人工智能
计算机科学
农业
有害生物分析
机器学习
植物病害
种植
农业害虫
深度学习
农业工程
生物技术
工程类
生物
生态学
植物
作者
Pratibha Nayar,Shivank Chhibber,Ashwani Kumar Dubey
标识
DOI:10.1109/cises58720.2023.10183522
摘要
Recently, the use of artificial intelligence (AI) in agriculture has become the most important due to its applicability in a non-exhaustive sector of the economy. The creative approach to the introduction of agricultural technology is highly increased today. Advances in computer vision and artificial intelligence (AI) have enabled fast and efficient pest recognition algorithms. Control of diseased leaves in the cropping stage is an important step. Detecting disease at an early stage and analysing affected leaves is always beneficial for agricultural development. Similarly, pest diseases hit down the development and production of Agri based resources, so their accurate recognition is required to use pesticides and eradicate the pests. In this study we provide a transfer learning-based explanation for detecting multiple diseases in different plant selections using images of healthy and diseased plants, derived from Plant Doc dataset. This paper shows a comparative study of various YOLO versions on the PlantDoc and Our own curated Plant Disease and Pest Detection Models based on YOLO versions v7 and v8 and the ability to perform detection much faster and with higher precision than the existing models developed previously.
科研通智能强力驱动
Strongly Powered by AbleSci AI