CN109344687A - The obstacle detection method of view-based access control model, device, mobile device - Google Patents
The obstacle detection method of view-based access control model, device, mobile device Download PDFInfo
- Publication number
- CN109344687A CN109344687A CN201810884385.0A CN201810884385A CN109344687A CN 109344687 A CN109344687 A CN 109344687A CN 201810884385 A CN201810884385 A CN 201810884385A CN 109344687 A CN109344687 A CN 109344687A
- Authority
- CN
- China
- Prior art keywords
- mobile device
- barrier
- information
- obstacle
- access control
- 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
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T9/00—Image coding
- G06T9/20—Contour coding, e.g. using detection of edges
-
- 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
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Geometry (AREA)
- Traffic Control Systems (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The present invention relates to the obstacle detection method of view-based access control model, device, mobile devices, are applied to mobile device, mobile device includes image collecting device, and image collecting device is set in mobile device, the realtime graphic on direction of travel for acquiring mobile device；The obstacle detection method of view-based access control model the following steps are included: S1, obtain image acquisition device to mobile device direction of travel on current realtime graphic；S2, view-based access control model positioning are analyzed and processed with map structuring system, to current realtime graphic, obtain the obstacle information on mobile device direction of travel；Obstacle information is the range information of the barrier and mobile device on mobile device direction of travel；S3, mobile device progress avoidance is controlled according to obstacle information.The present invention can be contactless detection barrier, avoid contact with detection, promote the reliability and detection accuracy of mobile device.
Description
Technical field
The present invention relates to robot fields, obstacle detection method, dress more specifically to a kind of view-based access control model
It sets, mobile device.
Background technique
In recent years, sweeper as household electrical appliance in family life using more more and more universal, in the daily work
Various barriers can inevitably be frequently encountered.
Traditional sweeper design mainly uses the presence of collision mode disturbance of perception object, and this mode is after a long time
The precision of path planning when can not only reduce the service life of sweeper, while also will affect its work.
Summary of the invention
The technical problem to be solved in the present invention is that in view of the above drawbacks of the prior art, providing the obstacle of view-based access control model
Object detecting method, device, mobile device.
The technical solution adopted by the present invention to solve the technical problems is: constructing a kind of detection of obstacles side of view-based access control model
Method is applied to mobile device, and the mobile device includes image collecting device, and described image acquisition device is set to the movement
The realtime graphic on direction of travel in equipment, for acquiring the mobile device；
The obstacle detection method of the view-based access control model the following steps are included:
Current realtime graphic on S1, the acquisition collected mobile device direction of travel of described image acquisition device；
S2, view-based access control model positioning are analyzed and processed with map structuring system, to the current realtime graphic, described in acquisition
Obstacle information on mobile device direction of travel；The obstacle information on mobile device direction of travel barrier and institute
State the range information of mobile device；
S3, the mobile device progress avoidance is controlled according to the obstacle information.
Preferably, the step S2 includes:
S21, pretreatment is cut out to the current realtime graphic based on predeterminable area, obtains area-of-interest；
S22, processing is extracted to the area-of-interest using default extraction algorithm, obtained in the area-of-interest
Barrier candidate regions；
S23, according to the barrier candidate regions, determine the candidate regions information of the barrier candidate regions；The candidate regions
Information includes height, width and the area of the barrier candidate regions.
Preferably, the step S22 includes:
S221, image grayscale processing is carried out to the area-of-interest, obtains the ash of barrier in the area-of-interest
Spend image；
S222, the profile of the gray level image of the barrier is handled, obtains the profile of the barrier；
S223, the processing of morphology opening and closing operations is carried out to the profile of the barrier, obtains closing for the barrier profile
Close region；
S224, the enclosed region is handled, obtains the minimum rectangle boundary of the enclosed region, the minimum square
Shape boundary is the barrier candidate regions；
The step S23 includes:
S231, according to the barrier candidate regions, calculate the candidate regions information of the barrier candidate regions.
Preferably, the step S2 further include:
S24, judge whether the candidate regions information meets the first preset condition, if so, step S25 is executed, if it is not, then moving back
Analysis is handled out；
S25, the profile of the barrier is analyzed and processed, obtains the barrier at a distance from the mobile device
Information.
Preferably, the step S25 includes:
S251, the profile of the barrier is encoded, obtains the encoded information of the profile of the barrier；
S252, the institute at current time and in several moment thereafter provided based on the vision positioning and map structuring system
The location information for stating mobile device, the dense reconstruction for carrying out pixel scale to the candidate regions of the barrier is handled, described in acquisition
The depth image of barrier；
S253, coded treatment is carried out to the profile of the depth image of the barrier, obtains the profile of the depth image
Encoded information；
S254, calculate the barrier profile encoded information and the encoded information of the profile of the depth image phase
Like angle value；
S255, judge whether the similarity value meets the second preset condition, if so, step S256 is executed, if it is not, exiting
Analysis processing；
The range information of S256, the output barrier and the mobile device.
Preferably, the similarity value meets the second preset condition are as follows:
The similarity value is greater than preset threshold.
Preferably, the step S3 includes:
S41, all obstacle informations are analyzed and processed, the distance obtained in the obstacle information is minimum
Value；
S42, determination are with described apart from the corresponding barrier of minimum value；
S43, according to it is described with the location information control mobile device apart from the corresponding barrier of minimum value into
Row avoidance.
The present invention also constructs a kind of obstacle detector of view-based access control model, is applied to mobile device, the mobile device
Including image collecting device, described image acquisition device is set in the mobile device, for acquiring the mobile device
Realtime graphic on direction of travel；
The obstacle detector of the view-based access control model includes:
Acquiring unit, it is current on the collected mobile device direction of travel of described image acquisition device for obtaining
Realtime graphic；
Analysis and processing unit for view-based access control model positioning and map structuring system, divides the current realtime graphic
Analysis processing, obtains the obstacle information on the mobile device direction of travel；The obstacle information is mobile device traveling side
The range information of upward barrier and the mobile device；
Control unit carries out avoidance for controlling the mobile device according to the obstacle information.
The present invention also constructs a kind of mobile device, including processor, and the processor is used to executing to be stored in memory
The step of method as described above is realized when computer program.
The present invention also constructs a kind of readable storage medium storing program for executing, is stored thereon with computer program, and the computer program is located
The step of reason device realizes method as described above when executing.
The obstacle detection method for implementing view-based access control model of the invention has the advantages that the present invention can be contactless
Detection barrier, avoid contact with detection, promote the reliability and detection accuracy of mobile device.Moreover, the present invention is based on visions
Obstacle detection method can share a set of image collecting device, nothing with the vision positioning of mobile device and map structuring system
Other auxiliary devices need to additionally be increased, the whole design cost of mobile device can be reduced to the maximum extent.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples, in attached drawing:
Fig. 1 is using mobile device when the detection of obstacles carried out the present invention is based on the obstacle detection method of vision on ground
The real-time scene figure of face forward movement；
Fig. 2 is the flow diagram of the obstacle detection method first embodiment the present invention is based on vision；
Fig. 3 is the flow diagram of the obstacle detection method second embodiment the present invention is based on vision；
Fig. 4 is the flow diagram of barrier candidate regions extracting method of the present invention；
Fig. 5 is the structural schematic diagram of the obstacle detector the present invention is based on vision；
Fig. 6 is the logic diagram of mobile device.
Specific embodiment
For a clearer understanding of the technical characteristics, objects and effects of the present invention, now control attached drawing is described in detail
A specific embodiment of the invention.
In order to solve existing technical problem, the present invention constructs a kind of obstacle detection method of view-based access control model, the party
Method can be applied to mobile device, wherein mobile device includes but is not limited to sweeper.
It is using movement when the detection of obstacles carried out the present invention is based on the obstacle detection method of vision with reference to Fig. 1, Fig. 1
The real-time scene figure that equipment is moved in ground face forward.
The mobile device of the embodiment of the present invention is illustrated by taking sweeper as an example.
As shown in Figure 1, for a sweeper 102 ground 101 forwards 102 movement real-time scene figure.103 be to be mounted on
The image collecting device of 102 direction of travel of sweeper, the image collecting device can be monocular cam.104 be to be placed on ground
A barrier on face 101, the barrier 104 appear in just at this time in the field of front vision region of sweeper 102, wherein
The area of visual field of sweeper 102 is determined by the FOV (field angle) of monocular cam 103.Monocular cam 103 is adopted at current time
The image of collection forms image 301.Further, in Fig. 1,302 be cut out pretreatment stage area-of-interest (ROI,
Region Of Interest), 401 project for barrier, and 303 be the barrier candidate regions for including barrier projection 401, and 304 are
The depth map of barrier candidate regions, 402 be the barrier projection in 304.
As shown in Fig. 2, the obstacle detection method can the present invention provides a kind of obstacle detection method of view-based access control model
To be applied to mobile device, mobile device includes image collecting device, and image collecting device is set in mobile device, for adopting
Collect the realtime graphic on the direction of travel of mobile device.Mobile device includes but is not limited to sweeper (the 102 of such as Fig. 1), image
Acquisition device includes but is not limited to monocular cam shown in FIG. 1.
First embodiment:
Specifically, as shown in Fig. 2, the obstacle detection method of the view-based access control model of the embodiment the following steps are included:
Step S1, obtain image acquisition device to mobile device direction of travel on current realtime graphic.
By taking sweeper as an example, the direction of travel of mobile device is the motion track of sweeper, and it is arranged in sweeper
Monocular cam on direction of travel can acquire the image on its direction of travel in real time.
Wherein, the current realtime graphic on mobile device direction of travel is the Image Acquisition in mobile device moving process
Device is in current time realtime graphic collected.
Step S2, view-based access control model positioning is analyzed and processed with map structuring system, to current realtime graphic, is moved
Obstacle information on equipment direction of travel；Obstacle information is barrier and mobile device on mobile device direction of travel
Range information.
Vision positioning and map structuring system are vSLAM system, which is built in mobile device,
Mobile device can be positioned and be built in real time figure, and the reality in mobile device in moving process using the vSLAM system
When output mobile equipment location information.Wherein, the location information of mobile device includes but is not limited to the coordinate letter of mobile device
Breath, angle information etc..
What needs to be explained here is that obstacle information obtained, i.e. barrier on mobile device direction of travel and shifting
The range information of dynamic equipment includes multiple range informations.Specifically as shown in Figure 1, image collecting device is collected at current time
Current realtime graphic 301 generally comprises multiple barriers (Fig. 1 is that a barrier is illustrated), so through the invention
The step S2 of embodiment can obtain the multiple obstacle distances for being included in current realtime graphic 301 collected of each moment
The range information of mobile device.
Step S3, mobile device is controlled according to obstacle information and carries out avoidance.
Specifically, obtaining the distance between barrier and the mobile device on mobile device direction of travel letter in step s 2
After breath, the mobile route of mobile device can be adjusted according to the distance between each barrier and mobile device information, is avoided
Mobile device collides with barrier.
By applying the present invention, mobile device traveling can be acquired in real time using the monocular vision camera of vSLAM system
Obstructions chart picture on direction is, it can be achieved that contactless disturbance of perception object, and real-time early warning barrier and mobile device are separated by
Distance.And do not need additionally to increase other auxiliary devices, such as pressure, microwave, infrared sensor, the standard of barrier can be realized
Really determine, the whole design cost of mobile device can be reduced to the maximum extent, while detection of obstacles precision can also be improved.
Second embodiment:
As shown in figure 3, the obstacle detection method of the view-based access control model of the embodiment include on the basis of example 1 with
Lower step:
Step S21, pretreatment is cut out to current realtime graphic based on predeterminable area, obtains area-of-interest.
Wherein, predeterminable area can be according to the condition (width of such as mobile device) of mobile device itself and and barrier
Distance determine.
By being cut out pretreatment to current realtime graphic, area-of-interest is obtained, image procossing can be greatly reduced
Data improve image procossing speed, reduce the Capability Requirement to hardware device.For example, it is assumed that current realtime graphic is resolution ratio
For 640 × 480 image, the predeterminable area of mobile device is that 100 × 100 (i.e. mobile device is only it needs to be determined that in its traveling side
The barrier in image that upward size resolution ratio is 640 × 480, so that it may reach avoidance demand), then area-of-interest is big
Small is 100 × 100 images.
S22, processing is extracted to area-of-interest using default extraction algorithm, obtains the barrier in area-of-interest
Candidate regions.
Optionally, carrying out candidate regions extraction process to area-of-interest using default extraction algorithm can be according to following steps
It carries out.
As shown in figure 4, to extract one embodiment of barrier candidate regions using default extraction algorithm:
Step S221, image grayscale processing is carried out to area-of-interest, obtains the grayscale image of barrier in area-of-interest
Picture.
Step S222, the profile of the gray level image of barrier is handled, obtains the profile of barrier.
Step S223, the processing of morphology opening and closing operations, the closed area of acquired disturbance object profile are carried out to the profile of barrier
Domain.
Step S224, enclosed region is handled, obtains the minimum rectangle boundary of enclosed region, minimum rectangle boundary is
Barrier candidate regions.
Step S23, according to barrier candidate regions, the candidate regions information of barrier candidate regions is determined；Candidate regions information includes
Height, width and the area of barrier candidate regions.
Optionally, step S23 includes:
Step S231, according to barrier candidate regions, the candidate regions information of barrier candidate regions is calculated.
Specifically, calculate barrier candidate regions candidate regions information be calculate separately out barrier candidate regions height (h),
Wide (w) and area (a).
Step S24, judge whether candidate regions information meets the first preset condition, if so, step S25 is executed, if it is not, then moving back
Analysis is handled out.
Optionally, the first preset condition are as follows: the height (h) of barrier candidate regions, wide (w) and area (a) are all larger than corresponding
Setting value.The height (h) for hindering phenology constituency, width (w) and the setting value of area (a) of placing obstacles are respectively h0、w0、a0；Then barrier is candidate
Candidate regions information h, w, a in area meet the first preset condition are as follows: h > h0And w > w0And a > a0。
Step S25, the profile of barrier is analyzed and processed, the range information of acquired disturbance object and mobile device.
Preferably, step S25 includes:
Step S251, the profile of barrier is encoded, the encoded information of the profile of acquired disturbance object.
Here, the profile of barrier is the profile of the barrier in barrier candidate regions.
Step S252, view-based access control model positioning is moved with what map structuring system provided at current time and in several moment thereafter
The location information of dynamic equipment, the dense reconstruction for carrying out pixel scale to the candidate regions of barrier are handled, the depth of field of acquired disturbance object
Image.
Step S253, coded treatment is carried out to the profile of the depth image of barrier, obtains the volume of the profile of depth image
Code information.
Here, the profile of depth image is the profile of the barrier in depth image.
Step S254, the similarity of the encoded information of the encoded information of the profile of barrier and the profile of depth image is calculated
Value.
Step S255, judge whether similarity value meets the second preset condition, if so, step S256 is executed, if it is not, exiting
Analysis processing.
Optionally, similarity value meets the second preset condition are as follows: similarity value is greater than preset threshold.
The encoded information of the profile of barrier indicates that the encoded information of the profile of depth image is indicated with C1 with C0, C0 with
The similarity value of C1 is indicated with S, then after obtaining C0 and C1 respectively, the similarity value S of C0 and C1 is first calculated, then by similarity
Value S is compared with preset threshold, judges whether S is greater than preset threshold.Wherein preset threshold can be preset.
Step S256, the range information of barrier and mobile device is exported.
Here, barrier and the range information of mobile device are the depth of field mean value of the barrier in depth image, wherein should
Depth of field mean value be the barrier each pixel to mobile device apart from mean value.
It will of course be understood that ground, when there is multiple barriers in area-of-interest, each barrier can be based on upper
The method of stating is detected, to obtain the range information of each barrier and mobile device.
Further, when there is multiple barriers in area-of-interest, the present invention is based on the obstacle detection methods of vision also
The following steps are included:
Step S41, all obstacle informations are analyzed and processed, obtain obstacle information in apart from minimum value.
Step S42, determination with apart from the corresponding barrier of minimum value.
Step S43, avoidance is carried out according to the location information control mobile device apart from the corresponding barrier of minimum value.
Due on the direction of travel of mobile device, barrier and mobile device corresponding to the minimum value are nearest, most
Urgency with processing.So needing barrier corresponding to selected distance minimum value when there is multiple barriers in area-of-interest
Hinder object, the travelling route of mobile device is adjusted according to the barrier, mobile device is avoided to collide with barrier.
As shown in figure 5, a kind of obstacle detector of view-based access control model has also been constructed in the present invention, it is applied to mobile device,
Mobile device includes image collecting device, and image collecting device is set in mobile device, for acquiring the traveling of mobile device
Realtime graphic on direction
The obstacle detector of the view-based access control model includes:
Acquiring unit 10, for obtain image acquisition device to mobile device direction of travel on current real-time figure
Picture.
Analysis and processing unit 20 is positioned for view-based access control model and is analyzed with map structuring system, to current realtime graphic
Processing obtains the obstacle information on mobile device direction of travel；Obstacle information is the obstacle on mobile device direction of travel
The range information of object and mobile device.
Control unit 30 carries out avoidance for controlling mobile device according to obstacle information.
As shown in fig. 6, a kind of mobile device, including processor has also been constructed in the present invention, the processor is deposited for executing
The step of realizing method as described above when the computer program stored in reservoir.
A kind of readable storage medium storing program for executing has also been constructed in the present invention, is stored thereon with computer program, which is characterized in that the meter
The step of calculation machine program realizes method as described above when being executed by processor.
Above embodiments only technical concepts and features to illustrate the invention, its object is to allow person skilled in the art
Scholar can understand the contents of the present invention and implement accordingly, can not limit the scope of the invention.It is all to be wanted with right of the present invention
The equivalent changes and modifications that range is done are sought, should belong to the covering scope of the claims in the present invention.
It should be understood that for those of ordinary skills, it can be modified or changed according to the above description,
And all these modifications and variations should all belong to the protection domain of appended claims of the present invention.
Claims (10)
1. a kind of obstacle detection method of view-based access control model, which is characterized in that be applied to mobile device, the mobile device includes
Image collecting device, described image acquisition device are set in the mobile device, for acquiring the traveling of the mobile device
Realtime graphic on direction；
The obstacle detection method of the view-based access control model the following steps are included:
Current realtime graphic on S1, the acquisition collected mobile device direction of travel of described image acquisition device；
S2, view-based access control model positioning are analyzed and processed with map structuring system, to the current realtime graphic, obtain the movement
Obstacle information on equipment direction of travel；The obstacle information is barrier and the shifting on mobile device direction of travel
The range information of dynamic equipment；
S3, the mobile device progress avoidance is controlled according to the obstacle information.
2. the obstacle detection method of view-based access control model according to claim 1, which is characterized in that the step S2 includes:
S21, pretreatment is cut out to the current realtime graphic based on predeterminable area, obtains area-of-interest；
S22, processing is extracted to the area-of-interest using default extraction algorithm, obtains the barrier in the area-of-interest
Hinder phenology constituency；
S23, according to the barrier candidate regions, determine the candidate regions information of the barrier candidate regions；The candidate regions information
Height, width and area including the barrier candidate regions.
3. the obstacle detection method of view-based access control model according to claim 2, which is characterized in that the step S22 includes:
S221, image grayscale processing is carried out to the area-of-interest, obtains the grayscale image of barrier in the area-of-interest
Picture；
S222, the profile of the gray level image of the barrier is handled, obtains the profile of the barrier；
S223, the processing of morphology opening and closing operations is carried out to the profile of the barrier, obtains the closed area of the barrier profile
Domain；
S224, the enclosed region is handled, obtains the minimum rectangle boundary of the enclosed region, the minimum rectangle side
Boundary is the barrier candidate regions；
The step S23 includes:
S231, according to the barrier candidate regions, calculate the candidate regions information of the barrier candidate regions.
4. the obstacle detection method of view-based access control model according to claim 3, which is characterized in that the step S2 is also wrapped
It includes:
S24, judge whether the candidate regions information meets the first preset condition, if so, step S25 is executed, if it is not, then exiting point
Analysis processing；
S25, the profile of the barrier is analyzed and processed, obtains the barrier and believes at a distance from the mobile device
Breath.
5. the obstacle detection method of view-based access control model according to claim 4, which is characterized in that the step S25 includes:
S251, the profile of the barrier is encoded, obtains the encoded information of the profile of the barrier；
S252, based on the vision positioning and map structuring system provide at current time and the shifting in several moment thereafter
The location information of dynamic equipment, the dense reconstruction for carrying out pixel scale to the candidate regions of the barrier are handled, and obtain the obstacle
The depth image of object；
S253, coded treatment is carried out to the profile of the depth image of the barrier, obtains the volume of the profile of the depth image
Code information；
S254, calculate the barrier profile encoded information and the depth image profile encoded information similarity
Value；
S255, judge whether the similarity value meets the second preset condition, if so, step S256 is executed, if it is not, exiting analysis
Processing；
The range information of S256, the output barrier and the mobile device.
6. the obstacle detection method of view-based access control model according to claim 5, which is characterized in that the similarity value meets
Second preset condition are as follows:
The similarity value is greater than preset threshold.
7. the obstacle detection method of view-based access control model according to claim 1, which is characterized in that the detection of obstacles side
Method further include:
S41, all obstacle informations are analyzed and processed, obtain in the obstacle information apart from minimum value；
S42, determination are with described apart from the corresponding barrier of minimum value；
S43, it is kept away according to described with the location information control mobile device apart from the corresponding barrier of minimum value
Barrier.
8. a kind of obstacle detector of view-based access control model, which is characterized in that be applied to mobile device, the mobile device includes
Image collecting device, described image acquisition device are set in the mobile device, for acquiring the traveling of the mobile device
Realtime graphic on direction；
The obstacle detector of the view-based access control model includes:
Acquiring unit, it is current real-time on the collected mobile device direction of travel of described image acquisition device for obtaining
Image；
Analysis and processing unit for view-based access control model positioning and map structuring system, carries out at analysis the current realtime graphic
Reason, obtains the obstacle information on the mobile device direction of travel；The obstacle information is on mobile device direction of travel
Barrier and the mobile device range information；
Control unit carries out avoidance for controlling the mobile device according to the obstacle information.
9. a kind of mobile device, which is characterized in that including processor, the processor is for executing the calculating stored in memory
It is realized when machine program such as the step of any one of claim 1-7 the method.
10. a kind of readable storage medium storing program for executing, is stored thereon with computer program, which is characterized in that the computer program is processed
It is realized when device executes such as the step of any one of claim 1-7 the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810884385.0A CN109344687B (en) | 2018-08-06 | 2018-08-06 | Vision-based obstacle detection method and device and mobile device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810884385.0A CN109344687B (en) | 2018-08-06 | 2018-08-06 | Vision-based obstacle detection method and device and mobile device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109344687A true CN109344687A (en) | 2019-02-15 |
| CN109344687B CN109344687B (en) | 2021-04-16 |
Family
ID=65296621
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810884385.0A Active CN109344687B (en) | 2018-08-06 | 2018-08-06 | Vision-based obstacle detection method and device and mobile device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109344687B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110531770A (en) * | 2019-08-30 | 2019-12-03 | 的卢技术有限公司 | One kind being based on improved RRT paths planning method and system |
| CN110658820A (en) * | 2019-10-10 | 2020-01-07 | 北京京东乾石科技有限公司 | Method and device for controlling unmanned vehicle, electronic device and storage medium |
| CN111104933A (en) * | 2020-03-20 | 2020-05-05 | 深圳飞科机器人有限公司 | Map processing method, mobile robot, and computer-readable storage medium |
| CN112171675A (en) * | 2020-09-28 | 2021-01-05 | 深圳市丹芽科技有限公司 | Obstacle avoidance method and device for mobile robot, robot and storage medium |
| CN112308033A (en) * | 2020-11-25 | 2021-02-02 | 珠海市一微半导体有限公司 | Obstacle collision warning method based on depth data and visual chip |
| CN112415532A (en) * | 2020-11-30 | 2021-02-26 | 上海炬佑智能科技有限公司 | Dust detection method, distance detection device, and electronic apparatus |
| CN113242353A (en) * | 2021-03-22 | 2021-08-10 | 帅培林 | Front rod body approximation degree analysis platform |
| CN113873868A (en) * | 2019-06-27 | 2021-12-31 | 株式会社久保田 | Obstacle detection system, agricultural work vehicle, obstacle detection program, storage medium storing obstacle detection program, and obstacle detection method |
| CN114387500A (en) * | 2020-10-16 | 2022-04-22 | 苏州科瓴精密机械科技有限公司 | Image recognition method and system applied to self-walking device, self-walking device and readable storage medium |
| CN114462726A (en) * | 2022-04-14 | 2022-05-10 | 青岛海滨风景区小鱼山管理服务中心 | Intelligent garden management method and system |
| CN115273552A (en) * | 2022-09-19 | 2022-11-01 | 南通立信自动化有限公司 | HMI control system of automobile instrument |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012040644A1 (en) * | 2010-09-24 | 2012-03-29 | Evolution Robotics, Inc. | Systems and methods for vslam optimization |
| CN103411536A (en) * | 2013-08-23 | 2013-11-27 | 西安应用光学研究所 | Auxiliary driving obstacle detection method based on binocular stereoscopic vision |
| CN104182756A (en) * | 2014-09-05 | 2014-12-03 | 大连理工大学 | Method for detecting barriers in front of vehicles on basis of monocular vision |
| CN105843223A (en) * | 2016-03-23 | 2016-08-10 | 东南大学 | Mobile robot three-dimensional mapping and obstacle avoidance method based on space bag of words model |
| CN106855411A (en) * | 2017-01-10 | 2017-06-16 | 深圳市极思维智能科技有限公司 | A kind of robot and its method that map is built with depth camera and obstacle avoidance system |
| CN108230392A (en) * | 2018-01-23 | 2018-06-29 | 北京易智能科技有限公司 | A kind of dysopia analyte detection false-alarm elimination method based on IMU |
-
2018
- 2018-08-06 CN CN201810884385.0A patent/CN109344687B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012040644A1 (en) * | 2010-09-24 | 2012-03-29 | Evolution Robotics, Inc. | Systems and methods for vslam optimization |
| CN103411536A (en) * | 2013-08-23 | 2013-11-27 | 西安应用光学研究所 | Auxiliary driving obstacle detection method based on binocular stereoscopic vision |
| CN104182756A (en) * | 2014-09-05 | 2014-12-03 | 大连理工大学 | Method for detecting barriers in front of vehicles on basis of monocular vision |
| CN105843223A (en) * | 2016-03-23 | 2016-08-10 | 东南大学 | Mobile robot three-dimensional mapping and obstacle avoidance method based on space bag of words model |
| CN106855411A (en) * | 2017-01-10 | 2017-06-16 | 深圳市极思维智能科技有限公司 | A kind of robot and its method that map is built with depth camera and obstacle avoidance system |
| CN108230392A (en) * | 2018-01-23 | 2018-06-29 | 北京易智能科技有限公司 | A kind of dysopia analyte detection false-alarm elimination method based on IMU |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113873868A (en) * | 2019-06-27 | 2021-12-31 | 株式会社久保田 | Obstacle detection system, agricultural work vehicle, obstacle detection program, storage medium storing obstacle detection program, and obstacle detection method |
| CN110531770A (en) * | 2019-08-30 | 2019-12-03 | 的卢技术有限公司 | One kind being based on improved RRT paths planning method and system |
| CN110658820A (en) * | 2019-10-10 | 2020-01-07 | 北京京东乾石科技有限公司 | Method and device for controlling unmanned vehicle, electronic device and storage medium |
| CN111104933A (en) * | 2020-03-20 | 2020-05-05 | 深圳飞科机器人有限公司 | Map processing method, mobile robot, and computer-readable storage medium |
| CN111104933B (en) * | 2020-03-20 | 2020-07-17 | 深圳飞科机器人有限公司 | Map processing method, mobile robot, and computer-readable storage medium |
| CN112171675A (en) * | 2020-09-28 | 2021-01-05 | 深圳市丹芽科技有限公司 | Obstacle avoidance method and device for mobile robot, robot and storage medium |
| CN112171675B (en) * | 2020-09-28 | 2022-06-10 | 深圳市丹芽科技有限公司 | Obstacle avoidance method and device for mobile robot, robot and storage medium |
| CN114387500A (en) * | 2020-10-16 | 2022-04-22 | 苏州科瓴精密机械科技有限公司 | Image recognition method and system applied to self-walking device, self-walking device and readable storage medium |
| CN112308033A (en) * | 2020-11-25 | 2021-02-02 | 珠海市一微半导体有限公司 | Obstacle collision warning method based on depth data and visual chip |
| CN112308033B (en) * | 2020-11-25 | 2024-04-05 | 珠海一微半导体股份有限公司 | Obstacle collision warning method based on depth data and visual chip |
| CN112415532A (en) * | 2020-11-30 | 2021-02-26 | 上海炬佑智能科技有限公司 | Dust detection method, distance detection device, and electronic apparatus |
| CN113242353A (en) * | 2021-03-22 | 2021-08-10 | 帅培林 | Front rod body approximation degree analysis platform |
| CN113242353B (en) * | 2021-03-22 | 2023-11-03 | 启美科技(江苏)有限公司 | Front rod body approximation degree analysis platform |
| CN114462726A (en) * | 2022-04-14 | 2022-05-10 | 青岛海滨风景区小鱼山管理服务中心 | Intelligent garden management method and system |
| CN115273552A (en) * | 2022-09-19 | 2022-11-01 | 南通立信自动化有限公司 | HMI control system of automobile instrument |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109344687B (en) | 2021-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109344687A (en) | The obstacle detection method of view-based access control model, device, mobile device | |
| CN107330925B (en) | Multi-obstacle detection and tracking method based on laser radar depth image | |
| CN110163904A (en) | Object marking method, control method for movement, device, equipment and storage medium | |
| CN109409202A (en) | Robustness method for detecting lane lines based on dynamic area-of-interest | |
| CN111360780A (en) | Garbage picking robot based on visual semantic SLAM | |
| CN102074018B (en) | Depth information-based contour tracing method | |
| JP5023186B2 (en) | Object motion detection system based on combination of 3D warping technique and proper object motion (POM) detection | |
| Almansa-Valverde et al. | Mobile robot map building from time-of-flight camera | |
| CN111104933A (en) | Map processing method, mobile robot, and computer-readable storage medium | |
| KR20130066438A (en) | Image processing apparatus and image processing method | |
| WO2008020598A1 (en) | Subject number detecting device and subject number detecting method | |
| CN112698653A (en) | Robot autonomous navigation control method and system based on deep learning | |
| CN105760846A (en) | Object detection and location method and system based on depth data | |
| KR20080075730A (en) | Method for esrimating location using objectionrecognition of a robot | |
| CN113359692B (en) | Obstacle avoidance method and movable robot | |
| JP2019016116A (en) | Outside recognition device for vehicle | |
| CN110262487B (en) | Obstacle detection method, terminal and computer readable storage medium | |
| CN111552764A (en) | Parking space detection method, device and system, robot and storage medium | |
| JP2017083245A (en) | Clearance limit determination device | |
| McManus et al. | Distraction suppression for vision-based pose estimation at city scales | |
| Engel et al. | Deep object tracking on dynamic occupancy grid maps using rnns | |
| JP2007280387A (en) | Method and device for detecting object movement | |
| Aadi et al. | Proposed real-time obstacle detection system for visually impaired assistance based on deep learning | |
| JP4020982B2 (en) | Moving image processing device | |
| CN111368883B (en) | Obstacle avoidance method based on monocular camera, computing device and storage device |
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 |