AUTHOR=Zhang Wei , Xia Xulu , Zhou Guotao , Du Jianming , Chen Tianjiao , Zhang Zhengyong , Ma Xiangyang 

TITLE=Research on the identification and detection of field pests in the complex background based on the rotation detection algorithm

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2022.1011499

DOI=10.3389/fpls.2022.1011499

ISSN=1664-462X

ABSTRACT=As a country with a large population, China's annual food demand is exceptionally high, and crop yields are affected by various natural disasters yearly. One of the most critical factors affecting crops is the impact of insect disasters. Detecting, identifying, and giving feedback in the early stage of pest disaster is the key to solving the problem. 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 scene environments is constructed. A comparative study of image recognition was carried out. The final experiment proves that the best algorithm for rotation detection improves mAP by 21.5% compared to the best algorithm for horizontal detection, reaching 78.5%. Regarding recall rate, 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 the detection and recognition rate of pests, which can bring new application value and ideas, provide new methods for plant protection, and improve grain yield.