CN104076363A - Rapid automatic guided vehicle obstacle detection method based on multiple sensors - Google Patents
Rapid automatic guided vehicle obstacle detection method based on multiple sensors Download PDFInfo
- Publication number
- CN104076363A CN104076363A CN201410289872.4A CN201410289872A CN104076363A CN 104076363 A CN104076363 A CN 104076363A CN 201410289872 A CN201410289872 A CN 201410289872A CN 104076363 A CN104076363 A CN 104076363A
- Authority
- CN
- China
- Prior art keywords
- barrier
- white pixel
- guided vehicle
- image
- automatic guided
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/86—Combinations of sonar systems with lidar systems; Combinations of sonar systems with systems not using wave reflection
Abstract
The invention discloses a rapid automatic guided vehicle obstacle detection method based on multiple sensors. The rapid automatic guided vehicle obstacle detection method based on the multiple sensors is characterized by comprising the first step that a binaryzation image of an image collected by the video sensor is obtained, the second step that a left lane line and a right lane light are detected in the binaryzation image through a Hough algorithm, the third step that the minimum safe distance and farthest obstacle detection distance of an automatic guided vehicle are set, the fourth step that the rough mapping relation of the pixel distance between a certain point in the image and the middle point of the bottom line of the image and the actual distance between the video sensor and the point in the image is calibrated, the fifth step that ultrasonic detection starts through the ultrasonic sensor and obstacle information is detected in real time, and the sixth step that the obstacle is detected according to a method used for detecting the obstacle by searching for white pixel dots, and then the obstacle width, position relation of the obstacle and the left lane line and position relation of the obstacle and the right lane line are obtained. By the combination of the video sensor and the ultrasonic sensor, reliability and real-time performance of obstacle recognition of the automatic guided vehicle are improved remarkably.
Description
Technical field
The present invention relates to a kind of dolly obstacle detection method, concrete a kind of is sensor-based automatic guided vehicle barrier method for quick.
Background technology
Along with the automaticity of modern logistics improves constantly and the continuous expansion of scale, the residing environment of automatic guided vehicle becomes increasingly complex, and for the control of automatic guided vehicle, requires also more and more higher.Adopt real-time and the reliability of the automatic guided vehicle of single-sensor more and more not to meet people's requirement.
Detection of obstacles is one of gordian technique of automatic guided vehicle.The detection of obstacles of traditional automatic guided vehicle is generally used the single sensors such as infrared ray, ultrasound wave or radar, and quantity of information that this mode collects is single, reliability is not high.
Above-mentioned patent is different from the technical scheme of this patent, and the occasion of using is also different.
Summary of the invention
The object of the invention is to overcome deficiency of the prior art, a kind of reliability with cognitive disorders thing is provided, improve the automatic guided vehicle barrier method for quick based on multisensor of the real-time detecting.
For achieving the above object, the technical solution adopted in the present invention is:
Automatic guided vehicle barrier method for quick based on multisensor, comprises the following steps:
Step 1: the image of video sensor collection is carried out to pre-service, rim detection and finally obtain binary image;
Step 2: detect left and right lane line by Hough algorithm in binary image;
Step 3: the minimum safe distance of setting automatic guided vehicle and farthest detection of obstacles distance; When described minimum safe distance occurs suddenly for barrier, dolly stops in emergency, and detection of obstacles distance is for the normal investigative range higher limit of dolly farthest;
Step 4: in uncalibrated image, certain point arrives the roughly mapping relations between this actual range to image bottom line mid point pixel distance and video sensor, and these mapping relations are also applicable to smooth road surface;
Step 5: utilize ultrasonic sensor to start ultrasound examination, detect in real time the information of barrier;
Step 6: in the region surrounding at the left and right of binary image lane line, if now ultrasonic sensor has detected in real time barrier and has returned to obstacle distance, so just near the corresponding image of this distance, utilize the method for searching white pixel point detection barrier to detect barrier, obtain barrier width and barrier with the position relationship of left and right lane line; If ultrasonic sensor does not detect barrier, need not search white pixel point.
Further, utilize and search the method that white pixel point detects barrier, comprise the following steps:
Step 6.1: at the doubtful range searching white pixel point of barrier, if search white pixel point, it is launched to connected pixel search;
Step 6.2: the white pixel searching is pressed to their relative positions originally and be stored in a temporary realm;
Step 6.3: if the pixel number being communicated with is not more than the threshold value of regulation, be undesired signal, do not deal with; Then exclude the point in temporary realm, continue search white pixel point; Step 6.4: if the pixel number being communicated with is greater than the threshold value of regulation, to preserving the temporary realm of white pixel point, carry out uniformly-spaced repeatedly horizontal scanning, the coordinate that draws first white pixel point and last white pixel point, then draws barrier width according to the difference of the coordinate of horizontal direction;
Step 6.5: draw after the left-right dots coordinate of barrier width, calculated this straight line of 2 with the intersection point of left and right lane line, can show that according to the coordinate of intersection point barrier follows the position relationship of left and right lane line.
Described threshold value is 50.
Beneficial effect of the present invention: the mode that adopts video sensor and ultrasonic sensor to combine due to this method, by these two kinds of sensors, obtain respectively the information of barrier in environment, then carry out respectively feature extraction, finally according to feature, carry out sending trolley control system to after fuzzy Fusion again.The present invention can obviously improve the reliability of automatic guided vehicle cognitive disorders thing, improves its real-time.
Accompanying drawing explanation
Below in conjunction with the drawings and specific embodiments, the present invention is described in further detail:
Fig. 1 is the process flow diagram of detection barrier of the present invention;
Fig. 2 is temporary realm of the present invention model.
Embodiment
As shown in Figure 1, the automatic guided vehicle barrier method for quick based on multisensor, comprises the following steps:
Step 1: the image of video sensor collection is carried out to pre-service, rim detection and finally obtain binary image;
Step 2: detect left and right lane line by Hough algorithm in binary image;
Step 3: the minimum safe distance of setting automatic guided vehicle and farthest detection of obstacles distance; When described minimum safe distance occurs suddenly for barrier, dolly stops in emergency, and detection of obstacles distance is for the normal investigative range higher limit of dolly farthest;
Step 4: in uncalibrated image, certain point arrives the roughly mapping relations between this actual range to image bottom line mid point pixel distance and video sensor, and these mapping relations are also applicable to smooth road surface;
Step 5: utilize ultrasonic sensor to start ultrasound examination, detect in real time the information of barrier;
Step 6: in the region surrounding at the left and right of binary image lane line, if now ultrasonic sensor has detected in real time barrier and has returned to obstacle distance, so just near the corresponding image of this distance, utilize the method for searching white pixel point detection barrier to detect barrier, obtain barrier width and barrier with the position relationship of left and right lane line; If ultrasonic sensor does not detect barrier, need not search white pixel point.
As shown in Figure 2, the black round dot in figure, represents the white pixel point in actual detection, and 3 horizontal dotted line in Fig. 2 are sweep trace.Utilize and search the method that white pixel point detects barrier, comprise the following steps:
Step 6.1: at the doubtful range searching white pixel point of barrier, if search white pixel point, it is launched to connected pixel search;
Step 6.2: the white pixel searching is pressed to their relative positions originally and be stored in a temporary realm;
Step 6.3: if the pixel number being communicated with is not more than the threshold value 50 of regulation, be undesired signal, do not deal with; Then exclude the point in temporary realm, continue search white pixel point; Step 6.4: if the pixel number being communicated with is greater than the threshold value 50 of regulation, to preserving the temporary realm of white pixel point, carry out uniformly-spaced repeatedly horizontal scanning, the coordinate that draws first white pixel point and last white pixel point, then draws barrier width according to the difference of the coordinate of horizontal direction;
Step 6.5: draw after the left-right dots coordinate of barrier width, calculated this straight line of 2 with the intersection point of left and right lane line, can show that according to the coordinate of intersection point barrier follows the position relationship of left and right lane line.
The above is the preferred embodiment of the present invention; certainly can not limit with this interest field of the present invention; should be understood that; for those skilled in the art; technical scheme of the present invention is modified or is equal to replacement, do not depart from the protection domain of technical solution of the present invention.
Claims (3)
1. the automatic guided vehicle barrier method for quick based on multisensor, is characterized in that: comprise the following steps:
Step 1: the image of video sensor collection is carried out to pre-service, rim detection and finally obtain binary image;
Step 2: detect left and right lane line by Hough algorithm in binary image;
Step 3: the minimum safe distance of setting automatic guided vehicle and farthest detection of obstacles distance; When described minimum safe distance occurs suddenly for barrier, dolly stops in emergency, and detection of obstacles distance is for the normal investigative range higher limit of dolly farthest;
Step 4: in uncalibrated image, certain point arrives the roughly mapping relations between this actual range to image bottom line mid point pixel distance and video sensor, and these mapping relations are also applicable to smooth road surface;
Step 5: utilize ultrasonic sensor to start ultrasound examination, detect in real time the information of barrier;
Step 6: in the region surrounding at the left and right of binary image lane line, if now ultrasonic sensor has detected in real time barrier and has returned to obstacle distance, so just near the corresponding image of this distance, utilize the method for searching white pixel point detection barrier to detect barrier, obtain barrier width and barrier with the position relationship of left and right lane line; If ultrasonic sensor does not detect barrier, need not search white pixel point.
2. the automatic guided vehicle barrier method for quick based on multisensor according to claim 1, is characterized in that: utilize the method for searching white pixel point detection barrier, comprise the following steps:
Step 6.1: at the doubtful range searching white pixel point of barrier, if search white pixel point, it is launched to connected pixel search;
Step 6.2: the white pixel searching is pressed to their relative positions originally and be stored in a temporary realm;
Step 6.3: if the pixel number being communicated with is not more than the threshold value of regulation, be undesired signal, do not deal with; Then exclude the point in temporary realm, continue search white pixel point; Step 6.4: if the pixel number being communicated with is greater than the threshold value of regulation, to preserving the temporary realm of white pixel point, carry out uniformly-spaced repeatedly horizontal scanning, the coordinate that draws first white pixel point and last white pixel point, then draws barrier width according to the difference of the coordinate of horizontal direction;
Step 6.5: draw after the left-right dots coordinate of barrier width, calculated this straight line of 2 with the intersection point of left and right lane line, can show that according to the coordinate of intersection point barrier follows the position relationship of left and right lane line.
3. the automatic guided vehicle barrier method for quick based on multisensor according to claim 1, is characterized in that: described threshold value is 50.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410289872.4A CN104076363A (en) | 2014-06-26 | 2014-06-26 | Rapid automatic guided vehicle obstacle detection method based on multiple sensors |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410289872.4A CN104076363A (en) | 2014-06-26 | 2014-06-26 | Rapid automatic guided vehicle obstacle detection method based on multiple sensors |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104076363A true CN104076363A (en) | 2014-10-01 |
Family
ID=51597749
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410289872.4A Pending CN104076363A (en) | 2014-06-26 | 2014-06-26 | Rapid automatic guided vehicle obstacle detection method based on multiple sensors |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104076363A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105425803A (en) * | 2015-12-16 | 2016-03-23 | 纳恩博（北京）科技有限公司 | Autonomous obstacle avoidance method, device and system |
| CN108536141A (en) * | 2018-03-08 | 2018-09-14 | 杭州晶智能科技有限公司 | A kind of stochastic path planning method of automatic dust absorption machine people |
| CN109062215A (en) * | 2018-08-24 | 2018-12-21 | 北京京东尚科信息技术有限公司 | Robot and barrier-avoiding method, system, equipment and medium are followed based on its target |
| CN109712427A (en) * | 2019-01-03 | 2019-05-03 | 广州小鹏汽车科技有限公司 | A kind of method for detecting parking stalls and device |
| CN109895763A (en) * | 2018-05-17 | 2019-06-18 | 华为技术有限公司 | Parking space's detection method and terminal based on ultrasonic radar |
| CN110864908A (en) * | 2019-11-21 | 2020-03-06 | 中国汽车工程研究院股份有限公司 | Automatic drive car place lane line and gather dolly |
| CN112925326A (en) * | 2021-01-29 | 2021-06-08 | 泗阳县人民医院 | AGV obstacle avoidance method based on data fusion of laser radar and depth camera |
| CN116451981A (en) * | 2023-06-15 | 2023-07-18 | 天津万事达物流装备有限公司 | Logistics shuttle recognition management method based on regional positioning information |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH02114110A (en) * | 1988-10-24 | 1990-04-26 | Kumamoto Techno Porisu Zaidan | Method for detecting three-dimensional object |
| JPH10143665A (en) * | 1996-11-14 | 1998-05-29 | Ohbayashi Corp | Obstacle detecting method of automatically guided vehicle |
| JP2006048238A (en) * | 2004-08-02 | 2006-02-16 | Toshiba Corp | Image processor and image processing program |
| JP2009009331A (en) * | 2007-06-27 | 2009-01-15 | Nissan Motor Co Ltd | White line detector and white line detection method |
| CN102927964A (en) * | 2012-10-24 | 2013-02-13 | 安科智慧城市技术（中国）有限公司 | Distance measuring device and method and vehicle |
| CN103558414A (en) * | 2013-11-04 | 2014-02-05 | 武汉理工大学 | Navigation mark collision detection system |
| CN103723107A (en) * | 2014-01-08 | 2014-04-16 | 曹小兵 | Two-wheeled vehicle intelligent anti-collision system and control method thereof |
| CN103770761A (en) * | 2012-10-24 | 2014-05-07 | 鸿富锦精密工业（深圳）有限公司 | Automatic brake system |
| CN203623524U (en) * | 2013-11-15 | 2014-06-04 | 观致汽车有限公司 | Barrier hinting system for vehicle |
-
2014
- 2014-06-26 CN CN201410289872.4A patent/CN104076363A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH02114110A (en) * | 1988-10-24 | 1990-04-26 | Kumamoto Techno Porisu Zaidan | Method for detecting three-dimensional object |
| JPH10143665A (en) * | 1996-11-14 | 1998-05-29 | Ohbayashi Corp | Obstacle detecting method of automatically guided vehicle |
| JP2006048238A (en) * | 2004-08-02 | 2006-02-16 | Toshiba Corp | Image processor and image processing program |
| JP2009009331A (en) * | 2007-06-27 | 2009-01-15 | Nissan Motor Co Ltd | White line detector and white line detection method |
| CN102927964A (en) * | 2012-10-24 | 2013-02-13 | 安科智慧城市技术（中国）有限公司 | Distance measuring device and method and vehicle |
| CN103770761A (en) * | 2012-10-24 | 2014-05-07 | 鸿富锦精密工业（深圳）有限公司 | Automatic brake system |
| CN103558414A (en) * | 2013-11-04 | 2014-02-05 | 武汉理工大学 | Navigation mark collision detection system |
| CN203623524U (en) * | 2013-11-15 | 2014-06-04 | 观致汽车有限公司 | Barrier hinting system for vehicle |
| CN103723107A (en) * | 2014-01-08 | 2014-04-16 | 曹小兵 | Two-wheeled vehicle intelligent anti-collision system and control method thereof |
Non-Patent Citations (3)
| Title |
|---|
| 刘仕照等: ""基于边界特征的车道标识线检测方法"", 《电子设计工程》 * |
| 唐详燕: ""基于信息融合的道路和障碍物检测方法研究"", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 路燕等: ""基于视觉的物体特征点检测算法研究"", 《液压与气动》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105425803A (en) * | 2015-12-16 | 2016-03-23 | 纳恩博（北京）科技有限公司 | Autonomous obstacle avoidance method, device and system |
| CN108536141A (en) * | 2018-03-08 | 2018-09-14 | 杭州晶智能科技有限公司 | A kind of stochastic path planning method of automatic dust absorption machine people |
| CN109895763A (en) * | 2018-05-17 | 2019-06-18 | 华为技术有限公司 | Parking space's detection method and terminal based on ultrasonic radar |
| CN109062215A (en) * | 2018-08-24 | 2018-12-21 | 北京京东尚科信息技术有限公司 | Robot and barrier-avoiding method, system, equipment and medium are followed based on its target |
| CN109712427A (en) * | 2019-01-03 | 2019-05-03 | 广州小鹏汽车科技有限公司 | A kind of method for detecting parking stalls and device |
| WO2020140410A1 (en) * | 2019-01-03 | 2020-07-09 | 广州小鹏汽车科技有限公司 | Parking space detection method and device |
| CN110864908A (en) * | 2019-11-21 | 2020-03-06 | 中国汽车工程研究院股份有限公司 | Automatic drive car place lane line and gather dolly |
| CN110864908B (en) * | 2019-11-21 | 2020-10-20 | 中国汽车工程研究院股份有限公司 | Automatic drive car place lane line and gather dolly |
| CN112925326A (en) * | 2021-01-29 | 2021-06-08 | 泗阳县人民医院 | AGV obstacle avoidance method based on data fusion of laser radar and depth camera |
| CN112925326B (en) * | 2021-01-29 | 2022-04-08 | 泗阳县人民医院 | AGV obstacle avoidance method based on data fusion of laser radar and depth camera |
| CN116451981A (en) * | 2023-06-15 | 2023-07-18 | 天津万事达物流装备有限公司 | Logistics shuttle recognition management method based on regional positioning information |
| CN116451981B (en) * | 2023-06-15 | 2023-08-18 | 天津万事达物流装备有限公司 | Logistics shuttle recognition management method based on regional positioning information |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104076363A (en) | Rapid automatic guided vehicle obstacle detection method based on multiple sensors | |
| EP3208635A1 (en) | Vision algorithm performance using low level sensor fusion | |
| US9818301B2 (en) | Lane correction system, lane correction apparatus and method of correcting lane | |
| KR102178433B1 (en) | Auto emergency braking system and method for recognizing pedestrian of the same | |
| US11014566B2 (en) | Object detection apparatus | |
| CN102428385B (en) | Object detecting device | |
| JP6361366B2 (en) | Object recognition device | |
| US20170053533A1 (en) | Object Recognition Apparatus and Vehicle Travel Controller Using Same | |
| US20160104047A1 (en) | Image recognition system for a vehicle and corresponding method | |
| JP6468136B2 (en) | Driving support device and driving support method | |
| KR101968349B1 (en) | Method for detecting lane boundary by visual information | |
| US9665781B2 (en) | Moving body detection device and moving body detection method | |
| CN110386065B (en) | Vehicle blind area monitoring method and device, computer equipment and storage medium | |
| KR101637716B1 (en) | Apparatus and method for recognizing position of obstacle in vehicle | |
| JP6396714B2 (en) | Object recognition device | |
| KR101176693B1 (en) | Method and System for Detecting Lane by Using Distance Sensor | |
| US9594965B2 (en) | Lane boundary lane recognition device and computer-readable storage medium storing program for recognizing lane boundary lines on roadway | |
| CN107097794B (en) | System and method for detecting lane line of road | |
| CN105460009A (en) | Automobile control method and device | |
| Sehestedt et al. | Robust lane detection in urban environments | |
| US10268204B2 (en) | Cross traffic detection using cameras | |
| JP6557923B2 (en) | On-vehicle radar device and area detection method | |
| CN108106617A (en) | A kind of unmanned plane automatic obstacle-avoiding method | |
| KR20150096924A (en) | System and method for selecting far forward collision vehicle using lane expansion | |
| CN110659548A (en) | Vehicle and target detection method and device thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20141001 |
|
| RJ01 | Rejection of invention patent application after publication |