Computer Vision for Site-Specific Weed Management in Precision Agriculture: A Review
Puranjit Singh, Biquan Zhao, Yeyin Shi
Abstract
Weed management is always a challenge in crop production, exacerbated by the issue of herbicide resistance. Excessive herbicide application not only leads to the development of herbicide resistance weeds but also causes environmental problems. In precision agriculture, innovative weed management methods, especially advanced remote sensing and computer vision technologies for targeted herbicide applications, i.e., site-specific weed management (SSWM), have recently drawn a lot of attention. Challenges exist in accurately and reliably detecting diverse weed species under varying field conditions. Significant efforts have been made to advance computer vision technologies for weed detection. This comprehensive review provides an in-depth examination of various methodologies used in developing weed detection systems. These methodologies encompass a spectrum ranging from traditional image processing techniques to state-of-the-art machine and deep learning models. The review further discusses the potential of these methods for real-time applications, highlighting recent innovations, and identifying future research hotspots in SSWM. These advancements hold great promise for further enhancing and innovating weed management practices in precision agriculture.