CN111681246B - Region segmentation method of laser map - Google Patents
Region segmentation method of laser map Download PDFInfo
- Publication number
- CN111681246B CN111681246B CN202010341056.9A CN202010341056A CN111681246B CN 111681246 B CN111681246 B CN 111681246B CN 202010341056 A CN202010341056 A CN 202010341056A CN 111681246 B CN111681246 B CN 111681246B
- Authority
- CN
- China
- Prior art keywords
- map
- area
- laser
- closed
- robot
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000011218 segmentation Effects 0.000 title claims abstract description 24
- 230000008859 change Effects 0.000 claims description 6
- 239000003086 colorant Substances 0.000 claims description 6
- 230000004888 barrier function Effects 0.000 claims description 5
- 230000002093 peripheral effect Effects 0.000 claims description 4
- 238000009432 framing Methods 0.000 claims description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 3
- 238000003672 processing method Methods 0.000 claims 1
- 230000000694 effects Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000000638 solvent extraction Methods 0.000 description 3
- 230000002349 favourable effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20152—Watershed segmentation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Manipulator (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a region segmentation method of a laser map, which comprises the following steps: step one, denoising a graying laser map, wherein the laser map is a map constructed in advance through rotary scanning of a laser sensor assembled on a robot and comprises contour information of a map environment obtained through laser scanning; and secondly, determining at least two central points of a robot work area according to the distance information between the white pixel points of the gray laser map and the black pixel points marked by the nearest obstacle, and dividing the image of the laser map processed in the first step into closed map areas which take the central points of the robot work area as local minimum points and meet the requirement of the optimal working area of the robot by using a watershed algorithm, wherein each closed map area is an influence area which is obtained by outwards expanding the central points of the corresponding robot work area. Thereby avoiding the reduction of robot work efficiency caused by the division of the map into a plurality of areas.
Description
Technical Field
The invention relates to the technical field of grid map construction by laser vision, in particular to a region segmentation method of a laser map.
Background
In the field of robots, maps are one of the main tools that help robots describe environments and pinpoint. The most common type of map used in robotic autonomous positioning navigation technology is a grid map. The existing 4*4 coverage type cleaning mode does not reasonably utilize the obstacle information in the grid map to divide a plurality of room areas, so that the knowledge of one autonomous mobile robot on the environment is only remained in the level of the independent room; the existing map segmentation method does not effectively utilize the linear advantage caused by laser sensor scanning, and is easy to segment the idle area in the grid map into more areas, so that the working efficiency of the robot is reduced.
Disclosure of Invention
In order to solve the technical problems, the invention provides a region segmentation method of a laser map, which uses a contour boundary line scanned by laser data to be closer to a wall, then determines a central point of a robot working region in a region to be segmented according to the contour boundary line scanned by the laser data, and on the basis, iteratively segments the laser map by using a watershed algorithm, thereby determining which pixel regions belong to the same working region, realizing the segmentation of the working region, and reducing the problem that the robot working efficiency is reduced after a whole idle region is possibly divided into a plurality of regions. The specific technical scheme is as follows:
a region segmentation method of a laser map, comprising: step one, denoising a graying laser map, wherein the laser map is a map constructed in advance through rotary scanning of a laser sensor assembled on a robot and comprises contour information of a map environment obtained through laser scanning; and secondly, determining at least two central points of a robot work area according to the distance information between the white pixel points of the gray laser map and the black pixel points marked by the nearest obstacle, and dividing the image of the laser map processed in the first step into closed map areas which take the central points of the robot work area as local minimum points and meet the requirement of the optimal working area of the robot by using a watershed algorithm, wherein each closed map area is an influence area which is obtained by outwards expanding the central points of the corresponding robot work area.
Compared with the prior art, the method has the advantages that the central point positions in each partitioned area are arranged according to the outline of laser data scanning, and local minima which can represent the wall environment characteristics of the partitionable areas are provided for the area partitioning operation of the watershed algorithm, so that the map partitioning result of the watershed algorithm is closer to all the areas possibly occurring in the robot at present, the effective partitioning of the robot work area is realized, and the working efficiency of the robot is improved.
Further, the second step specifically includes: step 21, judging whether the area of one closed map area divided by the watershed algorithm is larger than a preset area threshold value, if yes, entering a step 22, otherwise, entering a step III; and 22, determining at least two new robot working area center points in the closed map area according to the distance information between the white pixel points in the closed map area and the black pixel points marked by the nearest barrier, segmenting the closed map area again by using a watershed algorithm, and returning to the step 21. According to the technical scheme, the optimal working area of the robot is set to limit the division times of the watershed algorithm, so that the influence on the working efficiency of the robot caused by overlarge local area in a closed map area obtained by division is avoided.
Further, the method for determining the center point of at least two robot work areas according to the distance information between the white pixel point of the gray laser map and the black pixel point of the nearest obstacle mark specifically comprises the following steps: calculating the distance between each white pixel point on the gray laser map and the black pixel point of the nearest obstacle mark; starting from the outline of the laser map, determining at least two robot working area center points in the area to be segmented with the channel connection condition according to the gradient incremental change of the distance; the contour information comprises position information corresponding to black pixels of the obstacle mark, which are closest to each white pixel, and position information of black pixels of the contour boundary mark of the region to be segmented. The center points of the at least two robot working areas determined by the technical scheme can reflect the area required by the environment outline, and are favorable for developing the optimal segmentation area.
Further, the specific method for segmenting the image of the laser map processed in the step one by using the watershed algorithm comprises the following steps: starting from a central point of a robot working area, expanding an influence area outwards in the to-be-segmented area according to the sequence from low gray level to high gray level of the set pixel points, and when the influence area is expanded to an outline formed by the maximum allowable gray level of the image or the influence area expanded by the central point of other robot working areas, converging the influence areas of the central points of at least two robot working areas to form a water diversion boundary, so that the to-be-segmented area is segmented into at least two adjacent closed map areas; the gray level of the pixels of the image of the laser map is ranked from low to high, and the gray level is converted according to the gradient change rule of the distance between each white pixel of the image of the laser map and the black pixel of the corresponding mark of the nearest obstacle. According to the technical scheme, from the position of the robot working center of the region to be segmented, gray level contour lines are established according to the gray value of each unmarked pixel point and the distance between nearest obstacles, the gray level contour lines are gradually expanded to segment the region connected with the narrow channel, the watershed algorithm is utilized to determine which pixel regions belong to the same closed map region, the effective segmentation of the laser map is realized, and the problem of low robot work efficiency caused by the fact that the whole idle region is possibly divided into a plurality of working regions is solved.
Further, the region segmentation method further includes: and filling colors with different gray levels into each closed map area divided in the step, and stopping filling operation when each closed map area is filled until white pixel points are not detected. According to the technical scheme, the clustering processing of the closed map areas is completed in a color filling mode, whether the dividing lines between the closed map areas are straight lines or not is facilitated to be recognized, and the complete corridor and room are obtained by combining the classes according to the connectivity of the classes.
Further, the method further comprises the following steps: and after the closed map areas are filled with colors with different gray levels, dividing and linearizing the boundaries between adjacent closed map areas. The method for dividing and linearizing comprises the following steps: framing a minimum bounding rectangle for bounding the border such that the border is distributed around a diagonal of the minimum bounding rectangle; and then setting a median line parallel to the long side in the minimum bounding rectangle as a straight line fitting boundary between the pair of adjacent closed map areas so as to realize segmentation linearization processing and effectively remove noise in the map.
Drawings
Fig. 1 is an effect diagram of a grayscaled image of a laser map constructed by rotational scanning of a laser sensor mounted on a robot.
FIG. 2 is an effect diagram of an embodiment of the present invention separating isolated clutter and small enclosed areas in a map by thresholding.
Fig. 3 is an effect diagram of each closed map area obtained after the laser map is cut by the watershed algorithm once according to the embodiment of the invention.
Fig. 4 is an effect diagram of each closed map area obtained after the laser map is cut by the watershed algorithm twice according to the embodiment of the invention.
Fig. 5 is a flowchart of a method for dividing a region of a laser map according to an embodiment of the present invention.
Detailed Description
The following describes the technical solution in the embodiment of the present invention in detail with reference to the drawings in the embodiment of the present invention. For further illustration of the various embodiments, the invention is provided with the accompanying drawings. The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate embodiments and together with the description, serve to explain the principles of the embodiments. With reference to these matters, one of ordinary skill in the art will understand other possible embodiments and advantages of the present invention. The components in the figures are not drawn to scale and like reference numerals are generally used to designate like components.
The embodiment of the invention discloses a region segmentation method of a laser map, which is shown in fig. 5 and comprises the following steps:
step S1, carrying out graying treatment on an image of a global laser map which is scanned and built by a robot in advance by setting a threshold value, and then carrying out denoising treatment on the graying laser map, so as to remove sundry interference and small interference of a closed area in the laser map of FIG. 1, namely filtering a tiny black area and discretely distributed black mark points in a white large area of FIG. 1, thereby obtaining the graying image of the laser map shown in FIG. 2. The reason for performing this step is that there are many small black spots or fragments in the binarized laser map shown in fig. 1, which easily cause many masks, i.e., too many small hills, during the watershed segmentation, resulting in excessive segmentation, which causes the idle region to be segmented into more regions, thus reducing the working efficiency of the robot. The laser map of fig. 1 is a map constructed in advance by rotational scanning of a laser sensor mounted on a robot, and includes contour information of a map environment obtained by laser scanning. It should be noted that, black pixel points marked in the binarized laser map may represent barriers and walls; the white pixels in the binarized laser map represent map area locations not occupied by other objects or landmarks. When the binarized laser map is a grid map, the grid corresponding to the black pixel point represents a grid area marking obstacle information, and the grid corresponding to the white pixel point represents an idle grid area not filled with information.
And S2, determining at least two central points of the robot work area according to the distance information between the white pixel points of the gray laser map and the black pixel points of the nearest obstacle marks, and dividing the image of the laser map processed in the step S1 into closed map areas which take the central points of the robot work area as local minimum points and meet the requirements of the optimal working area of the robot by using a watershed algorithm, wherein each closed map area is an influence area which is obtained by outwards expanding the central points of the corresponding robot work area.
The method for determining the center point of at least two robot work areas according to the distance information between the white pixel point of the laser map and the black pixel point of the nearest obstacle mark comprises the following steps: calculating the distance between each white pixel point on the gray laser map and the black pixel point marked by the nearest obstacle, namely, starting from the outline of the laser map, including starting from the wall outline of the laser map and the peripheral edge of the obstacle, calculating the distance between each white pixel point on the laser map and the black pixel point marked by the nearest wall outline of the laser map or the peripheral edge of the obstacle, and determining at least two central points of the robot working area in the area to be segmented with the channel connection condition according to the gradient incremental change of the distance from the outer outline to the inner marking area; the contour information comprises position information corresponding to black pixels of the obstacle mark, which are closest to each white pixel, and position information of black pixels of the contour boundary mark of the region to be segmented. The center points of the at least two robot working areas determined in the step can reflect the area required by the environment outline, and the optimal segmentation area is developed, namely the most area is segmented on the laser map.
The method for dividing the image of the laser map processed in the step S1 into a closed map area which takes the central point of the working area of the robot as a local minimum point and meets the requirement of the optimal working area of the robot by using a watershed algorithm comprises the following steps: and starting from the central point of the robot working area, expanding an influence area outwards in the to-be-segmented area according to the sequence from low gray level to high gray level of the set pixel points, and when the influence area is expanded to an outline formed by the maximum allowable gray level of the image or the influence area expanded by the central point of other robot working areas, converging the influence areas of the central points of at least two robot working areas to form a water diversion boundary, so that the to-be-segmented area is segmented into at least two adjacent closed map areas, and the area of each closed map area meets the requirement of the optimal working area of the robot. In the same region to be segmented, the contour formed by the white pixel points with the same gray level is uniformly expanded by the contour formed by the white pixel points with the same gray level, and the contour formed by the white pixel points with the same gray level surrounds the contour formed by the white pixel points with the lower gray level. The embodiment starts from the working center position of the robot in the region to be segmented, establishes a gray level contour line according to the distance between each unmarked pixel point (white pixel point) and the black pixel point marked by the nearest obstacle, expands outwards from the working center position of the robot one circle by one circle until expanding to the outline (the black pixel point marking position) of the laser map scanning or converging in other central expansion regions so as to segment the regions connected with a narrow channel, thereby determining which pixel regions belong to the same closed map region meeting the requirement of the optimal working area of the robot by using a watershed algorithm, realizing the effective segmentation of the laser map, and being beneficial to adjusting and achieving the optimal segmentation result.
It should be noted that the watershed algorithm is a mathematical morphology-based method, and any image can be regarded as a map, and the gray value of each pixel represents the altitude of the point. The main purpose of the watershed algorithm is to find the watershed between each region. The basic principle is as follows: when the pixels in different areas are measured, the gray level of the pixels of the image of the laser grid map is ranked from low to high, the gray level is converted according to the gradient change rule of the distance between each white pixel of the image of the laser grid map and the pixel marked by the nearest barrier, the distance between the two white pixels and the pixel marked by the nearest barrier is in a decreasing trend, and the gray level contour line where the two white pixels are located presents an increasing trend; when pixels in different areas are to be aggregated, a dam is built to prevent aggregation. Finally, these dams form the cutwater in the image. As shown in fig. 3, a part of the region to be divided of the laser map is divided into a closed map region #1, a closed map region #2, a closed map region #3, and a closed map region #4, wherein each closed map region is surrounded by boundary lines marked with black pixels to form an external mark, and the internal mark of each closed map region is marked with white pixels.
In this embodiment, the step S2 specifically includes: step 21, judging whether the area of one closed map area divided by the watershed algorithm is larger than a preset area threshold value, if yes, entering a step 22 to divide the area with overlarge local area for the second time, avoiding the overlarge local area, otherwise entering a step 3; it should be noted that, in the step 21, a closed map area can be converted into an optimal working area of the robot only when the area is smaller than or equal to the preset area threshold. Step 22, determining at least two new central points of the working area of the robot in the closed map area according to the distance information between the white pixel points in the closed map area and the black pixel points marked by the nearest obstacle, dividing the closed map area again by using a watershed algorithm, and returning to step 21, and repeatedly and iteratively dividing until a closed map area with the central point of the redetermined working area of the robot as a local minimum point and the area smaller than or equal to a preset area threshold is selected, so that the closed map area meets the requirement of the optimal working area of the robot, thereby realizing the optimal dividing effect of the watershed algorithm. As shown in fig. 4, a part of the area to be segmented of the laser map is segmented into a closed map area #1, a closed map area #21, a closed map area #22, a closed map area #3 and a closed map area #4 by fig. 4, wherein the closed map area #21 and the closed map area #22 are two closed map areas which are obtained by segmenting the closed map area #2 of fig. 3 by using a watershed algorithm and have an area smaller than or equal to a preset area threshold value, so that the area of all the closed map areas in the map meets the optimal working area requirement of the robot, wherein a white boundary line in fig. 4 is the contour line of each closed map area, forms the effective edge of each closed map area and surrounds the black pixel area inside the closed map areas. The embodiment limits the division times of the watershed algorithm by setting the optimal working area of the robot, so that the problem of low robot work efficiency caused by the fact that the whole idle area is possibly divided into a plurality of areas is solved.
It should be noted that, in this embodiment, the multiple sub-regions are set in a split manner by using a watershed algorithm according to the adjacent relationship and the obstacle distribution in the map, so that the boundaries of the multiple sub-regions become more reasonable, and the discontinuity of the subsequent generation path can be well reduced.
And step S3, filling colors with different gray levels into each closed map area divided in the step S2, and stopping filling operation when each closed map area divided in the step S2 is filled to the point that white pixels cannot be detected in the process of executing the step S3. The step utilizes a color filling mode to complete clustering processing of the closed map areas, is favorable for identifying whether the dividing lines between the closed map areas are straight lines, and achieves that the complete corridor and room are obtained by combining the classes according to the connectivity of the classes.
Preferably, after the closed map areas are filled with colors of different gray levels, a division linearization process is performed on boundaries between adjacent closed map areas. The method for dividing and linearizing comprises the following steps: framing a minimum bounding rectangle for bounding the border such that the border is distributed around a diagonal of the minimum bounding rectangle; and then setting a median line parallel to the long side in the minimum bounding rectangle as a straight line fitting boundary between the pair of adjacent closed map areas so as to realize segmentation linearization processing and effectively remove noise in the map.
The foregoing embodiments are merely illustrative of the technical concept and features of the present invention, and are intended to enable those skilled in the art to understand the present invention and to implement the same according to the present invention, not to limit the scope of the present invention. All changes and modifications that come within the meaning and range of equivalency of the invention are to be embraced within their scope.
Claims (6)
1. A region segmentation method of a laser map, comprising:
step one, denoising a graying laser map, wherein the laser map is a map constructed in advance through rotary scanning of a laser sensor assembled on a robot and comprises contour information of a map environment obtained through laser scanning;
the method is characterized in that the method for dividing the region further comprises the following steps:
step two, determining at least two robot work area center points according to distance information between white pixel points of the gray laser map and black pixel points of the nearest obstacle mark, and dividing the image of the laser map processed in the step one into closed map areas which take the center points of the robot work areas as local minimum points and meet the requirements of the optimal working areas of the robots by using a watershed algorithm, wherein each closed map area is an influence area which is obtained by outwards expanding the center points of the corresponding robot work areas;
the method for determining the center point of at least two robot work areas according to the distance information between the white pixel point of the gray laser map and the black pixel point of the nearest obstacle mark comprises the following specific steps: calculating the distance between each white pixel point on the laser map and the black pixel point marked by the wall contour of the laser map or the peripheral edge of the obstacle nearest to the white pixel point from the wall contour of the laser map or the peripheral edge of the obstacle, and determining at least two central points of the robot working area in the area to be segmented with the channel connection condition according to the gradient incremental change of the distance from the outer contour to the inner marking area; the contour information comprises position information corresponding to black pixels of the obstacle mark, which are closest to each white pixel, and position information of black pixels of the contour boundary mark of the region to be segmented.
2. The method of area division according to claim 1, wherein the second step specifically includes:
step 21, judging whether the area of one closed map area divided by the watershed algorithm is larger than a preset area threshold value, and if so, entering step 22;
and 22, determining at least two new robot working area center points in the closed map area according to the distance information between the white pixel points in the closed map area and the black pixel points marked by the nearest barrier, segmenting the closed map area again by using a watershed algorithm, and returning to the step 21.
3. The method for segmenting the region according to claim 2, wherein the specific method for segmenting the image of the laser map processed in the step one by using a watershed algorithm comprises the following steps:
starting from a central point of a robot working area, expanding an influence area outwards in the to-be-segmented area according to the sequence from low gray level to high gray level of the set pixel points, and when the influence area is expanded to an outline formed by the maximum allowable gray level of the image or the influence area expanded by the central point of other robot working areas, converging the influence areas of the central points of at least two robot working areas to form a water diversion boundary, so that the to-be-segmented area is segmented into at least two adjacent closed map areas;
the gray level of the pixels of the image of the laser map is ranked from low to high, and the gray level is converted according to the gradient change rule of the distance between each white pixel of the image of the laser map and the black pixel of the nearest obstacle mark.
4. The region segmentation method as set forth in claim 1, further comprising: and filling colors with different gray levels into each closed map area divided in the step, and stopping filling operation when each closed map area is filled until white pixel points are not detected.
5. The region segmentation method as set forth in claim 4, further comprising: and after the closed map areas are filled with colors with different gray levels, dividing and linearizing the boundaries between adjacent closed map areas.
6. The area segmentation method according to claim 5, characterized in that the segmentation linearization processing method includes:
framing a minimum bounding rectangle for bounding the border such that the border is distributed around a diagonal of the minimum bounding rectangle;
the median line parallel to the long sides in the smallest bounding rectangle is then set as the straight line fit boundary between the pair of adjacent closed map regions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010341056.9A CN111681246B (en) | 2020-04-27 | 2020-04-27 | Region segmentation method of laser map |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010341056.9A CN111681246B (en) | 2020-04-27 | 2020-04-27 | Region segmentation method of laser map |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111681246A CN111681246A (en) | 2020-09-18 |
| CN111681246B true CN111681246B (en) | 2024-01-23 |
Family
ID=72452196
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010341056.9A Active CN111681246B (en) | 2020-04-27 | 2020-04-27 | Region segmentation method of laser map |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111681246B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112258517A (en) * | 2020-09-30 | 2021-01-22 | 无锡太机脑智能科技有限公司 | Automatic map repairing method and device for laser radar grid map |
| CN112395380B (en) * | 2020-11-20 | 2022-03-22 | 上海莉莉丝网络科技有限公司 | Merging method, merging system and computer readable storage medium for dynamic area boundary in game map |
| CN112561927B (en) * | 2020-12-07 | 2024-03-12 | 深圳市愚公科技有限公司 | Image area dividing method, system, electronic device and storage medium |
| CN112556687B (en) * | 2020-12-08 | 2023-04-07 | 广州赛特智能科技有限公司 | Robot starting positioning method, system, electronic equipment and storage medium |
| CN117908528A (en) * | 2022-10-14 | 2024-04-19 | 珠海一微半导体股份有限公司 | Laser robot path planning method and chip |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108898605A (en) * | 2018-07-25 | 2018-11-27 | 电子科技大学 | A kind of grating map dividing method based on figure |
| CN109191482A (en) * | 2018-10-18 | 2019-01-11 | 北京理工大学 | A kind of image combination and segmentation method based on region adaptivity spectral modeling threshold value |
| CN111063029A (en) * | 2019-12-11 | 2020-04-24 | 深圳市优必选科技股份有限公司 | Map construction method and device, computer readable storage medium and robot |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| ITRM20040563A1 (en) * | 2004-11-12 | 2005-02-12 | St Microelectronics Srl | METHOD OF PROCESSING A DIGITAL IMAGE. |
-
2020
- 2020-04-27 CN CN202010341056.9A patent/CN111681246B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108898605A (en) * | 2018-07-25 | 2018-11-27 | 电子科技大学 | A kind of grating map dividing method based on figure |
| CN109191482A (en) * | 2018-10-18 | 2019-01-11 | 北京理工大学 | A kind of image combination and segmentation method based on region adaptivity spectral modeling threshold value |
| CN111063029A (en) * | 2019-12-11 | 2020-04-24 | 深圳市优必选科技股份有限公司 | Map construction method and device, computer readable storage medium and robot |
Non-Patent Citations (2)
| Title |
|---|
| P.Buschka et al..A virtual sensor for room detection.《IEEE/RSJ International Conference on Intelligent Robots and Systems》.2002,第637-642页. * |
| 彩色图像分割方法综述;杨红亚 等;软件导刊;第17卷(第04期);第1-5页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111681246A (en) | 2020-09-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111681246B (en) | Region segmentation method of laser map | |
| WO2020134082A1 (en) | Path planning method and apparatus, and mobile device | |
| CN111258320B (en) | Robot obstacle avoidance method and device, robot and readable storage medium | |
| Yokoya et al. | Range image segmentation based on differential geometry: A hybrid approach | |
| CN102945368B (en) | Method for positioning and identifying laser character of beer bottle cap | |
| CN111595356B (en) | Method for constructing working area of laser navigation robot | |
| JP2023522262A (en) | MAP GENERATION METHOD, APPARATUS, STORAGE MEDIUM AND PROCESSOR | |
| CN110390306B (en) | Method for detecting right-angle parking space, vehicle and computer readable storage medium | |
| CN111631642B (en) | Working area expanding method based on laser map, chip and robot | |
| US11514633B1 (en) | Systems and methods for automating conversion of drawings to indoor maps and plans | |
| JP6649743B2 (en) | Matching evaluation device and matching evaluation method | |
| CN115661173B (en) | Remote sensing image-based land parcel segmentation method | |
| CN111640323A (en) | Road condition information acquisition method | |
| CN111681250A (en) | Segmentation method based on laser grid map | |
| CN113282088A (en) | Unmanned driving method, device and equipment of engineering vehicle, storage medium and engineering vehicle | |
| US6963664B2 (en) | Segmentation of digital images | |
| CN113516765B (en) | Map management method, map management device and intelligent equipment | |
| CN114365974A (en) | Indoor cleaning and partitioning method and device and floor sweeping robot | |
| US11703350B2 (en) | System and method for automatically annotating a map | |
| CN114140760A (en) | Obstacle detection interference removing method and device in intelligent driving and computer equipment | |
| CN116339302A (en) | Edge small area dividing and cleaning method and area merging and displaying method | |
| CN109614952B (en) | Target signal detection and identification method based on waterfall plot | |
| CN117948984B (en) | Path planning method of mobile operation robot in variable width traffic domain | |
| US20240020846A1 (en) | Corner point detection method and apparatus | |
| Mandelbaum | Sensor processing for mobile robot localization, exploration and navigation |
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 | ||
| CB02 | Change of applicant information |
Address after: 519000 2706, No. 3000, Huandao East Road, Hengqin new area, Zhuhai, Guangdong Applicant after: Zhuhai Yiwei Semiconductor Co.,Ltd. Address before: Room 105-514, No.6 Baohua Road, Hengqin New District, Zhuhai City, Guangdong Province Applicant before: AMICRO SEMICONDUCTOR Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |