Real-time on-device weed identification using a hardware-efficient lightweight CNN

Accurate and timely weed identification is fundamental to sustainable crop management, particularly for autonomous agricultural systems operating under strict energy and hardware constraints. While deep learning has significantly advanced image-based weed recognition, most existing models rely on GPU-based inference and therefore cannot be deployed directly in low-power field devices. In this study, we propose a hardware-efficient lightweight convolutional neural network (CNN), named TinyWeedNet, designed specifically for real-time on-device weed identification in precision agriculture. The model integrates multi-scale feature extraction, depthwise separable inverted residual blocks, and compact channel…

• SF
  Stiftelsen för Kunskaps- och Kompetensutveckling

  Award: 20180170, 20240029-H-02
• BU
  Beijing University of Agriculture

  Award: QJKC-2025020
• NI
  Nanjing Institute of Industry Technology