WO2021029203A1 - 周辺映像生成装置、周辺映像生成方法、およびプログラム - Google Patents

周辺映像生成装置、周辺映像生成方法、およびプログラム Download PDF

Info

Publication number
WO2021029203A1
WO2021029203A1 PCT/JP2020/028542 JP2020028542W WO2021029203A1 WO 2021029203 A1 WO2021029203 A1 WO 2021029203A1 JP 2020028542 W JP2020028542 W JP 2020028542W WO 2021029203 A1 WO2021029203 A1 WO 2021029203A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
peripheral
unit
dimensional shape
video
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.)
Ceased
Application number
PCT/JP2020/028542
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
小口　貴弘
陽介 服部
雄介 関川
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.)
Denso Corp
Original Assignee
Denso Corp
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 Denso Corp filed Critical Denso Corp
Priority to CN202080056408.4A priority Critical patent/CN114206674B/zh
Priority to DE112020003788.6T priority patent/DE112020003788T5/de
Publication of WO2021029203A1 publication Critical patent/WO2021029203A1/ja
Priority to US17/650,201 priority patent/US12450784B2/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
    • B60R1/00—Optical viewing arrangements; Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/50—Depth or shape recovery
    • G06T7/55—Depth or shape recovery from multiple images
    • G06T7/579—Depth or shape recovery from multiple images from motion
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T11/00—Two-dimensional [2D] image generation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T1/00—General purpose image data processing
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/50—Depth or shape recovery
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/50—Depth or shape recovery
    • G06T7/55—Depth or shape recovery from multiple images
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/16—Anti-collision systems
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/16—Anti-collision systems
    • G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
    • 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
    • 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
    • H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
    • 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
    • B60R2300/10—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of camera system used
    • B60R2300/105—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of camera system used using multiple cameras
    • 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
    • B60R2300/30—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of image processing
    • B60R2300/303—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of image processing using joined images, e.g. multiple camera images
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10028—Range image; Depth image; 3D point clouds
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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

Definitions

  • This disclosure relates to a peripheral image generator, a peripheral image generation method, and a program.
  • Patent Document 1 discloses an invention of a peripheral image generator that corrects images taken by cameras installed on the front, rear, left side, and right side of a vehicle into a top view form and provides the driver with a peripheral image generator.
  • an object of the present disclosure is to provide a peripheral image generator or the like capable of generating a peripheral image that does not give a sense of discomfort regardless of the presence of an object.
  • the peripheral image generation device includes a video input unit for inputting peripheral image data taken by a plurality of cameras and a video synthesis unit for synthesizing the peripheral image data to generate a composite image viewed from a predetermined viewpoint. And, using the three-dimensional shape estimation unit that estimates the three-dimensional shape of the surrounding object based on the peripheral image data and the estimation result of the three-dimensional shape, the shielded area that cannot be seen from the predetermined viewpoint in the composite image is estimated. It includes a shielded area estimation unit, an inference unit that infers an image of the shielded area using deep learning, and an image superimposing unit that superimposes the image inferred by the reasoning unit on the shielded area of the composite image. ..
  • the three-dimensional shape estimation unit may estimate the three-dimensional shape based on the detection data detected by the distance measuring sensor.
  • peripheral image generator according to the embodiment of the present disclosure will be described with reference to the drawings.
  • the peripheral image generator of the embodiment described below is mounted on the vehicle and is used to generate and display a top view image of the periphery of the vehicle.
  • a scene for generating a peripheral image in a parking lot will be described.
  • the use of the peripheral image generator of the present disclosure is not limited to the vehicle, and may be used for other purposes.
  • FIG. 1 is a diagram showing a configuration of a peripheral image generation device 1 according to the first embodiment.
  • the peripheral image generator 1 is connected to four cameras 20 mounted on the vehicle and a display 21.
  • the four cameras 20 are cameras 20 that photograph the front, rear, left, and right of the vehicle, respectively.
  • the display 21 may also be used as the display 21 of the navigation device, and displays an image captured by the camera 20.
  • the peripheral image generation device 1 is a video input unit 10 for inputting peripheral video data taken by four cameras 20 and a video for processing the peripheral video data input to the video input unit 10 to generate a top view video. It has a processing unit 11, a video output unit 17 that outputs a top view video, a memory 18, and a power supply unit 19. The video output unit 17 transmits video data to the display 21.
  • the image processing unit 11 synthesizes peripheral image data to generate a top-view image viewed from above the vehicle, and three-dimensional shape estimation that estimates the three-dimensional shape of surrounding objects based on the peripheral image data.
  • Unit 13 the shield area estimation unit 14 that estimates the shield area that cannot be seen from a predetermined viewpoint in the composite image using the estimation result of the three-dimensional shape, and the inference unit 15 that infers the image of the shield area using deep learning.
  • the image superimposing unit 16 superimposes the image inferred by the reasoning unit 15 on the shielded region of the composite image.
  • the video synthesis unit 12 synthesizes the video data from the four cameras 20 input to the video input unit 10 to generate a top view video.
  • the video compositing unit 12 for example, a known technique as described in Patent Document 1 can be used.
  • the three-dimensional shape estimation unit 13 estimates the three-dimensional shape of an object reflected in the image by using the technology of SfM (Structure from Motion) from the image data from each camera 20 input to the image input unit 10.
  • SfM Structure from Motion
  • SfM is, for example, the technology described in Photogrammetry and Remote Sensing Vol. 55, No. 3, "Explanation: Structure from Motion (SfM), 1st Outline of SfM and Bundle Adjustment" by Kazuo Oda.
  • the three-dimensional shape estimation unit 13 superimposes the estimation results from the video data of each camera 20 to estimate the three-dimensional shape of the object around the vehicle.
  • the shielded area estimation unit 14 uses the information on the three-dimensional shape of the estimated object to estimate the shielded area that is blocked by the object and is not visible in the top view image, and masks the shielded area.
  • the inference unit 15 infers the image of the shielded region using the generator created by deep learning.
  • GAN hostile generation network
  • FIG. 2 is a diagram for explaining GAN.
  • the GAN includes a Generator (hereinafter, also referred to as “G”) and a Discriminator (hereinafter, also referred to as “D”).
  • G is a neural network model that generates an image that deceives “D”
  • D distinguishes the image (fake data) generated by "G” from the correct image (true data). It is a neural network model.
  • learning of "G” and “D” is performed alternately.
  • the vector z is sampled and given to "G”
  • an image (fake data) is output. This image is given to "D” to judge true / false.
  • the parameter of "G” is updated and learning is performed so that it is determined to be true by “D”. As a result, "G” will generate an image that deceives "D”.
  • the inference unit 15 has a Generator (generator) generated by GAN in advance.
  • the image of the actual parking lot may be used, but the image of the parking lot may be created by CG, the shielded area may be automatically labeled in the CG image, and the teacher data may be used. ..
  • the teacher data may be used. .. According to the method of generating the image of the parking lot by CG, a large amount of teacher data can be easily prepared.
  • the reasoning unit 15 infers the image of the masked shielded area using the Generator as a fill-in-the-blank problem in which the area masked by the shielded area estimation unit 14 is the missing part.
  • the image superimposing unit 16 superimposes the image of the shielded area inferred by the inference unit 15 on the top view image.
  • the image superimposing unit 16 superimposes the image estimated by the inference unit 15 in a display mode different from that of the top view image so that it can be seen as an invisible region.
  • the different display mode is, for example, translucent coloring of the inferred image.
  • peripheral image generator 1 of the present embodiment has been described above, but the hardware example of the peripheral image generator 1 described above is an ECU provided with a CPU, RAM, ROM, hard disk, communication interface, and the like. ..
  • the peripheral image generation device 1 described above is realized by storing a program having a module that realizes each of the above functions in a RAM or ROM and executing the program by a CPU. Such programs are also included within the scope of this disclosure. Similarly, other embodiments described below can be implemented programmatically.
  • FIG. 3 is a diagram showing the operation of the peripheral image generator 1 according to the first embodiment.
  • the peripheral video generation device 1 synthesizes the video data of the four cameras 20 to generate a top view video (S11). Further, in parallel with this, the peripheral image generator 1 estimates the three-dimensional shape of the object reflected in the image by using the SfM technique for the image data (S12).
  • the peripheral image generation device 1 estimates an invisible shielded area in the top view image by using the information on the three-dimensional shape of the object (S13). Subsequently, the peripheral image generation device 1 infers the image in the shielded region by GAN (S14), and superimposes the inferred image on the top view image (S15).
  • GAN GAN
  • S15 superimposes the inferred image on the top view image
  • the peripheral image generation device 1 of the first embodiment infers an image in a shielded area that is blocked by an object and cannot be seen, and superimposes the inferred image, so that a top view image without discomfort can be displayed. Further, since the inferred image is superimposed in a display mode different from that of the top view image, the driver can be made to recognize that it is an invisible shielded area. As a result, it is possible to avoid the risk that the driver believes in the inferred image and operates the driving. It also has the effect of calling attention to the shielded area where people, motorcycles, etc. may pop out.
  • GAN is used as a means for inferring an image in a shielded area
  • an image may be inferred by a method other than GAN.
  • a variational autoencoder (VAE) or an autoregressive model may be used to infer the image of the shielded region.
  • the peripheral image generator 1 of the present embodiment is an automatic valet parking that parks by automatic driving. This is because in this scene, since the driver does not drive, there is no problem in superimposing the inferred image on the shielded area, so it is important that the image does not give a sense of discomfort.
  • FIG. 4 is a diagram showing the configuration of the peripheral image generation device 2 according to the second embodiment.
  • the peripheral image generation device 2 of the second embodiment includes a detection data acquisition unit 23 that acquires detection data from the LIDAR 22 in addition to the configuration described in the first embodiment.
  • the three-dimensional shape estimation unit 13 estimates the three-dimensional shape of an object around the vehicle by using the detection data acquired from the LIDAR 22.
  • FIG. 5 is a diagram showing the operation of the peripheral image generation device 2 according to the second embodiment.
  • the peripheral video generation device 2 synthesizes the video data of the four cameras 20 to generate a top view video (S21).
  • the peripheral image generator 2 acquires data from LIDAR 22 (S22) and estimates the three-dimensional shape of an object around the vehicle based on the acquired data (S23).
  • the peripheral image generator 2 estimates an invisible shielded area in the top view image using the information on the three-dimensional shape of the object (S24). Subsequently, the peripheral image generation device 2 infers the image in the shielded area by GAN (S25), and superimposes the inferred image on the top view image (S26).
  • the configuration and operation of the peripheral image generator 2 according to the second embodiment have been described above.
  • the peripheral image generation device 2 of the second embodiment can display a top view image without a sense of discomfort, as in the first embodiment. Further, in the second embodiment, the three-dimensional shape of the object can be estimated with high accuracy by using the data acquired from LIDAR22.
  • LIDAR22 for estimating the three-dimensional shape of the object
  • a ranging sensor other than LIDAR22.
  • radar, ultrasonic sonar, millimeter wave radar and the like can be used.
  • FIG. 6 is a diagram showing the configuration of the peripheral image generation device 3 according to the third embodiment.
  • the peripheral image generation device 3 of the third embodiment is different in that the image of the shielded area is not estimated by using deep learning, but is generated by using an image of the environment in which the vehicle is placed.
  • the peripheral image generation device 3 of the third embodiment has a communication unit 24 and communicates with the parking lot management device 30 that manages the parking lot.
  • the parking lot management device 30 includes a storage unit that stores an image of the parking lot being managed. When the parking lot management device 30 is requested to transmit an image of the parking lot by the peripheral image generation device 3 mounted on the vehicle, the parking lot management device 30 transmits the image to the peripheral image generation device 3.
  • the image processing unit 11 of the peripheral image generation device 3 of the third embodiment includes a shielding area image generation unit 25 in place of the inference unit 15 provided by the peripheral image generation device 1 of the first embodiment. ing.
  • the shielded area image generation unit 25 processes the image of the parking lot received from the parking lot management device 30 to generate an image of the shielded area.
  • the shape of the shielded area may be cut out from the image of the parking lot, or the shape of the shielded area may be cut out after the image of the parking lot is filtered to blur the image.
  • FIG. 7 is a diagram showing the operation of the peripheral image generator 3 according to the third embodiment.
  • the peripheral video generation device 3 synthesizes the video data of the four cameras 20 to generate a top view video (S31). Further, in parallel with this, the peripheral image generator 3 estimates the three-dimensional shape of the object reflected in the image by using the SfM technique for the image data (S32).
  • the peripheral image generation device 3 estimates an invisible shielded area in the top view image by using the information on the three-dimensional shape of the object (S33). Subsequently, the peripheral image generation device 3 acquires an image of the parking lot from the parking lot management device 30 (S34), generates an image of the shielded area using the acquired image (S35), and tops the generated image. It is superimposed on the view image (S36).
  • the configuration and operation of the peripheral image generator 3 according to the third embodiment have been described above.
  • the peripheral image generator 3 of the third embodiment can display a top view image without a sense of discomfort, as in the above-described embodiment. Further, in the third embodiment, since the image of the parking lot is used, it is easy to generate the image of the shielded area. Since the shielded area is an area where the video data cannot be acquired by the camera 20, the risk caused by the shielded area can be reduced by displaying the fact that the video data has not been acquired without discomfort.
  • an example of acquiring an image of the parking lot where the vehicle is actually placed is given as an image of the environment where the vehicle is placed, but it is not an image of the parking lot itself where the vehicle is actually placed.
  • an image of an environment of the type of parking lot in which the vehicle is placed may be used to generate an image of the shielded area.
  • the present disclosure is useful as a device for generating a peripheral image of a vehicle, and can be used, for example, to generate a peripheral image of a vehicle.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Biophysics (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Signal Processing (AREA)
  • Mechanical Engineering (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)
  • Closed-Circuit Television Systems (AREA)
  • Traffic Control Systems (AREA)
PCT/JP2020/028542 2019-08-09 2020-07-22 周辺映像生成装置、周辺映像生成方法、およびプログラム Ceased WO2021029203A1 (ja)

Priority Applications (3)

Application Number Priority Date Filing Date Title
CN202080056408.4A CN114206674B (zh) 2019-08-09 2020-07-22 周边影像生成装置、周边影像生成方法以及存储介质
DE112020003788.6T DE112020003788T5 (de) 2019-08-09 2020-07-22 Peripheres-Video-Erzeugungsvorrichtung, Verfahren zur Erzeugung peripherer Videos, und Programm
US17/650,201 US12450784B2 (en) 2019-08-09 2022-02-07 Peripheral video generation device, peripheral video generation method, and storage medium storing program

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2019147985A JP7251401B2 (ja) 2019-08-09 2019-08-09 周辺映像生成装置、周辺映像生成方法、およびプログラム
JP2019-147985 2019-08-09

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/650,201 Continuation US12450784B2 (en) 2019-08-09 2022-02-07 Peripheral video generation device, peripheral video generation method, and storage medium storing program

Publications (1)

Publication Number Publication Date
WO2021029203A1 true WO2021029203A1 (ja) 2021-02-18

Family

ID=74569578

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2020/028542 Ceased WO2021029203A1 (ja) 2019-08-09 2020-07-22 周辺映像生成装置、周辺映像生成方法、およびプログラム

Country Status (5)

Country Link
US (1) US12450784B2 (https=)
JP (1) JP7251401B2 (https=)
CN (1) CN114206674B (https=)
DE (1) DE112020003788T5 (https=)
WO (1) WO2021029203A1 (https=)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11816585B2 (en) * 2018-12-03 2023-11-14 Tesla, Inc. Machine learning models operating at different frequencies for autonomous vehicles
DE102020101637A1 (de) * 2020-01-24 2021-07-29 Bayerische Motoren Werke Aktiengesellschaft Erzeugen einer Draufsicht auf ein Kraftfahrzeug
JP7800559B2 (ja) 2021-11-22 2026-01-16 日本電気株式会社 映像表示システム、映像表示方法、および映像表示装置

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001034898A (ja) * 1999-07-21 2001-02-09 Toyota Central Res & Dev Lab Inc 探査不能領域推定装置及び運転支援システム
JP2010072836A (ja) * 2008-09-17 2010-04-02 Toyota Motor Corp 周辺監視装置
JP2018122627A (ja) * 2017-01-30 2018-08-09 株式会社デンソー 車両制御装置
JP2018142297A (ja) * 2017-02-27 2018-09-13 パナソニック インテレクチュアル プロパティ コーポレーション オブ アメリカＰａｎａｓｏｎｉｃ Ｉｎｔｅｌｌｅｃｔｕａｌ Ｐｒｏｐｅｒｔｙ Ｃｏｒｐｏｒａｔｉｏｎ ｏｆ Ａｍｅｒｉｃａ 情報処理装置およびプログラム

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4600760B2 (ja) * 2005-06-27 2010-12-15 アイシン精機株式会社 障害物検出装置
KR100966288B1 (ko) 2009-01-06 2010-06-28 주식회사 이미지넥스트 주변 영상 생성 방법 및 장치
CN105667518B (zh) * 2016-02-25 2018-07-24 福州华鹰重工机械有限公司 车道检测的方法及装置
US20180178840A1 (en) * 2016-12-28 2018-06-28 Automotive Research & Testing Center Automatic vehicle parking assistance correcting system with instant environmental detection and correcting method thereof
GB2559760B (en) * 2017-02-16 2019-08-28 Jaguar Land Rover Ltd Apparatus and method for displaying information
CN108501949B (zh) 2017-02-27 2022-11-22 松下电器（美国）知识产权公司 信息处理装置以及记录介质
JP7003730B2 (ja) 2018-02-27 2022-01-21 トヨタ自動車株式会社 金属積層造形方法
US10901416B2 (en) * 2018-07-19 2021-01-26 Honda Motor Co., Ltd. Scene creation system for autonomous vehicles and methods thereof

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001034898A (ja) * 1999-07-21 2001-02-09 Toyota Central Res & Dev Lab Inc 探査不能領域推定装置及び運転支援システム
JP2010072836A (ja) * 2008-09-17 2010-04-02 Toyota Motor Corp 周辺監視装置
JP2018122627A (ja) * 2017-01-30 2018-08-09 株式会社デンソー 車両制御装置
JP2018142297A (ja) * 2017-02-27 2018-09-13 パナソニック インテレクチュアル プロパティ コーポレーション オブ アメリカＰａｎａｓｏｎｉｃ Ｉｎｔｅｌｌｅｃｔｕａｌ Ｐｒｏｐｅｒｔｙ Ｃｏｒｐｏｒａｔｉｏｎ ｏｆ Ａｍｅｒｉｃａ 情報処理装置およびプログラム

Also Published As

Publication number Publication date
JP2021029037A (ja) 2021-02-25
US20220156985A1 (en) 2022-05-19
DE112020003788T5 (de) 2022-06-30
US12450784B2 (en) 2025-10-21
CN114206674B (zh) 2025-01-14
CN114206674A (zh) 2022-03-18
JP7251401B2 (ja) 2023-04-04

Similar Documents

Publication Publication Date Title
US20210241495A1 (en) Method and system for reconstructing colour and depth information of a scene
US9215382B1 (en) Apparatus and method for data fusion and visualization of video and LADAR data
US9672432B2 (en) Image generation device
US6570566B1 (en) Image processing apparatus, image processing method, and program providing medium
US8446471B2 (en) Method and system for generating surrounding seamless bird-view image with distance interface
US9633266B2 (en) Image processing apparatus and method that synthesizes an all-round image of a vehicle's surroundings
WO2021029203A1 (ja) 周辺映像生成装置、周辺映像生成方法、およびプログラム
EP3695381B1 (en) Floor detection in virtual and augmented reality devices using stereo images
KR102438078B1 (ko) 어라운드뷰 제공 장치 및 방법
US20140300941A1 (en) Method and apparatus for generating hologram based on multi-view image
US20170132762A1 (en) Method and device for generating stencil matrices and synthesizing parking images
JP2023046746A (ja) 情報処理装置、制御方法、およびプログラム
CN101044390B (zh) 视觉距离测量设备及其用途
Eskandari et al. Observation-based diminished reality: a systematic literature review
JP2021029037A5 (https=)
JP2024022212A (ja) 画像処理装置、画像処理方法およびプログラム
TWI499999B (zh) The 3D ring car image system based on probability calculation and its obtaining method
EP4246966A3 (en) Lenticular image generation
CN119379957A (zh) 作业环境中障碍物可视化方法及装置
Rudzitis et al. Alternative inverse perspective mapping homography matrix computation for ADAS systems using camera intrinsic and extrinsic calibration parameters
CN117201705B (zh) 一种全景图像的获取方法、装置、电子设备及存储介质
US20250029321A1 (en) Image processing method, neural network training method, three-dimensional image display method, image processing system, neural network training system, and three-dimensional image display system
TWM486116U (zh) 以機率方式計算爲基礎之３ｄ環車影像系統
WO2025024226A3 (en) Enhanced user interface generation for parking based on occupancy machine learning models
Hund et al. Integrating Object Detection in Bird-View Systems for Enhancing Safety in Construction Machinery

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: 20851440

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 20851440

Country of ref document: EP

Kind code of ref document: A1

WWG Wipo information: grant in national office

Ref document number: 202080056408.4

Country of ref document: CN