Scholarlink

<p>Agriculture remains a cornerstone for ensuring food security and is a vital employment sector, particularly in developing countries like India, where it contributes around 20% to the GDP. The agricultural process spans three crucial phases: pre-harvesting, harvesting, and post-harvesting. Recent advances in artificial intelligence (AI) and computer vision (CV) have revolutionized agriculture, offering innovative solutions to long-standing challenges. From crop disease detection and yield estimation in pre-harvesting, to real-time monitoring and automation during harvesting, and post-harvest quality control and loss reduction—these technologies have significantly enhanced productivity and precision. This paper provides an in-depth review of AI and CV applications across these stages, outlining the techniques used, challenges faced, and open issues that persist. The integration of these technologies not only minimizes labor but also improves crop quality and reduces losses, setting the stage for smarter, data-driven agriculture. However, significant hurdles such as data scarcity, model generalization, and technology adoption still remain, necessitating further research.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Artificial intelligence in agriculture: applications, approaches, and adversities across pre-harvesting, harvesting, and post-harvesting phases

  • 期刊论文

  • 发表日期：

    2025年4月14日

查看全文
  • Nidhi Upadhyay,
  • Anuja Bhargava

摘要

Agriculture remains a cornerstone for ensuring food security and is a vital employment sector, particularly in developing countries like India, where it contributes around 20% to the GDP. The agricultural process spans three crucial phases: pre-harvesting, harvesting, and post-harvesting. Recent advances in artificial intelligence (AI) and computer vision (CV) have revolutionized agriculture, offering innovative solutions to long-standing challenges. From crop disease detection and yield estimation in pre-harvesting, to real-time monitoring and automation during harvesting, and post-harvest quality control and loss reduction—these technologies have significantly enhanced productivity and precision. This paper provides an in-depth review of AI and CV applications across these stages, outlining the techniques used, challenges faced, and open issues that persist. The integration of these technologies not only minimizes labor but also improves crop quality and reduces losses, setting the stage for smarter, data-driven agriculture. However, significant hurdles such as data scarcity, model generalization, and technology adoption still remain, necessitating further research.