Unmanned aerial vehicle route planning method suitable for agricultural investigation

Abstract

The invention discloses an unmanned aerial vehicle route planning method suitable for agricultural investigation; the method comprises the steps: firstly, obtaining an overall image, obtaining the coordinate information of a ground control point, carrying out the image geometric correction of high-resolution satellite remote sensing data and the aerial photo of an unmanned aerial vehicle in a high-flight to-be-investigated region; then inputting the corrected unmanned aerial vehicle aerial photo into a pre-trained YOLOv3 field obstacle recognition model to obtain an obstacle coordinate of the area, and using a multi-scale combination aggregation segmentation algorithm to realize field boundary automatic extraction; obtaining the central points of the field pieces by using the polygonal triangulation skeleton diagram, eliminating redundant central points of the field pieces according to the coverage range of pictures shot by the unmanned aerial vehicle, and generating an initial route; then, generating a buffer area in a certain range by taking the obstacle as the center, judging whether the initial waypoint is in the buffer area or not by adopting a ray guide method; finally, eliminating the waypoint in the buffer area, and generating a final route.

Description

technical field [0001] The invention relates to the field of UAV route planning, in particular to a UAV route planning method suitable for agricultural surveys. Background technique [0002] With the rapid development of my country's "smart agriculture", it will become an inevitable trend for agriculture to become intelligent and informatized. In recent years, the country has vigorously promoted the modernization of agriculture. With its unique advantages in flexibility, high resolution, and less affected by weather, drones have penetrated into all aspects of agricultural production. Compared with traditional remote sensing satellite image data, UAVs can carry out tasks in real time according to different agricultural needs and terrain characteristics, which solves the problems of complex data and scale sensitivity of remote sensing satellite images. [0003] However, in the actual UAV agricultural data collection, there are the following deficiencies: [0004] 1. The fiel...

AI Technical Summary

Problems solved by technology

[0004] 1. The field environment is complex: the distribution of rural buildings is relatively scattered, the network of utility poles and wires is intricate, the heights of trees are different, the network of rivers is densely covered, and the size of fields is unevenly distributed. data collection

[0005] 2. Complex and diverse crop planting: my country's current agriculture is generally in the mode of smallholder planting, using complex planting modes such as multiple cropping, intercropping, and interplanting. There are also characteristics of spatial diversity, dynamics, and seasonal variability in crop planting, which lead to fundamental uncertainty. Man-machine path planning is not suitable for agricultural census work

[0006] 3. Typical obstacle avoidance systems are not suitable for farmland operations: the principle of UAV obstacle avoidance technology is to judge the distance between obstacles and itself according to the sensors carried by the UAV, and then control the output of the motor to avoid obstacles

However, this method is susceptible to environmental interference and is only suitable for sensing short-distance obstacles

Images