Deep Learning-Based Weed Detection in Turf: A Review

Precision spraying can significantly reduce herbicide input for turf weed management. A major challenge autonomous precision is to accurately and reliably detect weeds growing in turf. Deep convolutional neural networks (DCNNs), an important artificial intelligent tool, demonstrated extraordinary capability learn complex features from images. The feasibility of using DCNNs, including various image classification or object detection networks, has been investigated Due the high level performance detection, DCNNs are suitable ground-based discrimination However, reliable may be subject influence (e.g., biotypes, species, densities, growth stages) factors quality, mowing height, dormancy vs. non-dormancy). present review article summarizes previous research findings as machine vision decision system smart sprayers spraying, with aim providing insights into future research.