CN104346794A - Video flicker detection method and device - Google Patents
Video flicker detection method and device Download PDFInfo
- Publication number
- CN104346794A CN104346794A CN201310320260.2A CN201310320260A CN104346794A CN 104346794 A CN104346794 A CN 104346794A CN 201310320260 A CN201310320260 A CN 201310320260A CN 104346794 A CN104346794 A CN 104346794A
- Authority
- CN
- China
- Prior art keywords
- image
- video
- detected
- frame difference
- brightness value
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/254—Analysis of motion involving subtraction of images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20224—Image subtraction
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a video flicker detection method and device. The method comprises the steps that a video image to be detected is acquired from a video to be detected; binary processing is performed on a frame difference image between the video image to be detected and a previous frame of video image so that a binary frame difference image is obtained; a scan-line algorithm is adopted to exclude areas which do not meet with a preset size condition from the binary frame difference image so that an image after scan processing is obtained; area density of all the communicated areas in the image after scan processing is respectively confirmed, and the area density indicates proportion of effective pixel points in the communicated areas; and whether the video to be detected is a flicker video is confirmed according to the comparison result whether the area density of all the communicated areas is less than a preset density threshold value. Compared with methods and devices in the prior art, reliability, accuracy and detection efficiency of video flicker detection are enhanced via application of the method and the device.
Description
Technical field
The present invention relates to video analysis and field of video monitoring, particularly relate to a kind of video flashes detection method and device.
Background technology
In video monitoring system, because video camera is by the time shutter, the interference of the external environment conditions such as the interference of shooting visual angle and equipment faults itself and illumination condition, the front and back two field picture of video image is made totally or locally to occur the situation that brightness variation abnormality is violent, thus cause video to occur the phenomenon of flicker, have a strong impact on the visual effect of video image, picture quality and stability, simultaneously video flashes can increase more bit information and carrys out Description Image, cause the increase of coding bit rate, be unfavorable for follow-up image transmitting, store, treatment and analysis, therefore to the video flashes in video image be detected, determine the intensity of video flashes.
At present, existing video flashes detection method mainly adopts mode manually on duty, is observed video by duty personnel, judges whether video exists flashing state by human eye, finds after video flashes, sends warning message to go forward side by side row relax by duty personnel.
The method of above-mentioned existing artificial detection video flashes on duty, duty personnel is needed to observe video within continuous time, because the notice of people is limited, can not be primarily focused on viewing video for a long time, multiple paths of video images is monitored simultaneously, each road video image can not be taken into account, easily cause undetected.Because whole testing process adds the impact of artificial subjective factor, artificially also different to the judgement of video flashes intensity, reduce the reliability of video flashes detection, accuracy and detection efficiency.
Summary of the invention
The embodiment of the present invention provides a kind of video flashes detection method and device, in order to solve exist in prior art the reliability of carrying out video flashes detection, accuracy and the lower problem of detection efficiency.
The embodiment of the present invention provides a kind of video flashes detection method, comprising:
Video image to be detected is obtained from video to be detected;
Binary conversion treatment is carried out to the frame difference image between described video image to be detected and its former frame video image, obtains binaryzation frame difference image;
Adopt scan-line algorithm, get rid of not meet from described binaryzation frame difference image and preset the region of size condition, obtain image after scan process;
Determine the areal concentration of each connected region in image after described scan process respectively, described areal concentration characterizes effective pixel points proportion in connected region;
Whether the areal concentration according to described each connected region is all less than pre-set density threshold value, determines whether described video to be detected is flicker video.
Adopt the said method that the embodiment of the present invention provides, from binaryzation frame difference image, the region not meeting and preset size condition is got rid of owing to adopting scanning Beam Method, thus eliminate the interference that moving target brings flicker detection, and image after scan process is carried out regional connectivity, effective blinking region is remained, thus reduce loss, and whole testing process is automatic detection, do not need manually to participate in detecting, namely improve the reliability, accuracy rate and the detection efficiency that carry out video flashes detection compared to existing technology.
Further, adopt scan-line algorithm, get rid of not meet from described binaryzation frame difference image and preset the region of size condition, obtain image after scan process, specifically comprise:
By lining by line scan to described binaryzation frame difference image, the brightness value being multiple continuous print pixels of 1 by the brightness value that quantity in described binaryzation frame difference image often row is less than default row amount threshold changes to 0, obtain image after line scanning process, as image after scan process; Or
By scanning by column described binaryzation frame difference image, in often being arranged by described binaryzation frame difference image, quantity is less than the brightness value of default number of columns threshold value is that the brightness value of multiple continuous print pixels of 1 changes to 0, obtain image after column scan process, as image after scan process; Or
By lining by line scan to described binaryzation frame difference image, the brightness value being multiple continuous print pixels of 1 by the brightness value that quantity in described binaryzation frame difference image often row is less than default row amount threshold changes to 0, obtains image after line scanning process; And by scanning by column described binaryzation frame difference image, in often being arranged by described binaryzation frame difference image, quantity is less than the brightness value of default number of columns threshold value is that the brightness value of multiple continuous print pixels of 1 changes to 0, obtain image after column scan process; The brightness value of the pixel of same position in image after image after described line scanning process and described column scan process is carried out logic and operation, obtain with calculation process after image, as image after scan process.
Like this, adopt scan-line algorithm to get rid of not meet from binaryzation frame difference image and preset the region of size condition, thus eliminate the interference that moving target brings flicker detection.
Further, determine the areal concentration of each connected region in image after described scan process respectively, specifically comprise:
By lining by line scan to each connected region, pixel quantity in this connected region being less than the pixel of each row of pre-set length threshold, being defined as the effective pixel points of this connected region; By the ratio of the pixel sum of the quantity of the effective pixel points of this connected region and this connected region, be defined as the areal concentration of this connected region.
Like this, adopt based on the effective pixel points determination areal concentration in connected region, and by this areal concentration compared with pre-set density threshold value, the erroneous judgement caused by large moving target can be got rid of, thus can determine that video to be detected is flicker video more accurately.
Further, when the areal concentration inequality of described each connected region is less than pre-set density threshold value, following formula is adopted to determine the scintillation intensity of described video to be detected:
I=100%*SumRect/SumAll；
Wherein, I represents the scintillation intensity of video to be detected, and SumRect is the total quantity of the effective pixel points that connected regions to be detected all in video image to be detected comprises, and SumAll is the pixel quantity that this video image to be detected comprises.
Like this, by the scintillation intensity of video to be detected determined, the degree of each video flashes power to be detected can be obtained.
Further, carrying out binary conversion treatment to the frame difference image between described video image to be detected and its former frame video image, before obtaining binaryzation frame difference image, said method can also comprise:
Determine the average brightness value of the frame difference image between described video image to be detected and its former frame video image;
Determine that described average brightness value is not less than predetermined luminance threshold value.
Further, when described average brightness value is less than described predetermined luminance threshold value, said method also comprises:
Determine that described video to be detected is not flicker video.
The embodiment of the present invention also provides a kind of video flashes pick-up unit, comprising:
Acquiring unit, for obtaining video image to be detected from video to be detected;
Binary conversion treatment unit, for carrying out binary conversion treatment to the frame difference image between described video image to be detected and its former frame video image, obtains binaryzation frame difference image;
Scanning element, for adopting scan-line algorithm, getting rid of not meet and presetting the region of size condition from described binaryzation frame difference image, obtains image after scan process;
Areal concentration determining unit, for determining the areal concentration of each connected region in image after described scan process respectively, described areal concentration characterizes effective pixel points proportion in connected region;
First flicker determining unit, whether the areal concentration according to described each connected region is all less than pre-set density threshold value, determines whether described video to be detected is flicker video.
Adopt the said apparatus that the embodiment of the present invention provides, from binaryzation frame difference image, the region not meeting and preset size condition is got rid of owing to adopting scanning Beam Method, thus eliminate the interference that moving target brings flicker detection, and image after scan process is carried out regional connectivity, effective blinking region is remained, thus reduce loss, and whole testing process is automatic detection, do not need manually to participate in detecting, namely improve the reliability, accuracy rate and the detection efficiency that carry out video flashes detection compared to existing technology.
Further, described scanning element, specifically for by lining by line scan to described binaryzation frame difference image, the brightness value being multiple continuous print pixels of 1 by the brightness value that quantity in described binaryzation frame difference image often row is less than default row amount threshold changes to 0, obtain image after line scanning process, as image after scan process; Or
By scanning by column described binaryzation frame difference image, in often being arranged by described binaryzation frame difference image, quantity is less than the brightness value of default number of columns threshold value is that the brightness value of multiple continuous print pixels of 1 changes to 0, obtain image after column scan process, as image after scan process; Or
By lining by line scan to described binaryzation frame difference image, the brightness value being multiple continuous print pixels of 1 by the brightness value that quantity in described binaryzation frame difference image often row is less than default row amount threshold changes to 0, obtains image after line scanning process; And by scanning by column described binaryzation frame difference image, in often being arranged by described binaryzation frame difference image, quantity is less than the brightness value of default number of columns threshold value is that the brightness value of multiple continuous print pixels of 1 changes to 0, obtain image after column scan process; The brightness value of the pixel of same position in image after image after described line scanning process and described column scan process is carried out logic and operation, obtain with calculation process after image, as image after scan process.
Like this, adopt scan-line algorithm to get rid of not meet from binaryzation frame difference image and preset the region of size condition, thus eliminate the interference that moving target brings flicker detection.
Further, described areal concentration determining unit, specifically for by lining by line scan to each connected region, being less than the pixel of each row of pre-set length threshold, being defined as the effective pixel points of this connected region by pixel quantity in this connected region; By the ratio of the pixel sum of the quantity of the effective pixel points of this connected region and this connected region, be defined as the areal concentration of this connected region.
Like this, like this, adopt based on the effective pixel points determination areal concentration in connected region, and by this areal concentration compared with pre-set density threshold value, the erroneous judgement caused by large moving target can be got rid of, thus can determine that video to be detected is flicker video more accurately.
Further, described first flicker determining unit, is also less than pre-set density threshold value for the areal concentration inequality when described each connected region, when determining that described video to be detected is flicker video, adopts following formula to determine the scintillation intensity of described video to be detected:
I=100%*SumRect/SumAll；
Wherein, I represents the scintillation intensity of video to be detected, and SumRect is the total quantity of the effective pixel points that connected regions to be detected all in video image to be detected comprises, and SumAll is the pixel quantity that this video image to be detected comprises.
Like this, by the scintillation intensity of video to be detected determined, the degree of each video flashes power to be detected can be obtained.
Further, said apparatus can also comprise:
Brightness value determining unit, for carrying out binary conversion treatment at described binary conversion treatment unit to the frame difference image between described video image to be detected and its former frame video image, before obtaining binaryzation frame difference image, determine the average brightness value of the frame difference image between described video image to be detected and its former frame video image;
Second flicker determining unit, for determining that described average brightness value is not less than predetermined luminance threshold value.
Further, described second flicker determining unit, also for when determining that described average brightness value is less than predetermined luminance threshold value, determines that described video to be detected is not flicker video.
The further feature of the application and advantage will be set forth in the following description, and, partly become apparent from instructions, or understand by implementing the application.The object of the application and other advantages realize by structure specifically noted in write instructions, claims and accompanying drawing and obtain.
Accompanying drawing explanation
Accompanying drawing is used to provide a further understanding of the present invention, and forms a part for instructions, is used from explanation the present invention, is not construed as limiting the invention with the embodiment of the present invention one.In the accompanying drawings:
The process flow diagram of the video flashes detection method that Fig. 1 provides for the embodiment of the present invention;
The process flow diagram of the video flashes detection method that Fig. 2 provides for the embodiment of the present invention 1;
The structural representation of the video flashes pick-up unit that Fig. 3 provides for the embodiment of the present invention 2.
Embodiment
In order to provide improve video flashes and detect reliability, accuracy and detection efficiency implementation, embodiments provide a kind of video flashes detection method and device, below in conjunction with Figure of description, the preferred embodiments of the present invention are described, be to be understood that, preferred embodiment described herein, only for instruction and explanation of the present invention, is not intended to limit the present invention.And when not conflicting, the embodiment in the application and the feature in embodiment can combine mutually.
The embodiment of the present invention provides a kind of video flashes detection method, as shown in Figure 1, comprising:
Step 101, from video to be detected, obtain video image to be detected.
Step 102, binary conversion treatment is carried out to the frame difference image between this video image to be detected and its former frame video image, obtain binaryzation frame difference image.
Step 103, adopt scan-line algorithm, get rid of not meet from this binaryzation frame difference image and preset the region of size condition, obtain image after scan process.
Step 104, determine the areal concentration of each connected region in image after this scan process respectively, this areal concentration characterizes effective pixel points proportion in connected region.
Step 105, whether be all less than pre-set density threshold value according to the areal concentration of this each connected region, determine whether this video to be detected is flicker video.
Further, when the areal concentration inequality of each connected region is less than pre-set density threshold value, determine that this video to be detected is flicker video, or, when the areal concentration of each connected region is all less than pre-set density threshold value, whether, when determining that this video to be detected is not flicker video, also can adopt other detection schemes, be that flicker video further detects to this video to be detected.
In said method, the video image to be detected carrying out video flashes detection can be from the second frame video image of video to be detected after each frame video image, thus can when detecting, carry out binary conversion treatment based on the frame difference image between video image to be detected and its former frame video image, obtain binaryzation frame difference image.
In the embodiment of the present invention, after obtaining binaryzation frame difference image, adopt scan-line algorithm, get rid of not meet from this binaryzation frame difference image and preset the region of size condition, obtain image after scan process, can be realized by following several mode:
First kind of way:
By lining by line scan to binaryzation frame difference image, the brightness value being multiple continuous print pixels of 1 by the brightness value that quantity in this binaryzation frame difference image often row is less than default row amount threshold changes to 0, obtain image after line scanning process, as image after scan process.
In the manner, binaryzation frame difference image is lined by line scan, adding up each group brightness value in often going is the quantity Sum1 (p) of multiple continuous print pixels of 1, p represents p group, when Sum1 (p) is less than default row amount threshold M, the brightness value 1 of the multiple continuous print pixels this group comprised changes to 0, when Sum1 (p) is not less than default row amount threshold M, the brightness value 1 of multiple continuous print pixels that this group comprises remains unchanged, above-mentioned process is carried out to all row of this binaryzation frame difference image, obtain image after line scanning process, as image after scan process.
The second way:
By scanning by column binaryzation frame difference image, in often being arranged by this binaryzation frame difference image, quantity is less than the brightness value of default number of columns threshold value is that the brightness value of multiple continuous print pixels of 1 changes to 0, obtain image after column scan process, as image after scan process.
In the manner, binaryzation frame difference image is scanned by column, during statistics often arranges, each group brightness value is the quantity Sum2 (q) of multiple continuous print pixels of 1, q represents q group, when Sum2 (q) is less than default number of columns threshold value N, the brightness value 1 of the multiple continuous print pixels this group comprised changes to 0, when Sum2 (q) is not less than default number of columns threshold value N, the brightness value 1 of multiple continuous print pixels that this group comprises remains unchanged, above-mentioned process is carried out to all row of this binaryzation frame difference image, obtain image after column scan process, as image after scan process.
The third mode:
By lining by line scan to binaryzation frame difference image, the brightness value being multiple continuous print pixels of 1 by the brightness value that quantity in described binaryzation frame difference image often row is less than default row amount threshold changes to 0, obtains image after line scanning process; And by scanning by column this binaryzation frame difference image, in often being arranged by this binaryzation frame difference image, quantity is less than the brightness value of default number of columns threshold value is that the brightness value of multiple continuous print pixels of 1 changes to 0, obtain image after column scan process; The brightness value of the pixel of same position in image after image after this line scanning process and this column scan process is carried out logic and operation, obtain with calculation process after image, as image after scan process.
In the manner, binaryzation frame difference image is lined by line scan, adding up each group brightness value in often going is the quantity Sum1 (p) of multiple continuous print pixels of 1, p represents p group, when Sum1 (p) is less than default row amount threshold M, the brightness value 1 of the multiple continuous print pixels this group comprised changes to 0, when Sum1 (p) is not less than default row amount threshold M, the brightness value 1 of multiple continuous print pixels that this group comprises remains unchanged, above-mentioned process is carried out to all row of this binaryzation frame difference image, obtains image after line scanning process.Again binaryzation frame difference image is scanned by column, during statistics often arranges, each group brightness value is the quantity Sum2 (q) of multiple continuous print pixels of 1, q represents q group, when Sum2 (q) is less than default number of columns threshold value N, the brightness value 1 of the multiple continuous print pixels this group comprised changes to 0, when Sum2 (q) is not less than default number of columns threshold value N, the brightness value 1 of multiple continuous print pixels that this group comprises remains unchanged, above-mentioned process is carried out to all row of this binaryzation frame difference image, obtains image after column scan process.The brightness value of the pixel of same position in image after image after this line scanning process and this column scan process is carried out logic and operation, when image after this line scanning process is different from the brightness value of the pixel of same position in image after this column scan process, the result of this logic and operation is 0, when in image after image after this line scanning process with this column scan process, the brightness value of the pixel of same position is all 0 mutually, the result of this logic and operation is 0, when in image after image after this line scanning process with this column scan process, the brightness value of the pixel of same position is all 1 mutually, the result of this logic and operation is 1, obtain with calculation process after image, as image after scan process.
In the embodiment of the present invention, the concrete disposal route of each connected region after determining scan process in image can adopt various mode of the prior art, such as: four neighbor scan are carried out to the pixel that each brightness value in image after scan process is 1, namely scan on this pixel, under, left, the brightness value of the pixel of right position, when being the pixel of 1 when there being brightness value in four neighborhoods scanning this pixel, the pixel being 1 by this pixel and the brightness value in four neighborhoods is communicated with, after above-mentioned process is carried out to the pixel that is 1 of each brightness value in image after this scan process, obtain multiple connected region.Can also be to each brightness value in image after scan process 1 pixel carry out eight neighborhood scanning, concrete treatment step is identical with the above-mentioned treatment step carrying out four neighbor scan, is no longer described in detail at this.
Below in conjunction with accompanying drawing, with specific embodiment, method provided by the invention and device are described in detail.
Embodiment 1:
The process flow diagram of a kind of video flashes detection method that Fig. 2 provides for the embodiment of the present invention 1, specifically comprises following treatment step:
Step 201, from video to be detected, obtain video image to be detected.
Step 202, utilize background frame difference method, determine the frame difference image of video image to be detected and its former frame video image, specifically can be as follows:
By the difference of the brightness value of each pixel in video image to be detected with the brightness value of pixel identical with this pixel position in its former frame video image, be defined as the brightness value of the identical pixel in this pixel position of video image to be detected with this in frame difference image, thus obtain frame difference image.
Step 203, determine the average brightness value of this frame difference image.
In this step, the brightness value of each pixel in frame difference image sued for peace and does average, obtaining the average brightness value G1 of this frame difference image.
Step 204, determine whether this average brightness value G1 is not less than predetermined luminance threshold value Y, if be less than, enters step 205, if be not less than, enters step 206.
Step 205, when G1 is less than Y, determine this video to be detected be not flicker video.
Step 206, binary conversion treatment is carried out to this frame difference image, obtain binaryzation frame difference image.
Step 207, adopt scan-line algorithm, get rid of not meet from this binaryzation frame difference image and preset the region of size condition, obtain image after scan process.
Step 208, determine each connected region of image after this scan process.
Step 209, determine the areal concentration of each connected region respectively, this areal concentration characterizes effective pixel points proportion in connected region.
In this step, to each connected region, areal concentration can be determined in the following way:
This connected region is lined by line scan, add up pixel quantity len (j) of every a line, j represents jth row, len (j) in this connected region is greater than the summation of the pixel of each row of pre-set length threshold L, be defined as the quantity B (k) of the effective pixel points of this connected region, k represents a kth connected region, by the ratio R (k) of the quantity B (k) of the effective pixel points of this connected region with pixel sum C (k) of this connected region, be defined as the areal concentration of this connected region.
Step 210, determine whether the areal concentration of each connected region is all less than pre-set density threshold value, if so, enters step 211, if not, enters step 212.
Step 211, when the areal concentration of each connected region is all less than pre-set density threshold value, determine this video to be detected be not flicker video.
In this step, when areal concentration R (k) of each connected region is all less than pre-set density threshold value R, determine that this video to be detected is not flicker video.
Step 212, when the areal concentration inequality of each connected region is less than pre-set density threshold value, determine this video to be detected be flicker video.
In this step, when areal concentration R (k) that there is a connected region or multiple connected region in each connected region is not less than pre-set density threshold value R, determine that this video to be detected is flicker video.
Further, when determining that this video to be detected is flicker video, following formula can also be adopted to determine the scintillation intensity of described video to be detected:
I=100%*SumRect/SumAll；
Wherein, I represents the scintillation intensity of video to be detected, and SumRect is the total quantity of the effective pixel points that connected regions to be detected all in video image to be detected comprises, and SumAll is the pixel quantity that this video image to be detected comprises.
By the method that the above embodiment of the present invention 1 and 2 provides, from binaryzation frame difference image, the region not meeting and preset size condition is got rid of owing to adopting scanning Beam Method, thus eliminate the interference that moving target brings flicker detection, and image after scan process is carried out regional connectivity, effective blinking region is remained, thus reduce loss, and whole testing process is automatic detection, do not need manually to participate in detecting, namely improve the reliability, accuracy rate and the detection efficiency that carry out video flashes detection compared to existing technology.
Embodiment 2:
Based on same inventive concept, according to the video flashes detection method that the above embodiment of the present invention provides, correspondingly, the embodiment of the present invention 2 additionally provides a kind of video flashes pick-up unit, and its structural representation as shown in Figure 3, specifically comprises:
Acquiring unit 301, for obtaining video image to be detected from video to be detected;
Binary conversion treatment unit 302, for carrying out binary conversion treatment to the frame difference image between described video image to be detected and its former frame video image, obtains binaryzation frame difference image;
Scanning element 303, for adopting scan-line algorithm, getting rid of not meet and presetting the region of size condition from described binaryzation frame difference image, obtains image after scan process;
Areal concentration determining unit 304, for determining the areal concentration of each connected region in image after described scan process respectively, described areal concentration characterizes effective pixel points proportion in connected region;
First flicker determining unit 305, whether the areal concentration according to described each connected region is all less than pre-set density threshold value, determines whether described video to be detected is flicker video.
Further, scanning element 303, specifically for by lining by line scan to described binaryzation frame difference image, the brightness value being multiple continuous print pixels of 1 by the brightness value that quantity in described binaryzation frame difference image often row is less than default row amount threshold changes to 0, obtain image after line scanning process, as image after scan process; Or
By scanning by column described binaryzation frame difference image, in often being arranged by described binaryzation frame difference image, quantity is less than the brightness value of default number of columns threshold value is that the brightness value of multiple continuous print pixels of 1 changes to 0, obtain image after column scan process, as image after scan process; Or
By lining by line scan to described binaryzation frame difference image, the brightness value being multiple continuous print pixels of 1 by the brightness value that quantity in described binaryzation frame difference image often row is less than default row amount threshold changes to 0, obtains image after line scanning process; And by scanning by column described binaryzation frame difference image, in often being arranged by described binaryzation frame difference image, quantity is less than the brightness value of default number of columns threshold value is that the brightness value of multiple continuous print pixels of 1 changes to 0, obtain image after column scan process; The brightness value of the pixel of same position in image after image after described line scanning process and described column scan process is carried out logic and operation, obtain with calculation process after image, as image after scan process.
Further, areal concentration determining unit 304, specifically for by lining by line scan to each connected region, being less than the pixel of each row of pre-set length threshold, being defined as the effective pixel points of this connected region by pixel quantity in this connected region; By the ratio of the pixel sum of the quantity of the effective pixel points of this connected region and this connected region, be defined as the areal concentration of this connected region.
Further, the first flicker determining unit 305, is also less than pre-set density threshold value for the areal concentration inequality when described each connected region, when determining that described video to be detected is flicker video, adopts following formula to determine the scintillation intensity of described video to be detected:
I=100%*SumRect/SumAll；
Wherein, I represents the scintillation intensity of video to be detected, and SumRect is the total quantity of the effective pixel points that connected regions to be detected all in video image to be detected comprises, and SumAll is the pixel quantity that this video image to be detected comprises.
Further, said apparatus, also comprises:
Brightness value determining unit 306, for carrying out binary conversion treatment at described binary conversion treatment unit to the frame difference image between described video image to be detected and its former frame video image, before obtaining binaryzation frame difference image, determine the average brightness value of the frame difference image between described video image to be detected and its former frame video image;
Second flicker determining unit 307, for determining that described average brightness value is not less than predetermined luminance threshold value.
Further, the second flicker determining unit 307, also for when determining that described average brightness value is less than predetermined luminance threshold value, determines that described video to be detected is not flicker video.
The function of above-mentioned each unit may correspond to the respective handling step in flow process shown in Fig. 2, does not repeat them here.
In sum, the scheme that the embodiment of the present invention provides, comprise: from video to be detected, obtain video image to be detected, binary conversion treatment is carried out to the frame difference image between this video image to be detected and its former frame video image, obtain binaryzation frame difference image, and adopt scan-line algorithm, the region not meeting and preset size condition is got rid of from this binaryzation frame difference image, obtain image after scan process, determine the areal concentration of each connected region in image after this scan process respectively, this areal concentration characterizes effective pixel points proportion in connected region, whether the areal concentration according to this each connected region is all less than pre-set density threshold value, determine whether this video to be detected is flicker video.The scheme adopting the embodiment of the present invention to provide, improves the reliability, accuracy rate and the detection efficiency that carry out video flashes detection.
The video flashes pick-up unit that the embodiment of the application provides realizes by computer program.Those skilled in the art should be understood that; above-mentioned Module Division mode is only the one in numerous Module Division mode; if be divided into other modules or do not divide module, as long as video flashes pick-up unit has above-mentioned functions, all should within the protection domain of the application.
The application describes with reference to according to the process flow diagram of the method for the embodiment of the present application, equipment (system) and computer program and/or block scheme.Should understand can by the combination of the flow process in each flow process in computer program instructions realization flow figure and/or block scheme and/or square frame and process flow diagram and/or block scheme and/or square frame.These computer program instructions can being provided to the processor of multi-purpose computer, special purpose computer, Embedded Processor or other programmable data processing device to produce a machine, making the instruction performed by the processor of computing machine or other programmable data processing device produce device for realizing the function of specifying in process flow diagram flow process or multiple flow process and/or block scheme square frame or multiple square frame.
These computer program instructions also can be stored in can in the computer-readable memory that works in a specific way of vectoring computer or other programmable data processing device, the instruction making to be stored in this computer-readable memory produces the manufacture comprising command device, and this command device realizes the function of specifying in process flow diagram flow process or multiple flow process and/or block scheme square frame or multiple square frame.
These computer program instructions also can be loaded in computing machine or other programmable data processing device, make on computing machine or other programmable devices, to perform sequence of operations step to produce computer implemented process, thus the instruction performed on computing machine or other programmable devices is provided for the step realizing the function of specifying in process flow diagram flow process or multiple flow process and/or block scheme square frame or multiple square frame.
Obviously, those skilled in the art can carry out various change and modification to the present invention and not depart from the spirit and scope of the present invention.Like this, if these amendments of the present invention and modification belong within the scope of the claims in the present invention and equivalent technologies thereof, then the present invention is also intended to comprise these change and modification.
Claims (12)
1. a video flashes detection method, is characterized in that,
Video image to be detected is obtained from video to be detected;
Binary conversion treatment is carried out to the frame difference image between described video image to be detected and its former frame video image, obtains binaryzation frame difference image;
Adopt scan-line algorithm, get rid of not meet from described binaryzation frame difference image and preset the region of size condition, obtain image after scan process;
Determine the areal concentration of each connected region in image after described scan process respectively, described areal concentration characterizes effective pixel points proportion in connected region;
Whether the areal concentration according to described each connected region is all less than pre-set density threshold value, determines whether described video to be detected is flicker video.
2. the method for claim 1, is characterized in that, adopts scan-line algorithm, gets rid of not meet and preset the region of size condition from described binaryzation frame difference image, obtains image after scan process, specifically comprises:
By lining by line scan to described binaryzation frame difference image, the brightness value being multiple continuous print pixels of 1 by the brightness value that quantity in described binaryzation frame difference image often row is less than default row amount threshold changes to 0, obtain image after line scanning process, as image after scan process; Or
By scanning by column described binaryzation frame difference image, in often being arranged by described binaryzation frame difference image, quantity is less than the brightness value of default number of columns threshold value is that the brightness value of multiple continuous print pixels of 1 changes to 0, obtain image after column scan process, as image after scan process; Or
By lining by line scan to described binaryzation frame difference image, the brightness value being multiple continuous print pixels of 1 by the brightness value that quantity in described binaryzation frame difference image often row is less than default row amount threshold changes to 0, obtains image after line scanning process; And by scanning by column described binaryzation frame difference image, in often being arranged by described binaryzation frame difference image, quantity is less than the brightness value of default number of columns threshold value is that the brightness value of multiple continuous print pixels of 1 changes to 0, obtain image after column scan process; The brightness value of the pixel of same position in image after image after described line scanning process and described column scan process is carried out logic and operation, obtain with calculation process after image, as image after scan process.
3. the method for claim 1, is characterized in that, determines the areal concentration of each connected region in image after described scan process respectively, specifically comprises:
By lining by line scan to each connected region, pixel quantity in this connected region being less than the pixel of each row of pre-set length threshold, being defined as the effective pixel points of this connected region; By the ratio of the pixel sum of the quantity of the effective pixel points of this connected region and this connected region, be defined as the areal concentration of this connected region.
4. the method for claim 1, is characterized in that, also comprises:
When the areal concentration inequality of described each connected region is less than pre-set density threshold value, following formula is adopted to determine the scintillation intensity of described video to be detected:
I=100%*SumRect/SumAll；
Wherein, I represents the scintillation intensity of video to be detected, and SumRect is the total quantity of the effective pixel points that connected regions to be detected all in video image to be detected comprises, and SumAll is the pixel quantity that this video image to be detected comprises.
5. the method as described in as arbitrary in claim 1-4, is characterized in that, carrying out binary conversion treatment, before obtaining binaryzation frame difference image, also comprise the frame difference image between described video image to be detected and its former frame video image:
Determine the average brightness value of the frame difference image between described video image to be detected and its former frame video image;
Determine that described average brightness value is not less than predetermined luminance threshold value.
6. method as claimed in claim 5, is characterized in that, also comprise:
When determining that described average brightness value is less than predetermined luminance threshold value, determine that described video to be detected is not flicker video.
7. a video flashes pick-up unit, is characterized in that, comprising:
Acquiring unit, for obtaining video image to be detected from video to be detected;
Binary conversion treatment unit, for carrying out binary conversion treatment to the frame difference image between described video image to be detected and its former frame video image, obtains binaryzation frame difference image;
Scanning element, for adopting scan-line algorithm, getting rid of not meet and presetting the region of size condition from described binaryzation frame difference image, obtains image after scan process;
Areal concentration determining unit, for determining the areal concentration of each connected region in image after described scan process respectively, described areal concentration characterizes effective pixel points proportion in connected region;
First flicker determining unit, whether the areal concentration according to described each connected region is all less than pre-set density threshold value, determines whether described video to be detected is flicker video.
8. device as claimed in claim 7, it is characterized in that, described scanning element, specifically for by lining by line scan to described binaryzation frame difference image, the brightness value being multiple continuous print pixels of 1 by the brightness value that quantity in described binaryzation frame difference image often row is less than default row amount threshold changes to 0, obtain image after line scanning process, as image after scan process; Or
By scanning by column described binaryzation frame difference image, in often being arranged by described binaryzation frame difference image, quantity is less than the brightness value of default number of columns threshold value is that the brightness value of multiple continuous print pixels of 1 changes to 0, obtain image after column scan process, as image after scan process; Or
By lining by line scan to described binaryzation frame difference image, the brightness value being multiple continuous print pixels of 1 by the brightness value that quantity in described binaryzation frame difference image often row is less than default row amount threshold changes to 0, obtains image after line scanning process; And by scanning by column described binaryzation frame difference image, in often being arranged by described binaryzation frame difference image, quantity is less than the brightness value of default number of columns threshold value is that the brightness value of multiple continuous print pixels of 1 changes to 0, obtain image after column scan process; The brightness value of the pixel of same position in image after image after described line scanning process and described column scan process is carried out logic and operation, obtain with calculation process after image, as image after scan process.
9. device as claimed in claim 8, it is characterized in that, described areal concentration determining unit, specifically for by lining by line scan to each connected region, pixel quantity in this connected region is less than the pixel of each row of pre-set length threshold, is defined as the effective pixel points of this connected region; By the ratio of the pixel sum of the quantity of the effective pixel points of this connected region and this connected region, be defined as the areal concentration of this connected region.
10. device as claimed in claim 9, it is characterized in that, described first flicker determining unit, also be less than pre-set density threshold value for the areal concentration inequality when described each connected region, when determining that described video to be detected is flicker video, following formula is adopted to determine the scintillation intensity of described video to be detected:
I=100%*SumRect/SumAll；
Wherein, I represents the scintillation intensity of video to be detected, and SumRect is the total quantity of the effective pixel points that connected regions to be detected all in video image to be detected comprises, and SumAll is the pixel quantity that this video image to be detected comprises.
11. as arbitrary in claim 7-10 as described in device, it is characterized in that, also comprise:
Brightness value determining unit, for carrying out binary conversion treatment at described binary conversion treatment unit to the frame difference image between described video image to be detected and its former frame video image, before obtaining binaryzation frame difference image, determine the average brightness value of the frame difference image between described video image to be detected and its former frame video image;
Second flicker determining unit, for determining that described average brightness value is not less than predetermined luminance threshold value.
12. devices as claimed in claim 11, is characterized in that, described second flicker determining unit, also for when determining that described average brightness value is less than predetermined luminance threshold value, determine that described video to be detected is not flicker video.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310320260.2A CN104346794A (en) | 2013-07-25 | 2013-07-25 | Video flicker detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310320260.2A CN104346794A (en) | 2013-07-25 | 2013-07-25 | Video flicker detection method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104346794A true CN104346794A (en) | 2015-02-11 |
Family
ID=52502337
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310320260.2A Pending CN104346794A (en) | 2013-07-25 | 2013-07-25 | Video flicker detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104346794A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113923373A (en) * | 2021-09-30 | 2022-01-11 | 北京地平线信息技术有限公司 | Image flicker detection method and detection device |
| CN114354138A (en) * | 2021-12-30 | 2022-04-15 | 杭州电子科技大学 | Screen stroboscopic detection system and method based on image processing |
-
2013
- 2013-07-25 CN CN201310320260.2A patent/CN104346794A/en active Pending
Non-Patent Citations (2)
| Title |
|---|
| 王景艳: "旧电影图像质量评价方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 陈振学: "基于特征显著性的目标识别方法及其应用研究", 《中国博士学位论文全文数据库 信息科技辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113923373A (en) * | 2021-09-30 | 2022-01-11 | 北京地平线信息技术有限公司 | Image flicker detection method and detection device |
| CN114354138A (en) * | 2021-12-30 | 2022-04-15 | 杭州电子科技大学 | Screen stroboscopic detection system and method based on image processing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102428127B1 (en) | Apparatus and method detecting motion mask | |
| CN104346793A (en) | Video flicker detection method and device thereof | |
| CN110399831B (en) | Inspection method and device | |
| EP2665039B1 (en) | Detection of near-field camera obstruction | |
| JP2010238032A (en) | Smoke detection device | |
| CN104282011A (en) | Method and device for detecting interference stripes in video images | |
| CN104424632A (en) | Video contrast abnormity detection method and device | |
| CN105260716A (en) | Fault indicator state identification method and fault indicator state identification device | |
| US10853692B2 (en) | Vicinity supervising device and method for supervising vicinity of vehicle | |
| KR102066290B1 (en) | Image recognition apparatus and method thereof | |
| JP2012185684A (en) | Object detection device and object detection method | |
| CN104346794A (en) | Video flicker detection method and device | |
| CN104424633A (en) | Video contrast abnormity detection method and device | |
| CN102387321A (en) | Image pickup device | |
| CN104427210A (en) | A method and device for detecting a random abnormal blinking dot | |
| CN105469414B (en) | profile connection method and device | |
| KR101553707B1 (en) | Image stain detection method for camera module defect determination | |
| JP2012039440A (en) | Dark area noise correction device | |
| JP2017009533A (en) | Image inspection system | |
| JP4547213B2 (en) | Object detection apparatus and method | |
| KR102516839B1 (en) | System and method for detecting leakage | |
| CN105291982B (en) | Stopping thread detector rapidly and reliably | |
| JPH11108660A (en) | Equipment for detecting distance | |
| US20180013932A1 (en) | Detecting shot changes in a video | |
| KR20150009842A (en) | System for testing camera module centering and method for testing camera module centering using the same |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150211 |