CN1274146C - Sports image detecting method - Google Patents
Sports image detecting method Download PDFInfo
- Publication number
- CN1274146C CN1274146C CN 02131392 CN02131392A CN1274146C CN 1274146 C CN1274146 C CN 1274146C CN 02131392 CN02131392 CN 02131392 CN 02131392 A CN02131392 A CN 02131392A CN 1274146 C CN1274146 C CN 1274146C
- Authority
- CN
- China
- Prior art keywords
- motion
- blit
- pixel
- field picture
- file
- 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 - Lifetime
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000012545 processing Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 abstract description 10
- 230000003287 optical effect Effects 0.000 abstract 3
- 238000010586 diagram Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 6
- 230000006835 compression Effects 0.000 description 5
- 238000007906 compression Methods 0.000 description 5
- 230000008520 organization Effects 0.000 description 4
- 125000004122 cyclic group Chemical group 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 241001062009 Indigofera Species 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 239000000975 dye Substances 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Images
Abstract
The present invention discloses a method for detecting motion images. In the method, a motion image in a motion optical impression file is identified and tracked on the premise that a background is not changed; the designated motion optical impression file is processed by programs, and an object file is generated; then, all the edges of the motion parts of the image in the motion optical impression file are represented in the generated object file, and a part circled by the edges correspondingly moves by following the motion of the image. The present invention has the advantages that motion detection analysis is directly carried out through a microcomputer in the method of the present invention, the image does not need to be separated, and people do not need to join in the detection. In the method of the present invention, the description of the motion outline of an object is clear, and the motion track of the object can be intuitively displayed, which is convenient for the detection of motion parameters. The motion detection is realized in software, and the transportability is strong.
Description
Technical field
The present invention relates to method for testing motion, particularly a kind of method that moving image is detected, under the constant situation of background, the edge contour that obtains moving object is to show the motion of target to be measured.
Background technology
The variation of one group of moving image in fact matter corresponding in the frame picture certain/brightness of some concrete parts change.The brightness value of each pixel is changed and threshold, just can judge its quiet moving state, and then delineate out its movement edge profile.
A lot of methods about motion detection and analysis have been proposed at present:
The image of Chinese patent CN 91111320.7 usefulness moving targets is analyzed kinetic characteristic.It when each two field picture arrives, writes down the gray value of this two field picture on moving target position with the method that compares gray scale to one group of consecutive image of moving target, thereby forms the gray scale trajectory diagram.On this two field picture of record in the gray value of target position, the pixel value of corresponding target location among another frame figure is written as this frame number, thereby forms the trajectory diagram of band frame number.Then gray scale trajectory diagram or band frame number trajectory diagram are analyzed by interface circuit input computer.
Multiple security system has been arranged now, and the method that utilization is analyzed moving image is enrolled the personnel's image that enters the protection zone, is used for the protection zone is monitored.Proposed among the Chinese patent application file CN 96193009.8 to deposit the DID of the view picture of a series of separation in memory, and then the motion of the target in the picture has been detected, to reach the purpose that protection monitors.Usually these systems are very expensive, and need a lot of field check personnel.
Chinese patent application file CN 95113626.7 and for example.It is a kind of method for measuring moving articles based on image recognition of field of measuring technique, the method of measurement that it provided, be pickup image to tested moving object marking the time by synchronised clock commander, identification mark and calculate the coordinate of marker characteristic point then calculates the testee movement locus, again along the length of track and current parameters such as movement velocity.
Yet these inventions more are partial to extract own required parameter by motion detection, and are with strong points, but on treatment of picture, observability is poor, especially is applied to the image monitoring aspect, and its intuitive and operability obviously also need further perfect.
The object of the present invention is to provide a kind of like this method for testing motion, it is under the constant prerequisite of background, and the moving image in the motion image file is carried out recognition and tracking: program is handled the motion image file of appointment, and generates file destination.Then in the file destination that is generated, the outer rim of all motion parts in the above-mentioned motion image document image is showed, and the part of being drawn a circle to approve by outer rim is along with the mobile and corresponding of image moved.
Summary of the invention
The purpose that the present invention proposes realizes by following scheme: a kind of motion image detecting method, from one group of moving image, extract two frame still images in turn continuously, and judge the difference of this two two field picture successively; Judge that wherein difference taked to adopt such method: the fritter that every two field picture is decomposed into several BLIT*BLIT (pixel), all pixel G values in each BLIT piece are added up, and average after finishing adding up, calculate the poor of the corresponding BLIT piece of two two field pictures G value mean value then, if this difference greater than preset threshold then will this discrepant BLIT piece outer rim show, and then outmost edge, moving region is shown.
Described outmost edge, moving region is shown adopted such method: allow the overlapped pixel of adjacent BLIT piece, and difference is carried out inverse greater than the outer rim pixel of the BLIT piece of setting threshold handle.
The selection principle of the pixel that participation G value adds up in the described BLIT piece is: the BLIT piece pressed from bottom to up, and dextrosinistral reverse sequence, and the pixel column train value is handled from 0 to BLIT-1.
The described two frame still images that extract continuously in turn are achieved like this: extract still image from motion pictures files continuously, earlier the 1st two field picture is read the region of memory of pointer fp1 indication, the next frame image is read pointer fp2 region of memory pointed, two two field pictures are compared; The data of the region of memory that pointer fp1 is pointed to are write corresponding position in the file destination then, then exchange the value of fp1, fp2 two pointers, finish once circulation; Circulation is next time read in the region of memory that fp2 points to a new two field picture.
Compared with prior art, the invention has the advantages that:
1. the present invention directly carries out the motion detection analysis by microcomputer, does not need image is separated, and does not need the people to participate in detecting.
2. the present invention is more clear to sketching the contours of target travel profile, can demonstrate target trajectory intuitively, is more convenient for the detection to kinematic parameter.
3. motion detection is realized in software, portable strong.Its movement locus can be delineated out to any one image file.This program is a very basic program module, can be for monitoring in real time, laying the foundation as safety device, the application of carrying out aspects such as quiet power detection.
Description of drawings
Below in conjunction with accompanying drawing be not that certain embodiments comes the present invention is done more detailed explanation.
Fig. 1 is the storage organization that 24bits does not compress the BMP image.
Fig. 2 is the storage organization of uncompressed a/v I file video data.
Fig. 3 is to use the front and back contrast of " overlapping edge inverse " method.
Fig. 4 is the program flow diagram of the method for the invention.
Specific embodiment
To be that example comes the present invention is made more detailed description with the AVI image file below.
For the non-compression BMP file of 24bits, its file header sees Table 1 (only listing parameter relevant with this program and structure) with relevant parameter in the image head; The storage organization of image pixel sees that (establish picture size is M*N to accompanying drawing 1, unit: pixel).
| Parameter name | Side-play amount | Take up room | Describe |
| bfSize bfOffBits biWidth biHeight | 2 bytes, 10 bytes, 18 bytes, 22 bytes | 4 bytes, 4 bytes, 4 bytes, 4 bytes | The size of file (byte) image begins to locate byte offsets picture traverse (pixel) picture altitude (pixel) from file header label |
Relevant parameter in table 1 file header and the image head
The storage of image pixel is deferred to from left to right, principle from the bottom to top.For example, for the BMP image of a 24bits, there is the foremost in file data district in the pixel in the lower left corner, and the upper right corner pixel exist file backmost.Each pixel occupies 3 bytes, deposits its B, G, R channel value successively, from 0 to 255.On behalf of indigo plant, green, ruddiness, these three passages learn three primary colors respectively, its light intensity separately of their value representation, wherein 0 be unglazed, 255 be the light intensity maximum.Therefore (0,0,0) represents ater, and (255,255,255) represent pure white.Be the convenience file storage, each row pixel of specified image occupies an integral multiple byte of 4 in the BMP file.Insufficient section needs to mend 0 at the end.It is 6 pixels that a 24bitsBMP picture traverse is for example arranged, and then should mend two 0 in the R value back of the 6th pixel of its each row.(20-3*6＝2)
And for the non-compression 24bits avi file that only has video flowing, the relevant parameter of its file structure file header sees Table 2 (only listing parameter relevant with this program and structure).
| Parameter name | Side-play amount | Take up room | Describe |
| biWidth biHeight | 64 bytes, 68 bytes | 4 bytes, 4 bytes | Picture traverse (pixel) picture altitude (pixel) |
Relevant parameter in table 2 file header and the image head
The storage organization (see figure 2) of avi file is the same with the BMP file, and avi file has also comprised main leader, and it has defined the general information of relevant this file, such as the stream piece number in the file, and AVI sequence wide, highly, total data frame number or the like.Followed by one or more streams piece and stream format piece, they have comprised the information of the relevant stream of file behind the main leader.Data type (video or audio frequency), compression property, the demonstration characteristic of stream for example have been described, data format in the stream or the like.What and then deposit is actual data block.Wherein voice data identifies (" ## " is flow identifier) with " ##wb ", and video data (compression) identifies (as Fig. 2) with " ##dc " sign, video data (compression) with " ##db ".Also have other optional of index block etc. in addition, but they and this program relation are not quite, so be not described in detail.
To sum up in the point that finally that to the recognition and tracking of AVI dynamic video file the processing to two width of cloth still images comes up.Program variable, pointer declaration see Table 3.
| Variable (pointer) title | Purposes |
| *file1 *file3 *fp1 *fp2 | The pointer of pointed the 2nd two field picture place internal memory of input file pointer output file pointed the 1st two field picture place internal memory |
| *fp1s *fp2s bmpbytes changeloc ? loc ? blitnummax blitnum blitx blity width height s1，s2 ? i，j k n flag BLIT CON | * occupied space (byte) coordinate in certain BLIT piece of playback pointer one two field picture of the playback pointer * fp2 of fp1 is＜i j〉biasing (byte) k frame (k=0 of G value in internal memory of pixel, 1,2 ...) cumulative (mean value) variable cyclic variable of pixel G value records current processing frame number in the corresponding BLIT piece of height (pixel) two two field pictures of width (pixel) two field picture of row coordinate one two field picture of the current BLIT piece of row-coordinate of the current BLIT piece of numbering of the total current BLIT piece of BLIT piece number of the biasing (byte) of B value in internal memory of first pixel variable assists the threshold value variable of the length of side (pixel) judgement image motion severe degree of cyclic variable frame of video end mark (0 for finishing) the BLIT piece of pixel inverse operation |
Table 3 program variable, pointer gauge
Program flow diagram with reference to accompanying drawing 4 the method for the invention can be done clearer understanding to the embodiment of the invention.A kind of method described below has been passed through in the processing of avi file realized, the present invention is referred to as " getting frame in turn " method temporarily.Described " getting frame in turn " method is exactly to extract the method for still image from avi file continuously.In brief, earlier the 1st two field picture is read the region of memory of fp1 indication exactly, the next frame image is read fp2 region of memory pointed, two two field pictures are compared.The data of the region of memory that fp1 is pointed to are write corresponding position in the file destination.Then exchange the value of fp1, fp2 two pointers, finish once circulation.Circulation is next time read in the region of memory that fp2 points to a new two field picture.Because fp1, fp2 exchange in advance, be equivalent to last two field picture is covered.Like this, in turn still image is compared.
By loc=2056+ (bmpbytes+8) * k statement it is located before reading in every two field picture, wherein k=0,1,2... are the number of frames that is about to handle.With a two field picture to read in internal memory be (is example to read in the region of memory that fp1 points to) by statement fread (fp1, bmpbytes, 1, file1) realize.The statement of exchange memory pointer is fp2=fp1s-1 and fp1=fp2s-1.
The present invention judges the difference of adjacent two two field pictures by " piece mean value " method then, and it also is the core algorithm of this program.Briefly be every two field picture to be decomposed into the fritter of several BLIT*BLIT (pixel), and calculate the mean value of all pixel G values in each BLIT piece.Ask the poor of the corresponding BLIT piece of two two field pictures G value mean value then.If it is greater than preset threshold CON, then the outer rim of this BLIT piece is drawn a circle to approve.Wherein, the selection of threshold value is very important, and threshold value is fixed usually, the present invention is directed to different backgrounds, different moving images, and the setting of threshold value is targetedly.Motion between each frame of judgement that will be appropriate, suitably selected threshold.If coefficient of determination is little, be judged as moving image between then many rest images, if coefficient of determination is too big, will be difficult to accurately distinguish the motion of target.After treating that all the BLIT piece outer rims that need draw a circle to approve are drawn a circle to approve, the data in the internal memory are write corresponding position in the file destination.
Wherein said outer rim delineation with discrepant BLIT piece is handled, and the present invention has adopted a kind of method of novelty to realize, is referred to as " overlapping edge inverse " method herein temporarily.So-called " overlapping edge inverse " method is by hereinafter describing.
At painted, there are following two problems to the outward flange of each BLIT piece: the one, should use what color dyes? if use a constant color, this color must be close with some regional color of some image, is difficult to distinguish with former figure; The 2nd, facing mutually under the situation that several BLIT pieces all there are differences, outward flange is painted to be easy to form " grid effect " (see figure 3).Yet we just hope the outward flange of depicting moving object, do not want frame on them." overlapping edge inverse " method simply says to be exactly to allow the overlapped pixel of adjacent BLIT piece.Because outward flange is painted also is a pixel, and painted if adjacent like this BLIT piece all carries out outward flange, the overlapping region will be colored twice or four times.If just think " painted " changed into " inverse ", through twice (or four times) inverse color reduction, grid can disappear.For the outer rim of moving object, only carry out inverse one time, so the pixel groups that a pixel wide is arranged in this outer rim by inverse, regardless of image, all can form the contrast of maximum.And, can find in the practice that the overlapping bight of BLIT piece can be by inverse four times, this has just in time formed the ideal effect at " dotted line edge ".So " overlapping edge inverse " method of employing shows outmost edge, moving region.After certain corresponding BLIT piece of having judged two two field pictures there are differences, can carry out mark to this species diversity by " overlapping edge inverse " method, and output to file at last.
For example to handle the avi file of a 160*120, suppose that the BLIT value is made as 10.So every row is divided into the 160/10=16 piece, and every row are divided into the 120/10=12 piece.With 16*12=192 BLIT block number (blitnum=0--191), successively to its processing.
Ask the ranks coordinate figure of each BLIT piece earlier:
blity＝width/BLIT-fmod(blitnum，width/BLIT)-1；
blitx＝height/BLIT-(blitnum-blity)/(width/BLIT)-1；
Calculate the biasing (with fp1 is example) of first G value of this piece in internal memory again:
fp1＝fp1s+(blitx*BLIT)*(4*(int)(3*width/4.0-0.1)+4)+blity*BLIT*3；
G value with this each pixel of piece adds up afterwards, by variable s1, the s2 of adding up.Add up at all pixel values and to average after finishing:
s1＝s1/(double)(BLIT*BLIT)；
s2＝s2/(double)(BLIT*BLIT)；
If the absolute value of s1, s2 difference is greater than predetermined threshold value CON at this moment, then use of the outer rim delineation of " overlapping edge inverse " method with this BLIT piece.After s1, s2 is clear 0, blitnum adds 1, carries out the operation of next BLIT piece.
With the average method of piecemeal, can find discrepant.Actually but pixel is from (i1 moves on to j1) that (Hai Shi i2 is j2) from (i2 moves on to j2) that (i1 j1) but can't judge.In fact because the existence of " wallpaper effect ", be may be to its judgement only by two frame still images.(" wallpaper effect " be exactly only by two frame still images can't judge (i1, j1) and (i2, j2) who be wallpaper who be the effect of thing.Yet), because " getting frame in turn " method that the front was carried can fundamentally weaken the influence of " wallpaper effect ".
If all pixels in certain BLIT piece are added up entirely, promptly pixel column train value (in the BLIT piece) all from 0 to BLIT.If find like this then in the end can have more delegation's one row (influence that has more row is little), exceed region of memory, cause comparison error; If make the pixel column train value all from 0 to BLIT-1, but if previous BLIT piece has been finished comparison, the region of memory data that fp1 points to have become, row (or row) value is that 0 pixel has been carried out inverse, so relatively mistake can take place; If the pixel column train value all from 1 to BLIT-1, can be made mistakes when BLIT is 1; BLIT is not 1 but very mistake can occurs when very little, and is inadvisable yet.So the selection principle that participates in the pixel that G value adds up in the BLIT piece is such: with the BLIT piece by from bottom to up, dextrosinistral reverse sequence processing, and the pixel column train value can overcome the above problems well from 0 to BLIT-1.
The method that moving image is detected of the present invention, be not limited only to listed utilization in specification and the execution mode, it can be applied to various suitable the present invention's field fully, for those skilled in the art, can easily realize additional advantage and make amendment, therefore under the situation of the spirit and scope of the universal that does not deviate from claim and equivalency range and limited, the examples shown that the present invention is not limited to specific details, representational equipment and illustrates here and describe.
Claims (7)
1, a kind of motion image detecting method compares one group of consecutive image, it is characterized in that:
From one group of moving image, extract two frame still images in turn continuously, judge the difference of this two two field picture successively; Judge that wherein difference taked to adopt such method: the fritter that every two field picture is decomposed into several BLIT*BLIT, all pixel G values in each BLIT piece are added up, and average after finishing adding up, calculate the poor of the corresponding BLIT piece of two two field pictures G value mean value then, if this difference greater than preset threshold then will this discrepant BLIT piece outer rim show, and then outmost edge, moving region is shown; Described outmost edge, moving region is shown adopted such method: allow the overlapped pixel of adjacent BLIT piece, and difference is carried out inverse or painted processing greater than the outer rim pixel of the BLIT piece of setting threshold.
2, motion image detecting method according to claim 1, it is characterized in that, the selection principle of the pixel that participation G value adds up in the described BLIT piece is: the BLIT piece pressed from bottom to up, and dextrosinistral reverse sequence, and the pixel column train value is handled from 0 to BLIT-1.
3, motion image detecting method according to claim 1, it is characterized in that, the described two frame still images that extract continuously in turn are achieved like this: extract still image from motion pictures files continuously, earlier the 1st two field picture is read the region of memory of pointer fp1 indication, the next frame image is read pointer fp2 region of memory pointed, two two field pictures are compared; The data of the region of memory that pointer fp1 is pointed to are write corresponding position in the file destination then, then exchange the value of fp1, fp2 two pointers, finish once circulation; Circulation is next time read in the region of memory that fp2 points to a new two field picture.
4, motion image detecting method according to claim 3, it is characterized in that, before reading in every two field picture, it is located by loc=2056+ (bmpbytes+8) * k statement, wherein k=0,1,2..., be the number of frames that is about to handle, loc is the biasing of B value in internal memory of first pixel of k frame, and bmpbytes is the occupied space of a two field picture.
5, motion image detecting method according to claim 3, it is characterized in that, it is by statement fread (fp1 that one two field picture is read in internal memory, bmpbytes, 1, file1) realize, wherein the statement of exchange memory pointer is fp2=fp1s-1 and fp1=fp2s-1, wherein file1 is the input file pointer, bmpbytes is the occupied space of a two field picture, and fp1 is for pointing to the pointer of the 1st two field picture place internal memory, and fp2 is for pointing to the pointer of the 2nd two field picture place internal memory, fp1s is the playback pointer of fp1, and fp2s is the playback pointer of fp2.
6, the described motion image detecting method of arbitrary claim the basis from 1 to 5 is characterized in that described motion pictures files is the AVI dynamic video file.
7, motion image detecting method according to claim 6 is characterized in that, each row pixel of specified image occupies an integral multiple byte of 4 in the file, and insufficient section mends 0 at the end.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 02131392 CN1274146C (en) | 2002-10-10 | 2002-10-10 | Sports image detecting method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 02131392 CN1274146C (en) | 2002-10-10 | 2002-10-10 | Sports image detecting method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN1489112A CN1489112A (en) | 2004-04-14 |
| CN1274146C true CN1274146C (en) | 2006-09-06 |
Family
ID=34144917
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 02131392 Expired - Lifetime CN1274146C (en) | 2002-10-10 | 2002-10-10 | Sports image detecting method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN1274146C (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101271672A (en) * | 2007-03-23 | 2008-09-24 | 奇美电子股份有限公司 | Dynamic image detector for LCD device and its detection method |
Families Citing this family (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1333327C (en) * | 2004-05-26 | 2007-08-22 | 凌阳科技股份有限公司 | Optimum correlation matching method and system used to judge locus behavior |
| JP2006098803A (en) * | 2004-09-29 | 2006-04-13 | Toshiba Corp | Moving image processing method, moving image processing apparatus and moving image processing program |
| JP4290164B2 (en) * | 2006-01-31 | 2009-07-01 | キヤノン株式会社 | Display method for displaying display showing identification area together with image, program executed by computer apparatus, and imaging apparatus |
| JP2007208723A (en) * | 2006-02-02 | 2007-08-16 | Victor Co Of Japan Ltd | Method and program for enhancing contour |
| JP4187748B2 (en) * | 2006-03-23 | 2008-11-26 | 株式会社コナミデジタルエンタテインメント | Image generating apparatus, image generating method, and program |
| JP4915655B2 (en) * | 2006-10-27 | 2012-04-11 | パナソニック株式会社 | Automatic tracking device |
| CN101184235B (en) * | 2007-06-21 | 2010-07-28 | 腾讯科技（深圳）有限公司 | Method and apparatus for implementing background image extraction from moving image |
| CN101593348B (en) * | 2008-05-26 | 2012-09-26 | 英华达(上海)电子有限公司 | Mobile call terminal with image processing function and image processing method thereof |
| JP4507129B2 (en) * | 2008-06-06 | 2010-07-21 | ソニー株式会社 | Tracking point detection apparatus and method, program, and recording medium |
| CN101447078B (en) * | 2008-12-10 | 2011-06-15 | 东软集团股份有限公司 | Method for obstacle segmentation and device thereof |
| CN101567087B (en) * | 2009-05-25 | 2012-05-23 | 北京航空航天大学 | Method for detecting and tracking small and weak target of infrared sequence image under complex sky background |
| CN101909145B (en) * | 2009-06-05 | 2012-03-28 | 鸿富锦精密工业（深圳）有限公司 | Image noise filtering system and method |
| CN101882217B (en) * | 2010-02-26 | 2012-06-27 | 杭州海康威视软件有限公司 | Target classification method of video image and device |
| EP2538372A1 (en) * | 2011-06-23 | 2012-12-26 | Alcatel Lucent | Dynamic gesture recognition process and authoring system |
| CN102779504A (en) * | 2012-05-16 | 2012-11-14 | 新奥特（北京）视频技术有限公司 | Method for realizing video split screen display |
| CN103885461B (en) * | 2012-12-21 | 2017-03-01 | 宗经投资股份有限公司 | Automatically the moving method of the color make-up instrument of color make-up machine |
-
2002
- 2002-10-10 CN CN 02131392 patent/CN1274146C/en not_active Expired - Lifetime
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101271672A (en) * | 2007-03-23 | 2008-09-24 | 奇美电子股份有限公司 | Dynamic image detector for LCD device and its detection method |
| CN101271672B (en) * | 2007-03-23 | 2013-08-14 | 群创光电股份有限公司 | Dynamic image detector for LCD device and its detection method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN1489112A (en) | 2004-04-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN1274146C (en) | Sports image detecting method | |
| US7609855B2 (en) | Method of analyzing moving objects using a vanishing point algorithm | |
| CN102609934B (en) | Multi-target segmenting and tracking method based on depth image | |
| CN102789234B (en) | Robot navigation method and robot navigation system based on color coding identifiers | |
| EP0848886B1 (en) | Method and apparatus for determining the position of a tv camera for use in a virtual studio | |
| CN110580723B (en) | Method for carrying out accurate positioning by utilizing deep learning and computer vision | |
| CN101464946B (en) | Detection method based on head identification and tracking characteristics | |
| CN103150559B (en) | Head recognition and tracking method based on Kinect three-dimensional depth image | |
| CN102222104B (en) | Method for intelligently extracting video abstract based on time-space fusion | |
| CN109145708B (en) | Pedestrian flow statistical method based on RGB and D information fusion | |
| CN104933710A (en) | Intelligent analysis method of store people stream track on the basis of surveillance video | |
| KR20030060328A (en) | Method and apparatus for color-based object tracking in video sequences | |
| CN102289948A (en) | Multi-characteristic fusion multi-vehicle video tracking method under highway scene | |
| CN101094413A (en) | Real time movement detection method in use for video monitoring | |
| CN106874884A (en) | Human body recognition methods again based on position segmentation | |
| CN1506686A (en) | Moving image detecting method | |
| Pallavi et al. | Ball detection from broadcast soccer videos using static and dynamic features | |
| CN106295491A (en) | Track line detection method and device | |
| CN111238365B (en) | Subway train distance measurement and positioning method and system based on stereoscopic vision | |
| US6549659B1 (en) | Method and apparatus for determining the location of a reflective object within a video field | |
| CN111402289A (en) | Crowd performance error detection method based on deep learning | |
| WO2022028383A1 (en) | Lane line labeling method, detection model determining method, lane line detection method, and related device | |
| CN108364306A (en) | A kind of vision real-time detection method of high speed periodic motion | |
| CN107506753A (en) | A kind of more wireless vehicle trackings towards dynamic video monitoring | |
| JPH10255057A (en) | Mobile object extracting device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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 | ||
| ASS | Succession or assignment of patent right |
Owner name: GUANGDONG ZHONGXING ELECTRONICS CO., LTD. Free format text: FORMER OWNER: BEIJING VIMICRO CORPORATION Effective date: 20150228 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| COR | Change of bibliographic data |
Free format text: CORRECT: ADDRESS; FROM: 100083 HAIDIAN, BEIJING TO: 519031 ZHUHAI, GUANGDONG PROVINCE |
|
| TR01 | Transfer of patent right |
Effective date of registration: 20150228 Address after: 519031 Guangdong city of Zhuhai province Hengqin Baohua Road No. 6, room 105 -478 Patentee after: Guangdong Zhongxing Electronics Co.,Ltd. Address before: 100083, Haidian District, Xueyuan Road, Beijing No. 35, Nanjing Ning building, 15 Floor Patentee before: VIMICRO Corp. |
|
| DD01 | Delivery of document by public notice |
Addressee: Guangdong Zhongxing Electronics Co.,Ltd. Document name: Notification of Passing Examination on Formalities |
|
| DD01 | Delivery of document by public notice | ||
| DD01 | Delivery of document by public notice |
Addressee: Shen Yingming Document name: payment instructions |
|
| CX01 | Expiry of patent term | ||
| CX01 | Expiry of patent term |
Granted publication date: 20060906 |
|
| DD01 | Delivery of document by public notice | ||
| DD01 | Delivery of document by public notice |
Addressee: Guangdong Zhongxing Electronics Co.,Ltd. patent The person in charge Document name: Notice of termination upon expiration of patent right |