CN109579863A - Unknown topographical navigation system and method based on image procossing - Google Patents
Unknown topographical navigation system and method based on image procossing Download PDFInfo
- Publication number
- CN109579863A CN109579863A CN201811522084.XA CN201811522084A CN109579863A CN 109579863 A CN109579863 A CN 109579863A CN 201811522084 A CN201811522084 A CN 201811522084A CN 109579863 A CN109579863 A CN 109579863A
- Authority
- CN
- China
- Prior art keywords
- map
- road
- unit
- image
- camera
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
- G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- 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
- 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
Abstract
The unknown topographical navigation system based on image procossing that the present invention provides a kind of, including road condition acquiring module, map reconstructed module and navigation module, road condition acquiring module include monocular vision camera and image transmitting unit；Map reconstructed module includes image processing unit and map reconfiguration unit；Navigation module includes movement instruction unit and path planning unit, wherein, image transmitting unit sends camera local road conditions image collected in real time to image processing unit, image processing unit extracts the Road feature in local road conditions, map reconfiguration unit constantly reconstructs map until global map is completed in reconstruct according to extracted Road feature, and the movement instruction unit issues movement instruction information to mobile platform according to the map of reconstruct.The present invention also provides a kind of air navigation aids based on above system.Navigation share system for unknown landform of the invention, have the characteristics that it is of simple structure and low cost, be easily achieved study upgrading.
Description
Technical field
This application involves field in intelligent robotics, specifically but not exclusively, are related to a kind of sharing based on image procossing
Unknown topographical navigation system and method.
Background technique
Navigation system based on image procossing is the industry having a extensive future, and wherein mobile robot is producing
It is had been widely used in the multiple fields such as manufacture field, logistics field, scientific research.And computer computation ability is substantially
Promoted but also processing the collected abundant information of visual sensor efficiency greatly promoted, pass through vision auxiliary movement
The navigation system of robot has obtained the extensive concern of people, such as in various known or unknown scene, using monocular or
Binocular vision come help mobile robot complete automatic obstacle avoiding even path planning task.
However, mobile robot will realize that automatic obstacle avoiding or path planning need to explore in advance in unknown landform,
It can determine that the distribution of obstacle in the landform.
Summary of the invention
In order to solve the problems, such as that path planning needs to explore in advance in unknown landform, the present invention provides one kind to be based on image
The unknown topographical navigation system and method for processing has the characteristics that of simple structure and low cost and is easily achieved study upgrading.
According to an aspect of the present invention, a kind of unknown topographical navigation system based on image procossing, the navigation system are provided
On a mobile platform, the navigation system includes road condition acquiring module, map reconstructed module and navigation module for system installation,
The road condition acquiring module includes monocular vision camera and image transmitting unit；
The map reconstructed module includes image processing unit and map reconfiguration unit；
The navigation module includes movement instruction unit,
Wherein, described image transmission unit sends the camera local road conditions image collected in real time to described image
Processing unit, described image processing unit extract the Road feature in local road conditions, and the map reconfiguration unit is according to institute
The Road feature of extraction constantly reconstructs map until global map is completed in reconstruct, and the movement instruction unit is according to reconstruct
Map issues movement instruction information to the mobile platform.
Further, described image processing unit is obtained by Threshold segmentation, edge detection and accumulated probability Hough transformation
The extraction of Road feature is realized in position of the Road profile endpoint in imaging plane in local road conditions.
Further, the map reconfiguration unit is according to monocular vision image-forming principle, by the road line wheel in local road conditions
Position of the wide endpoint in imaging plane is converted to the position relative to camera, and position of the combining camera in map, obtains
The actual position of Road profile endpoint constantly reconstructs map according to the actual position of Road profile endpoint later, until
Global map is completed in reconstruct.
Further, the map reconstructed module further includes the motion state and map weight of mobile platform described in real-time display
The graphics interface unit of structure situation.
Further, the navigation module further includes the path rule that path optimization is carried out according to the global map that reconstruct is completed
Unit is drawn, the path planning unit is found out in the global map of reconstruct using dijkstra's algorithm from the most short of origin-to-destination
Path.
Further, described image transmission unit includes serial communication and wireless LAN communication, and the serial communication will
For the image transmitting of camera acquisition to WiFi module, the image transmitting that wireless LAN communication receives WiFi module gives map weight
Model block.
According to another aspect of the present invention, a kind of method for carrying out unknown topographical navigation using above system is additionally provided,
Characterized by comprising the following steps:
S01: monocular vision camera calibration is carried out, the focal length and attitude parameter of camera are sought；
S02: camera follows mobile platform to acquire local road conditions image in real time from the off, and image processing unit is to acquisition
To local road conditions image handled, obtain the imaging position of the Road profile endpoint of local road conditions；
S03: by the imaging position of Road profile endpoint obtained in step S02, in conjunction with the camera sought in step S01
Focal length and attitude parameter, the actual position of Road profile endpoint is calculated according to monocular vision imaging model；
S04: map is constantly reconstructed according to the actual position of Road profile endpoint obtained in step S03, will be reconstructed
Map carries out rasterizing, the value of grid represent in the grid whether P Passable, establish grid matrix according to these grid point values；
S05: judging whether mobile platform reaches fork on the road by the grid matrix that step S04 is established, when not reaching point
When in cross road mouth, the instruction of straight trip is generated to mobile platform；Backtracking method time when reaching in fork on the road, according to depth-first
Each outlet of the fork on the road is gone through, and generates the instruction of corresponding steering to mobile platform；
S06: when mobile platform is not reached home, step S02 to step S05 is repeated；When mobile platform is reached home,
Global map is completed in reconstruct.
Further, it further comprises the steps of: and fork on the road is considered as the distance between node, calculate node, and according to node
Value establishes adjacency matrix；It is found out in the global map that reconstruct is completed according to the adjacency matrix of foundation by dijkstra's algorithm
From the shortest path of origin-to-destination.
Further, in step S02, image processing unit passes through Threshold segmentation first will be local in HSV color space
Then road conditions image binaryzation uses the Canny operator edge detection algorithm based on brightness step to obtain the road of local road conditions
The contour images of line, the accumulated probability Hough transformation straight-line detection function for calling OpenCV to provide obtain the Road of local road conditions
The imaging position of profile endpoint.
Further, in step S01, according to monocular vision imaging model, first calibration for cameras focal length, then further according to known
The position of calibration point calculate the attitude parameter of camera, the attitude parameter includes camera imaging planar inclination and relative movement
The position of platform.
The beneficial effects of the present invention are:
(1) present invention realizes the structuring of unknown landform, so that unknown by being abstracted and being modeled to fork on the road
The search work of landform is more complete.
(2) present invention is found out by the structural model and passage path planning algorithm of establishing unknown landform and is explored in region
Optimal path realized unknown so that instructing other not explore the mobile platform of the zone of ignorance passes through the landform
The navigation of landform is shared.
Detailed description of the invention
It, below will be to required in embodiment description in order to illustrate more clearly of the technical solution in the application embodiment
Attached drawing to be used is briefly described.
Fig. 1 is the composition block diagram of the unknown topographical navigation system based on image procossing of one embodiment of the invention.
Fig. 2 (a)-(c) is the road line feature extraction effect picture of image processing unit of the invention.
Fig. 3 (a)-(b) is monocular vision imaging model figure of the invention.
Fig. 4 is map reconfiguration unit of the invention by carrying out map reconstruct to collected five frame part road conditions image
As a result.
Fig. 5 is the graphic software platform interface at the end PC of the invention.
Fig. 6 is that the focal length of the camera of image acquisition units of the invention demarcates schematic diagram.
Fig. 7 (a)-(b) is the posture calibration result figure of the camera of image acquisition units of the invention.
Specific embodiment
Below in conjunction with the attached drawing in the application embodiment, the technical solution in presently filed embodiment is carried out clear
Chu, complete description, it is clear that described embodiment is merely possible to illustrate, and is not intended to limit the application.
Fig. 1 is the composition block diagram of the unknown topographical navigation system of the invention based on image procossing, including road condition acquiring mould
Block, map reconstructed module and navigation module.Road condition acquiring module includes image acquisition units and image transmitting unit, wherein
Image acquisition units are made of monocular CMOS camera, realize the acquisition of image information；Image transmitting unit include serial communication and
Wireless LAN communication, the image transmitting that serial communication acquires monocular CMOS camera is to WiFi module, wireless LAN communication
The image transmitting that WiFi module is received to the end PC (HP TPN-Q173 portable computer) map reconstructed module, it is described
WiFi module model XRBOT LINKS5.0MT, version WF.7620.E, the WiFi module Built In Operating System
BusyBox v1.24.1built-in shell。
Map reconstructed module includes the image processing unit of road information being extracted from the image of local road conditions, according to monocular
The position that visual imaging theory restores collected road constantly reconstructs map reconfiguration unit and the real-time display movement of map
The graphics interface unit of motion state and map the reconstruct situation of platform.
Image processing unit uses the Open Source Platform OpenCV library (opencv_python-3.4.3-cp37- based on C++
Cp37m-win32) developed, first by Threshold segmentation in HSV color space by original local road conditions image binaryzation,
Then the Canny operator edge detection algorithm based on brightness step is used to obtain the contour images of Road, for the profile diagram
As obtaining position of the Road profile endpoint in imaging plane in image by accumulated probability Hough transformation line detection method
It sets, to realize the extraction of Road feature.Fig. 2 (a)-(c) is the road line feature extraction of image processing unit of the invention
Effect picture, figure (a) are original image, and figure (b) is edge detection results figure, and figure (c) is straight-line detection result figure.
Map reconfiguration unit is developed using Python (Python3.7), the national forest park in Xiaokeng according to monocular vision
The location information of Road feature in image is restored, to obtain actual position of the Road in map.Fig. 3 (a)-
It (b) is monocular vision national forest park in Xiaokeng used in map reconfiguration unit of the invention, A is that image is adopted on ground in figure (a)
Collect any point in the camera fields of view of unit, straight line OG indicates camera optical axis, and point O is camera photocentre, and figure (b) is imaging model
Lateral plan.Fig. 4 is that map reconfiguration unit of the invention is restored and reconstructed to part road conditions at five in same landform
Global map (left figure), and by the effect picture (right figure) of the global map rasterizing.
Graphics interface unit uses the library the Pygame (pygame-1.9.4-cp37- based on Python (Python3.7)
Cp37m-win32 it) is developed.Fig. 5 is graphics interface unit of the invention, the region in left side entitled " labyrinth ", display movement
The position of platform will not show landform if landform is unknown, only show position of the mobile platform relative to starting point；Entitled " depending on
The region of open country ", the local road conditions image in the front that real-time display image acquisition units obtain；Entitled " global map and movement rail
The region of mark ", the global map of display map reconfiguration unit reconstruct, and new local road can be collected with image acquisition units
Condition and real-time update, meanwhile, which can also describe motion profile of the mobile platform from starting point；Character area in box
The quantitative parameter of real-time display mobile platform, such as relative to the location parameter of starting point, run duration；Four buttons of lower right
Function is that " starting " button starts mobile platform respectively, makes its advance, if mobile platform is moving, this button, which can be shown, " to stop
Only ", the movement that can stop mobile platform being clicked, mobile platform is then recovered to start position by the click of " resetting " button, and is emptied
Stored information relevant to current landform, to restart to navigate, " new map " push button function uses in testing, in order to
Navigation algorithm is tested by emulating, needs to arrange unknown landform in advance, when clicking this button, computer can give birth at random
Emulation testing is carried out as unknown landform at a labyrinth；The function of " saving result " button is to save current location landform
Under, global map that mobile platform is explored.
Navigation module includes issuing the movement instruction unit of advance or steering order to mobile platform and being completed according to reconstruct
Global map carry out path optimization path planning unit.When global map is not set up also, movement instruction unit is being turned to
Place generates the instruction turned to according to the backtracking method thought of depth-first；When global map has built up, that is, reach terminal
Afterwards, the path planning unit finds out the shortest path in the global map of reconstruct from origin-to-destination using dijkstra's algorithm
Diameter, movement instruction unit generate the instruction turned in turning point according to the shortest path found out.
Particularly, the unknown topographical navigation method based on image procossing that the present invention provides a kind of, comprising the following steps:
S01: monocular vision camera calibration is carried out, the focal length and attitude parameter of camera are sought；
Fig. 6 is the schematic diagram of calibration for cameras focal length of the present invention, and Fig. 7 is the effect picture of calibration for cameras attitude parameter of the present invention.
The attitude parameter of camera is calculated by the imaging position of any on the road surface of known location, that is, upper right with blank sheet of paper in Fig. 7 (a)
The crosspoint of " ten " word at upper angle first measures the specific location of calibration point as calibration point, then schemes using shown in Fig. 7 (b)
As after processing unit processes as a result, obtain the position of the imaging of calibration point, according to monocular vision shown in Fig. 3 (a)-(b) at
As model calculates the attitude parameter of camera, the position of inclination angle and camera relative to mobile platform including imaging plane.
S02: image acquisition units, that is, camera follows mobile platform from starting point, and in real time in front of acquisition mobile platform
Road local road conditions image, the local road conditions image of road is transmitted to upper by image transmitting unit by WLAN
The image processing unit of machine, image processing unit handle each frame part road conditions image, are examined by Threshold segmentation, edge
Survey the imaging position that the Road profile endpoint occurred in local road conditions image is extracted with accumulated probability Hough transformation straight-line detection；
S03: by the imaging position of Road profile endpoint obtained in step S02, in conjunction with the camera sought in step S01
Focal length and attitude parameter, the actual position of Road profile endpoint is calculated according to monocular vision imaging model；
S04: the actual position of map reconfiguration unit Road profile endpoint according to obtained in step S03, it will be mobile flat
Platform traveling process Road in collected local road conditions be stitched together and constantly reconstruct map, then will reconstruct ground
Figure carries out rasterizing, the value of grid represent in the grid whether P Passable, the region impassabitity of Road covering, without road
The region of route covering can then pass through, and the map of rasterizing is recorded as grid matrix, is sentenced by traversing the value in the matrix
Whether offset moving platform reaches fork on the road, and fork on the road is considered as node, and the distance between fork on the road is recorded in square
In battle array, adjacency matrix is established；
S05: movement instruction unit judges whether mobile platform reaches bifurcated road according to the grid matrix that step S04 is established
Mouthful, when not reaching in fork on the road, the instruction of straight trip is generated to mobile platform；When reaching in fork on the road, according to depth
Preferential backtracking method traverses each outlet of the fork on the road, and the instruction of corresponding steering is generated to mobile platform；
S06: when mobile platform is not reached home, step S02 to step S05 is repeated；When mobile platform is reached home,
Execute step S07；
S07: path planning unit is found out from according to the adjacency matrix established in step S04 by dijkstra's algorithm
Point arrives the shortest path of terminal, and is stored in host computer.
What is applied above is only some embodiments of the application.For those of ordinary skill in the art, not
Under the premise of being detached from the application concept, several variations and modifications can also be made, these belong to the protection model of the application
It encloses.
Claims (10)
1. a kind of unknown topographical navigation system based on image procossing, which is characterized in that the navigation system is mounted on mobile flat
On platform, the navigation system includes road condition acquiring module, map reconstructed module and navigation module,
The road condition acquiring module includes monocular vision camera and image transmitting unit；
The map reconstructed module includes image processing unit and map reconfiguration unit；
The navigation module includes movement instruction unit,
Wherein, described image transmission unit sends the camera local road conditions image collected in real time to described image processing
Unit, described image processing unit extract the Road feature in local road conditions, and the map reconfiguration unit is according to being extracted
Road feature constantly reconstruct map until global map is completed in reconstruct, the movement instruction unit is according to the map of reconstruct
Movement instruction information is issued to the mobile platform.
2. the system as claimed in claim 1, which is characterized in that described image processing unit passes through Threshold segmentation, edge detection
Position of the Road profile endpoint in imaging plane in local road conditions is obtained with accumulated probability Hough transformation, realizes local road
The extraction of Road feature in condition.
3. the system as claimed in claim 1, which is characterized in that the map reconfiguration unit foundation monocular vision image-forming principle,
Position of the Road profile endpoint in imaging plane in local road conditions is converted into the position relative to camera, and combines phase
Position of the machine in map, obtains the actual position of Road profile endpoint, later according to the true position of Road profile endpoint
It sets and constantly reconstructs map, until global map is completed in reconstruct.
4. the system as claimed in claim 1, which is characterized in that the map reconstructed module further includes moving described in real-time display
The graphics interface unit of motion state and map the reconstruct situation of platform.
5. the system as described in claim 1, which is characterized in that the navigation module further includes being completed globally according to reconstruct
Figure carries out the path planning unit of path optimization, and the path planning unit finds out the overall situation of reconstruct using Di jkstra algorithm
From the shortest path of origin-to-destination in map.
6. the system as described in claim 1, which is characterized in that described image transmission unit includes serial communication and wireless local area
Network Communication, the image transmitting that the serial communication acquires camera connect WiFi module to WiFi module, wireless LAN communication
The image transmitting received gives map reconstructed module.
7. a kind of method that the system using as described in one of claim 1-6 carries out unknown topographical navigation, which is characterized in that packet
Include following steps:
S01: monocular vision camera calibration is carried out, the focal length and attitude parameter of camera are sought；
S02: camera follows mobile platform to acquire local road conditions image in real time from the off, and image processing unit is to collected
Local road conditions image is handled, and the imaging position of the Road profile endpoint of local road conditions is obtained；
S03: by the imaging position of Road profile endpoint obtained in step S02, in conjunction with the coke for the camera sought in step S01
Away from and attitude parameter, the actual position of Road profile endpoint is calculated according to monocular vision imaging model；
S04: map is constantly reconstructed according to the actual position of Road profile endpoint obtained in step S03, map will be reconstructed
Carry out rasterizing, the value of grid represent in the grid whether P Passable, establish grid matrix according to these grid point values；
S05: judging whether mobile platform reaches fork on the road by the grid matrix that step S04 is established, when not reaching bifurcated road
When in mouthful, the instruction of straight trip is generated to mobile platform；When reaching in fork on the road, the backtracking method traversal according to depth-first should
Each outlet of fork on the road, and the instruction of corresponding steering is generated to mobile platform；
S06: when mobile platform is not reached home, step S02 to step S05 is repeated；When mobile platform is reached home, reconstruct
Complete global map.
8. the method for claim 7, which is characterized in that further comprise the steps of: fork on the road being considered as node, calculate node
The distance between, and adjacency matrix is established according to nodal value；It is found out according to the adjacency matrix of foundation by dijkstra's algorithm
Reconstruct the shortest path of the slave origin-to-destination in the global map completed.
9. the method as described in claim 1, which is characterized in that in step S02, image processing unit passes through Threshold segmentation first
By local road conditions image binaryzation in HSV color space, the Canny operator edge detection based on brightness step is then used to calculate
Method obtains the contour images of the Road of local road conditions, the accumulated probability Hough transformation straight-line detection function for calling OpenCV to provide
Obtain the imaging position of the Road profile endpoint of local road conditions.
10. the method as described in claim 7, which is characterized in that in step S01, according to monocular vision imaging model, first demarcate
Camera focus, then the position further according to known calibration point calculates the attitude parameter of camera, and the attitude parameter includes phase
The position at machine imaging plane inclination angle and relative movement platform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811522084.XA CN109579863A (en) | 2018-12-13 | 2018-12-13 | Unknown topographical navigation system and method based on image procossing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811522084.XA CN109579863A (en) | 2018-12-13 | 2018-12-13 | Unknown topographical navigation system and method based on image procossing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109579863A true CN109579863A (en) | 2019-04-05 |
Family
ID=65928438
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811522084.XA Pending CN109579863A (en) | 2018-12-13 | 2018-12-13 | Unknown topographical navigation system and method based on image procossing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109579863A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110570653A (en) * | 2019-08-09 | 2019-12-13 | 杭州博信智联科技有限公司 | Automatic driving assistance method and system |
| CN111494927A (en) * | 2020-04-20 | 2020-08-07 | 张洋 | Maze with haptic feedback and method of generating maze haptic feedback |
| CN112598010A (en) * | 2020-11-26 | 2021-04-02 | 厦门大学 | Binocular vision unstructured terrain real-time perception and reconstruction method |
| CN112614171A (en) * | 2020-11-26 | 2021-04-06 | 厦门大学 | Air-ground integrated dynamic environment sensing system for cluster operation of engineering machinery |
| CN113108780A (en) * | 2021-03-30 | 2021-07-13 | 沈奥 | Unmanned ship autonomous navigation method based on visual inertial navigation SLAM algorithm |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101231669A (en) * | 2007-12-28 | 2008-07-30 | 北京工业大学 | Method for searching optimum route of maze |
| CN102521589A (en) * | 2011-11-18 | 2012-06-27 | 深圳市宝捷信科技有限公司 | Method and system for detecting lane marked lines |
| CN103400392A (en) * | 2013-08-19 | 2013-11-20 | 山东鲁能智能技术有限公司 | Binocular vision navigation system and method based on inspection robot in transformer substation |
| CN103413313A (en) * | 2013-08-19 | 2013-11-27 | 国家电网公司 | Binocular vision navigation system and method based on power robot |
| WO2014021421A1 (en) * | 2012-08-03 | 2014-02-06 | クラリオン株式会社 | Camera parameter computation device, navigation system, and camera parameter computation method |
| CN103954275A (en) * | 2014-04-01 | 2014-07-30 | 西安交通大学 | Lane line detection and GIS map information development-based vision navigation method |
| CN106525057A (en) * | 2016-10-26 | 2017-03-22 | 陈曦 | Generation system for high-precision road map |
| CN106802668A (en) * | 2017-02-16 | 2017-06-06 | 上海交通大学 | Based on the no-manned plane three-dimensional collision avoidance method and system that binocular is merged with ultrasonic wave |
-
2018
- 2018-12-13 CN CN201811522084.XA patent/CN109579863A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101231669A (en) * | 2007-12-28 | 2008-07-30 | 北京工业大学 | Method for searching optimum route of maze |
| CN102521589A (en) * | 2011-11-18 | 2012-06-27 | 深圳市宝捷信科技有限公司 | Method and system for detecting lane marked lines |
| WO2014021421A1 (en) * | 2012-08-03 | 2014-02-06 | クラリオン株式会社 | Camera parameter computation device, navigation system, and camera parameter computation method |
| CN103400392A (en) * | 2013-08-19 | 2013-11-20 | 山东鲁能智能技术有限公司 | Binocular vision navigation system and method based on inspection robot in transformer substation |
| CN103413313A (en) * | 2013-08-19 | 2013-11-27 | 国家电网公司 | Binocular vision navigation system and method based on power robot |
| CN103954275A (en) * | 2014-04-01 | 2014-07-30 | 西安交通大学 | Lane line detection and GIS map information development-based vision navigation method |
| CN106525057A (en) * | 2016-10-26 | 2017-03-22 | 陈曦 | Generation system for high-precision road map |
| CN106802668A (en) * | 2017-02-16 | 2017-06-06 | 上海交通大学 | Based on the no-manned plane three-dimensional collision avoidance method and system that binocular is merged with ultrasonic wave |
Non-Patent Citations (6)
| Title |
|---|
| 冯杰: "《C图形化实践编程》", 31 August 2015, 南开大学出版社 * |
| 李瑞峰: "《工业机器人设计与应用》", 31 January 2017, 哈尔滨工业大学出版社 * |
| 李道新: "基于深广结合算法的迷宫机器人路径规划研究", 《中国优秀博硕士学位论文全文数据库(硕士) 信息科技辑》 * |
| 杨文元: "《数据结构与算法项目化教程》", 28 February 2011, 西安电子科技大学出版社 * |
| 陈家乾: "移动机器人自主创建环境地图的研究", 《中国优秀博硕士学位论文全文数据库(博士) 信息科技辑》 * |
| 韦鹏程等: "《基于虚拟化技术的云计算架构的技术与实践探究》", 30 June 2018, 电子科学技术大学出版社 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110570653A (en) * | 2019-08-09 | 2019-12-13 | 杭州博信智联科技有限公司 | Automatic driving assistance method and system |
| CN111494927A (en) * | 2020-04-20 | 2020-08-07 | 张洋 | Maze with haptic feedback and method of generating maze haptic feedback |
| CN111494927B (en) * | 2020-04-20 | 2023-06-09 | 张洋 | Maze with haptic feedback and method of generating haptic feedback for maze |
| CN112598010A (en) * | 2020-11-26 | 2021-04-02 | 厦门大学 | Binocular vision unstructured terrain real-time perception and reconstruction method |
| CN112614171A (en) * | 2020-11-26 | 2021-04-06 | 厦门大学 | Air-ground integrated dynamic environment sensing system for cluster operation of engineering machinery |
| CN112598010B (en) * | 2020-11-26 | 2023-08-01 | 厦门大学 | Unstructured terrain real-time sensing and reconstructing method for binocular vision |
| CN112614171B (en) * | 2020-11-26 | 2023-12-19 | 厦门大学 | Air-ground integrated dynamic environment sensing system for engineering machinery cluster operation |
| CN113108780A (en) * | 2021-03-30 | 2021-07-13 | 沈奥 | Unmanned ship autonomous navigation method based on visual inertial navigation SLAM algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109579863A (en) | Unknown topographical navigation system and method based on image procossing | |
| US11900536B2 (en) | Visual-inertial positional awareness for autonomous and non-autonomous tracking | |
| CN107356230B (en) | Digital mapping method and system based on live-action three-dimensional model | |
| Zhang et al. | Intelligent collaborative localization among air-ground robots for industrial environment perception | |
| KR101947619B1 (en) | Slam on a mobile device | |
| JP5473304B2 (en) | Remote location image display device, remote control device, vehicle control device, remote control system, remote control method, remote control program, vehicle control program, remote location image display method, remote location image display program | |
| Pink et al. | Visual features for vehicle localization and ego-motion estimation | |
| CN110275540A (en) | Semantic navigation method and its system for sweeping robot | |
| CN112894832A (en) | Three-dimensional modeling method, three-dimensional modeling device, electronic equipment and storage medium | |
| CN112740268B (en) | Target detection method and device | |
| CN112734765B (en) | Mobile robot positioning method, system and medium based on fusion of instance segmentation and multiple sensors | |
| CN207115193U (en) | A kind of mobile electronic device for being used to handle the task of mission area | |
| CN110553648A (en) | method and system for indoor navigation | |
| Wang et al. | Three-dimensional reconstruction based on visual SLAM of mobile robot in search and rescue disaster scenarios | |
| CN110992487B (en) | Rapid three-dimensional map reconstruction device and reconstruction method for hand-held airplane fuel tank | |
| CN112505065A (en) | Method for detecting surface defects of large part by indoor unmanned aerial vehicle | |
| Zhao et al. | Reconstruction of textured urban 3D model by fusing ground-based laser range and CCD images | |
| Chen et al. | Low-drift odometry, mapping and ground segmentation using a backpack LiDAR system | |
| CN111721281B (en) | Position identification method and device and electronic equipment | |
| WO2021017211A1 (en) | Vehicle positioning method and device employing visual sensing, and vehicle-mounted terminal | |
| CN105014675A (en) | Intelligent mobile robot visual navigation system and method in narrow space | |
| Xiong et al. | Neural map prior for autonomous driving | |
| CN111768489B (en) | Indoor navigation map construction method and system | |
| Xiang et al. | Hybrid bird’s-eye edge based semantic visual SLAM for automated valet parking | |
| Pannen et al. | Lane marking learning based on crowdsourced data |
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 |