WO2020259284A1 - Procédé et dispositif de détection d'obstacle - Google Patents
Procédé et dispositif de détection d'obstacle Download PDFInfo
- Publication number
- WO2020259284A1 WO2020259284A1 PCT/CN2020/095278 CN2020095278W WO2020259284A1 WO 2020259284 A1 WO2020259284 A1 WO 2020259284A1 CN 2020095278 W CN2020095278 W CN 2020095278W WO 2020259284 A1 WO2020259284 A1 WO 2020259284A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- obstacle
- road condition
- image
- information
- roi
- Prior art date
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 119
- 238000000034 method Methods 0.000 claims abstract description 99
- 238000012545 processing Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 13
- 238000003709 image segmentation Methods 0.000 claims description 12
- 230000005856 abnormality Effects 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 description 21
- 238000005516 engineering process Methods 0.000 description 17
- 230000006870 function Effects 0.000 description 15
- 230000000007 visual effect Effects 0.000 description 11
- 230000002093 peripheral effect Effects 0.000 description 10
- 238000004891 communication Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000013528 artificial neural network Methods 0.000 description 7
- 230000003287 optical effect Effects 0.000 description 7
- 239000000284 extract Substances 0.000 description 6
- 238000003384 imaging method Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 230000004888 barrier function Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 238000013500 data storage Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 2
- 238000004220 aggregation Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 239000002253 acid Substances 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 229910001416 lithium ion Inorganic materials 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
Definitions
- the present application provides an obstacle detection method and device to expand the detection range of obstacle detection, thereby improving the accuracy of obstacle detection.
- the first device can obtain at least one first obstacle and at least one second obstacle, thereby expanding the detection range of obstacle detection, which can detect common obstacles. It can also detect uncommon obstacles, thereby improving the accuracy of obstacle detection and facilitating the design of subsequent obstacle avoidance control algorithms. Further, since the detection of obstacles in the road condition image is pixel-level detection, the obtained descriptions of the first obstacle and the second obstacle are also pixel-level descriptions, so compared to other obstacle detection methods, the detection range is wider .
- the first device detects the first part of the road condition image by the second image recognition method, including: the first device determines the region of interest (ROI) in the first part ; The first device detects the ROI through the second image recognition method.
- ROI region of interest
- the above-mentioned ROI may be used as a detection area of the second-level image recognition, so that the first device can obtain at least one second obstacle by detecting the ROI.
- the ROI includes an upper boundary, a lower boundary, a left boundary, and/or a right boundary; accordingly, the above method further includes: the first device acquires scene information, the scene information corresponding to the current driving Scene; then, the first device obtains the ROI from the first part, including at least one of the following: the first device scans the pixels of the first part line by line to determine the upper boundary of the ROI; the first device determines the ROI according to the scene information Lower boundary; the first device scans the pixels of the first part column by column to determine the left boundary and/or right boundary of the ROI.
- anomaly detection algorithms may include spatiotemporal autoencoder-based detection algorithms, saliency detection algorithms, and the like.
- the first device combines the results of the first-level image recognition and the results of the second-level image recognition to jointly determine the obstacles in the road condition image, and remove at least one first obstacle from the at least one second obstacle Part or all of the, so as to determine the obstacles not detected by the first-level image recognition.
- the ROI includes an upper boundary, a lower boundary, a left boundary, and/or a right boundary; the processing module is also used to obtain scene information, which corresponds to the current driving scene; and, processing The module is specifically used to perform one or more of the following: scan the pixels of the first part line by line to determine the upper boundary of the ROI; determine the lower boundary of the ROI according to the scene information; scan the pixels of the first part column by column , Determine the left boundary and/or right boundary of the ROI.
- the camera device is a monocular camera
- the scene information includes speed parameters and/or shooting parameters of the monocular camera.
- FIG. 4 is a schematic diagram of the boundary of the ROI in an embodiment of the application.
- the power supply 101 may be configured to provide power to some or all of the components of the vehicle 100.
- the power source 110 may include, for example, a rechargeable lithium ion or lead-acid battery.
- one or more battery packs may be configured to provide power.
- Other power supply materials and configurations are also possible.
- the power supply 110 and the energy source 113 may be implemented together.
- the second image recognition method is a saliency detection algorithm.
- the training data can be calibrated according to the foreground and background, and the calibration data can be learned in a supervised learning manner to obtain a saliency detection model.
- the first device inputs the road surface data with obstacles, that is, the first part of the road condition image into the saliency detection model, which can calibrate the obstacles in the first part in the foreground. Calibrate in the background to determine the position of the second obstacle.
- the first device may extract the ROI by determining the boundary of the ROI.
- the ROI may include an upper boundary, a lower boundary, a left boundary, and/or a right boundary.
- the first device may also output the obstacle information to the second device according to the correspondence between the second device and the obstacle information.
- FIG. 6 is a schematic structural diagram of the computing device in an embodiment of the application.
- the computing device 600 may include: processing The processor 601 and the communication interface 602, and the processor 601 may be used to support the computing device 600 to implement the functions involved in the foregoing embodiments.
- the processor 601 may obtain the road condition images collected by the camera device through the communication interface 602.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
L'invention concerne un procédé et un dispositif de détection d'obstacle, apte à être appliqué à une caméra embarquée ou à un dispositif de capture d'image embarqué pour étendre la plage de détection de la détection d'obstacle de façon à améliorer la précision de la détection d'obstacle, et se rapportant au domaine de la conduite automatique ou de la conduite intelligente. Le procédé peut comprendre les étapes suivantes : un premier dispositif obtient une image de l'état de la route au moyen d'un dispositif de capture d'image (S201) ; le premier dispositif détermine, en fonction de l'image de l'état de la route, au moins un premier obstacle et une région pouvant être parcourue au moyen d'un premier procédé de reconnaissance d'image (S202), la région pouvant être parcourue correspondant à une première partie de l'image de l'état de la route ; et le premier dispositif détermine, en fonction de la première partie de l'image de l'état de la route, au moins un second obstacle au moyen d'un second procédé de reconnaissance d'image. Le procédé est utilisé pour la détection d'obstacles lors d'une conduite auxiliaire ou d'une conduite automatique.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910567635.2 | 2019-06-27 | ||
CN201910567635.2A CN112149460A (zh) | 2019-06-27 | 2019-06-27 | 一种障碍物检测方法及装置 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2020259284A1 true WO2020259284A1 (fr) | 2020-12-30 |
Family
ID=73868709
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2020/095278 WO2020259284A1 (fr) | 2019-06-27 | 2020-06-10 | Procédé et dispositif de détection d'obstacle |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN112149460A (fr) |
WO (1) | WO2020259284A1 (fr) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115147838A (zh) * | 2022-06-30 | 2022-10-04 | 小米汽车科技有限公司 | 图像处理方法、装置、车辆、介质及程序产品 |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112706764A (zh) * | 2020-12-30 | 2021-04-27 | 潍柴动力股份有限公司 | 一种主动防碰撞预警方法、装置、设备和存储介质 |
CN112793567A (zh) * | 2021-01-14 | 2021-05-14 | 史鹏飞 | 一种基于路况检测的辅助驾驶方法及系统 |
TWI766560B (zh) * | 2021-01-27 | 2022-06-01 | 國立臺灣大學 | 結合語義分割與光達點雲之物件辨識與測距系統 |
CN113011255B (zh) * | 2021-02-05 | 2024-01-16 | 北京中科慧眼科技有限公司 | 基于rgb图像的路面检测方法、系统和智能终端 |
CN114155447B (zh) * | 2021-12-02 | 2022-06-24 | 北京中科智易科技有限公司 | 人工智能大数据采集系统 |
CN116612194B (zh) * | 2023-07-20 | 2023-10-20 | 天津所托瑞安汽车科技有限公司 | 一种位置关系确定方法、装置、设备及存储介质 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105216797A (zh) * | 2015-08-21 | 2016-01-06 | 奇瑞汽车股份有限公司 | 超车方法及系统 |
US20170060132A1 (en) * | 2015-08-31 | 2017-03-02 | Korea University Research And Business Foundation | Method for detecting floor obstacle using laser range finder |
CN107563256A (zh) * | 2016-06-30 | 2018-01-09 | 北京旷视科技有限公司 | 辅助驾驶信息产生方法及装置、辅助驾驶系统 |
CN107953827A (zh) * | 2016-10-18 | 2018-04-24 | 杭州海康威视数字技术股份有限公司 | 一种车辆盲区预警方法及装置 |
CN109070882A (zh) * | 2016-11-28 | 2018-12-21 | 忠北国立大学产学合作基金会 | 利用摄像头影像的行驶信息提供方法及装置 |
-
2019
- 2019-06-27 CN CN201910567635.2A patent/CN112149460A/zh active Pending
-
2020
- 2020-06-10 WO PCT/CN2020/095278 patent/WO2020259284A1/fr active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105216797A (zh) * | 2015-08-21 | 2016-01-06 | 奇瑞汽车股份有限公司 | 超车方法及系统 |
US20170060132A1 (en) * | 2015-08-31 | 2017-03-02 | Korea University Research And Business Foundation | Method for detecting floor obstacle using laser range finder |
CN107563256A (zh) * | 2016-06-30 | 2018-01-09 | 北京旷视科技有限公司 | 辅助驾驶信息产生方法及装置、辅助驾驶系统 |
CN107953827A (zh) * | 2016-10-18 | 2018-04-24 | 杭州海康威视数字技术股份有限公司 | 一种车辆盲区预警方法及装置 |
CN109070882A (zh) * | 2016-11-28 | 2018-12-21 | 忠北国立大学产学合作基金会 | 利用摄像头影像的行驶信息提供方法及装置 |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115147838A (zh) * | 2022-06-30 | 2022-10-04 | 小米汽车科技有限公司 | 图像处理方法、装置、车辆、介质及程序产品 |
CN115147838B (zh) * | 2022-06-30 | 2023-08-29 | 小米汽车科技有限公司 | 图像处理方法、装置、车辆、介质及程序产品 |
Also Published As
Publication number | Publication date |
---|---|
CN112149460A (zh) | 2020-12-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2020259284A1 (fr) | Procédé et dispositif de détection d'obstacle | |
WO2021227645A1 (fr) | Procédé et dispositif de détection de cible | |
CN112665556B (zh) | 使用被动和主动测量生成场景的三维地图 | |
US10671860B2 (en) | Providing information-rich map semantics to navigation metric map | |
US10489686B2 (en) | Object detection for an autonomous vehicle | |
JP2021509238A (ja) | ダイナミックレンジを拡大するための複数の動作モード | |
CN107389084B (zh) | 行车路径规划方法及存储介质 | |
US20170359561A1 (en) | Disparity mapping for an autonomous vehicle | |
US11970186B2 (en) | Arithmetic operation system for vehicles | |
WO2023092451A1 (fr) | Procédé et appareil permettant de prédire une voie praticable | |
KR20210089588A (ko) | 신호등 검출을 위한 시스템들 및 방법들 | |
CN110647801A (zh) | 设置感兴趣区域的方法、装置、存储介质及电子设备 | |
KR20220012804A (ko) | 이미지 시맨틱스 네트워크로부터의 단안 3d 대상체 검출 | |
US20230237783A1 (en) | Sensor fusion | |
US20210370832A1 (en) | Data processing methods, devices, and apparatuses, and movable platforms | |
CN115718304A (zh) | 目标对象检测方法、装置、车辆及存储介质 | |
CN116137655A (zh) | 用于环绕视图增强的智能车辆系统和控制逻辑 | |
Gogineni | Multi-sensor fusion and sensor calibration for autonomous vehicles | |
CN114084129A (zh) | 一种基于融合的车辆自动驾驶控制方法及系统 | |
JP6827391B2 (ja) | 車両制御装置、車両制御方法、およびプログラム | |
US20220120568A1 (en) | Electronic device for vehicle, and method of operating electronic device for vehicle | |
US20240096109A1 (en) | Automatic lane marking extraction and classification from lidar scans | |
Jarnea et al. | Advanced driver assistance system for overtaking maneuver on a highway | |
EP4060373A2 (fr) | Détection multispectrale d'objets par imagerie thermique | |
CN115082886B (zh) | 目标检测的方法、装置、存储介质、芯片及车辆 |
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: 20831323 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20831323 Country of ref document: EP Kind code of ref document: A1 |