WO2022118422A1 - ライン位置推定装置、方法およびプログラム - Google Patents
ライン位置推定装置、方法およびプログラム Download PDFInfo
- Publication number
- WO2022118422A1 WO2022118422A1 PCT/JP2020/045000 JP2020045000W WO2022118422A1 WO 2022118422 A1 WO2022118422 A1 WO 2022118422A1 JP 2020045000 W JP2020045000 W JP 2020045000W WO 2022118422 A1 WO2022118422 A1 WO 2022118422A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- bird
- road
- eye view
- image
- line
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims description 28
- 235000004522 Pentaglottis sempervirens Nutrition 0.000 claims abstract description 108
- 240000004050 Pentaglottis sempervirens Species 0.000 claims description 104
- 238000003384 imaging method Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 3
- 230000010365 information processing Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Images
Classifications
-
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
- B60W40/06—Road conditions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
- G06V10/809—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of classification results, e.g. where the classifiers operate on the same input data
- G06V10/811—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of classification results, e.g. where the classifiers operate on the same input data the classifiers operating on different input data, e.g. multi-modal recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2552/00—Input parameters relating to infrastructure
- B60W2552/53—Road markings, e.g. lane marker or crosswalk
-
- 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
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
- G06T2207/30256—Lane; Road marking
Definitions
- the present invention relates to a line position estimation device for estimating the position of a line marked on a road surface, a line position estimation method, and a line position estimation program.
- Patent Document 1 describes an in-vehicle control device that recognizes a white line around a vehicle.
- the in-vehicle control device described in Patent Document 1 captures the imaging range in front of and on each side of the vehicle with a camera to generate a bird's-eye view image (top view image), and based on the generated bird's-eye view image, the surroundings of the vehicle. Recognize white lines in parking frames and driving lanes.
- Patent Document 1 By using the method described in Patent Document 1, it is possible to recognize the white line around the vehicle with a certain accuracy. However, the method described in Patent Document 1 does not consider the problem that occurs when recognizing a distant line as described above.
- an object of the present invention is to provide a line position estimation device, a line position estimation method, and a line position estimation program that can estimate the position of a line marked on a road surface.
- the line position estimation device uses an area recognition image generation means for generating an area recognition image including a road region from a vehicle front image which is an image of the front of the vehicle, and a generated area recognition image as a bird's-eye view image.
- an area recognition image including a road area is generated from a vehicle front image which is an image of the front of the vehicle, and the generated area recognition image is converted into a bird's-eye view image. Is generated, and the position of the line marked on the road surface is estimated from the road area specified by the generated first bird's-eye view image based on the principle of the lane boundary.
- the computer is subjected to an area recognition image generation process that generates an area recognition image including a road area from a vehicle front image that is an image of the front of the vehicle, and the generated area recognition image is converted into a bird's-eye view image.
- an area recognition image generation process that generates an area recognition image including a road area from a vehicle front image that is an image of the front of the vehicle, and the generated area recognition image is converted into a bird's-eye view image.
- the position of the line marked on the road surface is estimated based on the principle of lane boundary. It is characterized in that the line position estimation process is performed.
- the position of the line marked on the road surface can be estimated.
- the line in the following description means various lines indicating the boundary between vehicles marked on the road surface, such as "center line”, “lane boundary line”, and “roadside zone”.
- lines indicating the boundary between vehicles marked on the road surface such as "center line”, “lane boundary line”, and “roadside zone”.
- white solid lines, broken lines, yellow solid lines, etc. in the line, but in the following explanation, the line is referred to as a white line for the sake of simplicity.
- FIG. 1 is a block diagram showing a configuration example of an embodiment of the line position estimation device according to the present invention.
- the line position estimation device 1 of the present embodiment includes an image pickup device 100, an area recognition image generation unit 10, a bird's-eye view image generation unit 20, a road shape acquisition unit 30, a line position estimation unit 40, and a vehicle position determination unit 50.
- the output unit 60 and the display device 200 are provided.
- the image pickup device 100 is a device that captures an image in front of the vehicle, for example, an in-vehicle camera.
- the image of the front of the vehicle is referred to as the image of the front of the vehicle.
- the image pickup device 100 is installed in advance so that an image in front of the vehicle can be captured.
- the image pickup apparatus 100 may capture an image of the vehicle running, or may capture an image of the vehicle stopped.
- the display device 200 is a device that displays an image captured by the image pickup device 100. Further, the display device 200 may display the position of the line estimated by the line position estimation unit 40 described later.
- the display device 200 is realized by, for example, a display device or the like.
- the area recognition image generation unit 10 generates an image (hereinafter referred to as an area recognition image) in which the meaning indicated by each area in the image is recognized from the vehicle front image captured by the image pickup device 100.
- the area recognition image generation unit 10 generates an area recognition image including an area recognized as a road (hereinafter referred to as a road area) from the vehicle front image.
- the method by which the area recognition image generation unit 10 generates the area recognition image is arbitrary.
- the area recognition image generation unit 10 may generate an area recognition image by identifying the meaning of each image area by, for example, image segmentation. Further, when the image pickup apparatus 100 is provided with the depth sensor, it is possible to measure the distance to the object in the image in front of the vehicle. Therefore, the area recognition image generation unit 10 uses the detection result by the depth sensor to measure the area. A recognition image may be generated. Further, the area recognition image may be, for example, an image in which the meaning is labeled for each pixel in the image.
- FIG. 2 is an explanatory diagram showing an example of an area recognition image.
- the image V1 illustrated in FIG. 2 is an example of a vehicle front image captured by the image pickup apparatus 100.
- the area recognition image generation unit 10 may generate an area recognition image V2 including the road area R1 from the image V1.
- the area recognition image V2 illustrated in FIG. 2 is displayed in black and white binary values, but the area recognition image generation unit 10 uses, for example, a heat map in which the areas are color-coded according to the meaning to display the area recognition image V2. May be generated.
- the bird's-eye view image generation unit 20 converts the area recognition image generated by the area recognition image generation unit 10 into a bird's-eye view image (sometimes referred to as a bird's-eye view image or a top-view image) (hereinafter referred to as a first bird's-eye view image). .) Is generated. Further, the bird's-eye view image generation unit 20 may generate an image (hereinafter referred to as a second bird's-eye view image) obtained by converting the vehicle front image captured by the image pickup apparatus 100 into a bird's-eye view image. Since the method of converting an image into a bird's-eye view image is widely known, detailed description thereof will be omitted here.
- FIG. 3 is an explanatory diagram showing an example of a bird's-eye view image.
- the bird's-eye view image generation unit 20 generates the first bird's-eye view image V3 based on the area recognition image V2 generated by the area recognition image generation unit 10, and the vehicle front image V1 exemplified in FIG. 2 is used. It is shown that the second bird's-eye view image V4 is generated based on the above.
- the shaded area R2 of the first bird's-eye view image V3 illustrated in FIG. 3 is an area corresponding to the road area R1 exemplified in FIG.
- the road shape acquisition unit 30 determines the road shape from the first bird's-eye view image. Specifically, the road shape acquisition unit 30 determines the road shape from the shape of the boundary of the road region. For example, when the shape of the boundary is a straight line, the road shape acquisition unit 30 may determine that the road shape is a straight line. Further, when the shape of the boundary is a curve, the road shape acquisition unit 30 may determine that the road shape is curved.
- the road shape acquisition unit 30 may detect the boundary b1 and the boundary b2 from the first bird's-eye view image V3 to determine the road shape.
- the road shape acquisition unit 30 may acquire the road shape based on the current situation of the vehicle. Further, the current state of the vehicle includes the position where the vehicle currently exists, the driving state of the vehicle, and the like.
- the road shape acquisition unit 30 may acquire the position where the vehicle currently exists by, for example, GPS (Global Positioning System). Then, the road shape acquisition unit 30 identifies a position acquired from the map information prepared in advance, and obtains a road shape including lane information (for example, two lanes, three lanes, etc.) from the map information corresponding to the specified position. You may get it.
- the map information here may include not only the shape of the road but also lane information indicating the number of lanes of the road.
- the road shape acquisition unit 30 may acquire a lane shape (for example, a dotted line, a long line segment, a lane color, etc.) as lane information from the map information.
- a lane shape for example, a dotted line, a long line segment, a lane color, etc.
- the driving state of the vehicle is a driving state of the vehicle operated according to the shape of the road, and is specified based on, for example, CAN (Controller Area Network) information.
- CAN Controller Area Network
- the road shape acquisition unit 30 acquires the steering angle of the steering shaft generated by turning the steering wheel of the vehicle, and specifies the shape of the road according to the acquired steering angle. May be good.
- the line position estimation device 1 may not include the road shape acquisition unit 30.
- the line position estimation unit 40 estimates the position of the line marked on the road surface from the road area specified by the generated first bird's-eye view image based on the principle of the lane boundary.
- the principle of lane boundary is a universal rule of lanes marked according to the mode of the road (for example, road shape, road surface condition, etc.), and is defined in advance by a user or the like.
- the lane width is a predetermined width ( For example, a wide road designed to be (about 3.5 m) is provided with a plurality of lanes (that is, a central line and a plurality of lane boundaries are provided).
- the line position estimation unit 40 specifies lane information (number of lanes) from the map information acquired by the road shape acquisition unit 30, and the specified lane information is used. Based on this, the number of lines may be determined. The number of lines may be determined by the line position estimation unit 40 itself acquiring the position information and specifying the lane information.
- the principle of lane boundaries may be defined according to the characteristics of the region.
- Regional characteristics include, for example, narrow roads in central Tokyo and wide roads in local cities.
- the line position estimation unit 40 may estimate the position of the line from the acquired road shape and the road region specified by the first bird's-eye view image. .. For example, when it is estimated that the position of the line exists in the straight line direction from the road area specified by the first bird's-eye view image and the information that the road shape is curved is acquired, the line position estimation unit 40 uses the current straight line. However, it may be estimated that it becomes a curve at the destination.
- the line position estimation unit 40 may estimate the position of the line from the generated second bird's-eye view image.
- the second bird's-eye view image is a bird's-eye view image directly generated from the vehicle front image. Therefore, the line position estimation unit 40 may estimate the line position from the second bird's-eye view image by a generally known method (for example, the method described in Patent Document 1).
- the position of the line is estimated from the first bird's-eye view image and the second bird's-eye view image, respectively. Therefore, the line position estimation unit 40 predetermines the estimated intensity indicating the plausibility of the line for each bird's-eye view image, and selects the estimation result of the position of the line estimated to be more plausible based on the estimated intensity. May be good. It should be noted that this estimated intensity may be adjusted according to the application or the like used.
- the vehicle position determination unit 50 identifies the position of the vehicle existing on the vehicle front image or the bird's-eye view image based on the estimated position of the white line. Specifically, the vehicle position determination unit 50, for example, whether the vehicle traveling in front is traveling in the lane (ego lane) in which the own vehicle is present or traveling in another lane (for example, the overtaking lane). Identify if you are.
- the vehicle position determination unit 50 superimposes and displays the estimated line on the vehicle front image or the bird's-eye view image, and determines the position of the vehicle existing on the image from the positional relationship between the displayed line and the own vehicle. It may be specified.
- the output unit 60 outputs the estimation result of the line position.
- the output unit 60 may display, for example, the estimation result of the line position on the display device 200.
- FIG. 4 is an explanatory diagram showing an output example of the estimation result.
- the image V5 illustrated in FIG. 4 shows the estimation result of the position of the line superimposed on the image in front of the vehicle.
- the area recognition image generation unit 10, the bird's-eye view image generation unit 20, the road shape acquisition unit 30, the line position estimation unit 40, the vehicle position determination unit 50, and the output unit 60 follow a program (line position estimation program). It is realized by the processor of the operating computer (for example, CPU (Central Processing Unit), GPU (Graphics Processing Unit)).
- CPU Central Processing Unit
- GPU Graphics Processing Unit
- the program is stored in a storage unit (not shown) of the line position estimation device 1, the processor reads the program, and according to the program, the area recognition image generation unit 10, the bird's-eye view image generation unit 20, and the road shape acquisition unit. 30 may operate as a line position estimation unit 40, a vehicle position determination unit 50, and an output unit 60. Further, the function of the line position estimation device 1 may be provided in the SAAS (Software as a Service) format.
- SAAS Software as a Service
- the area recognition image generation unit 10, the bird's-eye view image generation unit 20, the road shape acquisition unit 30, the line position estimation unit 40, the vehicle position determination unit 50, and the output unit 60 are each dedicated hardware. It may be realized by. Further, a part or all of each component of each device may be realized by a general-purpose or dedicated circuit (circuitry), a processor, or a combination thereof. These may be composed of a single chip or may be composed of a plurality of chips connected via a bus. A part or all of each component of each device may be realized by the combination of the circuit or the like and the program described above.
- each component of the line position estimation device 1 when a part or all of each component of the line position estimation device 1 is realized by a plurality of information processing devices and circuits, the plurality of information processing devices and circuits may be centrally arranged. , May be distributed.
- the information processing device, the circuit, and the like may be realized as a form in which each is connected via a communication network, such as a client-server system and a cloud computing system.
- FIG. 5 is a flowchart showing an operation example of the line position estimation device 1 of the present embodiment.
- the image pickup apparatus 100 captures an image in front of the vehicle (step S11).
- the area recognition image generation unit 10 generates an area recognition image from the vehicle front image (step S12).
- the bird's-eye view image generation unit 20 generates a first bird's-eye view image from the generated area recognition image (step S13).
- the line position estimation unit 40 estimates the position of the line marked on the road surface from the road region specified by the generated first bird's-eye view image based on the principle of the lane boundary (step S14).
- the line position estimation unit 40 may estimate the position of the line from the acquired road shape and the specified road area. Then, the output unit 60 may output the position of the estimated line. Further, the vehicle position determination unit 50 may specify the position of the vehicle existing on the vehicle front image or the bird's-eye view image based on the estimated position of the white line.
- the area recognition image generation unit 10 generates the area recognition image from the vehicle front image
- the bird's-eye view image generation unit 20 generates the first bird's-eye view image from the generated area recognition image.
- the line position estimation unit 40 estimates the position of the line marked on the road surface from the road region specified by the generated first bird's-eye view image based on the principle of the lane boundary. Therefore, the position of the line marked on the road surface can be appropriately estimated.
- FIG. 6 is a block diagram showing an outline of the line position estimation device according to the present invention.
- the line position estimation device 80 (for example, the line position estimation device 1) according to the present invention is a region recognition image generation means 81 (for example, a region recognition image generation means 81 (for example) that generates an area recognition image including a road region from a vehicle front image which is an image of the front of the vehicle.
- the area recognition image generation unit 10 the area recognition image generation unit 10
- the bird's-eye view image generation means 82 for example, the bird's-eye view image generation unit 20
- the first bird's-eye view image obtained by converting the generated area recognition image into the bird's-eye view image (that is, the top view image).
- the line position estimation means 83 (for example, the line position estimation unit 40) that estimates the position of the line marked on the road surface from the road area specified by the generated first bird's-eye view image based on the principle of the lane boundary. ) And.
- the position of the line marked on the road surface can be estimated appropriately.
- the line position estimation device 80 may include a road shape acquisition means (for example, a road shape acquisition unit 30) that acquires a road shape based on the current situation of the vehicle. Then, the line position estimating means 83 may estimate the position of the line from the acquired road shape and the specified road area.
- a road shape acquisition means for example, a road shape acquisition unit 30
- the line position estimating means 83 may estimate the position of the line from the acquired road shape and the specified road area.
- the road shape acquisition means acquires the position where the vehicle exists (for example, by GPS), identifies the acquired position from the map information, and obtains the lane information from the map information corresponding to the specified position.
- the road shape including the road shape may be acquired.
- the road shape acquisition means may acquire the road shape based on the driving state (for example, CAN information) of the vehicle operated according to the shape of the road.
- the road shape acquisition means may acquire the steering angle of the steering shaft generated by turning the steering wheel of the vehicle, and specify the shape of the road according to the acquired steering angle.
- the bird's-eye view image generation means 82 may generate a second bird's-eye view image obtained by converting the vehicle front image into a bird's-eye view image. Then, the line position estimation means 83 estimates the position of the line from the generated second bird's-eye view image, and is estimated to be more plausible based on the estimated intensity indicating the plausibility of the line predetermined for each bird's-eye view image. You may select the estimation result of the position of the line.
- the line position estimation device 80 is a vehicle position determination means (for example, a vehicle position determination unit 50) that identifies the position of a vehicle existing on the vehicle front image or the first bird's-eye view image based on the estimated line position. May be provided. With such a configuration, it becomes possible to detect the lane position of the vehicle in front.
- a vehicle position determination means for example, a vehicle position determination unit 50
- FIG. 7 is a schematic block diagram showing a configuration of a computer according to at least one embodiment.
- the computer 1000 includes a processor 1001, a main storage device 1002, an auxiliary storage device 1003, and an interface 1004.
- the line position estimation device 80 described above is mounted on the computer 1000.
- the operation of each of the above-mentioned processing units is stored in the auxiliary storage device 1003 in the form of a program (line position estimation program).
- the processor 1001 reads a program from the auxiliary storage device 1003, expands it to the main storage device 1002, and executes the above processing according to the program.
- the auxiliary storage device 1003 is an example of a non-temporary tangible medium.
- non-temporary tangible media include magnetic disks, optomagnetic disks, CD-ROMs (Compact Disc Read-only memory), DVD-ROMs (Read-only memory), which are connected via interface 1004. Examples include semiconductor memory.
- the program may be for realizing a part of the above-mentioned functions. Further, the program may be a so-called difference file (difference program) that realizes the above-mentioned function in combination with another program already stored in the auxiliary storage device 1003.
- difference file difference program
- An area recognition image generation means for generating an area recognition image including a road area from a vehicle front image which is an image of the front of the vehicle.
- a bird's-eye view image generation means for generating a first bird's-eye view image obtained by converting the generated area recognition image into a bird's-eye view image,
- the line position estimation means is the line position estimation device according to Appendix 1, which estimates the position of a line from the acquired road shape and the specified road area.
- the road shape acquisition means acquires the position where the vehicle exists, identifies the acquired position from the map information, and acquires the road shape including the lane information from the map information corresponding to the specified position. 2.
- the line position estimation device according to 2.
- Appendix 4 The line position estimation device according to Appendix 2 or Appendix 3, wherein the road shape acquisition means acquires the road shape based on the driving state of the vehicle operated according to the shape of the road.
- the bird's-eye view image generation means generates a second bird's-eye view image obtained by converting the vehicle front image into a bird's-eye view image.
- the line position estimation means estimates the position of the line from the generated second bird's-eye view image, and based on the estimated intensity indicating the plausibility of the line predetermined for each bird's-eye view image, the line position is estimated to be more plausible.
- the line position estimation device according to any one of Supplements 1 to 5, which selects a position estimation result.
- Appendix 7 Any one of Appendix 1 to Appendix 6 provided with a vehicle position determining means for specifying the position of the vehicle existing on the vehicle front image or the first bird's-eye view image based on the estimated line position.
- vehicle position determining means for specifying the position of the vehicle existing on the vehicle front image or the first bird's-eye view image based on the estimated line position.
- An area recognition image including a road area is generated from a vehicle front image which is an image of the front of the vehicle.
- a first bird's-eye view image is generated by converting the generated area recognition image into a bird's-eye view image.
- a line position estimation method characterized in that the position of a line marked on a road surface is estimated from the road area specified by the generated first bird's-eye view image based on the principle of lane boundary.
- a bird's-eye view image generation process that generates a first bird's-eye view image obtained by converting the generated area recognition image into a bird's-eye view image, and Stores a line position estimation program for performing line position estimation processing that estimates the position of the line marked on the road surface from the road area specified by the generated first bird's-eye view image based on the principle of lane boundary.
- Program storage medium
- Appendix 11 To the computer Perform the road shape acquisition process to acquire the road shape based on the current situation of the vehicle,
- the program storage medium according to Appendix 10 which stores a line position estimation program for estimating the position of a line from the acquired road shape and the specified road area in the line position estimation process.
- a bird's-eye view image generation process that generates a first bird's-eye view image obtained by converting the generated area recognition image into a bird's-eye view image, and Stores a line position estimation program for performing line position estimation processing that estimates the position of the line marked on the road surface from the road area specified by the generated first bird's-eye view image based on the principle of lane boundary.
- Program storage medium
- Line position estimation device 10
- Area recognition image generation unit 20
- Bird's-eye view image generation unit 30
- Road shape acquisition unit 40
- Line position estimation unit 50
- Vehicle position determination unit 60
- Output unit 100
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Automation & Control Theory (AREA)
- Mathematical Physics (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
- Image Processing (AREA)
Abstract
Description
生成された前記領域認識映像を俯瞰映像に変換した第一俯瞰映像を生成する俯瞰映像生成手段と、
生成された第一俯瞰映像により特定される前記道路領域から、車線境界の原則に基づいて、路面に標示されたラインの位置を推定するライン位置推定手段とを備えた
ことを特徴とするライン位置推定装置。
ライン位置推定手段は、取得された道路形状および特定された道路領域からラインの位置を推定する
付記1記載のライン位置推定装置。
付記2記載のライン位置推定装置。
付記2または付記3記載のライン位置推定装置。
付記4記載のライン位置推定装置。
ライン位置推定手段は、生成された第二俯瞰映像からラインの位置を推定し、俯瞰映像ごとに予め定められたラインの尤もらしさを示す推定強度に基づいて、より尤もらしいと推定されたラインの位置の推定結果を選択する
付記1から付記5のうちのいずれか1つに記載のライン位置推定装置。
付記1から付記6のうちのいずれか1つに記載のライン位置推定装置。
生成された前記領域認識映像を俯瞰映像に変換した第一俯瞰映像を生成し、
生成された第一俯瞰映像により特定される前記道路領域から、車線境界の原則に基づいて、路面に標示されたラインの位置を推定する
ことを特徴とするライン位置推定方法。
取得された道路形状および特定された道路領域からラインの位置を推定する
付記8記載のライン位置推定方法。
車両の前方を撮像した映像である車両前方映像から、道路領域を含む領域認識映像を生成する領域認識映像生成処理、
生成された前記領域認識映像を俯瞰映像に変換した第一俯瞰映像を生成する俯瞰映像生成処理、および、
生成された第一俯瞰映像により特定される前記道路領域から、車線境界の原則に基づいて、路面に標示されたラインの位置を推定するライン位置推定処理
を実施させるためのライン位置推定プログラムを記憶するプログラム記憶媒体。
車両の現在の状況に基づいて道路形状を取得する道路形状取得処理を実施させ、
ライン位置推定処理で、取得された道路形状および特定された道路領域からラインの位置を推定させる
ためのライン位置推定プログラムを記憶する付記10記載のプログラム記憶媒体。
車両の前方を撮像した映像である車両前方映像から、道路領域を含む領域認識映像を生成する領域認識映像生成処理、
生成された前記領域認識映像を俯瞰映像に変換した第一俯瞰映像を生成する俯瞰映像生成処理、および、
生成された第一俯瞰映像により特定される前記道路領域から、車線境界の原則に基づいて、路面に標示されたラインの位置を推定するライン位置推定処理
を実施させるためのライン位置推定プログラムを記憶するプログラム記憶媒体。
車両の現在の状況に基づいて道路形状を取得する道路形状取得処理を実施させ、
ライン位置推定処理で、取得された道路形状および特定された道路領域からラインの位置を推定させる
ためのライン位置推定プログラムを記憶する付記12記載のプログラム記憶媒体。
10 領域認識映像生成部
20 俯瞰映像生成部
30 道路形状取得部
40 ライン位置推定部
50 車両位置判定部
60 出力部
100 撮像装置
200 表示装置
Claims (11)
- 車両の前方を撮像した映像である車両前方映像から、道路領域を含む領域認識映像を生成する領域認識映像生成手段と、
生成された前記領域認識映像を俯瞰映像に変換した第一俯瞰映像を生成する俯瞰映像生成手段と、
生成された第一俯瞰映像により特定される前記道路領域から、車線境界の原則に基づいて、路面に標示されたラインの位置を推定するライン位置推定手段とを備えた
ことを特徴とするライン位置推定装置。 - 車両の現在の状況に基づいて道路形状を取得する道路形状取得手段を備え、
ライン位置推定手段は、取得された道路形状および特定された道路領域からラインの位置を推定する
請求項1記載のライン位置推定装置。 - 道路形状取得手段は、車両が存在する位置を取得し、取得された位置を地図情報から特定し、特定された位置に対応する地図情報から車線情報を含む道路形状を取得する
請求項2記載のライン位置推定装置。 - 道路形状取得手段は、道路の形状に応じて操作される車両の駆動状態に基づいて道路形状を取得する
請求項2または請求項3記載のライン位置推定装置。 - 道路形状取得手段は、車両のハンドルを切ることで生じるステアリング軸の操舵角を取得し、取得した操舵角に応じて道路の形状を特定する
請求項4記載のライン位置推定装置。 - 俯瞰映像生成手段は、車両前方映像を俯瞰映像に変換した第二俯瞰映像を生成し、
ライン位置推定手段は、生成された第二俯瞰映像からラインの位置を推定し、俯瞰映像ごとに予め定められたラインの尤もらしさを示す推定強度に基づいて、より尤もらしいと推定されたラインの位置の推定結果を選択する
請求項1から請求項5のうちのいずれか1項に記載のライン位置推定装置。 - 推定されたラインの位置に基づいて、車両前方映像または第一俯瞰映像上に存在する車両の位置を特定する車両位置判定手段を備えた
請求項1から請求項6のうちのいずれか1項に記載のライン位置推定装置。 - 車両の前方を撮像した映像である車両前方映像から、道路領域を含む領域認識映像を生成し、
生成された前記領域認識映像を俯瞰映像に変換した第一俯瞰映像を生成し、
生成された第一俯瞰映像により特定される前記道路領域から、車線境界の原則に基づいて、路面に標示されたラインの位置を推定する
ことを特徴とするライン位置推定方法。 - 車両の現在の状況に基づいて道路形状を取得し、
取得された道路形状および特定された道路領域からラインの位置を推定する
請求項8記載のライン位置推定方法。 - コンピュータに、
車両の前方を撮像した映像である車両前方映像から、道路領域を含む領域認識映像を生成する領域認識映像生成処理、
生成された前記領域認識映像を俯瞰映像に変換した第一俯瞰映像を生成する俯瞰映像生成処理、および、
生成された第一俯瞰映像により特定される前記道路領域から、車線境界の原則に基づいて、路面に標示されたラインの位置を推定するライン位置推定処理
を実施させるためのライン位置推定プログラムを記憶するプログラム記憶媒体。 - コンピュータに、
車両の現在の状況に基づいて道路形状を取得する道路形状取得処理を実施させ、
ライン位置推定処理で、取得された道路形状および特定された道路領域からラインの位置を推定させる
ためのライン位置推定プログラムを記憶する請求項10記載のプログラム記憶媒体。
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2020/045000 WO2022118422A1 (ja) | 2020-12-03 | 2020-12-03 | ライン位置推定装置、方法およびプログラム |
US18/039,625 US20240095946A1 (en) | 2020-12-03 | 2020-12-03 | Line position estimation device, method, and program |
JP2022566570A JPWO2022118422A1 (ja) | 2020-12-03 | 2020-12-03 | |
EP20964275.0A EP4238843A4 (en) | 2020-12-03 | 2020-12-03 | DEVICE, METHOD AND PROGRAM FOR LINE POSITION ESTIMATION |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2020/045000 WO2022118422A1 (ja) | 2020-12-03 | 2020-12-03 | ライン位置推定装置、方法およびプログラム |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022118422A1 true WO2022118422A1 (ja) | 2022-06-09 |
Family
ID=81853071
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2020/045000 WO2022118422A1 (ja) | 2020-12-03 | 2020-12-03 | ライン位置推定装置、方法およびプログラム |
Country Status (4)
Country | Link |
---|---|
US (1) | US20240095946A1 (ja) |
EP (1) | EP4238843A4 (ja) |
JP (1) | JPWO2022118422A1 (ja) |
WO (1) | WO2022118422A1 (ja) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2002175534A (ja) * | 2000-12-06 | 2002-06-21 | Sumitomo Electric Ind Ltd | 道路の白線検出方法 |
JP2011186722A (ja) * | 2010-03-08 | 2011-09-22 | Nippon Soken Inc | 車載白線認識装置 |
JP2013122739A (ja) * | 2011-12-12 | 2013-06-20 | Fujitsu Ltd | 解析装置、解析プログラムおよび解析方法 |
JP2014104853A (ja) | 2012-11-27 | 2014-06-09 | Clarion Co Ltd | 車載用制御装置 |
JP2016004287A (ja) * | 2014-06-13 | 2016-01-12 | 富士通株式会社 | 車線境界線抽出装置、車線境界線抽出方法、及びプログラム |
JP2017016172A (ja) * | 2015-06-26 | 2017-01-19 | 日産自動車株式会社 | 走路境界推定装置及び走路境界推定方法 |
JP2018127073A (ja) * | 2017-02-08 | 2018-08-16 | トヨタ自動車株式会社 | 車線逸脱抑制装置 |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP4697480B2 (ja) * | 2008-01-11 | 2011-06-08 | 日本電気株式会社 | 車線認識装置、車線認識方法および車線認識プログラム |
KR102421855B1 (ko) * | 2017-09-28 | 2022-07-18 | 삼성전자주식회사 | 주행 차로를 식별하는 방법 및 장치 |
-
2020
- 2020-12-03 JP JP2022566570A patent/JPWO2022118422A1/ja active Pending
- 2020-12-03 EP EP20964275.0A patent/EP4238843A4/en active Pending
- 2020-12-03 WO PCT/JP2020/045000 patent/WO2022118422A1/ja active Application Filing
- 2020-12-03 US US18/039,625 patent/US20240095946A1/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2002175534A (ja) * | 2000-12-06 | 2002-06-21 | Sumitomo Electric Ind Ltd | 道路の白線検出方法 |
JP2011186722A (ja) * | 2010-03-08 | 2011-09-22 | Nippon Soken Inc | 車載白線認識装置 |
JP2013122739A (ja) * | 2011-12-12 | 2013-06-20 | Fujitsu Ltd | 解析装置、解析プログラムおよび解析方法 |
JP2014104853A (ja) | 2012-11-27 | 2014-06-09 | Clarion Co Ltd | 車載用制御装置 |
JP2016004287A (ja) * | 2014-06-13 | 2016-01-12 | 富士通株式会社 | 車線境界線抽出装置、車線境界線抽出方法、及びプログラム |
JP2017016172A (ja) * | 2015-06-26 | 2017-01-19 | 日産自動車株式会社 | 走路境界推定装置及び走路境界推定方法 |
JP2018127073A (ja) * | 2017-02-08 | 2018-08-16 | トヨタ自動車株式会社 | 車線逸脱抑制装置 |
Non-Patent Citations (2)
Title |
---|
LIU, J. ET AL.: "Lane detection based on straight line model and K-Means clustering", 2018 IEEE 7TH DATA DRIVEN CONTROL AND LEARNING SYSTEMS CONFERENCE, 2018, pages 527 - 532, XP033432459, DOI: 10.1109/DDCLS.2018.8515938 * |
See also references of EP4238843A4 |
Also Published As
Publication number | Publication date |
---|---|
EP4238843A4 (en) | 2023-12-06 |
EP4238843A1 (en) | 2023-09-06 |
US20240095946A1 (en) | 2024-03-21 |
JPWO2022118422A1 (ja) | 2022-06-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP3580475B2 (ja) | 周辺監視装置 | |
JP4052310B2 (ja) | 交差点までの距離算出方法、装置及びシステム | |
US20140365109A1 (en) | Apparatus and method for recognizing driving lane | |
JP2006209511A (ja) | 画像認識装置及び画像認識方法、並びにそれを用いた位置特定装置、車両制御装置及びナビゲーション装置 | |
US20200290600A1 (en) | Parking assistance device and parking assistance method | |
JP4702149B2 (ja) | 車両位置測位装置 | |
JP6941070B2 (ja) | ステレオカメラ装置 | |
JP7251582B2 (ja) | 表示制御装置および表示制御プログラム | |
JP2007164671A (ja) | 障害物接近判断装置および障害物衝突警告システム | |
JP2020126355A (ja) | 情報処理装置、情報処理システム、情報処理方法およびプログラム | |
JP2009252198A (ja) | 走行環境推測装置、方法及びプログラム並びに車線逸脱警報装置及び操舵アシスト装置 | |
JP4951481B2 (ja) | 路面標示認識装置 | |
JP2007066003A (ja) | 停止線検出装置 | |
KR20170055738A (ko) | 영상 기반 주행 차로 판단 장치 및 방법 | |
JP2018073275A (ja) | 画像認識装置 | |
US10789727B2 (en) | Information processing apparatus and non-transitory recording medium storing thereon a computer program | |
JP2007064894A (ja) | 物体検出装置、物体検出方法および物体検出プログラム | |
JP4968369B2 (ja) | 車載装置及び車両認識方法 | |
JP5012522B2 (ja) | 路側境界面検出装置 | |
JP2010107435A (ja) | 地物位置認識装置 | |
JP2017129543A (ja) | ステレオカメラ装置及び車両 | |
JP7398257B2 (ja) | 道路標示認識装置 | |
WO2022118422A1 (ja) | ライン位置推定装置、方法およびプログラム | |
JP4687381B2 (ja) | 車両認識方法及び車載装置 | |
JP5145138B2 (ja) | 運転支援装置、運転支援制御方法および運転支援制御処理プログラム |
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: 20964275 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2022566570 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 18039625 Country of ref document: US |
|
ENP | Entry into the national phase |
Ref document number: 2020964275 Country of ref document: EP Effective date: 20230602 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |