RESUMO
As a large agricultural and population country, China's annual demand for food is significant. The crop yield will be affected by various natural disasters every year, and one of the most important factors affecting crops is the impact of insect pests. The key to solving the problem is to detect, identify and provide feedback in time at the initial stage of the pest. In this paper, according to the pest picture data obtained through the pest detection lamp in the complex natural background and the marking categories of agricultural experts, the pest data set pest rotation detection (PRD21) in different natural environments is constructed. A comparative study of image recognition is carried out through different target detection algorithms. The final experiment proves that the best algorithm for rotation detection improves mean Average Precision by 18.5% compared to the best algorithm for horizontal detection, reaching 78.5%. Regarding Recall, the best rotation detection algorithm runs 94.7%, which is 7.4% higher than horizontal detection. In terms of detection speed, the rotation detection time of a picture is only 0.163s, and the model size is 66.54MB, which can be embedded in mobile devices for fast detection. This experiment proves that rotation detection has a good effect on pests' detection and recognition rate, which can bring new application value and ideas, provide new methods for plant protection, and improve grain yield.
