CA1333424C - Digital data processing - Google Patents
Digital data processingInfo
- Publication number
- CA1333424C CA1333424C CA000607884A CA607884A CA1333424C CA 1333424 C CA1333424 C CA 1333424C CA 000607884 A CA000607884 A CA 000607884A CA 607884 A CA607884 A CA 607884A CA 1333424 C CA1333424 C CA 1333424C
- Authority
- CA
- Canada
- Prior art keywords
- image
- corner
- edge
- positions
- digital data
- 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
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
- G08B13/1961—Movement detection not involving frame subtraction, e.g. motion detection on the basis of luminance changes in the image
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/04—Detecting movement of traffic to be counted or controlled using optical or ultrasonic detectors
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/20—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using video object coding
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
A method of processing digital data in a digitised image matrix in order to detect the positions of any sharp intensity variations present in adjacent ones of the pixels representing said image, the method comprising the steps of comparing the intensity of each primary pixel with those of the secondary pixels which surround it, calculating whether said primary pixel can be classified as having a constant, an edge-like or a corner-like value, and collating this information to give positions of both edge and corner features which are present in said image matrix.
The processing method can be used for example in detecting images, for instance in a burglar alarm system or for the cytological scanning of cell material.
The processing method can be used for example in detecting images, for instance in a burglar alarm system or for the cytological scanning of cell material.
Description
1~33~24 DlG~TAL DASA PROCESSING
This invention relates to digital data processing. It relates particularly to digital data inforrnation which is present in a stored digitised image matrix and to a method of and means for detecting significant features in the stored information.
When it is re~uired to ~Fiew a particular digitaJ image automatically, it is usually necessary to identify corner and ed~ge features since these correspond to the outlines of objects and to prominent surface markings which are present in the stored imace.
This operation gives a quantity of low-level information which can be used for further work, but it is most important that the data extracted at this early stage should be of a reliable quality.
A description of the cdge features present in an image is onl~-helpful for certain parts of the image. For other parts of the image, the so-called image corners, corresponding to cdge junctions and sharp bends in edges, and to isolated point-~ike features, are important. Where the kind of feature to be expected in the image is not restricted in an~ way, for example, in a depiction of a natural scene, then merely to descnbe the ima~ge in terms of edges alone or of corners alone would be incapable of providing understandin~ of the whole amount of the informat;on present.
Some data pro~essing methods ha~ e been proposed which will extract either edge or corner information from an image matrix. One edge extractor is the Canny- cdge hlter. However, ~his device can suffer from an inability to form edge junctions and it may be necessary to perform an additional heuristic processing operation in 1333~4 order to ovcrcome this problcm. In addi~ion, in texturcd rcgions of the image, cd~ges can sometimes form a poor and unreliable dcscriptive feature and this thcrcfore may Icad one to prefer a corner description.
Some of the best available corner detectors ha~e been proposed by Moravec, NageL Beaudet and Kitchen & Rosenfeld. These corner detectors are, however, not ideal since they can be temporall~
inconsistent in their responses (that is, they are unreliable)t and they can respond too readily to the presence of small imperfections in stron~ image edges.
The present invention was devised in an attempt to overcome some of the disadvantages of both cdge and corner feature detectors.
Accordin~ to the invention, there is provided a meth~d of processin~ dig~tal data in a di~itised image matrix in order to detect the positions of any sharp intensity ~ariations present in adjacent ones of the pixels representin~ said ima~e, the method comprising the steps of comparing the intensity of cach pnmary pixel ~ith those of the secondar~ pixels which surround it, calculatin~ whether said primar~ pixe~ can be classifie~ as ha~ in~ a constant, an edge~ ;e or a corner-li~e ralue, and collating this information to give positions of both ed~e ~nd corner features which are present in said imace matrix .
Con~ eniently, before said comparison sta~e, the ori~inal ima~e matrix ma~! be processed to form an intermediate simp]ified ima~e ~hich excludes unnecessary detail. This intermediate ima~e may be a quaternar~, Image.
1333~24 ID one cmbodiment, the mcthod may includc the furthcr step of ta~in~ a second digitised image matri~ after a given time intcr~ al has clapscd, and comparing the processed digital area of the said sccond image with that of a first image, such that any change in the posi~ions of the selected features of the images will be detected B~ wa~ of example, a particular embo~iment of the in~ention V. i11 DO~ be described with reference to the accompanying dra~ in~g the siD~le ~igure of which shows a block diagram of the main components of an image motion surveillance detector.
1 h~ detector device of the invention will first be described with referenc~ to the main components shown in the Figure and the operation of the feature extraction stage will be explained later.
The surveillance detector comprises a video camera 1 which pro~ides information for a digital data processor 2 and this act~ to suppl~- output si~nals on an output line 3. The processor 2 ~ives input si~na}s from the video camera and these are delivered to an image di~itisation stage 4. After this stage, the input informa~on ~s passed i~to a frame store 6 and the pixels in this store are ther processed in turn b~ a corner/ed~e feature extraction circuit 7.
The data obtained from the feature e~traction circuit ? is ther2 applied to a feature matching block 8. In parallel with this, the data is also fed into a dela~ block 9 which will hold this data for a predeterrnined time interval before delivering it to the block 8.
At the feature matchin~ bloc~ 8, the extracte~ fcatures of the data s~am are compared with the set of features which is compiled after t~e predetermined time interval. The information obtainod is thus able to sho-~ an~ movement of the selected extracted feature 133342~
which ~as takCD place during the pcci~cd timc intcr~al. Proa dlis information it is possible to calculate thc locat;on and image ~elocity of a mo~Lng body which is ~riCWcd by the ~rideo camcra 1.
In order to detect the presence of a sharp intensity ~ion in adjacent ones of the pixels representing the image matri~c, it is first necessar} to compare the intensity of light at one prima~ p~el with the inten sities of cach of the secondary pi~els which surround it.
There may be at least twentyfour of the secondary pi~els, or possibly several hundred.
A local auto-correlation function for each of the priman, pixels is thus re4uired and this will describe whether the local patcb of image i~ntensities, represented by the possible total of twent,~five pixels, is approximately constant in value, is cdge-like, or is corner-like. Corners are indicated by the auto-correlation function being sharply peaked, and edges by the auto-correlation function bciDg ridge shaped. The explicit auto~orrelation function may DOt ee~ to be calculated, but only a determination of its se~ond-order cxpansion about the origin may be necessarv. A mathematical specific~on of these r~quirements will no~ be given l,,et the ~possibly pre-smoothed) ima~e intensities be represented b~ the a~Tay of values l~y~ where x and y are ~
Cartesia~ image coordinates. To stan with, the two first gra~nts are calculated, thus X~,,y = 1 ~l.y ~ I,~ l,y Y ~ . y~ Y- 1 Next~ the smoothed quadratic gradients are calculated s 1~3 i2~
A = X2 ~ W
B = y2 * W
C = (X.Y) * W
where ' represents convolution, and W is a smoothing filter, explicit example being (] 2 1) = ~2 4 2~
(1 2~) Finall~-. the corner/edge response, R, is calculated R = (A.B-C2) - k(A~B)2 a alue of 0.1 being typical for the parameter k .
~ e presence of a corner region is indicated by the vaJu~ for R
bem~ lar~e and positive. An individual plxel is deeme~ to be a corner if its response, R, is larger than the responses of each ~ its eight nei,~hbourin~ pixels. Similarly, an edge region is indicate~ by R
beinc l~ge and negative. A pixel is deemed to be an ed~e pi~el if its response. R, is smaller (more negative) than its two nei~ghbour~ in either the x or y direction, depending on ~,vhich of the first ~adients, X and Y, are larger in magnitude.
S~andard edge clean-up algorithms (similar to those useJ in the Cann~- ~ige filter) are applied to the edge image, to remove s~
lines and spurs, and to complete break~ in edges. The result i~ a qua~ern~ry (that is, a four-state) ima~e, ~ith each pixel c}ass~fi.d as a corner. a corner neighbourhood, an uige or a background. ~h~
~;
edges ~re thin (that is, they are one pi~cl in width) and run ~e~ccn the cor~er regions. The p~oblem of junction fo~nation is ovacome by the presence of corncr regions surrounding the corners, ait ~hich regions ~he cdges terrninate. The problem of cdge inconsistcDc~- in texture~ ima~e regions is overcome by their being representcd by regions containing corners but few cdges.
One way of effectin~ the nccessary calculations would ~e by processin~ the data by means of an off-the-shelf microcomp~r, with the a}gorithm bein~ implemented in either high or lo~ el software The input to the microcomputer would be digitised ima~es, and the output would be the locations and image velocities o~ d~e required feature combinations. However, due to the number o~
calculations involved, use of a microcomputer would ~e rela~--ely slor~ d this slo~ ness will be undesirable for time-critical applications .
For the time-critical applications, special-purpose hard~-are could be constructed to calculate the intermediate images X, Y, ~, B, C
and R, and to select appropriate local maxima or minima va~ of the corner/edge response R as corner or edge pixe}s resp~c~
This proposed special-purpose hardr.~are would be pipelined, ~nd make u5e of convolution chips and other dedicated VLSI cir.~ ts.
This ssep would be followed by stages for edge clean-up ~ndi feature trac!~inc on one or more microcomputers.
~ 'here the scene viewed by the video camera can be e~pected to chan~e ~rith the passage of time, the inven~ion can be us~ to procecs a second digitised image matrix after a given bme i~ n al ha~ el~psed. The processed data o~ trhe said second image C;L~ then be comparcd vvith that of a first imagc ~o that any change in d~e positions of the selccted featurcs of the imagcs will be dctcctcd Usc of the digital data processing method has been prop~sed in the cons~uction of passive cquipment for ~urveying a scene, ~ch as for a bur~lar alarm system. With imagery acquired from a s~ic surveyin~ camera, any consistent motion of cdge and corner fcatures will indicate a mo~ ing target whilst inconsistent motion ma~ bc due to ima~e noise, wind-blo~n vegetation etc. ln a traffic controI
application, the method can be used to detect the presence of movin~
vehicle~. Since the digitised image could be produced from i~fra-red radiation rather than visible light, the system could still wor~
cffectivel~ at night-time or in bad weather conditions.
11 se of the data processing method for d~e automatic scannin~
of cytolo,~ical cell matenal has also been proposed.
The fore~going description of an embodiment of the invention has been given by way of example only and a number of modific~ions may be made without departing from the scope of the in~ention as defined in the appended claims. ~or instance, althou~gh the in~ ention has been described as a method of processin~ the data in a s~n~le image matrix, this would be cqually applica~le ~o processin~ material from two or more image matrices, so that a three-d~mensional cffect could be obtained.
This invention relates to digital data processing. It relates particularly to digital data inforrnation which is present in a stored digitised image matrix and to a method of and means for detecting significant features in the stored information.
When it is re~uired to ~Fiew a particular digitaJ image automatically, it is usually necessary to identify corner and ed~ge features since these correspond to the outlines of objects and to prominent surface markings which are present in the stored imace.
This operation gives a quantity of low-level information which can be used for further work, but it is most important that the data extracted at this early stage should be of a reliable quality.
A description of the cdge features present in an image is onl~-helpful for certain parts of the image. For other parts of the image, the so-called image corners, corresponding to cdge junctions and sharp bends in edges, and to isolated point-~ike features, are important. Where the kind of feature to be expected in the image is not restricted in an~ way, for example, in a depiction of a natural scene, then merely to descnbe the ima~ge in terms of edges alone or of corners alone would be incapable of providing understandin~ of the whole amount of the informat;on present.
Some data pro~essing methods ha~ e been proposed which will extract either edge or corner information from an image matrix. One edge extractor is the Canny- cdge hlter. However, ~his device can suffer from an inability to form edge junctions and it may be necessary to perform an additional heuristic processing operation in 1333~4 order to ovcrcome this problcm. In addi~ion, in texturcd rcgions of the image, cd~ges can sometimes form a poor and unreliable dcscriptive feature and this thcrcfore may Icad one to prefer a corner description.
Some of the best available corner detectors ha~e been proposed by Moravec, NageL Beaudet and Kitchen & Rosenfeld. These corner detectors are, however, not ideal since they can be temporall~
inconsistent in their responses (that is, they are unreliable)t and they can respond too readily to the presence of small imperfections in stron~ image edges.
The present invention was devised in an attempt to overcome some of the disadvantages of both cdge and corner feature detectors.
Accordin~ to the invention, there is provided a meth~d of processin~ dig~tal data in a di~itised image matrix in order to detect the positions of any sharp intensity ~ariations present in adjacent ones of the pixels representin~ said ima~e, the method comprising the steps of comparing the intensity of cach pnmary pixel ~ith those of the secondar~ pixels which surround it, calculatin~ whether said primar~ pixe~ can be classifie~ as ha~ in~ a constant, an edge~ ;e or a corner-li~e ralue, and collating this information to give positions of both ed~e ~nd corner features which are present in said imace matrix .
Con~ eniently, before said comparison sta~e, the ori~inal ima~e matrix ma~! be processed to form an intermediate simp]ified ima~e ~hich excludes unnecessary detail. This intermediate ima~e may be a quaternar~, Image.
1333~24 ID one cmbodiment, the mcthod may includc the furthcr step of ta~in~ a second digitised image matri~ after a given time intcr~ al has clapscd, and comparing the processed digital area of the said sccond image with that of a first image, such that any change in the posi~ions of the selected features of the images will be detected B~ wa~ of example, a particular embo~iment of the in~ention V. i11 DO~ be described with reference to the accompanying dra~ in~g the siD~le ~igure of which shows a block diagram of the main components of an image motion surveillance detector.
1 h~ detector device of the invention will first be described with referenc~ to the main components shown in the Figure and the operation of the feature extraction stage will be explained later.
The surveillance detector comprises a video camera 1 which pro~ides information for a digital data processor 2 and this act~ to suppl~- output si~nals on an output line 3. The processor 2 ~ives input si~na}s from the video camera and these are delivered to an image di~itisation stage 4. After this stage, the input informa~on ~s passed i~to a frame store 6 and the pixels in this store are ther processed in turn b~ a corner/ed~e feature extraction circuit 7.
The data obtained from the feature e~traction circuit ? is ther2 applied to a feature matching block 8. In parallel with this, the data is also fed into a dela~ block 9 which will hold this data for a predeterrnined time interval before delivering it to the block 8.
At the feature matchin~ bloc~ 8, the extracte~ fcatures of the data s~am are compared with the set of features which is compiled after t~e predetermined time interval. The information obtainod is thus able to sho-~ an~ movement of the selected extracted feature 133342~
which ~as takCD place during the pcci~cd timc intcr~al. Proa dlis information it is possible to calculate thc locat;on and image ~elocity of a mo~Lng body which is ~riCWcd by the ~rideo camcra 1.
In order to detect the presence of a sharp intensity ~ion in adjacent ones of the pixels representing the image matri~c, it is first necessar} to compare the intensity of light at one prima~ p~el with the inten sities of cach of the secondary pi~els which surround it.
There may be at least twentyfour of the secondary pi~els, or possibly several hundred.
A local auto-correlation function for each of the priman, pixels is thus re4uired and this will describe whether the local patcb of image i~ntensities, represented by the possible total of twent,~five pixels, is approximately constant in value, is cdge-like, or is corner-like. Corners are indicated by the auto-correlation function being sharply peaked, and edges by the auto-correlation function bciDg ridge shaped. The explicit auto~orrelation function may DOt ee~ to be calculated, but only a determination of its se~ond-order cxpansion about the origin may be necessarv. A mathematical specific~on of these r~quirements will no~ be given l,,et the ~possibly pre-smoothed) ima~e intensities be represented b~ the a~Tay of values l~y~ where x and y are ~
Cartesia~ image coordinates. To stan with, the two first gra~nts are calculated, thus X~,,y = 1 ~l.y ~ I,~ l,y Y ~ . y~ Y- 1 Next~ the smoothed quadratic gradients are calculated s 1~3 i2~
A = X2 ~ W
B = y2 * W
C = (X.Y) * W
where ' represents convolution, and W is a smoothing filter, explicit example being (] 2 1) = ~2 4 2~
(1 2~) Finall~-. the corner/edge response, R, is calculated R = (A.B-C2) - k(A~B)2 a alue of 0.1 being typical for the parameter k .
~ e presence of a corner region is indicated by the vaJu~ for R
bem~ lar~e and positive. An individual plxel is deeme~ to be a corner if its response, R, is larger than the responses of each ~ its eight nei,~hbourin~ pixels. Similarly, an edge region is indicate~ by R
beinc l~ge and negative. A pixel is deemed to be an ed~e pi~el if its response. R, is smaller (more negative) than its two nei~ghbour~ in either the x or y direction, depending on ~,vhich of the first ~adients, X and Y, are larger in magnitude.
S~andard edge clean-up algorithms (similar to those useJ in the Cann~- ~ige filter) are applied to the edge image, to remove s~
lines and spurs, and to complete break~ in edges. The result i~ a qua~ern~ry (that is, a four-state) ima~e, ~ith each pixel c}ass~fi.d as a corner. a corner neighbourhood, an uige or a background. ~h~
~;
edges ~re thin (that is, they are one pi~cl in width) and run ~e~ccn the cor~er regions. The p~oblem of junction fo~nation is ovacome by the presence of corncr regions surrounding the corners, ait ~hich regions ~he cdges terrninate. The problem of cdge inconsistcDc~- in texture~ ima~e regions is overcome by their being representcd by regions containing corners but few cdges.
One way of effectin~ the nccessary calculations would ~e by processin~ the data by means of an off-the-shelf microcomp~r, with the a}gorithm bein~ implemented in either high or lo~ el software The input to the microcomputer would be digitised ima~es, and the output would be the locations and image velocities o~ d~e required feature combinations. However, due to the number o~
calculations involved, use of a microcomputer would ~e rela~--ely slor~ d this slo~ ness will be undesirable for time-critical applications .
For the time-critical applications, special-purpose hard~-are could be constructed to calculate the intermediate images X, Y, ~, B, C
and R, and to select appropriate local maxima or minima va~ of the corner/edge response R as corner or edge pixe}s resp~c~
This proposed special-purpose hardr.~are would be pipelined, ~nd make u5e of convolution chips and other dedicated VLSI cir.~ ts.
This ssep would be followed by stages for edge clean-up ~ndi feature trac!~inc on one or more microcomputers.
~ 'here the scene viewed by the video camera can be e~pected to chan~e ~rith the passage of time, the inven~ion can be us~ to procecs a second digitised image matrix after a given bme i~ n al ha~ el~psed. The processed data o~ trhe said second image C;L~ then be comparcd vvith that of a first imagc ~o that any change in d~e positions of the selccted featurcs of the imagcs will be dctcctcd Usc of the digital data processing method has been prop~sed in the cons~uction of passive cquipment for ~urveying a scene, ~ch as for a bur~lar alarm system. With imagery acquired from a s~ic surveyin~ camera, any consistent motion of cdge and corner fcatures will indicate a mo~ ing target whilst inconsistent motion ma~ bc due to ima~e noise, wind-blo~n vegetation etc. ln a traffic controI
application, the method can be used to detect the presence of movin~
vehicle~. Since the digitised image could be produced from i~fra-red radiation rather than visible light, the system could still wor~
cffectivel~ at night-time or in bad weather conditions.
11 se of the data processing method for d~e automatic scannin~
of cytolo,~ical cell matenal has also been proposed.
The fore~going description of an embodiment of the invention has been given by way of example only and a number of modific~ions may be made without departing from the scope of the in~ention as defined in the appended claims. ~or instance, althou~gh the in~ ention has been described as a method of processin~ the data in a s~n~le image matrix, this would be cqually applica~le ~o processin~ material from two or more image matrices, so that a three-d~mensional cffect could be obtained.
Claims (4)
1. A method of processing digital data in a digitised image matrix in order to detect the positions of any sharp intensity variations present in adjacent ones of the pixels representing said image, the method comprising the steps of comparing the intensity of each primary pixel with those of the secondary pixels which surround it, calculating whether said primary pixel can be classified as having a constant, an edge-like or a corner-like value, and collating this information to give positions of both edge and corner features which are present in said image matrix.
2. A method as claimed in Claim 1, in which before said comparison stage, the original image matrix is processed to form an intermediate simplified image from which unwanted detail has been excluded.
3. A method as claimed in Claim 2, in which the said intermediate image is a quaternary image.
4. A method as claimed in any one of Claims 1 to 3, including the further step of taking a second digitised image matrix after a given time interval has elapsed, and comparing the processed digital data of the said second image with that of a first image, such that any change in the positions of the selected features of the images will be detected.
Priority Applications (5)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| GB8811223A GB2218507B (en) | 1989-05-15 | 1988-05-12 | Digital data processing |
| EP89906420A EP0449827A1 (en) | 1988-05-12 | 1989-05-15 | Digital data processing |
| JP1506161A JPH03502261A (en) | 1988-05-12 | 1989-05-15 | digital data processing |
| PCT/GB1989/000523 WO1990014634A1 (en) | 1988-05-12 | 1989-05-15 | Digital data processing |
| CA000607884A CA1333424C (en) | 1988-05-12 | 1989-08-09 | Digital data processing |
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| GB8811223A GB2218507B (en) | 1989-05-15 | 1988-05-12 | Digital data processing |
| PCT/GB1989/000523 WO1990014634A1 (en) | 1988-05-12 | 1989-05-15 | Digital data processing |
| CA000607884A CA1333424C (en) | 1988-05-12 | 1989-08-09 | Digital data processing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CA1333424C true CA1333424C (en) | 1994-12-06 |
Family
ID=25672936
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CA000607884A Expired - Fee Related CA1333424C (en) | 1988-05-12 | 1989-08-09 | Digital data processing |
Country Status (2)
| Country | Link |
|---|---|
| JP (1) | JPH03502261A (en) |
| CA (1) | CA1333424C (en) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS61126407A (en) * | 1984-11-26 | 1986-06-13 | Komatsu Ltd | Tracking device for moving body using dither method |
| JP2543505B2 (en) * | 1986-07-22 | 1996-10-16 | 安川商事 株式会社 | Signal processing device and measuring device using space-time differential method |
| JPS63303475A (en) * | 1987-06-04 | 1988-12-12 | Fuji Electric Co Ltd | Vectorization processing method for binarized image |
| JPS63305477A (en) * | 1987-06-06 | 1988-12-13 | Hitachi Ltd | Moving object image extracting system |
| JP2614864B2 (en) * | 1987-07-10 | 1997-05-28 | 繁 安藤 | Image feature extraction device |
-
1989
- 1989-05-15 JP JP1506161A patent/JPH03502261A/en active Pending
- 1989-08-09 CA CA000607884A patent/CA1333424C/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| JPH03502261A (en) | 1991-05-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| DE69533054T2 (en) | Multi-windowing technique for thresholding an image using local image properties | |
| EP0506327B1 (en) | A system and method for ranking and extracting salient contours for target recognition | |
| Tarel et al. | Fast visibility restoration from a single color or gray level image | |
| CN110033475B (en) | Aerial photograph moving object detection and elimination method based on high-resolution texture generation | |
| US7663647B2 (en) | Model based compositing | |
| EP1269394B1 (en) | Improved method for image binarization | |
| GB9219797D0 (en) | Automatic feature detection and side scan sonar overlap navigation via sonar image matching | |
| US20020175921A1 (en) | Image processing | |
| KR960706644A (en) | METHOD AND APPARATUS FOR BACKGROUND DETERMINATION AND SUBTRACTION FOR A MONOCULAR VISION SYSTEM | |
| CN111340749A (en) | Image quality detection method, device, equipment and storage medium | |
| GB2218507A (en) | Digital data processing | |
| CN111539980A (en) | Multi-target tracking method based on visible light | |
| US5892841A (en) | Process for automatic detection of the assessable areas in images of mechanical components | |
| CA1333424C (en) | Digital data processing | |
| US6693669B1 (en) | Method for reducing image blurring | |
| EP0834151B1 (en) | Object recognition method | |
| Lemmens et al. | Automated archaeological feature extraction from digital aerial photographs | |
| CN109175718B (en) | Picture laser engraving method based on halftone technology | |
| CN112669360A (en) | Multi-source image registration method based on non-closed multi-dimensional contour feature sequence | |
| JPS60217472A (en) | Edge extracting method in picture processing | |
| JP2988097B2 (en) | How to segment a grayscale image | |
| Nishimoto et al. | A Parallel Matching Algorithm for Stereo Vision. | |
| WO1990014634A1 (en) | Digital data processing | |
| Tyagi et al. | Side searching and object improving algorithms for Images | |
| Shibata et al. | Hough transform for target detection in infrared imagery |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| MKLA | Lapsed |