Technical vision system of qadcopter for precision farming

Abstract

Precision farming is a modern direction of agricultural development, which opens new opportunities to increase the productivity of each land by taking into account its specific features. Its implementation requires an assessment of the spatial heterogeneity of soils and agricultural vegetation. This ensures the timely application of adequate agricultural measures in those places that need it.
 In this work, ways of solving the problems of precision farming are analyzed. The expediency of using a quadcopter with a technical vision system to obtain high-resolution images of the studied land plot is shown.
 Specialized systems of technical vision for the tasks of precision agriculture are currently not mass-produced. Therefore, a block diagram of the quadcopter's technical vision system was developed, which made it possible to determine the necessary technical characteristics and select the appropriate industrial equipment.
 Necessary software and algorithms were developed for the technical vision system. The proposed algorithm is based on the use of high-quality images from the technical vision system of the quadcopter, low-resolution satellite images and the results of agrochemical analyzes. When processing data, individual images taken with a quadcopter camera are combined into a single orthofotoplan. Then NDVI indicators from satellite images and results of agrochemical analyzes are added to it. The identified zones of plant fertility make it possible to build a differentiated fertilizer application map and a map of the agro-operations task plan for precision farming equipment.
 To verify the results, studies were conducted on a test site with an area of 57.4 hectares, which was located in the Chaplin district of Kherson region. With the help of the selected equipment and the developed algorithms, images of the area were obtained, an orthofotoplan with plant germination zones was formed, and a map of fertilizer application for precision farming equipment was developed. Field studies fully confirmed the correctness of the calculations and the performance of the proposed algorithms.