CN-122015874-A - Intelligent planning method for pest control pesticide spraying path of fritillaria thunbergii

CN122015874ACN 122015874 ACN122015874 ACN 122015874ACN-122015874-A

Abstract

The invention relates to the technical field of intelligent plant protection, in particular to an intelligent planning method for a pesticide spraying path for controlling plant diseases and insect pests of fritillaria thunbergii, which comprises the steps of obtaining a thermal imaging image of a fritillaria thunbergii planting area and a spraying planning path of an unmanned aerial vehicle; obtaining conflict areas according to the quantity distribution of the unmanned aerial vehicle spraying planning paths at the positions of each grid area and the pixel values in the thermal imaging images; and re-planning the unmanned aerial vehicle spraying planning path according to the flying difficulty index of each conflict area on the spraying planning path of each unmanned aerial vehicle and the flying difficulty index change condition of other grid areas. The method and the device avoid space conflict in the flight process of the unmanned aerial vehicle caused by local path optimization, and improve the rationality of the unmanned aerial vehicle path planning scheme.

Inventors

HUI NING
LIU JIA
GE WEIHONG
HU WANYING
LI MENGMENG
TANG RUI
YANG YANG
WANG HUI
WANG LERAN
ZHU HONGHAI
Zheng Qiaomei

Assignees

浙江中医药大学(淳安千岛湖)研究院有限公司
浙江千岛湖美誉药业有限公司

Dates

Publication Date: 20260512
Application Date: 20260413

Claims (10)

1. An intelligent planning method for a pesticide spraying path for pest control of fritillary bulb is characterized by comprising the following steps: acquiring a thermal imaging image of a fritillaria planting area and a spraying planning path of each unmanned aerial vehicle, wherein the spraying planning path comprises a plurality of grid areas of the fritillaria planting area; Screening the grid areas according to the quantity distribution of the unmanned aerial vehicle spraying planning paths at the positions of the grid areas and the pixel value of the grid areas in the thermal imaging image to obtain conflict areas; according to the space-time distance distribution between each grid region and the adjacent grid region on the spraying planning path of each unmanned aerial vehicle, combining the pixel value of each conflict region in the thermal imaging image to obtain the flying difficulty index of each grid region on the spraying planning path of each unmanned aerial vehicle; and re-planning the unmanned aerial vehicle spraying planning path according to the change condition of the flying difficulty index of each conflict area and the flying difficulty index of other grid areas on the spraying planning path of each unmanned aerial vehicle.
2. The intelligent planning method of a pesticide spraying path for pest control of thunberg fritillary bulb according to claim 1, wherein the screening the grid areas to obtain the conflict areas according to the number distribution of the unmanned aerial vehicle spraying planned paths at the position of each grid area and the pixel value of each grid area in the thermal imaging image specifically comprises: acquiring the quantity ratio of the spraying planning paths of different unmanned aerial vehicles at the position of each grid area, and taking the ratio of the quantity ratio to the pixel value of each grid area in the thermal imaging area as a conflict characteristic index of each grid area; And screening the grid areas according to the conflict characteristic indexes of each grid area to obtain conflict areas.
3. The intelligent planning method of the pesticide spraying path for pest control of thunberg fritillary bulb according to claim 2, wherein the screening of the grid areas according to the conflict characteristic index of each grid area to obtain the conflict areas specifically comprises: and taking a grid area corresponding to the conflict characteristic index which is larger than or equal to a preset conflict threshold value as a conflict area.
4. The intelligent planning method for the pest control and pesticide spraying path of fritillary bulb according to claim 1, wherein the obtaining the flying difficulty index of each grid area on the spraying planning path of each unmanned aerial vehicle according to the space-time distance distribution between each grid area and the adjacent grid area on the spraying planning path of each unmanned aerial vehicle by combining the pixel value of each conflict area in the thermal imaging image specifically comprises the following steps: According to the flight distance distribution between the selected grid area and the adjacent grid area on each unmanned aerial vehicle spraying planning path, obtaining the flight cost factor of the selected grid area on each unmanned aerial vehicle spraying planning path; Taking the accumulated sum of the differences between the flight cost factors of the selected grid area in the selected spray planning path and the flight cost factors of other unmanned aerial vehicle spray planning paths as the cost fluctuation degree of the selected grid area, and taking the ratio of the flight cost factors of the selected grid area in the selected spray planning path to the cost fluctuation degree as the space-time reconstruction parameter of the selected grid area in the selected spray planning path; The selected grid area is any grid area on a spraying planning path, and the selected spraying planning path is the spraying planning path of any unmanned aerial vehicle; and obtaining the flight difficulty index of the selected grid region according to the space-time distance distribution between the selected grid region and the adjacent grid region on the spray planning path, the pixel value in the thermal imaging image and the space-time reconstruction parameter.
5. The intelligent planning method for the pest control pesticide spraying path of fritillary bulb according to claim 4, wherein the method is characterized in that the flight cost factor of the selected grid area in each unmanned aerial vehicle spraying planning path is obtained according to the flight distance distribution between the selected grid area and the adjacent grid area in each unmanned aerial vehicle spraying planning path, and specifically comprises the following steps: Acquiring the flight distance of the unmanned aerial vehicle in each grid area on a spraying planning path; The method comprises the steps of acquiring a first flight difference of the absolute value of the difference of the flight distance of an unmanned aerial vehicle between a selected grid area and a first adjacent grid area for a spraying planning path of any unmanned aerial vehicle, acquiring a second flight difference of the absolute value of the difference of the flight distance of the unmanned aerial vehicle between the selected grid area and a second adjacent grid area, wherein the accumulated sum of the first flight difference and the second flight difference is a flight cost factor of the selected grid area; wherein the first adjacent grid region is a previous grid region adjacent to the selected grid region on the spray planned path and the second adjacent grid region is a next grid region adjacent to the selected grid region on the spray planned path.
6. The intelligent planning method for the pest control and pesticide spraying path of thunberg fritillary bulb according to claim 5, wherein the obtaining the flight difficulty index of the selected grid area according to the space-time distance distribution between the selected grid area and the adjacent grid area on the spraying planning path, the pixel value in the thermal imaging image and the space-time reconstruction parameter specifically comprises: determining a space-time distance between the selected grid area and a second adjacent grid area based on the time corresponding to the selected grid area on the spray planning path and the position of the selected grid area; and taking the ratio of the pixel value of the selected grid area in the thermal imaging image and the product of the space-time distance and the space-time reconstruction parameter as a flight difficulty index of the selected grid area.
7. The intelligent planning method for the pest control pesticide spraying path of the fritillary bulb according to claim 1, wherein the re-planning of the unmanned aerial vehicle spraying planning path is performed according to the change condition of the flying difficulty index of each conflict area and the flying difficulty index of other grid areas on the spraying planning path of each unmanned aerial vehicle, and specifically comprises the following steps: for any one spray planning path, acquiring other non-conflict areas except a target conflict area as candidate grid areas, wherein the target conflict area is any conflict area on the spray planning path; Obtaining a path reconstruction parameter of each candidate grid region according to the difference of the flight difficulty index between the target conflict region and each candidate grid region; and adjusting the spraying planning path according to the path reconstruction parameters of each candidate grid area to obtain a reconstruction path of the unmanned aerial vehicle spraying planning path.
8. The intelligent planning method for the pesticide spraying path for Thunberg fritillary bulb disease and pest control according to claim 7, wherein the obtaining the path reconstruction parameters of each candidate grid area according to the difference of the flight difficulty index between the target conflict area and each candidate grid area specifically comprises: and taking the difference value of the flight difficulty index between the target conflict area and each candidate grid area as a path reconstruction parameter of each candidate grid area.
9. The intelligent planning method for the pesticide spraying path for the pest control of thunberg fritillary bulb according to claim 7, wherein the adjusting the spraying planning path according to the path reconstruction parameters of each candidate grid area, to obtain the reconstructed path of the unmanned aerial vehicle spraying planning path, comprises the following specific steps: Acquiring a candidate grid region corresponding to the maximum value of the path reconstruction parameters as an adjustment grid region, wherein the path reconstruction parameters are larger than a preset reconstruction threshold value; and adjusting the target conflict area in the spray planning path into an adjusted grid area, and re-planning the grid area behind the target conflict area in the adjusted spray planning path to obtain a reconstruction path.
10. The intelligent planning method for the spraying path for pest control of fritillary bulb according to claim 1, wherein the method for acquiring the spraying planned path of each unmanned aerial vehicle comprises the following steps: Acquiring the flight distance of the unmanned aerial vehicle in each grid area, and taking the average value of the pixel values of all pixel points of each grid area in a thermal imaging diagram as the pest and disease damage intensity of each grid area; and taking the negative correlation coefficient of the flight distance of the unmanned aerial vehicle as an pheromone of an ant colony algorithm, taking the plant disease and insect pest intensity as a priority weight, and planning the flight path of the unmanned aerial vehicle by utilizing the ant colony algorithm to obtain a spraying planning path of each unmanned aerial vehicle.

Description

Intelligent planning method for pest control pesticide spraying path of fritillaria thunbergii Technical Field The invention relates to the technical field of intelligent plant protection, in particular to an intelligent planning method for a pesticide spraying path for pest control of fritillaria thunbergii. Background Along with the deep landing of accurate agricultural technology, plant protection unmanned aerial vehicle relies on core advantages such as operating efficiency is high, topography adaptability is strong, pesticide application precision is high, has become the key equipment of the green prevention and control of large tracts of land farmland plant diseases and insect pests, especially in the scale planting scene of special cash crops such as fritillary bulb, uses increasingly extensively. However, the particularity of the planting area of fritillary bulb (which is distributed on sloping fields and hilly areas, the terrain is complex, the plants are short (30-50 cm), the planting is dense and sensitive to pesticides), and the real requirement of multi-machine collaborative operation make the traditional unmanned plane path planning algorithm face a bottleneck. The traditional path planning algorithm, for example, an ant colony algorithm aims at the shortest flight distance of a single unmanned aerial vehicle, can guide multiple unmanned aerial vehicles to preferentially select areas with flat terrain and close to a base station (such as a slope bottom land), so that the areas become high-frequency conflict areas, but the pest and disease risk of fritillary bulb can be concentrated in a slope (high humidity and easy occurrence of diseases), and the traditional algorithm cannot balance the distance and the pest and disease priority. Therefore, the existing spray path planning method is easy to cause cross overlapping of multiple paths, so that the rationality of path planning is poor. Disclosure of Invention In order to solve the technical problem that the rationality of path planning is poor due to the fact that multiple paths are overlapped in a crossing mode easily in the conventional pesticide spraying path planning method, the invention aims to provide an intelligent pesticide spraying path planning method for controlling the disease and pest damage of fritillary bulb, and the adopted technical scheme is as follows: acquiring a thermal imaging image of a fritillaria planting area and a spraying planning path of each unmanned aerial vehicle, wherein the spraying planning path comprises a plurality of grid areas of the fritillaria planting area; Screening the grid areas according to the quantity distribution of the unmanned aerial vehicle spraying planning paths at the positions of the grid areas and the pixel value of the grid areas in the thermal imaging image to obtain conflict areas; according to the space-time distance distribution between each grid region and the adjacent grid region on the spraying planning path of each unmanned aerial vehicle, combining the pixel value of each conflict region in the thermal imaging image to obtain the flying difficulty index of each grid region on the spraying planning path of each unmanned aerial vehicle; and re-planning the unmanned aerial vehicle spraying planning path according to the change condition of the flying difficulty index of each conflict area and the flying difficulty index of other grid areas on the spraying planning path of each unmanned aerial vehicle. Preferably, the screening the grid areas according to the number distribution of the unmanned aerial vehicle spraying planned paths at the position of each grid area and the pixel value of each grid area in the thermal imaging image to obtain the conflict area specifically includes: acquiring the quantity ratio of the spraying planning paths of different unmanned aerial vehicles at the position of each grid area, and taking the ratio of the quantity ratio to the pixel value of each grid area in the thermal imaging area as a conflict characteristic index of each grid area; And screening the grid areas according to the conflict characteristic indexes of each grid area to obtain conflict areas. Preferably, the screening the grid area according to the conflict characteristic index of each grid area to obtain a conflict area specifically includes: and taking a grid area corresponding to the conflict characteristic index which is larger than or equal to a preset conflict threshold value as a conflict area. Preferably, the obtaining, according to the space-time distance distribution between each grid region and the adjacent grid region on the spraying planned path of each unmanned aerial vehicle, the flight difficulty index of each grid region on the spraying planned path of each unmanned aerial vehicle by combining the pixel value of each conflict region in the thermal imaging image specifically includes: According to the flight distance distribution between the selected grid area and the a