Search

CN-122023440-A - Route planning method, route planning device, electronic equipment and storage medium

CN122023440ACN 122023440 ACN122023440 ACN 122023440ACN-122023440-A

Abstract

The invention discloses a route planning method, a route planning device, electronic equipment and a storage medium. The method comprises the steps of obtaining a plurality of target images collected by a cleaning device based on a binocular depth camera carried on the cleaning device, dividing first areas corresponding to a preset number of target images according to first size information of the target images, determining first boundary areas of the first areas based on boundary characteristic information of the first areas, determining whether the first areas are effective boundary areas based on the occupation ratio condition of depth information on two sides of the first boundary areas in the first areas, determining the first areas which are determined to be the effective boundary areas in the first areas to be second areas, determining boundary position information of the second areas, and determining cleaning routes of the cleaning device based on all the boundary position information after the cleaning device scans along a preset boundary route of a photovoltaic panel. The invention solves the problem of inaccurate cleaning route planning of the cleaning equipment caused by inaccurate edge detection of the photovoltaic panel.

Inventors

  • WANG FAN

Assignees

  • 星逻智能科技(苏州)有限公司

Dates

Publication Date
20260512
Application Date
20260123

Claims (11)

  1. 1. A method of route planning, the method comprising: acquiring a plurality of target images acquired by cleaning equipment based on a binocular depth camera carried on the cleaning equipment, wherein the target images are images obtained by scanning operation of the cleaning equipment along a preset boundary route of a photovoltaic panel before the cleaning operation of the photovoltaic panel is executed by the cleaning equipment; dividing a preset number of first areas corresponding to the target images according to the first size information of the target images, and determining a first boundary area of the first areas based on the boundary characteristic information of the first areas; Determining whether the first area is an effective boundary area or not based on the ratio situation of the depth information on two sides of the first boundary area in the first area, determining the first area which is determined to be the effective boundary area in the first area as a second area, and determining the boundary position information of the second area; And after the cleaning device finishes scanning along the preset boundary route of the photovoltaic panel, determining the cleaning route of the cleaning device based on all boundary position information.
  2. 2. The method according to claim 1, wherein dividing a preset number of first areas corresponding to the target image according to the first size information of the target image includes: determining second size information of an effective detection zone according to the first size information of the target image, wherein the effective detection zone is an area containing at least preset reference quantity of boundary characteristic information in the target image; the effective detection zone is divided into a preset number of first areas based on the first size information and the second size information.
  3. 3. The method according to claim 1 or 2, wherein after the determining of the first boundary region of the first region based on the boundary feature information of the first region, the method further comprises: determining a first center position of the first boundary region, dividing the first boundary region into a second boundary region and a third boundary region based on the first center position; Determining a second center position of the second boundary region and a third center position of the third boundary region; Determining angle information of the first area based on the second center position and the third center position, wherein the angle information is used for reflecting an included angle between a target line segment and the right side edge or the left side edge of the target image, and the right side edge or the left side edge is a anticlockwise or clockwise route depending on a preset boundary route; Determining whether the first region is an effective region based on the angle information; If the first area is an effective area, continuously determining whether the first area is an effective boundary area or not based on the ratio situation of the depth information at two sides of the first boundary area in the first area; and if the first area is not the effective area, deleting the corresponding first area.
  4. 4. The method of claim 3, wherein the determining whether the first region is a valid boundary region based on a duty cycle of depth information on both sides of the first boundary region in the first region comprises: Determining a line segment which passes through the connection line of the second center position and the third center position and intersects the target image as a target line segment; Dividing the first region into a first side region and a second side region based on the target line segment; determining a first median depth based on the depth information of the first side region, and determining a second median depth based on the depth information of the second side region; Based on the first median depth and the second median depth, it is determined whether the first region is a valid boundary region.
  5. 5. A method according to claim 3, wherein determining whether the first region is a valid boundary region based on the first and second median depths comprises: and determining whether the first area is a valid boundary area based on a difference value between the first median depth and the second median depth and a preset difference value.
  6. 6. The method according to claim 1 or 2, wherein before the dividing of a preset number of first areas corresponding to the target images according to the first size information of the target images, the method further comprises: determining an area with a preset height above the bottom edge of the target image as a third area, and dividing the third area into a preset number of grid areas; Determining pixel points larger than a first depth threshold value in the depth values of the pixel points of the grid area as first pixel points, and determining a first pixel point occupation ratio of the number of the first pixel points and the total pixel points of the grid area; If the first pixel point duty ratio is larger than or equal to a preset proportion, determining the grid area to be in a first state, wherein the first state is used for describing that the grid area does not have boundary characteristic information of the photovoltaic panel; If the first pixel point duty ratio is smaller than the preset proportion, determining the pixel points larger than a second depth threshold value in the depth values of the pixel points of the grid area as second pixel points, and determining the second pixel point duty ratio of the number of the second pixel points to the total pixel points of the grid area, wherein the first depth threshold value is smaller than the second depth threshold value; Determining state information of the grid region based on the second pixel point duty ratio and the average depth value of the grid region, wherein the state information is used for describing the characteristic duty ratio condition of boundary characteristic information of the photovoltaic panel in the grid region; Based on the status information of all the grid areas, it is determined whether the target image is a valid image.
  7. 7. The method of claim 6, wherein determining the status information of the grid region based on the second pixel point duty cycle and the average depth value of the grid region comprises: Determining target confidence coefficient of the grid region based on the second pixel point duty ratio, wherein the target confidence coefficient is used for reflecting the characteristic duty ratio condition of boundary characteristic information of the photovoltaic panel in the grid region; if the target confidence coefficient is larger than a preset confidence coefficient threshold value and the average depth value is larger than or equal to a third depth threshold value, determining the state information of the grid region to be a second state, wherein the second state is used for describing that the characteristic ratio of the boundary characteristic information of the photovoltaic panel in the grid region is a first characteristic ratio; If the average depth value is smaller than a third depth threshold value, determining the state information of the grid area to be a third state, wherein the third state is used for describing that the characteristic ratio of the boundary characteristic information of the photovoltaic panel in the grid area is a second characteristic ratio; and if the target confidence coefficient is larger than a preset confidence coefficient threshold value and the average depth value is larger than or equal to a fourth depth threshold value, determining the state information of the grid region to be a first state, wherein the fourth depth threshold value is larger than the third depth threshold value.
  8. 8. The method of claim 7, wherein determining whether the target image is a valid image based on status information of all the grid areas comprises: if the number of the second states is greater than or equal to the preset number, determining that the target image is an effective image, continuing to execute subsequent image processing operation, otherwise, determining that the target image is not the effective image, and deleting the corresponding target image.
  9. 9. A route planning device, the device comprising: The system comprises a cleaning device, an image acquisition module, a target image acquisition module and a display module, wherein the cleaning device is used for carrying out cleaning operation on a photovoltaic panel, the image acquisition module is used for acquiring a plurality of target images acquired by the cleaning device based on a binocular depth camera carried on the cleaning device, and the target images are images acquired by the cleaning device by scanning operation along a preset boundary route of the photovoltaic panel before the cleaning operation is carried out on the photovoltaic panel by the cleaning device; The area determining module is used for dividing a preset number of first areas corresponding to the target images according to the first size information of the target images, and determining a first boundary area of the first areas based on the boundary characteristic information of the first areas; the information determining module is used for determining whether the first area is an effective boundary area or not based on the ratio situation of the depth information on two sides of the first boundary area in the first area, determining the first area which is determined to be the effective boundary area in the first area as a second area and determining the boundary position information of the second area; And the route planning module is used for determining the cleaning route of the cleaning equipment based on all boundary position information after the cleaning equipment finishes scanning along the preset boundary route of the photovoltaic panel.
  10. 10. An electronic device, the electronic device comprising: at least one processor, and A memory communicatively coupled to the at least one processor, wherein, The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the route planning method of any one of claims 1-8.
  11. 11. A computer readable storage medium, characterized in that the computer readable storage medium stores computer instructions for causing a processor to implement the route planning method of any of claims 1-8 when executed.

Description

Route planning method, route planning device, electronic equipment and storage medium Technical Field The present invention relates to the field of image processing technologies, and in particular, to a route planning method, a route planning device, an electronic device, and a storage medium. Background With the continuous expansion of the scale of photovoltaic generators and the diversification of deployment areas, the problem of efficiency loss caused by dust accumulation on the surface of photovoltaic panels is increasingly prominent. Thus, photovoltaic panel cleaning is necessary to improve photovoltaic system energy efficiency. At present, a full-automatic cleaning device is generally adopted to clean a photovoltaic panel, but the full-automatic cleaning device has the risk of falling from high altitude in the edge process of cleaning the photovoltaic panel. Therefore, the full-automatic cleaning device needs to accurately determine the photovoltaic panel side edges to ensure that the full-automatic cleaning device can plan a cleaning route based on information of the photovoltaic panel edges. At present, the characteristic recognition of the photovoltaic panel generally carries out the characteristic recognition of the target through the collected image to determine the edge of the photovoltaic panel on the photovoltaic panel, but the characteristic recognition of the target has the defects of limited precision and frequent false detection. Disclosure of Invention The invention provides a route planning method, a route planning device, electronic equipment and a storage medium, which are used for solving the problem of inaccurate cleaning route planning of cleaning equipment caused by inaccurate edge detection of a photovoltaic panel. According to an aspect of the present invention, there is provided a route planning method, the method comprising: acquiring a plurality of target images acquired by cleaning equipment based on a binocular depth camera carried on the cleaning equipment, wherein the target images are images obtained by scanning operation of the cleaning equipment along a preset boundary route of a photovoltaic panel before the cleaning operation of the photovoltaic panel is executed by the cleaning equipment; dividing a preset number of first areas corresponding to the target images according to the first size information of the target images, and determining a first boundary area of the first areas based on the boundary characteristic information of the first areas; Determining whether the first area is an effective boundary area or not based on the ratio situation of the depth information on two sides of the first boundary area in the first area, determining the first area which is determined to be the effective boundary area in the first area as a second area, and determining the boundary position information of the second area; And after the cleaning device finishes scanning along the preset boundary route of the photovoltaic panel, determining the cleaning route of the cleaning device based on all boundary position information. According to another aspect of the present invention, there is provided a route planning apparatus, the apparatus comprising: The system comprises a cleaning device, an image acquisition module, a target image acquisition module and a display module, wherein the cleaning device is used for carrying out cleaning operation on a photovoltaic panel, the image acquisition module is used for acquiring a plurality of target images acquired by the cleaning device based on a binocular depth camera carried on the cleaning device, and the target images are images acquired by the cleaning device by scanning operation along a preset boundary route of the photovoltaic panel before the cleaning operation is carried out on the photovoltaic panel by the cleaning device; The area determining module is used for dividing a preset number of first areas corresponding to the target images according to the first size information of the target images, and determining a first boundary area of the first areas based on the boundary characteristic information of the first areas; the information determining module is used for determining whether the first area is an effective boundary area or not based on the ratio situation of the depth information on two sides of the first boundary area in the first area, determining the first area which is determined to be the effective boundary area in the first area as a second area and determining the boundary position information of the second area; And the route planning module is used for determining the cleaning route of the cleaning equipment based on all boundary position information after the cleaning equipment finishes scanning along the preset boundary route of the photovoltaic panel. According to another aspect of the present invention, there is provided an electronic apparatus including: at least one processor, and A memory communicativel