CN107796361A - One meadow identifying system based on linear laser scanning - Google Patents
One meadow identifying system based on linear laser scanning Download PDFInfo
- Publication number
- CN107796361A CN107796361A CN201710955932.5A CN201710955932A CN107796361A CN 107796361 A CN107796361 A CN 107796361A CN 201710955932 A CN201710955932 A CN 201710955932A CN 107796361 A CN107796361 A CN 107796361A
- Authority
- CN
- China
- Prior art keywords
- array
- meadow
- linear laser
- motion platform
- standard deviation
- 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
- G01C3/00—Measuring distances in line of sight; Optical rangefinders
- G01C3/02—Details
Landscapes
- Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
One meadow identifying system based on linear laser scanning is disclosed, including can be with the motion platform of autonomous, and installed in the anterior linear laser scanner of described motion platform, described linear laser scanner is set diagonally downward, controller is set inside described motion platform, it is connected with described linear laser scanner, Intelligent lawn recognizer is set inside described controller, comprised the following steps：1）Scanning survey, obtain apart from array A；2）Intermediate data in array A is preserved, array B is formed with previous data；3）Calculate array A standard deviation sigmaA；4）If array A standard deviation sigmaAMore than threshold value T, then scanning range is judged for meadow, and return to step 1；5）Calculate array B standard deviation sigmaB；6）If array B standard deviation sigmaBMore than threshold value T, then judge that scanning range remains as meadow, and return to step 1, otherwise judge scanning range for non-meadow.
Description
Technical field
This patent is related to a meadow identifying system based on linear laser scanning, belongs to Intelligent Measurement field.
Background technology
With the construction of urban afforestation, the growth increasingly of grassland area, need of the domestic and international consumer for grass-removing robot
Ask increasing.But meadow shape does not have unified form, also without the border of isolation, therefore in order to ensure grass-removing robot
Normal work lay electromagnetic wire, it is necessary to set specific border, such as around meadow, allow grass-removing robot work within this range
Make.But this mode needs the extra artificial and material cost of increase, will be no small expense for large-scale meadow.
The content of the invention
In view of the above-mentioned problems, this patent is using method of the Intelligent Measurement with judging, there is provided one is scanned based on linear laser
Meadow identifying system, allow the border on grass-removing robot automatic identification meadow.
Technical scheme is used by this patent solves its technical problem：
One meadow identifying system based on linear laser scanning, including can be with the motion platform of autonomous, and be arranged on
The anterior linear laser scanner of described motion platform, described linear laser scanner are set diagonally downward, scanning range
The width of described motion platform is at least covered, controller is set inside described motion platform, swept with described linear laser
Device connection is retouched, Intelligent lawn recognizer is set inside described controller, whether identifies described motion platform direction of advance
For meadow, described Intelligent lawn recognizer comprises the following steps：
（1）Described linear laser scanner is scanned measurement, and the reflecting surface obtained in scanning range linearly swashs to described
The distance of optical scanner, and described controller is transferred to, array A={ x [0], x [1], x [2] ..., x [N-1] } is stored as,
Wherein N is the quantity of described linear laser scanner output data；
（2）It is the history number preserved by data x [N/2] deposit arrays B={ y [0], y [1], y [2] ..., y [K-1] }, wherein K
According to quantity, make y [i-1]=y [i], i=1,2 ..., K-1, y [K-1]=x [N/2]；
（3）The average for calculating array A is=, therefore, the standard deviation that can try to achieve array A is σA =；
（4）If array A standard deviation sigmaAMore than threshold value T, then scanning range is judged for meadow, and return to step 1, otherwise continue
Perform, described threshold value T is to characterize the whether smooth empirical data of scanning area；
（5）Calculate array B average=, therefore, the standard deviation that can try to achieve array B is σB =；
（6）If array B standard deviation sigmaBMore than threshold value T, then judge that scanning range remains as meadow, and return to step 1, otherwise
Scanning range is judged for non-meadow, and return to step 1 continues executing with.
The beneficial effect of this patent is mainly manifested in：1st, automatic identification meadow and non-meadow, without laying electromagnetic wire, reduce
System cost；2nd, dependable performance, rate of false alarm are low.
Brief description of the drawings
Fig. 1 is the outline drawing of meadow identifying system；
Fig. 2 is the flow chart of Intelligent lawn recognizer.
Embodiment
The invention will be further described below in conjunction with the accompanying drawings：
Reference picture 1-2, a meadow identifying system based on linear laser scanning, including can be with the motion platform of autonomous
1, described motion platform 1 can advance on working face, retreat and left rotation and right rotation, in addition to be put down installed in described motion
The anterior linear laser scanner 2 of platform 1, in order to be met the Detection results of application requirement, described linear laser is scanned
Device 2 is set diagonally downward, its scanning range at least covers the width of described motion platform 1, so described in motion platform 1
Progress path all obtains effective scanning detection.
The described inside of motion platform 1 sets controller, and is connected with described linear laser scanner 2, described control
Device processed can obtain the scan data of described linear laser scanner 2.
Intelligent lawn recognizer is set inside described controller, whether identifies the described direction of advance of motion platform 1
For meadow, described Intelligent lawn recognizer comprises the following steps：
（1）Described linear laser scanner 2 is scanned measurement, and the reflecting surface obtained in scanning range linearly swashs to described
The distance of optical scanner 2, and described controller is transferred to, array A={ x [0], x [1], x [2] ..., x [N-1] } is stored as,
Wherein N is the quantity of the described output data of linear laser scanner 2；
Described linear laser scanner 2 is linear scan equipment, and detection range is a line segment, and output data is reflector space
To one group of distance value of described linear laser scanner 2.
（2）It is going through for preservation by data x [N/2] deposit arrays B={ y [0], y [1], y [2] ..., y [K-1] }, wherein K
The quantity of history data, make y [i-1]=y [i], i=1,2 ..., k-1, y [K-1]=x [N/2]；
Described array B is one group of scan data that described motion platform 1 retains on mobile route, and position is placed in the middle, can use
In the verification for being judged as non-meadow.
（3）Calculate array A average=, therefore, the standard deviation that can try to achieve array A is σA =；
Described standard deviation sigmaARepresent the degree size of the data deviation average in described array A.
（4）If array A standard deviation sigmaAMore than threshold value T, then scanning range is judged for meadow, and return to step 1, otherwise
Continue executing with, described threshold value T is to characterize the whether smooth empirical data of scanning area；
For real meadow, greenweed above can make reflecting surface be rugged non-burnishing surface, the number in the array A of acquisition
It is big according to dispersion, form obvious differentiation with ground grading.
（5）Calculate array B average=, therefore, the standard deviation that can try to achieve array B is σB =；
Described array B is the one group of scan data retained on the described travel path of motion platform 1, with described array A's
Data are orthogonal on position relationship, and array A judged result can be verified.
（6）If array B standard deviation sigmaBMore than threshold value T, then judge that scanning range remains as meadow, and return to step 1,
Otherwise scanning range is judged for non-meadow, and return to step 1 continues executing with.
If in step 4, being judged as non-meadow according to described array A data, in order to prevent erroneous judgement or once in a while
Detection mistake, verified using data B.Only as described array A and array B while it is judged as non-meadow, it is just final
Obtain the result on non-meadow.
Claims (1)
1. a meadow identifying system based on linear laser scanning, including can be with the motion platform of autonomous, and installation
In the linear laser scanner that described motion platform is anterior, described linear laser scanner is set diagonally downward, scans model
The width at least covering described motion platform is enclosed, controller is set inside described motion platform, with described linear laser
Scanner is connected, and Intelligent lawn recognizer is set inside described controller, identifies that described motion platform direction of advance is
No is meadow, it is characterised in that：Described Intelligent lawn recognizer comprises the following steps：
（1）Described linear laser scanner is scanned measurement, and the reflecting surface obtained in scanning range linearly swashs to described
The distance of optical scanner, and described controller is transferred to, array A={ x [0], x [1], x [2] ..., x [N-1] } is stored as,
Wherein N is the quantity of described linear laser scanner output data；
（2）It is the history number preserved by data x [N/2] deposit arrays B={ y [0], y [1], y [2] ..., y [K-1] }, wherein K
According to quantity, make y [i-1]=y [i], i=1,2 ..., K-1, y [K-1]=x [N/2]；
（3）Calculate array A average=, therefore, the standard deviation that can try to achieve array A is σA=；
（4）If array A standard deviation sigmaAMore than threshold value T, then scanning range is judged for meadow, and return to step 1, otherwise continue
Perform, described threshold value T is to characterize the whether smooth empirical data of scanning area；
（5）Calculate array B average=, therefore, the standard deviation that can try to achieve array B is σB=；
（6）If array B standard deviation sigmaBMore than threshold value T, then judge that scanning range remains as meadow, and return to step 1, otherwise
Judge scanning range for non-meadow.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710955932.5A CN107796361A (en) | 2017-10-15 | 2017-10-15 | One meadow identifying system based on linear laser scanning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710955932.5A CN107796361A (en) | 2017-10-15 | 2017-10-15 | One meadow identifying system based on linear laser scanning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107796361A true CN107796361A (en) | 2018-03-13 |
Family
ID=61533162
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710955932.5A Pending CN107796361A (en) | 2017-10-15 | 2017-10-15 | One meadow identifying system based on linear laser scanning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107796361A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105512689A (en) * | 2014-09-23 | 2016-04-20 | 苏州宝时得电动工具有限公司 | Lawn identification method based on images, and lawn maintenance robot |
| CN105785986A (en) * | 2014-12-23 | 2016-07-20 | 苏州宝时得电动工具有限公司 | Automatic working equipment |
| CN106489103A (en) * | 2014-10-10 | 2017-03-08 | 美国iRobot公司 | Robot turf-mown border determines |
-
2017
- 2017-10-15 CN CN201710955932.5A patent/CN107796361A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105512689A (en) * | 2014-09-23 | 2016-04-20 | 苏州宝时得电动工具有限公司 | Lawn identification method based on images, and lawn maintenance robot |
| CN106489103A (en) * | 2014-10-10 | 2017-03-08 | 美国iRobot公司 | Robot turf-mown border determines |
| CN105785986A (en) * | 2014-12-23 | 2016-07-20 | 苏州宝时得电动工具有限公司 | Automatic working equipment |
Non-Patent Citations (1)
| Title |
|---|
| 谭贲: "基于车载激光扫描数据的城市典型地物分类方法研究", 《中国优秀硕士学位论文全文数据库》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107390681B (en) | A kind of mobile robot real-time location method based on laser radar and map match | |
| CN107045629B (en) | Multi-lane line detection method | |
| CN110765916B (en) | Farmland seedling ridge identification method and system based on semantics and example segmentation | |
| CN110262287A (en) | Canopy height on-line water flushing method for the highly automated control of the harvest machinery ceding of Taiwan | |
| CN104866820B (en) | A kind of farm machinery navigation line drawing method and device based on genetic algorithm | |
| CN109215071A (en) | The intelligent harvester for both rice and wheat swath measurement method of view-based access control model | |
| CN109886155B (en) | Single-plant rice detection and positioning method, system, equipment and medium based on deep learning | |
| CN107870621B (en) | Autonomous underwater robot collision prevention method in unknown complex sea-floor relief environment | |
| CN103473763B (en) | Road edge detection method based on heuristic Probabilistic Hough Transform | |
| CN110163871A (en) | A kind of ground dividing method of multi-line laser radar | |
| CN110908374B (en) | Mountain orchard obstacle avoidance system and method based on ROS platform | |
| CN113487721B (en) | Automatic prefabricated part identification method based on three-dimensional point cloud | |
| CN103530606A (en) | Agricultural machine navigation path extraction method under weed environment | |
| Xiang et al. | Field‐based robotic leaf angle detection and characterization of maize plants using stereo vision and deep convolutional neural networks | |
| CN114239756B (en) | Insect pest detection method and system | |
| CN111178138A (en) | Distribution network wire operating point detection method and device based on laser point cloud and binocular vision | |
| CN109848996A (en) | Extensive three-dimensional environment map creating method based on figure optimum theory | |
| Mount et al. | 2d visual place recognition for domestic service robots at night | |
| CN116681243B (en) | Intelligent agricultural equipment management system and method based on Internet of things | |
| CN110110687A (en) | Fruit automatic identifying method on tree based on colouring information and three-D profile information | |
| CN117367402A (en) | Unmanned mower map construction method based on semantic segmentation and depth map | |
| CN109947129A (en) | Rotor wing unmanned aerial vehicle paths planning method based on Dijkstra and improvement particle swarm algorithm | |
| CN115187803A (en) | Positioning method for picking process of tender shoots of famous tea | |
| CN114342910A (en) | Laser bird repelling method and related device | |
| CN107796361A (en) | One meadow identifying system based on linear laser scanning |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180313 |