用多光谱数据提升农田杂草分割精度，模型轻量适合无人机实时部署。
Lightweight Multispectral Crop-Weed Segmentation for Precision Agriculture
- 融合RGB、近红外和红边波段，动态整合多源影像信息。
- 在WeedsGalore数据集上达到78.88%的平均IoU，比纯RGB模型高15.8个百分点。
- 仅870万参数，适合无人机与边缘设备，推动精准除草落地。
精准农业中的高效作物-杂草分割对变量施药至关重要。传统基于CNN的方法难以泛化且依赖RGB图像，在复杂田间条件下表现受限。为此，我们提出一种轻量级的Transformer-CNN混合模型，分别处理RGB、近红外（NIR）和红边（RE）波段，通过专用编码器与动态模态融合机制提升性能。在WeedsGalore数据集上，该模型实现78.88%的分割准确率（平均交并比），较仅使用RGB的模型提升15.8个百分点。模型参数仅870万，兼具高精度、低计算开销，具备在无人机（UAVs）与边缘设备上实时部署的潜力，显著推进精准杂草管理技术发展。
原文摘要 · Abstract (English)
Efficient crop-weed segmentation is critical for site-specific weed control in precision agriculture. Conventional CNN-based methods struggle to generalize and rely on RGB imagery, limiting performance under complex field conditions. To address these challenges, we propose a lightweight transformer-CNN hybrid. It processes RGB, Near-Infrared (NIR), and Red-Edge (RE) bands using specialized encoders and dynamic modality integration. Evaluated on the WeedsGalore dataset, the model achieves a segmentation accuracy (mean IoU) of 78.88%, outperforming RGB-only models by 15.8 percentage points. With only 8.7 million parameters, the model offers high accuracy, computational efficiency, and potential for real-time deployment on Unmanned Aerial Vehicles (UAVs) and edge devices, advancing precision weed management.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。