CN109684994A - The fork truck barrier-avoiding method and system of view-based access control model - Google Patents
The fork truck barrier-avoiding method and system of view-based access control model Download PDFInfo
- Publication number
- CN109684994A CN109684994A CN201811573562.XA CN201811573562A CN109684994A CN 109684994 A CN109684994 A CN 109684994A CN 201811573562 A CN201811573562 A CN 201811573562A CN 109684994 A CN109684994 A CN 109684994A
- Authority
- CN
- China
- Prior art keywords
- camera
- frame
- default
- fork truck
- distance
- 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses the fork truck barrier-avoiding methods of view-based access control model, and to solve fork truck avoidance higher cost in the prior art, the relatively narrow problem of investigative range, this method is comprising steps of S1: acquisition fork truck camera obtains the successive image frame of image;S2: the scale feature that object is corresponded in adjacent image frame is obtained respectively;S3: corresponding to the scale feature of object in the adjacent image frame in conjunction with acquisition, calculates separately the distance of interior object of each picture frame to camera;S4: judge to correspond to whether object is less than the distance for corresponding to object to camera in previous frame to the distance of camera in subsequent frame in adjacent image frame;If so, judging to correspond to whether object to the distance of camera is less than default avoidance threshold value in subsequent frame;If being less than default avoidance threshold value, stop fork truck operation.This method carries out image operation on the basis of original camera, does not need to add additional sensor, reduces cost, impact switch and infrared sensor compared with prior art, and investigative range is bigger.
Description
Technical field
The present invention relates to the fork truck barrier-avoiding method of image procossing and sensor technical field more particularly to view-based access control model and it is
System.
Background technique
The avoidance device used on fork truck at present mainly includes that mechanical touching switch, infrared sensor and ultrasound pass
Sensor etc..
Mechanical touching switch is usually mounted to pallet fork head, whether has barrier in the travelling route for judging pallet fork.
When any side touching switch and pallet collide and trigger its movement, then it is judged as that there are barriers.
The reflectivity properties of object are utilized in infrared sensor avoidance.In a certain range, if without barrier, launch
The infrared ray gone gradually weakens because propagation distance is remoter, finally disappears.If there is barrier, infrared ray encounters barrier,
It is reflected to up to sensor and receives head.Sensor detects that this signal then illustrates that there is obstacle in front.
The avoidance principle of ultrasonic sensor with it is infrared similar, simply by piezoelectric ceramic piece generate ultrasonic wave come realize barrier
Hinder detection.Compared with infrared, ultrasound is not easy to receive light interference, but is influenced by object surface shape and humidity etc., surpasses
The reliability of sound is more less better than infrared.
The method of view-based access control model uses less in practice, mainly needs additionally to install additional imaging sensor, and image passes
The cost is relatively high for sensor.
In conclusion needing to design a kind of fork truck barrier-avoiding method without increasing the view-based access control model of additional sensors and being
System, to solve the above problems.
Summary of the invention
In order to solve the problems, such as to propose in background technique, the present invention provides the fork truck barrier-avoiding method of view-based access control model and sides
Method.
In order to achieve the above object, the present invention uses following technical scheme,
The fork truck barrier-avoiding method of view-based access control model, comprising steps of
S1: acquisition fork truck camera obtains the successive image frame of image;
S2: by presetting feature acquisition algorithm, the scale feature that object is corresponded in adjacent image frame is obtained respectively;
S3: according to default conversion method, the scale feature of object is corresponded in the adjacent image frame in conjunction with acquisition, is calculated separately
In each picture frame the object to camera distance;
S4: judge to correspond to whether object to the distance of camera is less than correspondence in previous frame in adjacent image frame in subsequent frame
Object to camera distance;If so, judging to correspond to whether object to the distance of camera is less than default avoidance threshold in subsequent frame
Value, if so, stopping fork truck operation.
Further, step S1 includes:
S11: image information within the vision is preset by the camera acquisition on fork truck;
S12: the successive image frame for the default image information within sweep of the eye that acquisition obtains in real time.
Further, step S2 includes:
S21: by presetting feature acquisition algorithm, corresponding two pairs of default characteristic points in adjacent image frame are obtained;
S22: it according to default scale feature algorithm, calculates separately every in corresponding two pairs of default characteristic points in adjacent image frame
To the scale feature between characteristic point.
Further, step S21 includes:
S211: Hessian matrix is calculated to each point on each picture frame;
S222: it is down-sampled that default classification carried out to each point in each picture frame, generates corresponding scale space;
S223: using default non-maxima suppression algorithm, in conjunction with the Hessian matrix of each point and the corresponding ruler of generation
Space is spent, determines corresponding two pairs of default characteristic points in adjacent image frame.
The fork truck barrier-avoiding method of view-based access control model, comprising steps of
A1: acquisition fork truck camera obtains the successive image frame of image;
A2: by presetting feature acquisition algorithm, the scale that object is corresponded in continuous multiple adjacent image frames is obtained respectively
Feature;
A3: according to default conversion method, corresponding to the scale feature of object in each adjacent image frame in conjunction with acquisition, respectively
Calculate the distance that object to camera is corresponded in each adjacent image frame;
A4: judge multiple adjacent image frames, correspond to the distance of object to camera in each adjacent image frame in subsequent frame
Whether the distance that previous frame in corresponds to object to camera is respectively less than;If so, judging to correspond to object in subsequent frame to camera
Whether distance is less than default avoidance threshold value, if so, stopping fork truck operation.
Further, step A1 includes:
A11: image information within the vision is preset by the camera acquisition on fork truck;
A12: the successive image frame for the default image information within sweep of the eye that acquisition obtains in real time.
Further, step A2 includes:
A21: by presetting feature acquisition algorithm, corresponding two pairs of default features in multiple continuous adjacent image frames are obtained
Point;
A22: according to default scale feature algorithm, it is special to the scale between characteristic point to calculate separately in each picture frame this
Sign.
Further, step A21 includes:
A211: Hessian matrix is calculated to each point on each picture frame;
A222: it is down-sampled that default classification carried out to each point in each picture frame, generates corresponding scale space;
A223: using default non-maxima suppression algorithm, in conjunction with the Hessian matrix of each point and the corresponding ruler of generation
Space is spent, determines corresponding two pairs of default characteristic points in adjacent image frame.
The fork truck obstacle avoidance system of view-based access control model, comprising:
Image capture module obtains the successive image frame of image for acquiring fork truck camera;
Characteristic module is obtained, for obtaining in adjacent image frame correspond to object respectively by presetting feature acquisition algorithm
Scale feature;
Spacing module is calculated, for corresponding to the ruler of object in the adjacent image frame in conjunction with acquisition according to default conversion method
Feature is spent, the distance of interior object of each picture frame to camera is calculated separately;
Judge obstacle avoidance module, it is whether small to the distance of camera for judging to correspond to object in adjacent image frame in subsequent frame
In corresponding to distance of the object to camera in previous frame;If so, judge to correspond in subsequent frame object to camera distance whether
Less than default avoidance threshold value, if so, stopping fork truck operation.
Further, image capture module includes:
Camera presets image information within the vision for obtaining;
Picture frame acquiring unit, the successive image frame of the default image information within sweep of the eye for acquiring acquisition in real time.
The present invention has the following advantages:
(1), imaging sensor is installed additional without additional based on the fork truck barrier-avoiding method of vision, utilize the existing camera shooting of fork truck
Fork truck automatic obstacle avoidance can be realized in head, low in cost;
(2), the image information and default feature obtained based on the fork truck barrier-avoiding method of vision using camera, which is obtained, calculates
Method and default conversion algorithm are now in conjunction with effectively raising the robustness of avoidance.
It (3), can be special by the scale of the correspondence object of multiple adjacent image frames based on the fork truck barrier-avoiding method of vision
Sign variation calculates the variation of object distance camera in multiple adjacent image frames, ensure that the reliability of avoidance.
Detailed description of the invention
Fig. 1 is the fork truck barrier-avoiding method scheme of installation the present invention is based on vision;
Fig. 2 is the fork truck barrier-avoiding method image zooming-out feature schematic diagram the present invention is based on vision;
Fig. 3 is the Image Feature Matching schematic diagram of the fork truck barrier-avoiding method the present invention is based on vision;
Fig. 4 is the fork truck barrier-avoiding method flow chart one the present invention is based on vision;
Fig. 5 is the fork truck barrier-avoiding method flowchart 2 the present invention is based on vision;
Fig. 6 is the fork truck obstacle avoidance system structure chart one the present invention is based on vision.
In figure: 1, camera.
Specific embodiment
Following is a specific embodiment of the present invention in conjunction with the accompanying drawings, technical scheme of the present invention will be further described,
However, the present invention is not limited to these examples.
Embodiment one
Present embodiments provide the fork truck barrier-avoiding method of view-based access control model, as shown in Figures 1 to 4, this method comprising steps of
S1: acquisition fork truck camera obtains the successive image frame of image;
S2: by presetting feature acquisition algorithm, the scale feature that object is corresponded in adjacent image frame is obtained respectively;
S3: according to default conversion method, the scale feature of object is corresponded in the adjacent image frame in conjunction with acquisition, is calculated separately
In each picture frame the object to camera distance;
S4: judge to correspond to whether object to the distance of camera is less than correspondence in previous frame in adjacent image frame in subsequent frame
Object to camera distance;If so, judging to correspond to whether object to the distance of camera is less than default avoidance threshold in subsequent frame
Value, if so, stopping fork truck operation.
Further, step S1 includes:
S11: image information within the vision is preset by the camera acquisition on fork truck;
S12: the consecutive image of the default image information within sweep of the eye of acquisition is acquired in real time by picture frame acquiring unit
Frame.
First by being mounted on fork truck leading portion, optical axis level acquires fork truck work Shi Zhengqian in the camera on ground in real time
The image of side, the camera are the monitoring camera that common frame speed is higher than 60.
Then pass through the successive image frame in the image of the real-time acquisition camera acquisition of picture frame acquiring unit.
Further, step S2 includes:
S21: by presetting feature acquisition algorithm, corresponding two pairs of default characteristic points in adjacent image frame are obtained;
S22: it according to default scale feature algorithm, calculates separately every in corresponding two pairs of default characteristic points in adjacent image frame
To the scale feature between characteristic point.
Further, step S21 includes:
S211: Hessian matrix is calculated to each point on each picture frame in adjacent image frame;
S212: to carrying out in each picture frame in adjacent image frame, default classification is down-sampled, generates corresponding scale space;
S213: using default non-maxima suppression algorithm, corresponding two pairs of default characteristic points in adjacent image frame are determined.
The corresponding object in two adjacent image frames wherein judge by default feature acquisition algorithm, in the present embodiment in advance
If feature acquisition algorithm is Surf algorithm, the specific algorithm for obtaining default characteristic point are as follows:
(1) Hessian matrix is calculated to each point of each picture frame in adjacent image frame;
(2) down-sampled generation scale space is classified to the original image of each picture frame in adjacent image frame;
(3) characteristic point and precise positioning feature point are primarily determined using non-maxima suppression.
By each pixel crossed by hessian matrix disposal compared with 26 points of its three dimensional neighborhood carry out size,
If it is the maximum value or minimum value in this 26 points, remain, as preliminary characteristic point.
Then, the characteristic point of sub-pixel is obtained using linear interpolation method, while also removes those values and is less than centainly
The point of threshold value, increasing extreme value reduces the characteristic point quantity detected, and finally only several feature point of maximum intensity can be detected.
As shown in Figure 2;
(4) the Harr wavelet character in statistical nature vertex neighborhood.I.e. centered on characteristic point, calculating radius is that (S is special to 6s
Sign point where a scale-value) neighborhood in, count 60 degree sector in all the points both horizontally and vertically Haar small echo respond
Summation, and Gauss weight coefficient is assigned to these responses, so that the response contribution close to characteristic point is big, and the sound far from characteristic point
It should contribute small, then the response within the scope of 60 degree is summed to form new vector, traverses entire border circular areas, selects longest vector
Direction be this feature point principal direction.In this way, being calculated one by one by characteristic point, the main side of each characteristic point is obtained
To.
As shown in figure 3, characteristic matching in the present embodiment be by the Euclidean distance between two characteristic points it is i.e. practical away from
From matching degree is determined, Euclidean distance is shorter, the matching degree for representing two characteristic points is better.
The judgement of Hessian trace of a matrix is introduced in Surf algorithm, if the trace of a matrix sign phase of two characteristic points
Together, the two features are represented with the contrast variation on the same direction, if it is different, illustrating the contrast of the two characteristic points
Change direction be it is opposite, even if Euclidean distance be 0, also directly excluded.
Therefore corresponding two pairs of default characteristic points in available adjacent image frame;And according to default scale feature algorithm,
Calculate separately the scale feature in adjacent image frame in corresponding two pairs of default characteristic points between each pair of characteristic point.
And then it can be according in two pairs of default characteristic points corresponding in the adjacent image frame of calculating between each pair of characteristic point
Scale feature calculates the distance of the default characteristic point to camera.
Judge to correspond to whether object to the distance of camera is less than counterpart in previous frame in adjacent image frame in subsequent frame
Body to camera distance;
If so, confirming current fork truck close to the object;
Therefore, to judge to correspond to whether object to the distance of camera is less than default avoidance threshold value in subsequent frame, if so,
Stop fork truck operation.
Using this method, imaging sensor is installed additional without additional, fork truck master can be realized using the existing camera of fork truck
Dynamic avoidance, it is low in cost;The image information and default feature acquisition algorithm that are obtained using camera and default conversion algorithm are existing
In conjunction with effectively raising the robustness of avoidance.
Embodiment two
The fork truck barrier-avoiding method of view-based access control model is present embodiments provided, as shown in Fig. 1 to Fig. 3 and Fig. 5, this method includes
Step:
A1: acquisition fork truck camera obtains the successive image frame of image;
A2: by presetting feature acquisition algorithm, the scale that object is corresponded in continuous multiple adjacent image frames is obtained respectively
Feature;
A3: according to default conversion method, corresponding to the scale feature of object in each adjacent image frame in conjunction with acquisition, respectively
Calculate the distance that object to camera is corresponded in each adjacent image frame;
A4: judge multiple adjacent image frames, correspond to the distance of object to camera in each adjacent image frame in subsequent frame
Whether the distance that previous frame in corresponds to object to camera is respectively less than;If so, judging to correspond to object in subsequent frame to camera
Whether distance is less than default avoidance threshold value, if so, stopping fork truck operation.
Further, step A1 includes:
A11: image information within the vision is preset by the camera acquisition on fork truck;
A12: the successive image frame for the default image information within sweep of the eye that acquisition obtains in real time.
Further, step A2 includes:
A21: by presetting feature acquisition algorithm, corresponding two pairs of default features in multiple continuous adjacent image frames are obtained
Point;
A22: according to default scale feature algorithm, it is special to the scale between characteristic point to calculate separately in each picture frame this
Sign.
Further, step A21 includes:
A211: Hessian matrix is calculated to each point on each picture frame;
A212: it is down-sampled that default classification carried out to each point in each picture frame, generates corresponding scale space;
A213: using default non-maxima suppression algorithm, in conjunction with the Hessian matrix of each point and the corresponding ruler of generation
Space is spent, determines corresponding two pairs of default characteristic points in adjacent image frame.
Based on the fork truck barrier-avoiding method of vision, can be become by the scale feature of the correspondence object of multiple adjacent image frames
Change the variation for calculating object distance camera in multiple adjacent image frames, ensure that the reliability of avoidance.
Embodiment three
The system for present embodiments providing the fork truck avoidance of view-based access control model, as shown in fig. 6, this system includes:
Image capture module obtains the successive image frame of image for acquiring fork truck camera;
Characteristic module is obtained, for obtaining in adjacent image frame correspond to object respectively by presetting feature acquisition algorithm
Scale feature;
Spacing module is calculated, for corresponding to the ruler of object in the adjacent image frame in conjunction with acquisition according to default conversion method
Feature is spent, the distance of interior object of each picture frame to camera is calculated separately;
Judge obstacle avoidance module, it is whether small to the distance of camera for judging to correspond to object in adjacent image frame in subsequent frame
In corresponding to distance of the object to camera in previous frame;If so, judge to correspond in subsequent frame object to camera distance whether
Less than default avoidance threshold value, if so, stopping fork truck operation.
Further, image capture module includes:
Camera presets image information within the vision for obtaining, and is mounted on fork truck leading portion, optical axis level is in ground
Face, direction is towards front;The camera is capable of real-time acquisition the image immediately ahead of when fork truck works.
Picture frame acquiring unit, the successive image frame of the default image information within sweep of the eye for acquiring acquisition in real time.
The image immediately ahead of when fork truck works wherein is obtained using the camera in image capture module, then utilizes image
Frame acquiring unit obtains the successive image frame when the image of preceding camera acquisition.
Then by presetting feature acquisition algorithm, the scale feature that object is corresponded in adjacent image frame is obtained respectively, wherein
It is Surf algorithm that default feature acquisition algorithm is provided in the present embodiment;
After obtaining the scale feature for corresponding to object in adjacent image frame, according to default conversion method, in conjunction with the adjacent of acquisition
The scale feature that object is corresponded in picture frame calculates separately the distance of interior object of each picture frame to camera;
And judge to correspond to whether object to the distance of camera is less than correspondence in previous frame in adjacent image frame in subsequent frame
Object to camera distance;If so, judging to correspond to whether object to the distance of camera is less than default avoidance threshold in subsequent frame
Value, if so, stopping fork truck operation.
Specific embodiment described herein is only an example for the spirit of the invention.The neck of technology belonging to the present invention
The technical staff in domain can make various modifications or additions to the described embodiments or replace by a similar method
In generation, however, it does not deviate from the spirit of the invention or beyond the scope of the appended claims.
Claims (10)
1. the fork truck barrier-avoiding method of view-based access control model, which is characterized in that comprising steps of
S1: acquisition fork truck camera obtains the successive image frame of image;
S2: by presetting feature acquisition algorithm, the scale feature that object is corresponded in adjacent image frame is obtained respectively;
S3: according to default conversion method, the scale feature of object is corresponded in the adjacent image frame in conjunction with acquisition, is calculated separately each
In picture frame the object to camera distance;
S4: judge corresponding to object in adjacent image frame in subsequent frame corresponds to object to whether the distance of camera is less than in previous frame
To the distance of camera;If so, judge to correspond to whether object to the distance of camera is less than default avoidance threshold value in subsequent frame, if
Whether the distance for corresponding to object to camera in subsequent frame is less than default avoidance threshold value, then stops fork truck operation.
2. the fork truck barrier-avoiding method of view-based access control model according to claim 1, which is characterized in that step S1 includes:
S11: image information within the vision is preset by the camera acquisition on fork truck;
S12: the successive image frame for the default image information within sweep of the eye that acquisition obtains in real time.
3. the fork truck barrier-avoiding method of view-based access control model according to claim 1, which is characterized in that step S2 includes:
S21: by presetting feature acquisition algorithm, corresponding two pairs of default characteristic points in adjacent image frame are obtained;
S22: according to default scale feature algorithm, each pair of spy in corresponding two pairs of default characteristic points is calculated separately in adjacent image frame
Scale feature between sign point.
4. the fork truck barrier-avoiding method of view-based access control model according to claim 3, which is characterized in that step S21 includes:
S211: Hessian matrix is calculated to each point on each picture frame;
S212: it is down-sampled that default classification carried out to each point in each picture frame, generates corresponding scale space;
S213: empty in conjunction with the Hessian matrix of each point and the corresponding scale of generation using default non-maxima suppression algorithm
Between, determine corresponding two pairs of default characteristic points in adjacent image frame.
5. the fork truck barrier-avoiding method of view-based access control model, which is characterized in that comprising steps of
A1: acquisition fork truck camera obtains the successive image frame of image;
A2: by presetting feature acquisition algorithm, the scale feature that object is corresponded in continuous multiple adjacent image frames is obtained respectively;
A3: according to default conversion method, the scale feature of object is corresponded in each adjacent image frame in conjunction with acquisition, is calculated separately
The distance of object to camera is corresponded in each adjacent image frame;
A4: judging multiple adjacent image frames, corresponded in subsequent frame in each adjacent image frame object to camera distance whether
The distance of object to camera is respectively less than corresponded in previous frame;If so, judging the distance for corresponding to object to camera in subsequent frame
Whether default avoidance threshold value is less than, if whether the distance for corresponding to object to camera in subsequent frame is less than default avoidance threshold value,
Stop fork truck operation.
6. the fork truck barrier-avoiding method of view-based access control model according to claim 5, which is characterized in that step A1 includes:
A11: image information within the vision is preset by the camera acquisition on fork truck;
A12: the successive image frame for the default image information within sweep of the eye that acquisition obtains in real time.
7. the fork truck barrier-avoiding method of view-based access control model according to claim 5, which is characterized in that step A2 includes:
A21: by presetting feature acquisition algorithm, corresponding two pairs of default characteristic points in multiple continuous adjacent image frames are obtained;
A22: according to default scale feature algorithm, this is calculated separately in each picture frame to the scale feature between characteristic point.
8. the fork truck barrier-avoiding method of view-based access control model according to claim 7, which is characterized in that step A21 includes:
A211: Hessian matrix is calculated to each point on each picture frame;
A212: it is down-sampled that default classification carried out to each point in each picture frame, generates corresponding scale space;
A213: empty in conjunction with the Hessian matrix of each point and the corresponding scale of generation using default non-maxima suppression algorithm
Between, determine corresponding two pairs of default characteristic points in adjacent image frame.
9. the fork truck obstacle avoidance system of view-based access control model characterized by comprising
Image capture module obtains the successive image frame of image for acquiring fork truck camera;
Characteristic module is obtained, for obtaining the scale for corresponding to object in adjacent image frame respectively by presetting feature acquisition algorithm
Feature;
Spacing module is calculated, the scale for according to default conversion method, corresponding to object in the adjacent image frame in conjunction with acquisition is special
Sign calculates separately the distance of interior object of each picture frame to camera;
Obstacle avoidance module is judged, before judging whether the distance for corresponding to object to camera in subsequent frame in adjacent image frame is less than
The distance of object to camera is corresponded in the frame of face;If so, judging to correspond to whether object to the distance of camera is less than in subsequent frame
Default avoidance threshold value stops fork truck if whether the distance for corresponding to object to camera in subsequent frame is less than default avoidance threshold value
Operation.
10. the fork truck obstacle avoidance system of view-based access control model according to claim 9, which is characterized in that image capture module includes:
Camera presets image information within the vision for obtaining;
Picture frame acquiring unit, the successive image frame of the default image information within sweep of the eye for acquiring acquisition in real time.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811573562.XA CN109684994A (en) | 2018-12-21 | 2018-12-21 | The fork truck barrier-avoiding method and system of view-based access control model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811573562.XA CN109684994A (en) | 2018-12-21 | 2018-12-21 | The fork truck barrier-avoiding method and system of view-based access control model |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109684994A true CN109684994A (en) | 2019-04-26 |
Family
ID=66188095
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811573562.XA Pending CN109684994A (en) | 2018-12-21 | 2018-12-21 | The fork truck barrier-avoiding method and system of view-based access control model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109684994A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021063247A1 (en) * | 2019-09-30 | 2021-04-08 | 北京猎户星空科技有限公司 | Obstacle avoidance method and apparatus, electronic device and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104590573A (en) * | 2014-12-05 | 2015-05-06 | 国网通用航空有限公司 | Barrier avoiding system and method for helicopter |
CN106200672A (en) * | 2016-07-19 | 2016-12-07 | 深圳北航新兴产业技术研究院 | A kind of unmanned plane barrier-avoiding method based on light stream |
CN107031626A (en) * | 2017-03-29 | 2017-08-11 | 华南农业大学 | A kind of fork truck automatic obstacle avoiding system and method |
CN108037768A (en) * | 2017-12-13 | 2018-05-15 | 常州工学院 | Unmanned plane obstruction-avoiding control system, avoidance obstacle method and unmanned plane |
CN108140245A (en) * | 2017-12-25 | 2018-06-08 | 深圳市道通智能航空技术有限公司 | Distance measuring method, device and unmanned plane |
-
2018
- 2018-12-21 CN CN201811573562.XA patent/CN109684994A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104590573A (en) * | 2014-12-05 | 2015-05-06 | 国网通用航空有限公司 | Barrier avoiding system and method for helicopter |
CN106200672A (en) * | 2016-07-19 | 2016-12-07 | 深圳北航新兴产业技术研究院 | A kind of unmanned plane barrier-avoiding method based on light stream |
CN107031626A (en) * | 2017-03-29 | 2017-08-11 | 华南农业大学 | A kind of fork truck automatic obstacle avoiding system and method |
CN108037768A (en) * | 2017-12-13 | 2018-05-15 | 常州工学院 | Unmanned plane obstruction-avoiding control system, avoidance obstacle method and unmanned plane |
CN108140245A (en) * | 2017-12-25 | 2018-06-08 | 深圳市道通智能航空技术有限公司 | Distance measuring method, device and unmanned plane |
Non-Patent Citations (1)
Title |
---|
杨维: "基于单目视觉的多旋翼无人机自主避障硏究", 《万方学位论文》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021063247A1 (en) * | 2019-09-30 | 2021-04-08 | 北京猎户星空科技有限公司 | Obstacle avoidance method and apparatus, electronic device and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107738612B (en) | Automatic parking space detection and identification system based on panoramic vision auxiliary system | |
JP5551595B2 (en) | Runway monitoring system and method | |
JP4919036B2 (en) | Moving object recognition device | |
CN109344687B (en) | Vision-based obstacle detection method and device and mobile device | |
CN102859567B (en) | Device for monitoring vicinity of vehicle | |
US20150161881A1 (en) | In-Vehicle Surrounding Environment Recognition Device | |
TWI540462B (en) | Gesture recognition method and electronic apparatus using the same | |
CN112800860B (en) | High-speed object scattering detection method and system with coordination of event camera and visual camera | |
JP5809751B2 (en) | Object recognition device | |
CN110909705B (en) | Road side parking space sensing method and system based on vehicle-mounted camera | |
JPH06293236A (en) | Travel environment monitoring device | |
CN111462522B (en) | Visual parking space detection method capable of eliminating influence of strong ground reflected light | |
EP1839290A1 (en) | Integrated vehicular system for low speed collision avoidance | |
KR101765556B1 (en) | Apparatus and method for processing the image according to the velocity of automobile | |
JP2014127032A (en) | Outside view recognition device for vehicles | |
CN108375368A (en) | A kind of embedded onboard distance measuring method and its system based on monocular vision | |
CN117237597A (en) | Data processing terminal based on Beidou satellite data and AI graph fusion | |
CN109684994A (en) | The fork truck barrier-avoiding method and system of view-based access control model | |
JP4719996B2 (en) | Object detection device | |
CN104417454B (en) | Apparatus and method for detecting barrier | |
JP2006318064A (en) | Image sensor | |
JP2013244852A (en) | Device, method and program of parking support | |
JP5374549B2 (en) | Vehicle periphery monitoring device | |
JP4887540B2 (en) | Vehicle periphery monitoring device, vehicle, vehicle periphery monitoring program, and vehicle periphery monitoring method | |
CN117406234A (en) | Target ranging and tracking method based on single-line laser radar and vision fusion |
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 |