多光谱图像
油菜籽
天蓬
分割
人工智能
计算机科学
计算机视觉
遥感
环境科学
地质学
地理
农学
生物
考古
作者
Yuan-Kai Yang,Xiaole Wang,Fugui Zhang,Zhenchao Wu,Yu Wang,Yujie Liu,Xuan Lü,Bowen Luo,Liqing Chen,Yang Yang,Yang Yang,Yang Yang
标识
DOI:10.1016/j.aiia.2025.05.008
摘要
Precise detection of rapeseed and the growth of its canopy area are crucial phenotypic indicators of its growth status. Achieving accurate identification of the rapeseed target and its growth region provides significant data support for phenotypic analysis and breeding research. However, in natural field environments, rapeseed detection remains a substantial challenge due to the limited feature representation capabilities of RGB-only modalities. To address this challenge, this study proposes a dual-modal instance segmentation network, MSNet, based on YOLOv11n-seg, integrating both RGB and Near-Infrared (NIR) modalities. The main improvements of this network include three different fusion location strategies (frontend fusion, mid-stage fusion, and backend fusion) and the newly introduced Hierarchical Attention Fusion Block (HAFB) for multimodal feature fusion. Comparative experiments on fusion locations indicate that the mid-stage fusion strategy achieves the best balance between detection accuracy and parameter efficiency. Compared to the baseline network, the mAP50:95 improvement can reach up to 3.5 %. After introducing the HAFB module, the MSNet-H-HAFB model demonstrates a 6.5 % increase in mAP50:95 relative to the baseline network, with less than a 38 % increase in parameter count. It is noteworthy that the mid-stage fusion consistently delivered the best detection performance in all experiments, providing clear design guidance for selecting fusion locations in future multimodal networks. In addition, comparisons with various RGB-only instance segmentation models show that all the proposed MSNet-HAFB fusion models significantly outperform single-modal models in rapeseed count detection tasks, confirming the potential advantages of multispectral fusion strategies in agricultural target recognition. Finally, the MSNet was applied in an agricultural case study, including vegetation index level analysis and frost damage classification. The results show that ZN6–2836 and ZS11 were predicted as potential superior varieties, and the EVI2 vegetation index achieved the best performance in rapeseed frost damage classification. • Half fusion via MSNet's HAFB delivers optimal accuracy vs. parameter efficiency. • Instance segmentation performance of MSNet is improved with the NIR infrared into RGB. • The feature extraction ability of MSNet is improved by adding HAFB module.
科研通智能强力驱动
Strongly Powered by AbleSci AI