EcoWeedNet: A Lightweight and Automated Weed Detection Method for Sustainable Next-Generation Agricultural Consumer Electronics

TL;DR

EcoWeedNet tackles weed detection for sustainable precision agriculture by integrating parameter-free attention modules SPAB and SimAM within a lightweight backbone/neck design to preserve high accuracy on edge devices. It employs a three-scale detection head and efficient feature fusion to maintain robust performance on the CottonWeedDet12 dataset, while keeping parameters and GFLOPs far lower than large models. The approach achieves approximately $\mathrm{mAP}_{50}\approx95\%$ with around $2.78\text{M}$ parameters and $9.3$ GFLOPs, and GradCAM-based explanations confirm focused weed-region attention, validated through 5-fold cross-validation and ablations. Practically, EcoWeedNet enables real-time, low-energy weed detection on consumer agricultural electronics, offering a clear path toward scalable, carbon-aware precision agriculture.

Abstract

Sustainable agriculture plays a crucial role in ensuring world food security for consumers. A critical challenge faced by sustainable precision agriculture is weed growth, as weeds compete for essential resources with crops, such as water, soil nutrients, and sunlight, which notably affect crop yields. The adoption of automated computer vision technologies and ground agricultural consumer electronic vehicles in precision agriculture offers sustainable, low-carbon solutions. However, prior works suffer from issues such as low accuracy and precision, as well as high computational expense. This work proposes EcoWeedNet, a novel model that enhances weed detection performance without introducing significant computational complexity, aligning with the goals of low-carbon agricultural practices. The effectiveness of the proposed model is demonstrated through comprehensive experiments on the CottonWeedDet12 benchmark dataset, which reflects real-world scenarios. EcoWeedNet achieves performance comparable to that of large models (mAP@0.5 = 95.2%), yet with significantly fewer parameters (approximately 4.21% of the parameters of YOLOv4), lower computational complexity and better computational efficiency 6.59% of the GFLOPs of YOLOv4). These key findings indicate EcoWeedNet's deployability on low-power consumer hardware, lower energy consumption, and hence reduced carbon footprint, thereby emphasizing the application prospects of EcoWeedNet in next-generation sustainable agriculture. These findings provide the way forward for increased application of environmentally-friendly agricultural consumer technologies.

Figures (10)

• Figure 1: Illustration of the proposed lightweight, computationally- and energy-efficient EcoWeedNet model's performance in sustainable (low-carbon) consumer electronics-based precision agriculture applications for automated inspection and detection of weeds.
• Figure 2: Architecture of the proposed EcoWeedNet model.
• Figure 3: Important blocks in the architecture of the proposed EcoWeedNet model.
• Figure 4: Dataset Sample
• Figure 5: Comparative GradCAM$++$ visualizations for the baseline YOLOv11n and EcoWeedNet feature responses. The proposed EcoWeedNet demonstrated better emphasis and focus on weed-relevant regions.