WO2014054223A1 - キャリブレーション方法、及びキャリブレーション装置 - Google Patents
キャリブレーション方法、及びキャリブレーション装置 Download PDFInfo
- Publication number
- WO2014054223A1 WO2014054223A1 PCT/JP2013/005276 JP2013005276W WO2014054223A1 WO 2014054223 A1 WO2014054223 A1 WO 2014054223A1 JP 2013005276 W JP2013005276 W JP 2013005276W WO 2014054223 A1 WO2014054223 A1 WO 2014054223A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- camera
- markers
- marker
- vehicle
- road surface
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 66
- 239000003550 marker Substances 0.000 claims abstract description 129
- 235000004522 Pentaglottis sempervirens Nutrition 0.000 claims abstract description 60
- 238000006243 chemical reaction Methods 0.000 claims description 54
- 240000004050 Pentaglottis sempervirens Species 0.000 claims description 53
- 238000012545 processing Methods 0.000 claims description 29
- 241000905137 Veronica schmidtiana Species 0.000 claims description 2
- 238000006073 displacement reaction Methods 0.000 abstract 1
- 238000005259 measurement Methods 0.000 description 35
- 238000010586 diagram Methods 0.000 description 27
- 238000009434 installation Methods 0.000 description 7
- FFBHFFJDDLITSX-UHFFFAOYSA-N benzyl N-[2-hydroxy-4-(3-oxomorpholin-4-yl)phenyl]carbamate Chemical compound OC1=C(NC(=O)OCC2=CC=CC=C2)C=CC(=C1)N1CCOCC1=O FFBHFFJDDLITSX-UHFFFAOYSA-N 0.000 description 6
- 230000000694 effects Effects 0.000 description 6
- 238000013519 translation Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N17/00—Diagnosis, testing or measuring for television systems or their details
- H04N17/002—Diagnosis, testing or measuring for television systems or their details for television cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
- B60R2300/40—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the details of the power supply or the coupling to vehicle components
- B60R2300/402—Image calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30204—Marker
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30244—Camera pose
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Definitions
- This disclosure relates to a technique for performing measurement related to installation of an in-vehicle camera.
- the following technique is known as a technique for performing measurement (so-called calibration) related to installation of an in-vehicle camera.
- a predetermined positional relationship is defined in advance, a plurality of installation patterns (targets) are provided on the road surface, and the vehicle is stopped in the vicinity of the installation pattern. It is a method to do.
- Patent Document 2 is a method for performing measurement while fixing the positional relationship between the vehicle and the target device by positioning means such as a joint or a scope.
- a plurality of markers arranged in the same vertical direction, each of which has a known height from the road surface can be used to change the posture of the camera mounted on the vehicle.
- a calibration method for calibration which includes a first step to a third step.
- the first step is a step of obtaining a two-dimensional image by photographing a plurality of markers with a camera.
- the second step is a step of performing bird's-eye conversion of a plurality of markers in the two-dimensional image obtained in the first step into a road surface or a plane parallel to the road surface, reflecting the height of each marker.
- the third step is a step of calculating the parameter value of the camera based on the positional deviation between the plurality of markers on the surface obtained in the second step.
- FIG. 7C is an explanatory diagram of combining the bird's-eye images so that the same markers overlap in the camera coordinate system of one of the bird's-eye images, and specifying the horizontal component of the mounting position of each camera and the yaw angle in the shooting direction.
- FIG. 8A is a diagram conceptually showing a mounting position of each camera obtained by measurement (camera coordinate system).
- FIG. 8B is a diagram conceptually showing a coordinate system based on the vehicle based on the ideal camera arrangement.
- FIG. 8C is a diagram illustrating a state in which the line segment defined based on the camera position obtained by the measurement is translated and rotated so as to be aligned with the line segment defined based on the ideal arrangement.
- FIG. 8D is a diagram conceptually illustrating that the horizontal component of the camera mounting position and the yaw angle in the shooting direction of the camera are converted from the camera coordinate system to the vehicle coordinate system.
- the operation unit 23 includes a touch panel provided on the display surface of the display device 31 and mechanical key switches installed around the display device 31.
- the operation unit 23 is a device that can input various operation instructions from a driver or the like. is there.
- FIG. 4B is an image in which markers 42a and 42b and poles 41a and 41b are selectively drawn based on an image obtained by bird's-eye conversion of a captured image, and a line segment 44 that connects the marker 42a and the marker 42b is defined.
- the mounting position of the camera 11 that captured this image corresponds to the origin Oc of the camera coordinate system, and the shooting direction of the camera is on the YcZc plane.
- FIG. 4D shows a state in which the line segment 44 is translated and rotated so that the line segment 44 in FIG. 4B is aligned with the line segment 45 in FIG. 4C.
- the origin Oc of the camera coordinate system and each coordinate axis are also moved (the state of movement is not shown).
- FIG. 5B is a diagram conceptually showing a coordinate system (vehicle coordinate system) based on the center of the front end of the vehicle based on the ideal camera arrangement.
- the installation position of the camera 11a installed at the center of the front end of the vehicle is the origin, the horizontal direction in front of the vehicle is the Y axis, the horizontal direction to the right of the vehicle is the X axis, and the upper direction (vertical direction) is the Z axis.
- a camera 11a installed at the center of the vehicle front end and a camera 11c installed at the center of the vehicle rear end are selected, and a line segment 52 connecting the mounting positions of the cameras is defined.
- posture parameter determination processing 2 that is camera calibration executed by the image processing apparatus 21 will be described with reference to the flowchart of FIG.
- the vehicle is arranged as shown in FIG. 2B, and each measurer of the two marker poles 41 can be photographed by each camera 11, and the measurer operates the operation unit 23.
- the program is read from the posture parameter storage unit 24 into the control unit 25 and execution is started.
- the control unit 25 executes S205 to S235 described below in correspondence with each of the cameras 11a to 11d, and executes S240 to S250 once after S205 to S235 for each camera are completed.
- control unit 25 detects the coordinates of the lower marker 42 and the upper marker 43 from the acquired photographed image (S210). That is, as shown in FIG. 7A, the center positions of the markers 42a, 42b, 43a, 43b in the captured image are specified by the image coordinate system.
- the control unit 25 calculates the distance of the positional deviation between the lower marker 42 and the upper marker 43 of the same pole in the bird's-eye-view converted image (S220). For example, as shown in FIG. 7B, the positional deviation distance d1 between the lower marker 42a and the upper marker 43a and the positional deviation distance d2 between the lower marker 42b and the upper marker 43b are used as a reference. Is calculated in the coordinate system (camera coordinate system).
- control unit 25 determines whether or not the distance of the positional deviation between the lower marker 42 and the upper marker 43 of the same pole calculated in S ⁇ b> 220 can be evaluated as the minimum ( S225).
- the “minimum” is ideally preferably 0, but may be any value close to 0 in consideration of errors and the like.
- control unit 25 determines in S225 that the positional deviation distance between the lower marker 42 and the upper marker 43 of the same pole calculated in S220 can be evaluated to be the minimum, the control unit 25 proceeds to S235, while calculated in S220. When it is determined that the distance of the positional deviation between the lower marker 42 and the upper marker 43 of the same pole cannot be evaluated as the minimum, the process proceeds to S230.
- the control unit 25 uses the posture used in the bird's eye conversion in S215. Among the parameters, the vertical component (z) of the mounting position of the camera 11 and the next candidates for the pitch angle and roll angle in the shooting direction of the camera 11 are selected.
- the next candidate is a value obtained by changing a value of at least one of these elements by a small amount (for example, a value corresponding to 0.1%).
- control unit 25 proceeds to S215 described above and performs bird's-eye view conversion again using the selected value.
- control unit 25 executes the processing up to this point (S205 to S235) corresponding to each of the cameras 11a to 11d and obtains bird's-eye images (images obtained by the latest bird's-eye conversion of S215) for all the cameras 11, S240. The process starts.
- FIG. 8A is a diagram conceptually showing the horizontal component of the mounting position of each camera 11 in the camera coordinate system and the yaw angle in the shooting direction.
- a camera 11a installed at the center of the vehicle front end and a camera 11c installed at the center of the vehicle rear end are selected, and a line segment 71 connecting the mounting positions of the cameras is defined.
- the cameras to be selected are not limited to this example, and other combinations may be used.
- FIG. 8B is a diagram conceptually showing a coordinate system (vehicle coordinate system) based on the center of the front end of the vehicle based on the ideal camera arrangement.
- the installation position of the camera 11a installed at the center of the front end of the vehicle is the origin, the horizontal direction in front of the vehicle is the Y axis, the horizontal direction to the right of the vehicle is the X axis, and the upper direction (vertical direction) is the Z axis.
- a camera 11a installed at the center of the vehicle front end and a camera 11c installed at the center of the vehicle rear end are selected, and a line segment 72 connecting the mounting positions of the cameras is defined.
- FIG. 8C shows a state in which the line segment 71 in FIG. 8A is rotated and translated so as to overlap the line segment 72 in FIG. 8B.
- the midpoint of the line segment 71 and the midpoint of the line segment 72 may match, it is not restricted to this.
- control unit 25 stores the horizontal component of the mounting position of each camera 11 and the yaw angle in the shooting direction in the vehicle coordinate system converted in S245 in the posture parameter storage unit 24. (S250). And the control part 25 complete
- the installation position of the marker pole 41 does not need to be known (it does not need to be strictly installed at a predetermined position). ). For this reason, it is possible to easily perform the measurement by installing the marker pole 41 only when performing the measurement as compared with the first embodiment.
- the posture parameter value stored in the posture parameter storage unit 24 is not limited to the coordinate system described in the above embodiment, but may be converted into another coordinate system and stored in the posture parameter storage unit 24. Good.
- S105 and S205 executed by the control unit 25 correspond to an example of a first step and an image acquisition unit (or means).
- S115 and S215 executed by the control unit 25 correspond to an example of a second step and conversion (or means).
- S140, S145, S240, and S245 executed by the control unit 25 correspond to an example of a third step and a calculation unit (or means).
- the calibration method according to the first example of the present disclosure is mounted on a vehicle using a plurality of markers arranged in the same vertical direction, and each marker has a known height from the road surface.
- a calibration method for calibrating the posture of a camera that has a first step to a third step.
- the first step is a step of obtaining a two-dimensional image by photographing a plurality of markers with a camera.
- the second step is a step of performing bird's-eye conversion of a plurality of markers in the two-dimensional image obtained in the first step into a road surface or a plane parallel to the road surface, reflecting the height of each marker.
- the third step is a step of calculating the parameter value of the camera based on the positional deviation between the plurality of markers on the surface obtained in the second step.
- the space required for measurement is saved compared with the case where the marker is on the road surface. Space can be realized. And it is not necessary to physically fix the vehicle and the marker in a predetermined positional relationship by a joint, or to adjust the position of the marker using the scope means so that the vehicle and the marker have a predetermined positional relationship. Compared to the prior art, it does not require much time for measurement.
- the parameter value calculated in the third step may be at least one of the vertical component of the camera mounting position, the pitch angle, and the roll angle (second example). Such parameters can be accurately calculated by the third step.
- each step may be performed as follows (third example).
- the first step it is preferable to photograph the same plurality of markers with a plurality of cameras and obtain a two-dimensional image for each camera.
- the bird's-eye view conversion may be performed for each of the two-dimensional images obtained in the first step.
- the third step in addition to the calculation of the parameter value for each camera, at least the yaw angle of each camera, or the horizontal component of the mounting position of each camera, where the positions after bird's-eye conversion of the same marker match between the cameras. Any one may be further calculated as a parameter value for each camera.
- the calibration method according to the fourth example of the present application is mounted on a vehicle using a plurality of markers that are at a predetermined distance from the road surface and are displaced in the horizontal direction and whose positional relationship between the markers is known.
- a calibration method for calibrating the posture of a camera that has a first step to a third step.
- the first step is a step of obtaining a two-dimensional image by photographing a plurality of markers with a camera.
- the second step is a step of performing bird's-eye conversion of a plurality of markers in the two-dimensional image obtained in the first step into a road surface or a plane parallel to the road surface, reflecting the height of each marker.
- the third step is based on the difference between the distance between the plurality of markers on the surface obtained by the second step and the distance between the plurality of markers (actual distance) obtained from a known positional relationship. This is a step of calculating a parameter value.
- the space required for measurement is saved compared with the case where the marker is on the road surface. Space can be realized. And it is not necessary to physically fix the vehicle and the marker in a predetermined positional relationship by a joint, or to adjust the position of the marker using the scope means so that the vehicle and the marker have a predetermined positional relationship. Compared to the prior art, it does not require much time for measurement.
- the parameter value calculated in the third step may be at least one of the vertical component of the camera mounting position, the pitch angle, or the roll angle (fifth example). Such parameters can be accurately calculated by the third step.
- the parameter value calculated in the third step may be at least one of the vertical component of the camera mounting position, the pitch angle, or the roll angle.
- other parameter values may be calculated as follows. That is, based on the positional deviation between the line segment connecting the plurality of markers on the surface obtained by the second step and the line segment connecting the plurality of markers obtained from a known positional relationship, the yaw angle of the camera, Alternatively, at least one of the horizontal components of the camera mounting position may be further calculated as a camera parameter value (sixth example).
- the yaw angle related to the mounting position of each camera is a calibration method having such a process, while realizing space saving of the space necessary for measurement and facilitating the measurement, for a plurality of in-vehicle cameras, the yaw angle related to the mounting position of each camera, or It is possible to calculate at least one of the horizontal components of the mounting position of each camera in the same coordinate system.
- the first step to the third step may be performed for each camera (seventh example).
- a plurality of markers arranged in the same vertical direction, each of which has a known height from the road surface can be used to change the posture of the camera mounted on the vehicle.
- a calibration device for calibrating wherein the image acquisition unit obtains a two-dimensional image obtained by photographing the plurality of markers with the camera, and the plurality of markers in the two-dimensional image acquired by the image acquisition unit, Based on the position shift of the plurality of markers on the surface obtained by the conversion unit, a conversion unit that reflects the height of each marker to bird's eye view on a road surface or a plane parallel to the road surface, There is provided a calibration device having a calculation unit for calculating a parameter value.
- the parameter value calculated by the calculation unit may be at least one of a vertical component, a pitch angle, and a roll angle of the camera mounting position (a ninth example).
- the vehicle includes a plurality of cameras
- the image acquisition unit is a two-dimensional image obtained by photographing the same plurality of markers with the plurality of cameras
- the conversion unit performs the bird's-eye conversion for each of the two-dimensional images acquired by the image acquisition unit
- the calculation unit calculates the parameter value for each camera.
- at least one of the yaw angle of each camera and the horizontal component of each camera in which the positions after bird's-eye conversion of the same marker match between the cameras is further set as a parameter value for each camera. It may be configured to calculate (tenth example).
- a plurality of markers that are at a predetermined distance from the road surface and are displaced in the horizontal direction, and that are mounted on the vehicle using markers that have a known positional relationship between the markers.
- a calibration device that calibrates the posture of a camera, the image acquisition unit capturing a plurality of markers with the camera to acquire a two-dimensional image, and the plurality of markers in the two-dimensional image acquired by the image acquisition unit Reflecting the height of each marker to a bird's eye view on a road surface or a plane parallel to the road surface, the distance between the plurality of markers on the surface obtained by the conversion unit, and the known
- a calibration device is provided that includes a calculation unit that calculates a parameter value of the camera based on a deviation from the distance between the plurality of markers obtained from a positional relationship.
- the parameter value calculated by the calculation unit may be at least one of a vertical component, a pitch angle, and a roll angle of the camera mounting position (a twelfth example).
- the calculation unit obtains a line segment connecting the plurality of markers on the surface obtained by the conversion unit, and the known positional relationship. Further, at least one of the camera yaw angle or the horizontal component of the camera mounting position is further calculated as a parameter value of the camera based on a deviation from a line segment connecting the plurality of markers obtained from (13th example).
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Closed-Circuit Television Systems (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
- Mechanical Engineering (AREA)
Abstract
Description
図1に示すように、実施形態の画像処理システム5は、カメラ11a~11dと画像処理装置21と表示装置31とを備える。
次に第1実施形態の画像処理装置21の動作について説明するが、以下では本開示に関する処理を中心に説明し、従来より知られたこの手の車載カメラが撮影した撮影画像を表示装置に表示させるための処理(例えば、車庫入れを補助するために撮影画像を鳥瞰画像に変換し車輪の予測軌跡などを合成して表示装置に表示させる処理等)については、説明を省略する。
以上、第1実施形態の画像処理装置21の動作について説明したが、これによれば、マーカ42は路面から高さのある場所に設けられているため、路面上にマーカがある場合と比較して測定に必要なスペースの省スペース化を実現できる。そして、車両とマーカとをジョイントによって所定の位置関係に物理的に固定したり、車両とマーカとが所定の位置関係になるようにスコープ手段を用いてマーカの位置を調整する必要も無いため、従来技術と比較して測定に手間を要しない。
次に第2実施形態の画像処理装置21の動作について説明するが、以下では第1実施形態の画像処理装置21との相違点を中心に説明し、同一の動作については、説明を省略する。
以上、第2実施形態の画像処理装置21の動作について説明したが、これによれば、マーカ42,43は路面から高さのある場所に設けられているため、路面上にマーカがある場合と比較して測定に必要なスペースの省スペース化を実現できる。そして、車両とマーカとをジョイントによって所定の位置関係に物理的に固定したり、車両とマーカとが所定の位置関係になるようにスコープ手段を用いてマーカの位置を調整する必要も無いため、従来技術と比較して測定に手間を要しない。
(1)上記実施形態は、カメラ11の姿勢パラメータのうち、全ての姿勢パラメータ値を算出したが、一部の姿勢パラメータ値だけを算出してもよい。例えば、カメラ11の撮影方向のピッチ角及びヨー角のみを算出する等してもよい。
Claims (14)
- 同一鉛直方向に並んだ複数のマーカであって、いずれのマーカも路面からの高さが既知であるマーカを用いて、車両に搭載されたカメラの姿勢を校正するキャリブレーション方法であって、
前記カメラで前記複数のマーカを撮影して2次元画像を得る第一工程(S205)と、
前記第一工程(S205)によって得られた2次元画像における前記複数のマーカを、各マーカの高さを反映させて路面又は路面と平行な面に鳥瞰変換する第二工程(S215)と、
前記第二工程(S215)によって得られた、前記面における前記複数のマーカ同士の位置ずれに基づいて、前記カメラのパラメータ値を算出する第三工程(S240、S245)と、
を有するキャリブレーション方法。 - 請求項1に記載のキャリブレーション方法において、
前記第三工程(S240、S245)において算出する前記パラメータ値は、前記カメラの取付位置の鉛直成分、ピッチ角、又は、ロール角の少なくともいずれか一つである
キャリブレーション方法。 - 請求項2に記載のキャリブレーション方法において、
前記車両には複数のカメラが搭載されており、
前記第一工程(S205)では、前記複数のカメラで同一の前記複数のマーカを撮影し、カメラ毎に2次元画像を得、
前記第二工程(S215)では、前記第一工程(S205)で得られた前記2次元画像のそれぞれについて、前記鳥瞰変換を行い、
前記第三工程(S240、S245)では、前記カメラ毎の前記パラメータ値の算出に加え、前記カメラ間で同一のマーカの鳥瞰変換後の位置が一致する、前記各カメラのヨー角、又は、前記各カメラの取付位置の水平成分の少なくともいずれか一つを、前記カメラ毎にパラメータ値としてさらに算出する
キャリブレーション方法。 - 路面から所定距離にあり水平方向にずれた複数のマーカであって、前記マーカ間の位置関係が既知であるマーカを用いて、車両に搭載されたカメラの姿勢を校正するキャリブレーション方法であって、
前記カメラで前記複数のマーカを撮影して2次元画像を得る第一工程(S105)と、
前記第一工程(S105)によって得られた2次元画像における前記複数のマーカを、各マーカの高さを反映させて路面又は路面と平行な面に鳥瞰変換する第二工程(S115)と、
前記第二工程(S115)によって得られた、前記面における前記複数のマーカ間の距離と、前記既知の位置関係から求まる前記複数のマーカ間の距離とのずれに基づいて、前記カメラのパラメータ値を算出する第三工程(S140、S145)と、
を有するキャリブレーション方法。 - 請求項4に記載のキャリブレーション方法において、
前記第三工程(S140、S145)において算出する前記パラメータ値は、前記カメラの取付位置の鉛直成分、ピッチ角、又は、ロール角の少なくともいずれか一つである
キャリブレーション方法。 - 請求項5に記載のキャリブレーション方法において、
前記第三工程(S140、S145)では、前記カメラの前記パラメータ値の算出に加え、前記第二工程(S115)によって得られた、前記面における前記複数のマーカ同士を結ぶ線分と、前記既知の位置関係から求まる前記複数のマーカ同士を結ぶ線分との位置ずれに基づいて、前記カメラのヨー角、又は、前記カメラの取付位置の水平成分の少なくともいずれか一つを、前記カメラのパラメータ値としてさらに算出する
キャリブレーション方法。 - 請求項4~6のいずれかに記載のキャリブレーション方法において、
前記車両には複数のカメラが搭載されており、
前記第一工程(S105)ないし前記第三工程(S140、S145)を、前記カメラ毎に行う
キャリブレーション方法。 - 同一鉛直方向に並んだ複数のマーカであって、いずれのマーカも路面からの高さが既知であるマーカを用いて、車両に搭載されたカメラの姿勢を校正するためのキャリブレーション装置であって、
前記カメラで前記複数のマーカが撮影された2次元画像を得る画像取得部(25、S205)と、
前記画像取得部(25、S205)によって取得された2次元画像における前記複数のマーカを、各マーカの高さを反映させて路面又は路面と平行な面に鳥瞰変換する変換部(25、S215)と、
前記変換部(25、S215)によって得られた、前記面における前記複数のマーカ同士の位置ずれに基づいて、前記カメラのパラメータ値を算出する算出部(25、S240、S245)と、
を有するキャリブレーション装置。 - 請求項8に記載のキャリブレーション装置において、
前記算出部(25、S240、S245)が算出する前記パラメータ値は、前記カメラの取付位置の鉛直成分、ピッチ角、又は、ロール角の少なくともいずれか一つである
キャリブレーション装置。 - 請求項9に記載のキャリブレーション装置において、
前記車両には複数のカメラが搭載されており、
前記画像取得部(25、S205)は、前記複数のカメラで同一の前記複数のマーカが撮影された2次元画像であって、カメラ毎にその2次元画像を取得し、
前記変換部(25、S215)は、前記画像取得部(25、S205)が取得した前記2次元画像のそれぞれについて、前記鳥瞰変換を行い、
前記算出部(25、S240、S245)は、前記カメラ毎の前記パラメータ値の算出に加え、前記カメラ間で同一のマーカの鳥瞰変換後の位置が一致する、前記各カメラのヨー角、又は、前記各カメラの水平成分の少なくともいずれか一つを、前記カメラ毎にパラメータ値としてさらに算出する
キャリブレーション装置。 - 路面から所定距離にあり水平方向にずれた複数のマーカであって、前記マーカ間の位置関係が既知であるマーカを用いて、車両に搭載されたカメラの姿勢を校正するキャリブレーション装置であって、
前記カメラで前記複数のマーカを撮影して2次元画像を取得する画像取得部(25、S105)と、
前記画像取得部(25、S105)が取得した2次元画像における前記複数のマーカを、各マーカの高さを反映させて路面上又は路面と平行な面に鳥瞰変換する変換部(25、S115)と、
前記変換部(25、S115)によって得られた、前記面における前記複数のマーカ間の距離と、前記既知の位置関係から求まる前記複数のマーカ間の距離とのずれに基づいて、前記カメラのパラメータ値を算出する算出部(25、S140、S145)と、
を有するキャリブレーション装置。 - 請求項11に記載のキャリブレーション装置において、
前記算出部(25、S140、S145)が算出する前記パラメータ値は、前記カメラの取り付け位置の鉛直成分、ピッチ角、又は、ロール角の少なくともいずれか一つである
キャリブレーション装置。 - 請求項12に記載のキャリブレーション装置において、
前記算出部(25、S140、S145)は、前記カメラの前記パラメータ値の算出に加え、前記変換部(25、S115)によって得られた、前記面における前記複数のマーカ同士を結ぶ線分と、前記既知の位置関係から求まる前記複数のマーカ同士を結ぶ線分とのずれに基づいて、前記カメラのヨー角、又は、前記カメラの取付位置の水平成分の少なくともいずれか一つを、前記カメラのパラメータ値としてさらに算出する
キャリブレーション装置。 - 請求項11~13のいずれかに記載のキャリブレーション装置において、
前記車両には複数のカメラが搭載されており、
前記各部は、前記カメラ毎に前記の処理を行うこと
を特徴とするキャリブレーション装置。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE112013004851.5T DE112013004851B4 (de) | 2012-10-02 | 2013-09-05 | Kalibrierungsverfahren und Kalibrierungsvorrichtung |
CN201380051577.9A CN104718750B (zh) | 2012-10-02 | 2013-09-05 | 校准方法及校准装置 |
US14/431,456 US10171802B2 (en) | 2012-10-02 | 2013-09-05 | Calibration method and calibration device |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2012-220622 | 2012-10-02 | ||
JP2012220622A JP6009894B2 (ja) | 2012-10-02 | 2012-10-02 | キャリブレーション方法、及びキャリブレーション装置 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2014054223A1 true WO2014054223A1 (ja) | 2014-04-10 |
Family
ID=50434569
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2013/005276 WO2014054223A1 (ja) | 2012-10-02 | 2013-09-05 | キャリブレーション方法、及びキャリブレーション装置 |
Country Status (5)
Country | Link |
---|---|
US (1) | US10171802B2 (ja) |
JP (1) | JP6009894B2 (ja) |
CN (1) | CN104718750B (ja) |
DE (1) | DE112013004851B4 (ja) |
WO (1) | WO2014054223A1 (ja) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104008548A (zh) * | 2014-06-04 | 2014-08-27 | 无锡观智视觉科技有限公司 | 一种用于车载环视系统摄像头参数标定的特征点抽取方法 |
CN104240262A (zh) * | 2014-10-16 | 2014-12-24 | 中国科学院光电技术研究所 | 一种用于摄影测量的相机外参数标定装置及标定方法 |
CN106233711A (zh) * | 2014-09-30 | 2016-12-14 | 歌乐株式会社 | 摄像机校准装置以及摄像机校准系统 |
JP2017211200A (ja) * | 2016-05-23 | 2017-11-30 | 株式会社デンソー | カメラ校正装置及びカメラ校正方法 |
CN107481292A (zh) * | 2017-09-05 | 2017-12-15 | 百度在线网络技术(北京)有限公司 | 车载摄像头的姿态误差估计方法和装置 |
DE112015002764B4 (de) | 2014-06-11 | 2021-07-29 | Denso Corporation | Montagewinkeleinstellverfahren und Montagewinkelerfassungseinrichtung für bordeigene Kamera |
CN114993266A (zh) * | 2022-06-14 | 2022-09-02 | 深圳市道通科技股份有限公司 | 定位装置及定位系统 |
Families Citing this family (42)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6034775B2 (ja) * | 2013-11-29 | 2016-11-30 | クラリオン株式会社 | カメラ校正装置 |
WO2015145543A1 (ja) * | 2014-03-24 | 2015-10-01 | 株式会社日立製作所 | 物体検出装置、物体検出方法、および移動ロボット |
US9953420B2 (en) | 2014-03-25 | 2018-04-24 | Ford Global Technologies, Llc | Camera calibration |
DE102014107235A1 (de) * | 2014-05-22 | 2015-11-26 | Dr. Ing. H.C. F. Porsche Aktiengesellschaft | Verfahren zur Darstellung einer Fahrzeugumgebung auf einer Anzeigevorrichtung; eine Anzeigevorrichtung; ein System aus einer Mehrzahl an Bilderfassungseinheiten und einer Anzeigevorrichtung; ein Computerprogramm |
JP6413974B2 (ja) * | 2015-08-05 | 2018-10-31 | 株式会社デンソー | キャリブレーション装置、キャリブレーション方法、及びプログラム |
KR101740566B1 (ko) * | 2015-10-12 | 2017-05-31 | 아진산업(주) | 스테레오 카메라의 차량 설치 장비 |
JP6603094B2 (ja) * | 2015-10-20 | 2019-11-06 | クラリオン株式会社 | キャリブレーション装置、キャリブレーション方法、及び、キャリブレーションプログラム |
JP6565769B2 (ja) * | 2016-04-03 | 2019-08-28 | 株式会社デンソー | 車載カメラの取付角度検出装置、取付角度較正装置、取付角度検出方法、取付角度較正方法、およびコンピュータープログラム |
GB2549259B (en) * | 2016-04-05 | 2019-10-23 | Continental Automotive Gmbh | Determining mounting positions and/or orientations of multiple cameras of a camera system of a vehicle |
US11541825B2 (en) * | 2016-04-29 | 2023-01-03 | Faraday&Future Inc. | System for providing color balance in automotive display |
JP6614042B2 (ja) * | 2016-06-15 | 2019-12-04 | 株式会社Jvcケンウッド | 姿勢変化判定装置、俯瞰映像生成装置、俯瞰映像生成システム、姿勢変化判定方法およびプログラム |
US20180033124A1 (en) * | 2016-07-28 | 2018-02-01 | The Texas A&M University System | Method and apparatus for radiometric calibration and mosaicking of aerial images |
JP6536529B2 (ja) * | 2016-10-17 | 2019-07-03 | 株式会社デンソー | 車載カメラのキャリブレーション装置及び車載カメラのキャリブレーション方法 |
US10466027B2 (en) | 2017-06-21 | 2019-11-05 | Fujitsu Ten Corp. Of America | System and method for marker placement |
US10089753B1 (en) * | 2017-07-05 | 2018-10-02 | Almotive Kft. | Method, system and computer-readable medium for camera calibration |
CN107621278B (zh) * | 2017-08-04 | 2021-01-29 | 驭势科技(北京)有限公司 | 自主校准方法及装置 |
DE102018206190A1 (de) | 2018-04-23 | 2019-10-24 | Robert Bosch Gmbh | Verfahren zur Detektion einer Anordnung von zumindest zwei Kameras eines Multi-Kamerasystems einer mobilen Trägerplattform zueinander und Verfahren zur Detektion einer Anordnung der Kamera zu einem Objekt außerhalb der mobilen Trägerplattform |
US11115623B2 (en) * | 2018-05-07 | 2021-09-07 | Maxim Integrated Products, Inc. | Systems and methods for asymmetric image splitter with line mark memory |
KR102071418B1 (ko) * | 2018-05-17 | 2020-01-30 | 에스케이텔레콤 주식회사 | 차량용 카메라 캘리브레이션 장치 및 방법 |
JP2020016920A (ja) * | 2018-07-23 | 2020-01-30 | Necソリューションイノベータ株式会社 | 画像補正装置、カウント装置、画像補正方法、カウント方法、プログラム及び記録媒体 |
US10769813B2 (en) * | 2018-08-28 | 2020-09-08 | Bendix Commercial Vehicle Systems, Llc | Apparatus and method for calibrating surround-view camera systems |
JP2020034344A (ja) * | 2018-08-28 | 2020-03-05 | 株式会社Screenホールディングス | 可動部位置検出方法、基板処理方法、基板処理装置および基板処理システム |
CN109353276B (zh) * | 2018-09-21 | 2022-02-11 | 上海豫兴电子科技有限公司 | 一种车载摄像头角度标定方法和标定装置 |
CN109353275B (zh) * | 2018-09-21 | 2022-03-25 | 上海豫兴电子科技有限公司 | 一种车载摄像头角度标定贴膜及标定方法 |
KR20200050612A (ko) * | 2018-11-02 | 2020-05-12 | 현대자동차주식회사 | 차량용 레이더의 영점 조절 장치 및 그 방법 |
US11508055B2 (en) * | 2018-11-20 | 2022-11-22 | Bnsf Railway Company | Systems and methods for calibrating image capturing modules |
US10984521B2 (en) | 2018-11-20 | 2021-04-20 | Bnsf Railway Company | Systems and methods for determining defects in physical objects |
US11423527B2 (en) | 2018-11-20 | 2022-08-23 | Bnsf Railway Company | System and method for minimizing lost vehicle axel motion and filtering erroneous electrical signals |
CN111508027B (zh) * | 2019-01-31 | 2023-10-20 | 杭州海康威视数字技术股份有限公司 | 摄像机外参标定的方法和装置 |
JP6772324B2 (ja) * | 2019-03-20 | 2020-10-21 | 東芝エレベータ株式会社 | 画像処理装置 |
JP6781291B2 (ja) * | 2019-03-20 | 2020-11-04 | 東芝エレベータ株式会社 | 画像処理装置 |
US10723281B1 (en) * | 2019-03-21 | 2020-07-28 | Lyft, Inc. | Calibration of vehicle sensor array alignment |
CN110108203B (zh) * | 2019-04-11 | 2020-12-15 | 东莞中子科学中心 | 一种基于摄影测量技术的丝线位置测量方法及系统 |
CN110211176A (zh) * | 2019-05-31 | 2019-09-06 | 驭势科技(北京)有限公司 | 一种相机外参数校正系统与方法 |
CN114127658B (zh) | 2019-06-14 | 2023-05-23 | 宝马股份公司 | 使用道路模型2d流形的6d空间中的3d里程 |
JP2022535503A (ja) * | 2019-06-14 | 2022-08-09 | バイエリシエ・モトーレンウエルケ・アクチエンゲゼルシヤフト | 2次元軌道計画用道路モデル多様体 |
KR102297683B1 (ko) * | 2019-07-01 | 2021-09-07 | (주)베이다스 | 복수의 카메라들을 캘리브레이션하는 방법 및 장치 |
KR102277828B1 (ko) * | 2019-08-13 | 2021-07-16 | (주)베이다스 | 복수의 카메라들을 캘리브레이션하는 방법 및 장치 |
JP7067574B2 (ja) * | 2020-01-30 | 2022-05-16 | トヨタ自動車株式会社 | 距離推定装置及び距離推定用コンピュータプログラム |
US11270466B2 (en) * | 2020-03-12 | 2022-03-08 | Bnsf Railway Company | Systems and methods for calibrating image capturing modules |
CN113327293B (zh) * | 2021-06-18 | 2022-07-12 | 东莞理工学院 | 一种用于工业机器人抓取领域的深度相机标定装置 |
CN116381632B (zh) * | 2023-06-05 | 2023-08-18 | 南京隼眼电子科技有限公司 | 雷达横滚角的自标定方法、装置及存储介质 |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008209354A (ja) * | 2007-02-28 | 2008-09-11 | Toyota Motor Corp | キャリブレーション方法及び装置、並びに自動検知装置 |
JP2009288152A (ja) * | 2008-05-30 | 2009-12-10 | Nippon Soken Inc | 車載カメラのキャリブレーション方法 |
JP2010103730A (ja) * | 2008-10-23 | 2010-05-06 | Clarion Co Ltd | 車載カメラのキャリブレーション装置およびキャリブレーション方法 |
Family Cites Families (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP3663801B2 (ja) | 1997-01-30 | 2005-06-22 | いすゞ自動車株式会社 | 車両後方視界支援装置 |
US6542840B2 (en) | 2000-01-27 | 2003-04-01 | Matsushita Electric Industrial Co., Ltd. | Calibration system, target apparatus and calibration method |
JP3387911B2 (ja) | 2000-01-27 | 2003-03-17 | 松下電器産業株式会社 | キャリブレーションシステムおよびキャリブレーション方法 |
US6561202B1 (en) * | 2000-11-09 | 2003-05-13 | Steven Amadio | Extendible side guide poles for car wash |
KR100866450B1 (ko) * | 2001-10-15 | 2008-10-31 | 파나소닉 주식회사 | 차량 주위 감시 장치 및 그 조정 방법 |
JP2004280728A (ja) * | 2003-03-18 | 2004-10-07 | Lab:Kk | 画像合成装置及びカメラパラメータキャリブレーション用マーカー設定装置 |
JP4596978B2 (ja) * | 2005-03-09 | 2010-12-15 | 三洋電機株式会社 | 運転支援システム |
JP4820221B2 (ja) * | 2006-06-29 | 2011-11-24 | 日立オートモティブシステムズ株式会社 | 車載カメラのキャリブレーション装置およびプログラム |
JP2008187564A (ja) | 2007-01-31 | 2008-08-14 | Sanyo Electric Co Ltd | カメラ校正装置及び方法並びに車両 |
JP2009100342A (ja) * | 2007-10-18 | 2009-05-07 | Sanyo Electric Co Ltd | カメラ校正装置及び方法、並びに、車両 |
JP2009129001A (ja) * | 2007-11-20 | 2009-06-11 | Sanyo Electric Co Ltd | 運転支援システム、車両、立体物領域推定方法 |
JP2010076527A (ja) * | 2008-09-25 | 2010-04-08 | Sanyo Electric Co Ltd | 操縦支援装置 |
US9105080B2 (en) * | 2008-10-01 | 2015-08-11 | Hi-Key Limited | Method and a system for calibrating an image capture device |
JP2010121987A (ja) | 2008-11-18 | 2010-06-03 | Panasonic Corp | 車載カメラ用のキャリブレーションターゲット及びキャリブレーションシステム |
JP4876118B2 (ja) * | 2008-12-08 | 2012-02-15 | 日立オートモティブシステムズ株式会社 | 立体物出現検知装置 |
WO2010109730A1 (ja) * | 2009-03-26 | 2010-09-30 | アイシン精機株式会社 | カメラ校正装置 |
JP5091902B2 (ja) * | 2009-03-31 | 2012-12-05 | アイシン精機株式会社 | 車載カメラの校正に用いられる校正指標と、当該校正指標を用いた車載カメラの校正方法と、システムと、当該システムのためのプログラム |
JP5369873B2 (ja) * | 2009-04-27 | 2013-12-18 | 富士通株式会社 | 判定プログラムおよびキャリブレーション装置 |
JP5471038B2 (ja) * | 2009-05-27 | 2014-04-16 | アイシン精機株式会社 | 校正目標検出装置と、校正目標を検出する校正目標検出方法と、校正目標検出装置のためのプログラム |
JP5299231B2 (ja) * | 2009-11-17 | 2013-09-25 | 富士通株式会社 | キャリブレーション装置 |
JP5444139B2 (ja) * | 2010-06-29 | 2014-03-19 | クラリオン株式会社 | 画像のキャリブレーション方法および装置 |
US9834153B2 (en) * | 2011-04-25 | 2017-12-05 | Magna Electronics Inc. | Method and system for dynamically calibrating vehicular cameras |
-
2012
- 2012-10-02 JP JP2012220622A patent/JP6009894B2/ja active Active
-
2013
- 2013-09-05 CN CN201380051577.9A patent/CN104718750B/zh active Active
- 2013-09-05 DE DE112013004851.5T patent/DE112013004851B4/de active Active
- 2013-09-05 US US14/431,456 patent/US10171802B2/en active Active
- 2013-09-05 WO PCT/JP2013/005276 patent/WO2014054223A1/ja active Application Filing
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008209354A (ja) * | 2007-02-28 | 2008-09-11 | Toyota Motor Corp | キャリブレーション方法及び装置、並びに自動検知装置 |
JP2009288152A (ja) * | 2008-05-30 | 2009-12-10 | Nippon Soken Inc | 車載カメラのキャリブレーション方法 |
JP2010103730A (ja) * | 2008-10-23 | 2010-05-06 | Clarion Co Ltd | 車載カメラのキャリブレーション装置およびキャリブレーション方法 |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104008548A (zh) * | 2014-06-04 | 2014-08-27 | 无锡观智视觉科技有限公司 | 一种用于车载环视系统摄像头参数标定的特征点抽取方法 |
DE112015002764B4 (de) | 2014-06-11 | 2021-07-29 | Denso Corporation | Montagewinkeleinstellverfahren und Montagewinkelerfassungseinrichtung für bordeigene Kamera |
CN106233711A (zh) * | 2014-09-30 | 2016-12-14 | 歌乐株式会社 | 摄像机校准装置以及摄像机校准系统 |
CN106233711B (zh) * | 2014-09-30 | 2019-08-02 | 歌乐株式会社 | 摄像机校准装置以及摄像机校准系统 |
US10594943B2 (en) | 2014-09-30 | 2020-03-17 | Clarion Co., Ltd. | Camera calibration device and camera calibration system |
CN104240262A (zh) * | 2014-10-16 | 2014-12-24 | 中国科学院光电技术研究所 | 一种用于摄影测量的相机外参数标定装置及标定方法 |
CN104240262B (zh) * | 2014-10-16 | 2017-02-15 | 中国科学院光电技术研究所 | 一种用于摄影测量的相机外参数标定装置及标定方法 |
JP2017211200A (ja) * | 2016-05-23 | 2017-11-30 | 株式会社デンソー | カメラ校正装置及びカメラ校正方法 |
CN107481292A (zh) * | 2017-09-05 | 2017-12-15 | 百度在线网络技术(北京)有限公司 | 车载摄像头的姿态误差估计方法和装置 |
CN107481292B (zh) * | 2017-09-05 | 2020-07-28 | 百度在线网络技术(北京)有限公司 | 车载摄像头的姿态误差估计方法和装置 |
CN114993266A (zh) * | 2022-06-14 | 2022-09-02 | 深圳市道通科技股份有限公司 | 定位装置及定位系统 |
CN114993266B (zh) * | 2022-06-14 | 2024-03-22 | 深圳市道通科技股份有限公司 | 定位装置及定位系统 |
Also Published As
Publication number | Publication date |
---|---|
DE112013004851B4 (de) | 2019-05-09 |
JP2014074591A (ja) | 2014-04-24 |
JP6009894B2 (ja) | 2016-10-19 |
US20150254853A1 (en) | 2015-09-10 |
US10171802B2 (en) | 2019-01-01 |
CN104718750B (zh) | 2018-03-16 |
DE112013004851T5 (de) | 2015-06-18 |
CN104718750A (zh) | 2015-06-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2014054223A1 (ja) | キャリブレーション方法、及びキャリブレーション装置 | |
JP6458439B2 (ja) | 車載カメラ較正装置、画像生成装置、車載カメラ較正方法、画像生成方法 | |
JP5820787B2 (ja) | 画像処理装置、及びプログラム | |
JP5588812B2 (ja) | 画像処理装置及びそれを用いた撮像装置 | |
JP4737317B2 (ja) | 車両周辺撮影表示システム | |
CN111415387B (zh) | 相机位姿确定方法、装置、电子设备及存储介质 | |
US10509983B2 (en) | Operating device, operating system, operating method, and program therefor | |
JP5091902B2 (ja) | 車載カメラの校正に用いられる校正指標と、当該校正指標を用いた車載カメラの校正方法と、システムと、当該システムのためのプログラム | |
JP6277652B2 (ja) | 車両周辺画像表示装置及びカメラの調整方法 | |
CN107122770B (zh) | 多目相机系统、智能驾驶系统、汽车、方法和存储介质 | |
WO2010137364A1 (ja) | 校正目標検出装置と、校正目標を検出する校正目標検出方法と、校正目標検出装置のためのプログラム | |
JP2009288152A (ja) | 車載カメラのキャリブレーション方法 | |
JP2017139612A (ja) | 車載カメラ用校正システム | |
JP2010239409A (ja) | 車載カメラの校正装置 | |
KR20140065627A (ko) | 차량용 카메라 캘리브레이션 장치 및 방법 | |
CN111489288B (zh) | 一种图像的拼接方法和装置 | |
JP5175230B2 (ja) | カメラの自動キャリブレーション装置及び自動キャリブレーション方法 | |
US11145112B2 (en) | Method and vehicle control system for producing images of a surroundings model, and corresponding vehicle | |
CN112050806B (zh) | 一种移动车辆的定位方法及装置 | |
JP2016225719A (ja) | ステレオカメラ装置、車両、および較正方法 | |
JP7316620B2 (ja) | 画像正規化のためのシステムと方法 | |
CN110969664B (zh) | 一种相机外部参数的动态标定方法 | |
CN114170323A (zh) | 图像拍摄装置的参数标定方法、设备及存储介质 | |
CN110836656B (zh) | 用于单目adas的防抖测距方法、装置和电子设备 | |
JP2018170666A (ja) | カメラシステムおよびカメラのキャリブレーション方法 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 13843764 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 14431456 Country of ref document: US |
|
WWE | Wipo information: entry into national phase |
Ref document number: 112013004851 Country of ref document: DE Ref document number: 1120130048515 Country of ref document: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 13843764 Country of ref document: EP Kind code of ref document: A1 |