CN110147748A - A kind of mobile robot obstacle recognition method based on road-edge detection - Google Patents
A kind of mobile robot obstacle recognition method based on road-edge detection Download PDFInfo
- Publication number
- CN110147748A CN110147748A CN201910390236.3A CN201910390236A CN110147748A CN 110147748 A CN110147748 A CN 110147748A CN 201910390236 A CN201910390236 A CN 201910390236A CN 110147748 A CN110147748 A CN 110147748A
- Authority
- CN
- China
- Prior art keywords
- road
- detection
- mobile robot
- barrier
- existence
- 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.)
- Granted
Links
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
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to artificial intelligence field, specifically a kind of mobile robot obstacle recognition method based on road-edge detection, the specific steps of which are as follows: S1: obtaining boundary line；S2: edge detection；S3: target detection；S4: coordinate value；S5: road barrier domain of the existence calculates；S6: road barrier domain of the existence judgement；There is object in front of the mobile robot that can only be detected compared to traditional obstacle recognition, and for having intersection that can not accurately identify, barrier domain of the existence Ω is found using road-edge detection algorithm, target detection is carried out to the object in image using deep learning network frame, through the invention can be more accurate identify the barrier detected in target in the realtime graphic, intelligence degree is high.
Description
Technical field
The present invention relates to artificial intelligence field, specifically a kind of mobile robot barrier based on road-edge detection is known
Other method.
Background technique
Mobile robot technology and industry were rapidly developing in recent years, and mobile robot application scenarios are also increasingly wider
General, research and application have also extended to agricultural, household, service and security type industry from military and industrial circle.It is moving
Mobile robot research field, detection of obstacles are an important directions.Mobile robot on road when running, place road side
There can be barrier upwards.Barrier can hinder the advance of mobile robot, can collide with mobile robot, cause to move
Mobile robot is impaired or barrier damage, mobile robot only have continuous avoiding obstacles just to arrive at the destination.Therefore it completes
Mobile robot advance in robot barrier analyte detection be very it is necessary to.
Presently, there are the robot barrier object detecting methods based on laser radar information, although laser radar adapts to environment
Property is good, but laser radar can only detecting object, object cannot be identified, therefore can not be with judgment object behavior and kind
Class, and multithreading laser radar price is higher.And for the detection of barrier, ultrasonic wave, millimetre-wave radar these can only
Detect obstacle distance.
Summary of the invention
To solve the above-mentioned problems, the present invention proposes a kind of mobile robot obstacle recognition based on road-edge detection
Method.
A kind of mobile robot obstacle recognition method based on road-edge detection, the specific steps of which are as follows:
S1: obtain boundary line: the image capture device installed in mobile robot obtains realtime graphic, includes realtime graphic
Upper border line lupWith the following boundary line l of realtime graphicdown；
S2: road edge line l edge detection: is obtained by edge detection algorithmroad, and then determine road edge line lroad
Equation yl=Fl(x)；
S3: target detection: target detection is carried out using deep learning network frame realtime graphic, obtains each detection target side
Boundary's frame and its characterization function: f=(x, y, w, h, c)；
S4: the coordinate value point in each detection object boundary frame lower left corner and the lower right corner coordinate value: can be acquired using characterization function f
It Wei not (xL,yL) and (xR,yR)；
S5: road barrier domain of the existence calculates: calculating road edge line lroadWith the realtime graphic upper border line
lupWith the following boundary line l of realtime graphicdownSurround road barrier domain of the existence Ω；
S6: the judgement of road barrier domain of the existence: judge the coordinate value in each detection the object boundary frame lower left corner and the lower right corner
(xL,yL) and (xR,yR) whether be contained in the road barrier domain of the existence Ω and complete obstacle recognition.
The road edge line l of the step 1roadEquation yl=Fl(xl), wherein FlFor piecewise function:
Wherein, ylAnd xlUnit be px, the x, y, w in the characterization function f=(x, y, w, h, c), the unit of h
It is px, the px is pixel unit, and the x is the upper left corner abscissa value of the detection object boundary frame, described
Y be the described detection object boundary frame upper left corner ordinate value, the w is the transverse direction of the detection object boundary frame
Width, the h are the vertical height of the detection object boundary frame, and the c is the detection object boundary frame
Discrimination.
The size of the realtime graphic of the step 1 is that the unit of a*b, a and b are px, and a is institute
The length for the realtime graphic stated, the b are the height of the realtime graphic, the road edge equation F=f (x, y)
The value range of middle x is 0≤x≤a, 0≤x≤b.
The edge detection algorithm satisfaction of the step 2 is able to achieve road edge and completely detects, and the edge detection is calculated
The detection time of method is less than the braking time of mobile robot, and the target detection time of the realtime graphic is less than mobile machine
The braking time of people.
Each detection object boundary frame characterization function f=(x, y, w, h, c) of the step 4 and each detection object boundary frame
On (xL,yL) and (xR,yR) meet following relationship:
With
The road barrier domain of the existence Ω of the step 5 is the two-dimentional point set in the realtime graphic, is met such as
Lower condition:
Ω={ (x, y) q1≤ x < q2,q3≤ x < q4,…,qn-1≤ x < qn,qn≤a；0≤y≤b}.
If (the x in the step 6L,yL) and (xR,yR) be both contained in the road barrier and deposit
In region Ω, then (the x is determinedL,yL) and (xR,yR) belonging to the detection object boundary frame choose
Target object is barrier；
If (the x in the step 6L,yL) it is contained in the described road barrier domain of the existence Ω, it is described
(xR,yR) be not included in the road barrier domain of the existence Ω, then also determine the (xL,yL) and (xR,yR)
The target object that the belonging detection object boundary frame is chosen is barrier；
If (the x in the step 6R,yR) it is contained in the described road barrier domain of the existence Ω, it is described
(xL,yL) be not included in the road barrier domain of the existence Ω, then also determine the (xL,yL) and (xR,yR)
The target object that the belonging detection object boundary frame is chosen is barrier；
If (the x in the step 6L,yL) and (xR,yR) it is not included in the road barrier
Domain of the existence Ω then determines the (xL,yL) and (xR,yR) belonging to the detection object boundary frame choose
Target object be not barrier.
The beneficial effects of the present invention are: having object in front of the mobile robot that can only be detected compared to traditional obstacle recognition
Body, and for having intersection that can not accurately identify, barrier domain of the existence Ω is found using road-edge detection algorithm, benefit
Target detection is carried out to the object in image with deep learning network frame, through the invention can be more accurate identify institute
The barrier detected in target in realtime graphic is stated, intelligence degree is high.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples.
Fig. 1 is realtime graphic schematic diagram of the invention；
Fig. 2 is target detection bounding box schematic diagram of the invention；
Fig. 3 is realtime graphic target detection and road-edge detection schematic diagram of the invention；
Fig. 4 is the distribution schematic diagram of road barrier domain of the existence Ω of the invention in realtime graphic.
Specific embodiment
In order to be easy to understand the technical means, the creative features, the aims and the efficiencies achieved by the present invention, below it is right
The present invention is further described.
As shown in Figures 1 to 4, a kind of mobile robot obstacle recognition method based on road-edge detection, such as Fig. 1 institute
Show, camera is connected with laptop, notebook is mounted in mobile robot, then in front of camera acquisition robot
Realtime graphic, select trained deep learning neural network framework be used as image software detection instrument, in VS2015 ring
It is run under border, includes realtime graphic upper border line l in the realtime graphicupWith the following boundary line l of realtime graphicdown, coordinate origin O
(0,0) at the top left corner apex of the realtime graphic, the specific steps of which are as follows:
S1: obtain boundary line: the image capture device installed in mobile robot is obtained using the image capture device
The scene realtime graphic in front of moveable robot movement is taken, includes realtime graphic upper border line l in the realtime graphicupAnd reality
When image following boundary line ldown:
S2: it edge detection: to the realtime graphic described in step 1 by edge detection algorithm, detects in realtime graphic
Road edge obtains road edge line lroad, and then determine road edge line lroadEquation yl=Fl(x)；
S3: target detection: as shown in Fig. 2, being carried out using deep learning network frame to the realtime graphic described in step 1
Target detection obtains each detection object boundary frame and its characterization function: f=(x, y, w, h, c), respectively detects target in the present embodiment
The x, y, w in function are characterized, tetra- entry value of h is from left to right followed successively by
S4: each detection object boundary frame lower left corner and the right side can coordinate value: be acquired using the characterization function f described in step 3
The coordinate value of inferior horn is respectively (xL,yL) and (xR,yR), the seat in the object boundary frame lower left corner and the lower right corner is respectively detected as shown in Figure 3
Scale value is from left to right successively are as follows:
S5: road barrier domain of the existence calculates: calculating road edge line l described in step 2roadWith it is described real-time
Image upper border line lupWith the following boundary line l of realtime graphicdownRoad barrier domain of the existence Ω is surrounded, this implementation as shown in Figure 4
L in exampleupAnd ldownMeet following equation:
Then the road barrier domain of the existence Ω in the present embodiment meets following equation
S6: road barrier domain of the existence judgement: each detection object boundary frame lower left corner and the right side described in judgment step 4
Coordinate value (the x of inferior hornL,yL) and (xR,yR) whether be contained in the road barrier domain of the existence Ω and complete barrier knowledge
Not.
Judge the coordinate value (x in each detection the object boundary frame lower left corner and the lower right cornerL,yL) and (xR,yR) whether include
In the road barrier domain of the existence, specifically:
A: the coordinate value (135,450) in the bounding box lower left corner and the lower right corner for number 1 detects target tree,
(230,450) bring the area equation of Ω described in step 5 into, judge two coordinates not in road barrier domain of the existence, then
Determining that number 1 detects target tree is not barrier；
B: the coordinate value (360,199) in the bounding box lower left corner and the lower right corner for number 2 detects target tree,
(430,199) bring the area equation of Ω described in step 5 into, judge two coordinates not in road barrier domain of the existence,
Then determining that number 2 detects target tree is not barrier；
C: the coordinate value (390,480) in the bounding box lower left corner and the lower right corner for number 3 detects target Person,
(470,480) bring the area equation of Ω described in step 5 into, judge that two coordinates in road barrier domain of the existence, are then sentenced
It is barrier that number 3, which detects target Person, in fixed；
D: the coordinate value (512,290) in the bounding box lower left corner and the lower right corner for number 4 detects target bicycle,
(605,290) bring the area equation of Ω described in step 5 into, judge two coordinates in road barrier domain of the existence, then
It is barrier that number 4, which detects target bicycle, in judgement；
E: the coordinate value (590,180) in the bounding box lower left corner and the lower right corner for number 5 detects target bus, (670,
180) area equation for bringing Ω described in step 5 into judges two coordinates in road barrier domain of the existence, then in judgement
It is barrier that number 5, which detects target bus,；
F: the coordinate value (610,435) in the bounding box lower left corner and the lower right corner for number 6 detects target Person,
(685,435) bring the area equation of Ω described in step 5 into, judge that two coordinates in road barrier domain of the existence, are then sentenced
It is barrier that number 6, which detects target Person, in fixed.
The road edge line l of the step 1roadEquation yl=Fl(xl), wherein FlFor piecewise function:
Wherein, ylAnd xlUnit be px, the x, y, w in the characterization function f=(x, y, w, h, c), the unit of h
It is px, the px is pixel unit, and the x is the upper left corner abscissa value of the detection object boundary frame, described
Y be the described detection object boundary frame upper left corner ordinate value, the w is the transverse direction of the detection object boundary frame
Width, the h are the vertical height of the detection object boundary frame, and the c is the detection object boundary frame
Discrimination.
The road edge line lroadThere can be a plurality of, described road edge line lroadEither straight line can also be with
It is curve.
Have object in front of the mobile robot that can only be detected compared to traditional obstacle recognition, and have intersection i.e. without
For method accurately identifies, barrier domain of the existence Ω is found using road-edge detection algorithm, utilizes deep learning network frame
Target detection is carried out to the object in image, through the invention can be more accurate identify in the realtime graphic detects mesh
Barrier in mark, intelligence degree are high.
The mobile robot of the step 1 is equipped with image processing platform, and the image processing platform includes hardware
Part and software section；Image capture device is the monocular camera after calibration calibration, the coordinate value in the image be with
Pixel p x is the coordinate value of unit, and coordinate origin is in the upper left corner of the realtime graphic.
The size of the realtime graphic is that the unit of a*b, a and b are px, and a is the reality
When image length, the b is the height of the realtime graphic, and x's takes in the road edge equation F=f (x, y)
Value range is 0≤x≤a, 0≤x≤b.
The edge detection algorithm satisfaction is able to achieve road edge and completely detects, the detection of the edge detection algorithm
Time is less than the braking time of mobile robot, and the target detection time of the realtime graphic is less than the braking of mobile robot
Time.
Each detection object boundary frame characterization function f=(x, y, w, h, c) of the step 4 and each detection object boundary frame
On (xL,yL) and (xR,yR) meet following relationship:
With
The road barrier domain of the existence Ω of the step 5 is the two-dimentional point set in the realtime graphic, is met such as
Lower condition:
Ω={ (x, y) q1≤ x < q2,q3≤ x < q4,…,qn-1≤ x < qn,qn≤a；0≤y≤b}.
The realtime graphic detected by edge detection algorithm and the use deep learning network frame carry out
The realtime graphic of target detection is same frame image or the reality that target detection is carried out using deep learning network frame
When image, while also for it is described detected by edge detection algorithm after realtime graphic.
If (the x in the step 6L,yL) and (xR,yR) be both contained in the road barrier and deposit
In region Ω, then (the x is determinedL,yL) and (xR,yR) belonging to the detection object boundary frame choose
Target object is barrier；
If (the x in the step 6L,yL) it is contained in the described road barrier domain of the existence Ω, it is described
(xR,yR) be not included in the road barrier domain of the existence Ω, then also determine the (xL,yL) and (xR,yR)
The target object that the belonging detection object boundary frame is chosen is barrier；
If (the x in the step 6R,yR) it is contained in the described road barrier domain of the existence Ω, it is described
(xL,yL) be not included in the road barrier domain of the existence Ω, then also determine the (xL,yL) and (xR,yR)
The target object that the belonging detection object boundary frame is chosen is barrier；
If (the x in the step 6L,yL) and (xR,yR) it is not included in the road barrier
Domain of the existence Ω then determines the (xL,yL) and (xR,yR) belonging to the detection object boundary frame choose
Target object be not barrier.
The basic principles, main features and advantages of the present invention have been shown and described above.The technology of the industry
Personnel are it should be appreciated that the present invention is not limited to the above embodiments, and what is described in the above embodiment and the description is only the present invention
Principle, without departing from the spirit and scope of the present invention, various changes and improvements may be made to the invention, these variation and
Improvement all fall within the protetion scope of the claimed invention.The claimed scope of the invention is by appended claims and its equivalent
Object defines.
Claims (10)
1. a kind of mobile robot obstacle recognition method based on road-edge detection, it is characterised in that: its specific steps is such as
Under:
S1: obtain boundary line: the image capture device installed in mobile robot obtains realtime graphic, includes realtime graphic top
Boundary line lupWith the following boundary line l of realtime graphicdown；
S2: road edge line l edge detection: is obtained by edge detection algorithmroad, and then determine road edge line lroadSide
Journey yl=Fl(x)；
S3: target detection: target detection is carried out using deep learning network frame realtime graphic, obtains each detection object boundary frame
And its characterization function: f=(x, y, w, h, c)；
S4: coordinate value: it is respectively using the coordinate value that characterization function f can acquire each detection object boundary frame lower left corner and the lower right corner
(xL,yL) and (xR,yR)；
S5: road barrier domain of the existence calculates: calculating road edge line lroadWith the realtime graphic upper border line lupWith
The following boundary line l of realtime graphicdownSurround road barrier domain of the existence Ω；
S6: the judgement of road barrier domain of the existence: judge the coordinate value (x in each detection the object boundary frame lower left corner and the lower right cornerL,
yL) and (xR,yR) whether be contained in the road barrier domain of the existence Ω and complete obstacle recognition.
2. a kind of mobile robot obstacle recognition method based on road-edge detection according to claim 1, special
Sign is: the road edge line l of the step 1roadEquation yl=Fl(xl), wherein FlFor piecewise function:
Wherein, ylAnd xlUnit be px, the x in the characterization function f=(x, y, w, h, c), the unit of y, w, h is
Px, the px are pixel unit, and the x is the upper left corner abscissa value of the detection object boundary frame, and the y is
The upper left corner ordinate value of the detection object boundary frame, the w are the transverse widths of the detection object boundary frame,
The h is the vertical height of the detection object boundary frame, and the c is the identification of the detection object boundary frame
Rate.
3. a kind of mobile robot obstacle recognition method based on road-edge detection according to claim 1, special
Sign is: the size of the realtime graphic of the step 1 is that the unit of a*b, a and b are px, and a is institute
The length for the realtime graphic stated, the b are the height of the realtime graphic, the road edge equation F=f (x, y)
The value range of middle x is 0≤x≤a, 0≤x≤b.
4. a kind of mobile robot obstacle recognition method based on road-edge detection according to claim 1, special
Sign is: the edge detection algorithm satisfaction of the step 2 is able to achieve road edge and completely detects, the edge detection algorithm
Detection time be less than the braking time of mobile robot, target detection time of the realtime graphic is less than mobile robot
Braking time.
5. a kind of mobile robot obstacle recognition method based on road-edge detection according to claim 1, special
Sign is: each detection object boundary frame characterization function f=(x, y, w, h, c) of the step 4 and each detection object boundary frame
On (xL,yL) and (xR,yR) meet following relationship:
With
6. a kind of mobile robot obstacle recognition method based on road-edge detection according to claim 1, special
Sign is: the road barrier domain of the existence Ω of the step 5 is the two-dimentional point set in the realtime graphic, is met as follows
Condition:
Ω=(x, y) | q1≤ x < q2,q3≤ x < q4,…,qn-1≤ x < qn,qn≤a；0≤y≤b}.
7. a kind of mobile robot obstacle recognition method based on road-edge detection according to claim 1, special
Sign is: if (x described in the step 6L,yL) and (xR,yR) it is both contained in the road barrier presence
Region Ω then determines the (xL,yL) and (xR,yR) belonging to the mesh chosen of the detection object boundary frame
Mark object is barrier.
8. a kind of mobile robot obstacle recognition method based on road-edge detection according to claim 1, special
Sign is: if (x described in the step 6L,yL) it is contained in road barrier the domain of the existence the Ω, (xR,
yR) be not included in the road barrier domain of the existence Ω, then also determine the (xL,yL) and (xR,yR) belonging to
In the target object chosen of the detection object boundary frame be barrier.
9. a kind of mobile robot obstacle recognition method based on road-edge detection according to claim 1, special
Sign is: if (x described in the step 6R,yR) it is contained in road barrier the domain of the existence the Ω, (xL,
yL) be not included in the road barrier domain of the existence Ω, then also determine the (xL,yL) and (xR,yR) belonging to
In the target object chosen of the detection object boundary frame be barrier.
10. a kind of mobile robot obstacle recognition method based on road-edge detection according to claim 1, special
Sign is: if (x described in the step 6L,yL) and (xR,yR) be not included in the road barrier and deposit
In region Ω, then (the x is determinedL,yL) and (xR,yR) belonging to the detection object boundary frame choose
Target object is not barrier.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910390236.3A CN110147748B (en) | 2019-05-10 | 2019-05-10 | Mobile robot obstacle identification method based on road edge detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910390236.3A CN110147748B (en) | 2019-05-10 | 2019-05-10 | Mobile robot obstacle identification method based on road edge detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110147748A true CN110147748A (en) | 2019-08-20 |
| CN110147748B CN110147748B (en) | 2022-09-30 |
Family
ID=67595111
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910390236.3A Active CN110147748B (en) | 2019-05-10 | 2019-05-10 | Mobile robot obstacle identification method based on road edge detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110147748B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110696826A (en) * | 2019-10-09 | 2020-01-17 | 北京百度网讯科技有限公司 | Method and device for controlling a vehicle |
| CN110705492A (en) * | 2019-10-10 | 2020-01-17 | 北京北特圣迪科技发展有限公司 | Stage mobile robot obstacle target detection method |
| CN112307989A (en) * | 2020-11-03 | 2021-02-02 | 广州海格通信集团股份有限公司 | Method and device for identifying road surface object, computer equipment and storage medium |
| CN112486172A (en) * | 2020-11-30 | 2021-03-12 | 深圳市普渡科技有限公司 | Road edge detection method and robot |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015024407A1 (en) * | 2013-08-19 | 2015-02-26 | 国家电网公司 | Power robot based binocular vision navigation system and method based on |
| CN109145756A (en) * | 2018-07-24 | 2019-01-04 | 湖南万为智能机器人技术有限公司 | Object detection method based on machine vision and deep learning |
-
2019
- 2019-05-10 CN CN201910390236.3A patent/CN110147748B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015024407A1 (en) * | 2013-08-19 | 2015-02-26 | 国家电网公司 | Power robot based binocular vision navigation system and method based on |
| CN109145756A (en) * | 2018-07-24 | 2019-01-04 | 湖南万为智能机器人技术有限公司 | Object detection method based on machine vision and deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 张永博等: "激光点云在无人驾驶路径检测中的应用", 《测绘通报》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110696826A (en) * | 2019-10-09 | 2020-01-17 | 北京百度网讯科技有限公司 | Method and device for controlling a vehicle |
| CN110696826B (en) * | 2019-10-09 | 2022-04-01 | 北京百度网讯科技有限公司 | Method and device for controlling a vehicle |
| CN110705492A (en) * | 2019-10-10 | 2020-01-17 | 北京北特圣迪科技发展有限公司 | Stage mobile robot obstacle target detection method |
| CN112307989A (en) * | 2020-11-03 | 2021-02-02 | 广州海格通信集团股份有限公司 | Method and device for identifying road surface object, computer equipment and storage medium |
| CN112307989B (en) * | 2020-11-03 | 2024-05-03 | 广州海格通信集团股份有限公司 | Road surface object identification method, device, computer equipment and storage medium |
| CN112486172A (en) * | 2020-11-30 | 2021-03-12 | 深圳市普渡科技有限公司 | Road edge detection method and robot |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110147748B (en) | 2022-09-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110175576B (en) | Driving vehicle visual detection method combining laser point cloud data | |
| CN107045629B (en) | Multi-lane line detection method | |
| US10452931B2 (en) | Processing method for distinguishing a three dimensional object from a two dimensional object using a vehicular system | |
| CN108256446B (en) | Method, device and equipment for determining lane line in road | |
| CN110147748A (en) | A kind of mobile robot obstacle recognition method based on road-edge detection | |
| CN106203398B (en) | A kind of method, apparatus and equipment detecting lane boundary | |
| US9607227B2 (en) | Boundary detection apparatus and boundary detection method | |
| Yuan et al. | Robust lane detection for complicated road environment based on normal map | |
| US9245188B2 (en) | Lane detection system and method | |
| CN110379168B (en) | Traffic vehicle information acquisition method based on Mask R-CNN | |
| CN107014294A (en) | A kind of contact net geometric parameter detection method and system based on infrared image | |
| CN108280450A (en) | A kind of express highway pavement detection method based on lane line | |
| JP2002175535A (en) | Road white line recognizing device | |
| CN113370977A (en) | Intelligent vehicle forward collision early warning method and system based on vision | |
| CN104915642B (en) | Front vehicles distance measuring method and device | |
| Chong et al. | Integrated real-time vision-based preceding vehicle detection in urban roads | |
| JP5874831B2 (en) | Three-dimensional object detection device | |
| CN113642529B (en) | Barrier size prediction system and method based on GA-BP neural network | |
| CN108171695A (en) | A kind of express highway pavement detection method based on image procossing | |
| CN110674674A (en) | Rotary target detection method based on YOLO V3 | |
| CN112198170A (en) | Detection method for identifying water drops in three-dimensional detection of outer surface of seamless steel pipe | |
| Qing et al. | A novel particle filter implementation for a multiple-vehicle detection and tracking system using tail light segmentation | |
| Gaikwad et al. | An improved lane departure method for advanced driver assistance system | |
| KR101723536B1 (en) | Method and Apparatus for detecting lane of road | |
| CN104331708B (en) | A kind of zebra crossing automatic detection analysis method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |