CN202004914U - Intelligent video image quality automatic analysis system - Google Patents
Intelligent video image quality automatic analysis system Download PDFInfo
- Publication number
- CN202004914U CN202004914U CN2011201198628U CN201120119862U CN202004914U CN 202004914 U CN202004914 U CN 202004914U CN 2011201198628 U CN2011201198628 U CN 2011201198628U CN 201120119862 U CN201120119862 U CN 201120119862U CN 202004914 U CN202004914 U CN 202004914U
- Authority
- CN
- China
- Prior art keywords
- video
- image
- analysis
- control device
- video image
- 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
Images
Landscapes
- Closed-Circuit Television Systems (AREA)
Abstract
The utility model discloses an intelligent video image quality automatic analysis system, which comprises a control device, a video analysis device and a video matrix connected with an image acquisition device, and is characterized in that the control device is communicated with the video analysis device, is in charge of sending a video image analysis instruction request to the video analysis device and receives and displays results analyzed by the video analysis device to a user; and the video analysis device is communicated with the video matrix, video images are acquired from the video matrix according to the instructions of the control device, the video images are analyzed to obtain the analysis results of the video images, and the analysis results of the video images are transmitted to the control device. The system has high measurement accuracy, good repeatability and consistency, high system cost performance and good reliability. An indicator algorithm is scientific and advanced, and has the determination precision ratio of 90%.
Description
Technical field
The invention belongs to technical field of video monitoring, relate to a kind of fault detect aspect of video monitoring equipment, particularly a kind of intelligent video picture quality automatic analysis system and analytical method thereof.
Background technology
Video monitoring is the important component part of safety and protection system, directly perceived with it, accurately, in time and the information content abundant and be widely used in multiple occasions such as traffic, civil defence, community, market.Video monitoring is a kind of powerful general defensive character in all files.In recent years, along with the develop rapidly of computer, network and image processing, transmission technology, the video monitoring technology has also had significant progress.
Video monitoring equipment in the prior art is easy to be subjected to environmental factor (humidity, dust etc.) and other people and is factors such as malicious sabotage owing to be installed in the outfield mostly; The ageing equipment problem that also has himself in addition; Follow and various faults occur, it is invalid etc. to adjust, move as blank screen, blue screen, mosaic, interference stripes, disturbance, snowflake, focal length, video owing to be subjected to the interference of various factors, phenomenons such as picture disturbances, striped may occur in the middle of the process of transmission and conversion in addition.Yet, because watch-dog does not have the function of automatic detected image quality, nobody found after a lot of watch-dogs went wrong, still transmitting wrong picture, this has just brought a lot of inconvenience to monitoring management, the monitor staff can't find merit timely, stops the generation of case, and then influences the stable of urban public security and society.
Summary of the invention
The object of the invention is to provide a kind of intelligent video picture quality automatic analysis system, has solved in the prior art video monitoring equipment and has broken down and can't point out video monitoring user and camera image quality problem such as can't monitor.
In order to solve these problems of the prior art, technical scheme provided by the invention is:
A kind of intelligent video picture quality automatic analysis system comprises control device, video analysis device and is connected the video matrix of image collecting device; It is characterized in that described control device and video analysis device communication, be responsible for the instruction request of video image analysis is sent to video analysis device, and the result who accepts the video analysis device analysis is shown to the user; Described video analysis device and video matrix communication are obtained video image according to the instruction of control device from video matrix, video image is analyzed, and obtain the analysis result of video image, and the analysis result of video image is transferred to control device.
Preferably, between described control device and video analysis device switch is set, described switch connects video analysis device and the video matrix that is connected image collecting device respectively, described control device by switch respectively with video analysis device, video matrix communication.
Preferably, image is set in the described video analysis device and imports module, image detection module and output module; Described image imports module and is used for video image is imported in the video analysis device, and video image is carried out preliminary treatment; Described image detection module is used for the parameter of video image is detected, and is aggregated in the output module and exports; Described output module is used for the parameter of video image is transferred to control device by connecting line.
Preferably, described image detection module comprises monochromatic screen detection module, definition detection module, mosaic detection module, The Cloud Terrace detection module, camera parameters detection module.
Preferably, described monochromatic screen detection module is used for detecting the proportion of each pixel of video image each component in the RGB color mode, judges whether video image exists blank screen, blue screen, ash screen phenomenon; Described definition detection module is used for the edge feature of video image is detected, and judges the definition of video image; Described mosaic detection module is used for detecting the mosaic phenomenon of video image; Described The Cloud Terrace detection module is used to detect The Cloud Terrace rotation direction and rotation situation; Described camera parameters detection module changes judgement focal length of camera change information according to the definition of video image.
Preferably, described image imports module and is provided with video input interface, and described video input interface directly is connected by the VGA line with video matrix, accepts the input of 6 road analog videos.
Preferably, described control device, switch, video analysis device and video matrix constitute the video monitoring local area network (LAN), carry out network communication by switch between described video analysis device and video matrix.
Preferably, described control device is connected with the video matrix digital input-output interface by digital input-output interface, the vision signal of described video matrix is connected into the video signal input interface of video analysis device by connecting line, and the control signal transmit port of described video analysis device is connected with the RS232 interface of control device.
Preferably, the control signal transmit port of described video analysis device is connected with the RS232 interface of control device by the network switch; The instruction of described control device is connected with the video matrix digital input-output interface by the network switch by digital input-output interface output back.
Video matrix of the present invention can be existing product, shows by video image is switched to any one output channel from any one input channel.A M * N matrix can be arranged, can support image input of M road and the output of N road image simultaneously.
Video analysis device can realize video image quality is detected automatically and analyzes in the technical solution of the present invention intelligent video picture quality automatic analysis system, particularly to video image blank screen, blue screen, grey screen, definition, mosaic, The Cloud Terrace rotate up and down, The Cloud Terrace left-right rotation, eight quality index of focal length of camera carry out automatic analyzing and testing.
The present invention can detect and feedback result by the video image quality automatic analysis system, by visual analysis technology and the image recognition technology of using a computer, greatly improved plant maintenance efficient, patrolling and examining equipment fault targetedly by former no purpose, nothing detects automatically, reports to the police automatically, improve the efficient of patrolling and examining of outfield watch-dog, promoted the video monitoring system intelligent level.
The present invention has remedied the defective that video image self can't detect error picture automatically and report to the police, thereby provide a kind of video analyzer of automatic analysis image quality, the regularly regular monitor video image is detected as requested, automatically analyze and form the result, and formation result of determination form, in time feed back to the repair and maintenance personnel, thereby improve the efficient of patrolling and examining of outfield video camera, promote the video monitoring system intelligent level.
The control device of video image quality automatic analysis system of the present invention is an industrial computer that embeds the video image quality auto-analyzer procedure, and wherein trace routine can be carried out the detection of eight quality index such as " blank screen, blue screen, grey screen, definition, mosaic, The Cloud Terrace rotate up and down, The Cloud Terrace left-right rotation, focal length of camera " automatically to the video image of input.
The auto-analyzer procedure arthmetic statement of each quality index of video image is as follows:
(1) proportion of each pixel each component in the RGB color mode in the analysis video image judges whether to exist blank screen, blue screen, three kinds of phenomenons of ash screen;
(2) image definition is high more, and its image texture is clear more, and edge feature is obvious more, and vice versa; Based on this theory, native system proposes the video image clarity detection algorithm based on edge feature, realizes detection and analysis to image definition;
(3) in video image, mosaic shows as a series of shape unanimities, the uniform rectangular block of distribution of color; According to the characteristics of mosaic self, native system proposes the video image mosaic detection algorithm based on region growing;
(4) The Cloud Terrace is after each direction turns an angle, and video image background will inevitably change; Native system proposes inter-frame difference comparison algorithm based on background separation and detects The Cloud Terrace normal rotation whether on four direction up and down;
(5) focal length of camera is in the middle of the process of shrinking, and the video image clarity that obtains changes according to certain rule, and whether native system proposes to detect focal length of camera based on the algorithm that definition changes and can normally zoom in or out.
Detect the existing single frames index of index, the continuous multiple frames index is arranged again, judgment basis is abundant, rationally.
With respect to scheme of the prior art, advantage of the present invention is:
System's test video transmission channel fast in the technical solution of the present invention, test result can directly be presented on the computer screen of control device with figure or data mode, also printablely goes out corresponding figure or data.The measuring precision height of the present invention, repeatability, high conformity, systemic price ratio height.Good reliability.Index algorithm section emulates the advanced, and judges that accurate rate reaches more than 90%.
Video analysis device of the present invention is connected use by standard serial port with video matrix, the working interface close friend of control device.Video analysis device is simple in structure, realization is convenient and reliable, can carry out automatic analyzing and testing to video image, and timely feedback information, thereby watch-dog is realized effective and reasonable supervision, improved the efficient of patrolling and examining of outfield watch-dog,, and do not influence the operate as normal of original video matrix keyboard.System of the present invention highly versatile can be used in the video monitoring system of different brands, different size.
Description of drawings
Below in conjunction with drawings and Examples the present invention is further described:
Fig. 1 is the system architecture diagram of embodiment of the invention video image quality automatic analysis system;
Fig. 2 is another system architecture diagram of embodiment of the invention video image quality automatic analysis system;
Fig. 3 is video matrix, control device, the video analysis device interface connection layout of embodiment of the invention video image quality automatic analysis system;
Fig. 4 analyzes the method flow diagram of blank screen automatically for embodiment of the invention video image quality;
Fig. 5 analyzes the method flow diagram of ash screen automatically for embodiment of the invention video image quality;
Fig. 6 analyzes the method flow diagram of blue screen automatically for embodiment of the invention video image quality;
Fig. 7 analyzes the method flow diagram of definition automatically for embodiment of the invention video image quality;
Fig. 8 analyzes the method flow diagram of mosaic automatically for embodiment of the invention video image quality;
Fig. 9 analyzes the method flow diagram of The Cloud Terrace rotation situation automatically for embodiment of the invention video image quality;
Figure 10 analyzes the method flow diagram that focal length of camera is regulated situation automatically for embodiment of the invention video image quality.
Embodiment
Below in conjunction with specific embodiment such scheme is described further.Should be understood that these embodiment are used to the present invention is described and are not limited to limit the scope of the invention.The implementation condition that adopts among the embodiment can be done further adjustment according to the condition of concrete producer, and not marked implementation condition is generally the condition in the normal experiment.
Embodiment
As depicted in figs. 1 and 2, this intelligent video picture quality automatic analysis system comprises control device, video analysis device and is connected the video matrix of image collecting device; Described control device and video analysis device communication are responsible for the instruction request of video image analysis is sent to video analysis device, and the result who accepts the video analysis device analysis is shown to the user; Described video analysis device and video matrix communication are obtained video image according to the instruction of control device from video matrix, video image is analyzed, and obtain the analysis result of video image, and the analysis result of video image is transferred to control device.
As shown in Figure 2, between described control device and video analysis device switch can be set, described switch connects video analysis device and the video matrix that is connected image collecting device respectively, described control device by switch respectively with video analysis device, video matrix communication.
Image is set in the video analysis device imports module, image detection module and output module; Described image imports module and is used for video image is imported in the video analysis device, and video image is carried out preliminary treatment; Described image detection module is used for the parameter of video image is detected, and is aggregated in the output module and exports; Described output module is used for the parameter of video image is transferred to control device by connecting line.Described image detection module comprises monochromatic screen detection module, definition detection module, mosaic detection module, The Cloud Terrace detection module, camera parameters detection module.
Described monochromatic screen detection module is used for detecting the proportion of each pixel of video image each component in the RGB color mode, judges whether video image exists blank screen, blue screen, ash screen phenomenon; Described definition detection module is used for the edge feature of video image is detected, and judges the definition of video image; Described mosaic detection module is used for detecting the mosaic phenomenon of video image; Described The Cloud Terrace detection module is used to detect The Cloud Terrace rotation direction and rotation situation; Described camera parameters detection module changes judgement focal length of camera change information according to the definition of video image.
Image imports module and is provided with video input interface, and described video input interface directly is connected by the VGA line with video matrix, accepts the input of 6 road analog videos.Described control device, switch, video analysis device and video matrix constitute the video monitoring local area network (LAN), carry out network communication by switch between described video analysis device and video matrix.
When practical application, described control device is connected with the video matrix digital input-output interface by digital input-output interface, the vision signal of described video matrix is connected into the video signal input interface of video analysis device by connecting line, and the control signal transmit port of described video analysis device is connected with the RS232 interface of control device.Certainly, in LAN environment, the control signal transmit port of described video analysis device is connected with the RS232 interface of control device by the network switch; The instruction of described control device is connected with the video matrix digital input-output interface by the network switch by digital input-output interface output back.
Video analysis device of the present invention is an industrial computer that embeds the video image quality auto-analyzer procedure, and wherein trace routine can be carried out the detection of eight quality index such as " blank screen, blue screen, grey screen, definition, mosaic, The Cloud Terrace rotate up and down, The Cloud Terrace left-right rotation, focal length of camera " automatically to the video image of input.
The auto-analyzer procedure arthmetic statement of each quality index of video image is as follows:
(1) proportion of each pixel each component in the RGB color mode in the analysis video image judges whether to exist blank screen, blue screen, three kinds of phenomenons of ash screen.
Specifically, as shown in Figure 4, after video analysis device got access to video image, the pixel value of the pixel of cycle calculations video image judged that whether three component pixel values of R/G/B are all less than the effective threshold value of black.Promptly when the pixel value of first pixel, whether three component pixel values of R/G/B of pixel value of judging first pixel then are all less than the effective threshold value of black, and when condition was set up, the valid pixel number of spots increased, and continued next pixel of traversal.When effective pixel number amount surpassed threshold value, the pixel value of expression valid pixel number of spots met the blank screen condition, can judge that video image is a blank screen; Otherwise when the valid pixel number of spots was lower than threshold value when traversal was finished is non-blank screen.
Therewith in like manner, as shown in Figure 5, after video analysis device gets access to video image, the pixel value of the pixel of cycle calculations video image, whether the identical ash that judges whether shields to judge three component pixel values of R/G/B.As shown in Figure 6, after video analysis device got access to video image, the pixel value of the pixel of cycle calculations video image judged whether three component pixel values of R/G/B satisfy R<10 simultaneously, G<10, and whether these three condition judgment of B>200 blue screen.
(2) image definition is high more, and its image texture is clear more, and edge feature is obvious more, and vice versa; Based on this theory, native system proposes the video image clarity detection algorithm based on edge feature, realizes detection and analysis to image definition.
As shown in Figure 7, after video analysis device gets access to video image, by the canny algorithm video image being carried out marginalisation handles, by the pixel quantity of the image after the edge calculation processing, whether the pixel quantity by judging the image after marginalisation is handled judge the definition situation of video image greater than threshold value.
(3) in video image, mosaic shows as a series of shape unanimities, the uniform rectangular block of distribution of color; According to the characteristics of mosaic self, native system proposes the video image mosaic detection algorithm based on region growing.
As shown in Figure 8, after video analysis device gets access to video image, determine the minimum length of side of effective mosaic, determine the expansion datum mark according to the minimum length of side of effective mosaic, form the rectangle that need carry out the mosaic judgement by the expansion datum mark, undertaken by judgement whether the rectangle that mosaic judges is the quantity that effective mosaic is determined effective mosaic, when the quantity of effective mosaic less than 10 the time, show and contain a small amount of mosaic in the video image; When the quantity of effective mosaic greater than 10 less than 30 the time, show and contain mosaic in the video image; When the quantity of effective mosaic greater than 30 the time, show and contain a large amount of mosaics in the video image.
(4) The Cloud Terrace is after each direction turns an angle, and video image background will inevitably change; Native system proposes inter-frame difference comparison algorithm based on background separation and detects The Cloud Terrace normal rotation whether on four direction up and down.
As shown in Figure 9, after video analysis device gets access to video image, obtain the background of current video image by the continuous multiple frames video image; Then the following upward left and right directions of The Cloud Terrace is turned an angle and continue to calculate the background of continuous multiple frames video image, video image background after video image background before then The Cloud Terrace being rotated and The Cloud Terrace rotate carries out Difference Calculation, judges whether the video image background after The Cloud Terrace rotates preceding video image background and The Cloud Terrace rotates is identical.When identical, it is undesired to show that The Cloud Terrace rotates.
(5) focal length of camera is in the middle of the process of shrinking, and the video image clarity that obtains changes according to certain rule, and whether native system proposes to detect focal length of camera based on the algorithm that definition changes and can normally zoom in or out.
As shown in figure 10, after video analysis device gets access to video image, obtain the background of current video image by the continuous multiple frames video image; To regulate the far and near background that continues to calculate the continuous multiple frames video image of focal length of camera then, then the video image background before and after regulating be carried out Difference Calculation, judge whether the video image background before and after regulating is identical.When identical, show that focal length of camera is far and near flexible undesired.
The video image quality automatic analysis system of present embodiment can be analyzed for digital signaling system and analog signal system.As shown in Figure 3, video analysis device provides two common interfaces.An interface is a video input interface, can gather 6 road analog videos simultaneously, in actual detected, can do detection with 5 the tunnel, 1 the tunnel does realtime graphic, is used for obtaining the video that will analyze from video matrix (analog signal system) or dynamic decoder device (digital signaling system); The video analysis signal that another interface one side receiving front-end system sends sends to headend equipment to video image quality check and analysis result, on the other hand so that display analysis.During work, video analysis device is obtained video data to be analyzed according to the analysis task that receives, and detects eight quality index by built-in video image quality auto-analyzer procedure, and analysis result can feed back to front end by common interface, so that display analysis.
Video analysis device can be installed separately, as long as meet the common interface parameter of video analyzer during use.Video analysis device can be according in digital signal and analog signal system.
Above-mentioned example only is explanation technical conceive of the present invention and characteristics, and its purpose is to allow the people who is familiar with this technology can understand content of the present invention and enforcement according to this, can not limit protection scope of the present invention with this.All equivalent transformations that spirit is done according to the present invention or modification all should be encompassed within protection scope of the present invention.
Claims (6)
1. intelligent video picture quality automatic analysis system comprises control device, video analysis device and is connected the video matrix of image collecting device; It is characterized in that described control device and video analysis device communication, be responsible for the instruction request of video image analysis is sent to video analysis device, and the result who accepts the video analysis device analysis is shown to the user; Described video analysis device and video matrix communication are obtained video image according to the instruction of control device from video matrix, video image is analyzed, and obtain the analysis result of video image, and the analysis result of video image is transferred to control device.
2. intelligent video picture quality automatic analysis system according to claim 1, it is characterized in that between described control device and video analysis device switch being set, described switch connects video analysis device and the video matrix that is connected image collecting device respectively, described control device by switch respectively with video analysis device, video matrix communication.
3. intelligent video picture quality automatic analysis system according to claim 2 is characterized in that being provided with in the described video analysis device image and imports module, image detection module and output module; Described image imports module and is used for video image is imported in the video analysis device, and video image is carried out preliminary treatment; Described image detection module is used for the parameter of video image is detected, and is aggregated in the output module and exports; Described output module is used for the parameter of video image is transferred to control device by connecting line.
4. intelligent video picture quality automatic analysis system according to claim 3 is characterized in that described image detection module comprises monochromatic screen detection module, definition detection module, mosaic detection module, The Cloud Terrace detection module, camera parameters detection module.
5. intelligent video picture quality automatic analysis system according to claim 3, it is characterized in that described image imports module and is provided with video input interface, described video input interface directly is connected by the VGA line with video matrix, accepts the input of 6 road analog videos.
6. intelligent video picture quality automatic analysis system according to claim 3, it is characterized in that described control device, switch, video analysis device and video matrix constitute the video monitoring local area network (LAN), carry out network communication by switch between described video analysis device and video matrix.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2011201198628U CN202004914U (en) | 2011-04-21 | 2011-04-21 | Intelligent video image quality automatic analysis system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2011201198628U CN202004914U (en) | 2011-04-21 | 2011-04-21 | Intelligent video image quality automatic analysis system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN202004914U true CN202004914U (en) | 2011-10-05 |
Family
ID=44707638
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2011201198628U Expired - Fee Related CN202004914U (en) | 2011-04-21 | 2011-04-21 | Intelligent video image quality automatic analysis system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN202004914U (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103856774A (en) * | 2014-02-28 | 2014-06-11 | 北京航科威视光电信息技术有限公司 | Intelligent detection system and method for video surveillance |
CN109413411A (en) * | 2018-09-06 | 2019-03-01 | 腾讯数码(天津)有限公司 | A kind of blank screen recognition methods, device and the server of monitoring circuit |
-
2011
- 2011-04-21 CN CN2011201198628U patent/CN202004914U/en not_active Expired - Fee Related
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103856774A (en) * | 2014-02-28 | 2014-06-11 | 北京航科威视光电信息技术有限公司 | Intelligent detection system and method for video surveillance |
CN103856774B (en) * | 2014-02-28 | 2016-03-23 | 北京航科威视光电信息技术有限公司 | A kind of video monitoring intelligent checking system and method |
CN109413411A (en) * | 2018-09-06 | 2019-03-01 | 腾讯数码(天津)有限公司 | A kind of blank screen recognition methods, device and the server of monitoring circuit |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102131101A (en) | Intelligent video image quality automatic analysis system and method | |
CN107065743A (en) | A kind of Irrigation District Information System and its management method | |
CN105444891B (en) | A kind of yarn printing and dyeing aberration detecting system based on machine vision | |
CN102601131B (en) | A kind of billet surface quality on-line detecting device | |
CN203733445U (en) | Large screen detection and display device | |
CN102878647B (en) | Automatic monitoring system and automatic monitoring method for air conditioner running state | |
CN106483143A (en) | A kind of solar energy photovoltaic panel dust stratification on-Line Monitor Device and its detection method | |
CN105472355A (en) | Switch machine notch monitoring system and method based on binocular visual processing identification | |
CN104503351B (en) | Intelligent monitoring system and method for laying overhead line | |
CN106382960A (en) | System and method for automatically monitoring indoor environment of building based on Internet plus technology | |
CN105136804A (en) | High-speed strip steel surface image acquiring and image processing apparatus and method thereof | |
CN102984503A (en) | Network video storage server system | |
CN202004914U (en) | Intelligent video image quality automatic analysis system | |
CN110728212B (en) | Road well lid monitoring device and monitoring method based on computer vision | |
CN102891991A (en) | Automatic and continuous cruising method for cradle head | |
CN103063248A (en) | Hydropower station grouting centralized intelligent monitoring system | |
CN202158839U (en) | Online real-time plate width detection device for float glass | |
CN104096686A (en) | Product packing box surface printing quality automatic detection device | |
CN101521805A (en) | Helmet-site detecting system on construction field and detecting method thereof | |
CN107888600A (en) | A kind of localization method | |
CN106338960A (en) | Distributed production workshop intelligence data monitoring transmission apparatus | |
CN203788047U (en) | Patrol management system for state of equipment in transformer station based on video accurate recognition | |
CN106292523B (en) | Unit flow intelligent fault identification system and method | |
CN102740057B (en) | A kind of image determination method for city illumination facility and device | |
CN208568762U (en) | Landslide state monitor |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
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: 20111005 Termination date: 20170421 |