GB2344205A - Vehicle identification - Google Patents

Vehicle identification Download PDF

Info

Publication number
GB2344205A
GB2344205A GB9825776A GB9825776A GB2344205A GB 2344205 A GB2344205 A GB 2344205A GB 9825776 A GB9825776 A GB 9825776A GB 9825776 A GB9825776 A GB 9825776A GB 2344205 A GB2344205 A GB 2344205A
Authority
GB
United Kingdom
Prior art keywords
vehicle
feature
topography
information relating
image
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
GB9825776A
Other versions
GB2344205B (en
GB9825776D0 (en
Inventor
Kenneth David King
Christopher George Harris
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Roke Manor Research Ltd
Original Assignee
Roke Manor Research Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Roke Manor Research Ltd filed Critical Roke Manor Research Ltd
Priority to GB9825776A priority Critical patent/GB2344205B/en
Publication of GB9825776D0 publication Critical patent/GB9825776D0/en
Publication of GB2344205A publication Critical patent/GB2344205A/en
Application granted granted Critical
Publication of GB2344205B publication Critical patent/GB2344205B/en
Anticipated expiration legal-status Critical
Expired - Fee Related legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/01Detecting movement of traffic to be counted or controlled
    • G08G1/017Detecting movement of traffic to be counted or controlled identifying vehicles
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/20Image preprocessing
    • G06V10/255Detecting or recognising potential candidate objects based on visual cues, e.g. shapes

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Traffic Control Systems (AREA)
  • Image Analysis (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

In order to identify a vehicle type, features of a front of a vehicle are identified and two-dimensional measurements relating to the topography of the features are extracted from a two dimensional captured image of the vehicle. These extracted two dimensional measurements can be used to estimated three dimensional measurements in order to identify the vehicle type. The number plate 400 may also be recognised.

Description

METHOD OF AND APPARATUS FOR VEHICLE IDENTIFICATION The present invention relates to a method of and apparatus for vehicle identification, for example, to identify a vehicle travelling along a road, such as a motorway.
It is sometimes desirable to identify vehicle type information, for example, a vehicle manufacturer, the manufacture's make and/or model number in order to recognise a particular vehicle or to provide statistics relating to a number of vehicle types.
It is known to provide an Automatic Number Plate Reader (ANPR) system for the purposes of law enforcement in order to identify a vehicle from its number plate. Occasionally, the ANPR system is unable to accurately identify the number plate of the vehicle, for example, by identifying a numeral displayed by the number plate with a low degree of confidence, thereby leaving the identity of the vehicle unresolved; the vehicle is identified as one of a number of possible vehicles bearing similar number plates, but no further precision is possible.
It is therefore an object of the present invention to obviate or at least mitigate the above described problems associated with the identification of vehicles. It should be understood that the identification of a vehicle can include the content of the vehicle's number and/or the vehicle type.
According to the present invention, there is provided a method of vehicle identification comprising: obtaining an image of a vehicle to be identified, determining information relating to a topography of a feature of the vehicle from the image, and comparing the determined information with stored information relating to the topography of vehicles in order to identify a type of the vehicle.
Preferably, a best estimate of a unique identification code borne by the vehicle is obtained and the best estimate of the unique identification code and the type of the vehicle are used in order to accurately identify the vehicle. More preferably, the determination of information relating to the topography of the feature of the vehicle comprises the extraction of the feature from the image.
An attitude of the vehicle with respect to the imaging means may be determined and used to extract information relating to the topography of the feature from the image.
Preferably, the information relating to the topography of the feature is a measurement corresponding to a location of the feature extracted from the image.
Preferably, the determination of information relating to the topography of the feature of the vehicle comprises estimating a three dimensional measurement relating to the feature extracted from the image. More preferably, the three dimensional measurement is estimated using the attitude of the vehicle.
Preferably, the three dimensional measurement is estimated using knowledge of deployment of the imaging means, for example, a roll angle and/or a pitch angle of the imaging means.
Preferably, the three dimensional measurement is estimated based on an assumption that the feature is symmetrical about a longitudinal plane of the vehicle.
Advantageously, the feature comprises a first element and a second element disposed about the longitudinal plane, a notional line joining the first and second elements intersecting the longitudinal plane at a location of intersection.
The three dimensional measurement may be a distance of the feature from a predetermined location relative to the longitudinal plane.
The three dimensional measurement may be a location of intersection with a longitudinal plane of the vehicle of a vehicle brand identification feature.
The determined information relating to the topography of the feature may be the size of the feature.
The determined information relating to the topography of the feature may be the shape of the feature.
The determined information relating to the topography of the feature may be the location of intersection.
Conveniently, the feature is lights of the vehicle. Preferably, the lights are indicator lights.
Preferably, the feature is a grille of the vehicle.
According to the present invention, there is also provided an apparatus for vehicle identification comprising: imaging means for obtaining an image of a vehicle to be identified, processing means arranged to determine information relating to a topography of a feature of the vehicle from the image, wherein the processing means is arranged to compare the determined information with stored information relating to the topography of vehicles in order to identify a type of the vehicle.
Preferably, means are provided for obtaining a best estimate of a unique identification code borne by the vehicle and using the best estimate of the unique identification code and the type of the vehicle in order to accurately identify the vehicle.
In a preferred embodiment of the invention, the method of vehicle identification comprises: obtaining an image of a vehicle to be identified, determining information relating to a topography of a feature of the vehicle from the image, comparing the determined information with stored information relating to the topography of vehicles in order to identify a type of the vehicle, and obtaining a best estimate of a unique identification code borne by the vehicle, the best estimate of the unique identification code and the type of the vehicle being used in order to accurately identify the vehicle. A three dimensional measurement is estimated based on an assumption that the feature is symmetrical about a longitudinal plane of the vehicle, the feature comprising a first element and a second element disposed about the longitudinal plane, a notional line joining the first and second elements intersecting the longitudinal plane at a location of intersection.
It is thus possible to provide a method of and apparatus for accurate vehicle identification which requires only a single imaging means and is independent of deployment, i. e. no significant modifications to any software or stored information are required when employing the above method in different locations. The significance of the single imaging means is that only a single image of the vehicle is required in order to derive three-dimensional topographical data, i. e. data relating to the topography of the feature, instead of a plurality of images, and therefore the apparatus of the present invention has a lower running cost.
Additionally, the above method and apparatus can be integrated with the ANPR system (described above) in order to provide error-correction facilities when identifying vehicle number plates.
At least one embodiment of the invention will now be described, by way of example, with reference the accompanying drawings: Figure 1 is a schematic diagram of a travelling vehicle to be identified; Figure 2 is a schematic diagram of imaging apparatus shown in Figure 1; Figure 3 is a schematic diagram showing the apparatus of Figure 2 in greater detail; Figure 4 is a schematic diagram of an analysis of a front of a vehicle constituting an embodiment of the present invention; Figure 5 is a flow diagram of a method for use with the apparatus of Figures 2 to 4, and Figure 6 is a flow diagram showing a step from Figure 5 in greater detail.
A vehicle (Figure 1), for example, a car 100 travels along a motorway 102 in the direction of a bridge 104 upon which is located an imaging means 106 according to an embodiment of the present invention; an attitude 108 corresponds to the bearing of the car 100 relative to the imaging means 106.
Referring to Figure 2, the imaging apparatus 106 has a focal length f, a pitch angle 0 and/or roll angle (p which constitutes knowledge of the deployment of the imaging means 106. The imaging apparatus 106 is arranged to read a unique identification code borne by the vehicle, for example, a number plate 400 (Figure 4) and comprises (Figure 3) a digital camera 300 coupled to a processing unit, for example, a personal computer (PC) 302 via a data bus 304. The PC 302 comprises a database of topographical data stored in a storage means 306.
Although the above example has been described with reference to the digital camera 300, other imaging means can be used, for example, a standard analogue camera, such as a Close-Circuit Television camera or a CamCorder, coupled to a"frame grabber"card (known in the art) coupled to the PC 302.
A front portion of the car 100 comprises a plurality of features, for example, the number plate 400, a centrally disposed grille 402, or a first and a second lighting cluster 404,405, the lighting cluster 404 comprising at least one of a first and a second element, for example, a first and a second main lamp unit 406,407 and/or a first and a second indicator lamp 408,409. The car 100 also has a centrally disposed badge 410 for identifying the brand or manufacturer of the car 100; this is also a feature.
In one embodiment of the invention, position data of a feature in twodimensions (2D) is extracted by the PC 302 from an image generated by the digital camera 300. Where the feature comprises multiple elements, the position data can be more than a single position, for example, in the case of the first and second indicator lamps 408,409. The extraction process can be realised by means of a number of techniques known in the art of image processing, for example, by segmentation of the image in colour space in order to extract the position of the feature, such as the location of the first and second indicator lamps 408,409 which can be orange in colour.
In relation to a number of vehicles, the position data of the feature in 2D on a given vehicle is unique to the given vehicle, thereby enabling the vehicle type of the car 100 to be identified from the extracted position of the feature in 2D.
Typically, position data relating to between 4 and 12 features should be extracted in order to accurately identify the given vehicle, but a greater or fewer number of features can be used.
In order to provide increased accuracy, in another embodiment of the present invention the extracted position data of the feature in 2D is mapped onto a longitudinal plane 412 in order to produce an estimated three-dimensional (3D) information measurement, for example, heights and depths on the longitudinal plane 412. The longitudinal plane 412 is a notional plane which extends centrally from the front to the back of the car 100 parallel to a longitudinal axis (not shown) of the car 100. The 3D information measurements are generated based upon the estimate of the attitude 108 mentioned above, the knowledge of the deployment of the digital camera 300 and an assumption that the feature of the front of the car 100 is symmetrical, i. e. equidistant, or in the case of the badge 410, centrally located. The latter assumption relating to the badge 410 is only appropriate in the case of some vehicle types and where, for example, a vehicle does not have a badge or has indicator lamps formed from clear glass, 3D information measurements relating to other features are used.
Where the feature comprises more than one element, the position data of the feature in 2D is mapped onto the longitudinal plane 412 by constructing a notional line between, for example, the first element and the second element of the feature, such as, between the first and second indicator lamps 408,409, the point of intersection on the longitudinal plane 412 of the notional line constituting the 3D information measurement of the feature. Thus, it can also be seen that a set of points can be identified on the longitudinal plane 412 which together relate to the topography of features of the car 100 and form a unique configuration corresponding to a particular vehicle type. However, it is conceivable that a single point can be used to identify the particular vehicle type if the point is sufficiently uniquely located.
During normal operation (Figure 5), an image is captured (step 500) by the digital camera 300, the position of the number plate 400 is determined (step 502) and the number plate 400 is read (step 504) by the PC 302. The steps relating to the reading (step 504) of the number plate 400, including the determination of the position (step 502) of the number plate 400 is performed according to any known technique in the art, for example, using the standard ANPR technique.
Once the position of the number plate 400 has been determined (step 502) and the number plate 400 has been read, the attitude 108 is estimated (step 506) using knowledge of the focal length f, pitch angle 0, roll angle (p of the digital camera 300 and the position, size and orientation of the number plate 400, the size of the number plate 400 being predetermined and the orientation being derivable from identifying the position of corners of the number plate 400 in the image. The technique employed to estimate the attitude 108 can be any technique known in the art, for example, geometrical transformations as disclosed in"Fundamentals of Interactive Computer Graphics" (by JD Foley, A Van Dam, Addison Wesley, 1983). The feature, for example, the badge 410 or the first and second indicator lights 408,409 are identified and the position data of the feature in 2D within the captured image is extracted, for example, as described above by segmentation of the captured image in colour space. The position data in 2D of more than one feature can be extracted by the PC 302. The extracted position data are then used to estimate (step 510) 3D information measurements relating to the identified features.
The estimation (step 510) of the 3D information measurement will now be described in greater detail with reference to Figure 6. The PC 302 firstly determines if the feature is the badge 410 (step 600). This can be achieved by considering a number of possible features which can be the badge 410, for example, by an edge extraction and association technique, each of the considered features being considered as a candidate measurement for use in identifying the vehicle type. If the feature identified is the badge 410, the height and depth of the badge 410 relative to the number plate 400 is estimated (step 602) according to any known technique in the art as described above. The number plate 400 acts as a point of reference which is common to all vehicle types. If, however, the feature is not the badge 410, but the first and second indicator lights 408,409, the PC 302 defines the longitudinal plane 412 (step 604) and constructs (step 606) the notional line between elements of the first and second indicator lights 408,409 and identifies the point of intersection of the notional line with the longitudinal plane 412 (step 608).
Once the point of intersection has been identified (step 608), the height and depth of the point of intersection relative to the number plate 400 is estimated (step 610). This process is, preferably, repeated for as many features of the front of the car 100 as required in order to generate a number of estimated heights and depths capable of identifying the vehicle type.
It should be appreciated that further geometrical computations can be carried out using the height and depth measurements relating to features symmetrical about the longitudinal plate 412 in order to determine the distance between the features. It is thus possible to generate a more complete set of data relating to the 3D position of the features.
Once a sufficient number of heights and depths have been estimated, the estimated heights and depths are compared with those stored in the database (step 512) in order to identify the vehicle type. Any pattern classification technique known in the art, for example as described in"Pattern Classification & Scene Analysis" (by Duda & Hart, Wiley 1973), can be employed for the above described comparison step.
The notional line joining the centre of the first and second indicator lamps 408, 409 is assumed to be parallel with the number plate 400 to permit a horizontal offset of the indicator lamps 408,409 from the centre of the vehicle to be estimated relative to the number plate 400 (assumed to be of standard length).
Knowledge of the true physical length of the number plate 400 facilitates the absolute measurement of distances relating to the features, irrespective of the distance between the car 100 and the digital camera 300.
Although the above examples described measurements relative to the number plate 400, it should be appreciated that the measurements can be estimated relative to another predetermined location corresponding to another feature of the car 100.
Other measurements relating to the topography of features of the car 100 can be estimated from the captured image in order to determine properties of the features, for example, grille or headlight size and shape. These properties can be used to identify the vehicle type.
It should be appreciated that the present invention is not limited to the specific examples described above and other variations and modifications within the spirit of the present invention are conceivable without departing from the scope of the appended claims.

Claims (22)

  1. Claims 1. A method of vehicle identification comprising: obtaining an image of a vehicle to be identified, determining information relating to a topography of a feature of the vehicle from the image, and comparing the determined information with stored information relating to the topography of vehicles in order to identify a type of the vehicle.
  2. 2. A method as claimed in Claim 1, further comprising obtaining a best estimate of a unique identification code borne by the vehicle and using the best estimate of the unique identification code and the type of the vehicle in order to accurately identify the vehicle.
  3. 3. A method as claimed in Claim 1, wherein the determination of information relating to the topography of the feature of the vehicle comprises the extraction of the feature from the image.
  4. 4. A method as claimed in any one of Claims 1 to 3, further comprising determining an attitude of the vehicle with respect to the imaging means, the attitude being used to extract information relating to the topography of the feature from the image.
  5. 5. A method as claimed in any one of Claims 1 to 4, wherein the information relating to the topography of the feature is a measurement corresponding to a location of the feature extracted from the image.
  6. 6. A method as claimed in Claim 3, wherein the determination of information relating to the topography of the feature of the vehicle comprises estimating a three dimensional measurement relating to the feature extracted from the image.
  7. 7. A method as claimed in Claim 6, wherein the three dimensional measurement is estimated using the attitude of the vehicle.
  8. 8. A method as claimed in Claim 6 or Claim 7, wherein the three dimensional measurement is estimated using knowledge of deployment of the imaging means.
  9. 9. A method as claimed in any one of Claims 6 to 8, wherein the three dimensional measurement is estimated based on an assumption that the feature is symmetrical about a longitudinal plane of the vehicle.
  10. 10. A method as claimed in Claim 9, wherein the feature comprises a first element and a second element disposed about the longitudinal plane, a notional line joining the first and second elements intersecting the longitudinal plane at a location of intersection.
  11. 11. A method as claimed in any one of Claims 6 to 9, wherein the three dimensional measurement is a distance of the feature from a predetermined location relative to the longitudinal plane.
  12. 12. A method as claimed in any one of Claims 6 to 8, wherein the three dimensional measurement is a location of intersection with a longitudinal plane of the vehicle of a vehicle brand identification feature.
  13. 13. A method as claimed in Claim 1, wherein the determined information relating to the topography of the feature is the size of the feature.
  14. 14. A method as claimed in Claim 1, wherein the determined information relating to the topography of the feature is the shape of the feature.
  15. 15. A method as claimed in Claim 1, when dependent upon Claim 10 or Claim 12, wherein the determined information relating to the topography of the feature is the location of intersection.
  16. 16. A method as claimed in any one of Claims 1 to 15, wherein the feature is lights of the vehicle.
  17. 17. A method as claimed in Claim 16, wherein the lights are indicator lights.
  18. 18. A method as claimed in any one of Claims 1 to 15, wherein the feature is a grille of the vehicle.
  19. 19. An apparatus for vehicle identification comprising imaging means for obtaining an image of a vehicle to be identified, processing means arranged to determine information relating to a topography of a feature of the vehicle from the image, wherein the processing means is arranged to compare the determined information with stored information relating to the topography of vehicles in order to identify a type of the vehicle.
  20. 20. An apparatus as claimed in Claim 19, further comprising means for obtaining a best estimate of a unique identification code borne by the vehicle and using the best estimate of the unique identification code and the type of the vehicle in order to accurately identify the vehicle.
  21. 21. A method of vehicle identification substantially as hereinbefore described with reference to Figures 5 and 6.
  22. 22. An apparatus for vehicle identification substantially as hereinbefore described with reference to Figure 3 and 4.
GB9825776A 1998-11-26 1998-11-26 Method of and apparatus for vehicle indentification Expired - Fee Related GB2344205B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
GB9825776A GB2344205B (en) 1998-11-26 1998-11-26 Method of and apparatus for vehicle indentification

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
GB9825776A GB2344205B (en) 1998-11-26 1998-11-26 Method of and apparatus for vehicle indentification

Publications (3)

Publication Number Publication Date
GB9825776D0 GB9825776D0 (en) 1999-01-20
GB2344205A true GB2344205A (en) 2000-05-31
GB2344205B GB2344205B (en) 2003-04-30

Family

ID=10842986

Family Applications (1)

Application Number Title Priority Date Filing Date
GB9825776A Expired - Fee Related GB2344205B (en) 1998-11-26 1998-11-26 Method of and apparatus for vehicle indentification

Country Status (1)

Country Link
GB (1) GB2344205B (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2004042673A2 (en) * 2002-11-04 2004-05-21 Imperial Vision Ltd. Automatic, real time and complete identification of vehicles
WO2006071705A1 (en) * 2004-12-29 2006-07-06 Snap-On Incorporated Method, apparatus and system for implementing vehicle identification
US7676392B2 (en) 2005-06-10 2010-03-09 Accenture Global Services Gmbh Electronic toll management
US7970644B2 (en) 2003-02-21 2011-06-28 Accenture Global Services Limited Electronic toll management and vehicle identification
US8265988B2 (en) 2003-02-21 2012-09-11 Accenture Global Services Limited Electronic toll management and vehicle identification
US8504415B2 (en) 2006-04-14 2013-08-06 Accenture Global Services Limited Electronic toll management for fleet vehicles
GB2561100A (en) * 2011-01-12 2018-10-03 Videonetics Tech Private Limited An integrated intelligent server based system and method/systems adapted to facilitate fail-safe integration and/or optimised utilisation

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2016145547A1 (en) * 2015-03-13 2016-09-22 Xiaoou Tang Apparatus and system for vehicle classification and verification
CN112489436B (en) * 2020-10-29 2022-05-03 浙江预策科技有限公司 Vehicle identity recognition method, device and system and electronic device

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO1996005569A1 (en) * 1994-08-10 1996-02-22 Anderson Brent E Airborne video identification system and method

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3475700B2 (en) * 1997-02-19 2003-12-08 オムロン株式会社 Object recognition method, object recognition device, and vehicle recognition device

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO1996005569A1 (en) * 1994-08-10 1996-02-22 Anderson Brent E Airborne video identification system and method

Cited By (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2004042673A2 (en) * 2002-11-04 2004-05-21 Imperial Vision Ltd. Automatic, real time and complete identification of vehicles
WO2004042673A3 (en) * 2002-11-04 2004-07-15 Imp Vision Ltd Automatic, real time and complete identification of vehicles
US8775236B2 (en) 2003-02-21 2014-07-08 Accenture Global Services Limited Electronic toll management and vehicle identification
US8660890B2 (en) 2003-02-21 2014-02-25 Accenture Global Services Limited Electronic toll management
US7970644B2 (en) 2003-02-21 2011-06-28 Accenture Global Services Limited Electronic toll management and vehicle identification
US8265988B2 (en) 2003-02-21 2012-09-11 Accenture Global Services Limited Electronic toll management and vehicle identification
US10885369B2 (en) 2003-02-21 2021-01-05 Accenture Global Services Limited Electronic toll management and vehicle identification
US8463642B2 (en) 2003-02-21 2013-06-11 Accenture Global Services Limited Electronic toll management and vehicle identification
WO2006071705A1 (en) * 2004-12-29 2006-07-06 Snap-On Incorporated Method, apparatus and system for implementing vehicle identification
AU2006257287B2 (en) * 2005-06-10 2012-12-06 Accenture Global Services Limited Electronic vehicle indentification
US8548845B2 (en) 2005-06-10 2013-10-01 Accenture Global Services Limited Electric toll management
US8775235B2 (en) 2005-06-10 2014-07-08 Accenture Global Services Limited Electric toll management
US9240078B2 (en) 2005-06-10 2016-01-19 Accenture Global Services Limited Electronic toll management
US10115242B2 (en) 2005-06-10 2018-10-30 Accenture Global Services Limited Electronic toll management
US7676392B2 (en) 2005-06-10 2010-03-09 Accenture Global Services Gmbh Electronic toll management
US8768755B2 (en) 2006-04-14 2014-07-01 Accenture Global Services Limited Electronic toll management for fleet vehicles
US8504415B2 (en) 2006-04-14 2013-08-06 Accenture Global Services Limited Electronic toll management for fleet vehicles
GB2561100A (en) * 2011-01-12 2018-10-03 Videonetics Tech Private Limited An integrated intelligent server based system and method/systems adapted to facilitate fail-safe integration and/or optimised utilisation

Also Published As

Publication number Publication date
GB2344205B (en) 2003-04-30
GB9825776D0 (en) 1999-01-20

Similar Documents

Publication Publication Date Title
CN102317954B (en) Method for detecting objects
EP0747870B1 (en) An object observing method and device with two or more cameras
CN100452093C (en) Device for detecting road traveling lane
JP4391624B2 (en) Object recognition device
US7046822B1 (en) Method of detecting objects within a wide range of a road vehicle
US11989951B2 (en) Parking detection method, system, processing device and storage medium
JP6519262B2 (en) Three-dimensional object detection device, three-dimensional object detection method, three-dimensional object detection program, and mobile device control system
CN111179152B (en) Road identification recognition method and device, medium and terminal
US8180100B2 (en) Plane detector and detecting method
US8154594B2 (en) Mobile peripheral monitor
CN108197523B (en) Night vehicle detection method and system based on image conversion and contour neighborhood difference
JP2000517452A (en) Viewing method
CN100424724C (en) Device for detecting road traveling lane
US20090169052A1 (en) Object Detector
CN115717894B (en) Vehicle high-precision positioning method based on GPS and common navigation map
TWI504858B (en) A vehicle specification measuring and processing device, a vehicle specification measuring method, and a recording medium
JP2000357233A (en) Body recognition device
KR102491527B1 (en) Detection of objects in camera images
US20220398856A1 (en) Method for reconstruction of a feature in an environmental scene of a road
CN106651963A (en) Mounting parameter calibration method for vehicular camera of driving assistant system
Hinz et al. Vehicle detection in aerial images using generic features, grouping, and context
CN113759391A (en) Passable area detection method based on laser radar
GB2344205A (en) Vehicle identification
CN114913340A (en) Parking space detection method, device, equipment and storage medium
JP2022513830A (en) How to detect and model an object on the surface of a road

Legal Events

Date Code Title Description
PCNP Patent ceased through non-payment of renewal fee

Effective date: 20131126