Scholarlink

Conventional object detection machine learning models dedicated to the agriculture industry have improved since the origin of machine learning and computer vision. In this paper, we explore various state-of-the-art models built using different architectures as well as a density estimation model with context awareness for monitoring tassel growth. We explore the performance of pre-existing models like Faster R-CNN, ResNet and YOLOv5 on the Maize Counting Dataset.

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

YOLOv5-MasselNet: In-Field Maize Tassel Detection and Density Estimation Using YOLOv5

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Prerana Mukherjee,
  • Kavita Deshpande,
  • Vrishabhdhwaj Maharshi,
  • Bhavishya Raj

摘要

Conventional object detection machine learning models dedicated to the agriculture industry have improved since the origin of machine learning and computer vision. In this paper, we explore various state-of-the-art models built using different architectures as well as a density estimation model with context awareness for monitoring tassel growth. We explore the performance of pre-existing models like Faster R-CNN, ResNet and YOLOv5 on the Maize Counting Dataset.