video is poorer.
5. a quality evaluation device for disparity map, is characterized in that, comprising:
Parameter module, for determining the average of disparity map, the degree of bias and kurtosis;
Evaluation module, for evaluating the quality of described disparity map according to described average, the degree of bias and kurtosis;
Wherein, described evaluation module evaluates the quality of described disparity map and described average is inversely proportional to, and with the described degree of bias and kurtosis and be inversely proportional to.
6. device according to claim 5, is characterized in that, described parameter module comprises:
MU module, for arranging average MU=E [D];
SK module, for arranging degree of bias SK=E [(D-μ)
3]/(E [(D-μ)
2])
3/2;
KU arranges kurtosis KU=E [(D-μ)
4]/(E [(D-μ)
2])
2;
Wherein, E [] refers to and asks desired value, and D is the image value of each pixel in described disparity map, μ=MU.
7. device according to claim 6, is characterized in that, described evaluation module arranges quality coefficient INDEX=MU* (SK+KU); If INDEX is less, then the quality evaluating described disparity map is better; If INDEX is larger, then the quality evaluating described disparity map is poorer.
8. a quality evaluation device for 3D video, is characterized in that, comprising:
Acquisition module, for obtaining piece image from described 3D video;
Modular converter, for converting described image to disparity map;
Disparity map quality evaluation device according to any one of claim 5-7;
Video evaluation module, better for the quality evaluating described disparity map, then the quality evaluating described 3D video is better; The quality evaluating described disparity map is poorer, then the quality evaluating described 3D video is poorer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210349352.9A CN103686161B (en) | 2012-09-19 | 2012-09-19 | The quality evaluating method of disparity map and 3D video and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210349352.9A CN103686161B (en) | 2012-09-19 | 2012-09-19 | The quality evaluating method of disparity map and 3D video and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103686161A CN103686161A (en) | 2014-03-26 |
| CN103686161B true CN103686161B (en) | 2015-09-16 |
Family
ID=50322253
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210349352.9A Expired - Fee Related CN103686161B (en) | 2012-09-19 | 2012-09-19 | The quality evaluating method of disparity map and 3D video and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103686161B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108257117B (en) * | 2018-01-02 | 2022-06-28 | 中兴通讯股份有限公司 | Image exposure evaluation method and device |
| CN109862349B (en) * | 2019-02-18 | 2021-05-18 | 北京中科慧眼科技有限公司 | Quality detection method and device of disparity map and automatic driving system |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102209257A (en) * | 2011-06-17 | 2011-10-05 | 宁波大学 | Stereo image quality objective evaluation method |
-
2012
- 2012-09-19 CN CN201210349352.9A patent/CN103686161B/en not_active Expired - Fee Related
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102209257A (en) * | 2011-06-17 | 2011-10-05 | 宁波大学 | Stereo image quality objective evaluation method |
Non-Patent Citations (1)
| Title |
|---|
| 《ALGORITHMIC ASSESSMENT OF 3D QUALITY OF EXPERIENCE FOR IMAGES AND VIDEO》;Anish Mittal, Anush K.Moorthy, Joydeep Ghosh and Alan C.Bovik;《Digital Signal Processing Workshop and IEEE Signal Processing Education Workshop(DSP/SPE),2011 IEEE》;20110107;第338-343页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103686161A (en) | 2014-03-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108495110B (en) | Virtual viewpoint image generation method based on generation type countermeasure network | |
| Held et al. | Blur and disparity are complementary cues to depth | |
| CN104243976B (en) | A kind of three-dimensional image objective quality evaluation method | |
| Oh et al. | Stereoscopic 3D visual discomfort prediction: A dynamic accommodation and vergence interaction model | |
| CN109431763B (en) | VR-based visual accommodation function training method and system | |
| CN102708567B (en) | Visual perception-based three-dimensional image quality objective evaluation method | |
| CN104571474A (en) | Method and device for adaptively adjusting contents displayed on terminal screen | |
| EP2501139A3 (en) | Ghost-compensation for improved stereoscopic projection | |
| CN102833560A (en) | Image processing apparatus, image processing method, and program | |
| EP2551827A3 (en) | Presenting three dimensional depth | |
| CN105407349A (en) | No-reference objective three-dimensional image quality evaluation method based on binocular visual perception | |
| EP2408212A3 (en) | Mobile terminal and 3D image controlling method therein | |
| EP2629532A3 (en) | Display control program, display control apparatus, display control system, and display control method | |
| US20150304625A1 (en) | Image processing device, method, and recording medium | |
| CN103136748B (en) | The objective evaluation method for quality of stereo images of a kind of feature based figure | |
| CN103873854A (en) | Method for determining number of stereoscopic image subjective assessment testees and experiment data | |
| CN104506773A (en) | Camera automatic zoom control method based on human eye distance | |
| CN103686161B (en) | The quality evaluating method of disparity map and 3D video and device | |
| Geng et al. | A stereoscopic image quality assessment model based on independent component analysis and binocular fusion property | |
| CN106910322B (en) | A kind of pre- myopia prevention device of wear-type based on stereoscopic vision and behavioural analysis | |
| CN104954778A (en) | Objective stereo image quality assessment method based on perception feature set | |
| EP2461594A3 (en) | Image processing device, image processing method, and program | |
| Zhou et al. | PMFS: a perceptual modulated feature similarity metric for stereoscopic image quality assessment | |
| CN102999911B (en) | Three-dimensional image quality objective evaluation method based on energy diagrams | |
| CN102999912A (en) | Three-dimensional image quality objective evaluation method based on distorted images |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20150916 Termination date: 20190919 |