Li Jianian, Gao Long, Wang Xiaocheng, Fang Jiaoli, Su Zeyang, Li Yuecong, Chen Shaomin
Faculty of Modern Agricultural Engineering, Kunming University of Science and Technology, Kunming, China.
Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China.
Front Plant Sci. 2025 Aug 22;16:1635302. doi: 10.3389/fpls.2025.1635302. eCollection 2025.
Rice is an important food crop but is susceptible to diseases. However, currently available spot segmentation models have high computational overhead and are difficult to deploy in field environments.
To address these limitations, a lightweight rice leaf spot segmentation model (MV3L-MSDE-PGFF-CA-DeepLabv3+, MMPC-DeepLabv3+) was developed for three common rice leaf diseases: rice blast, brown spot and bacterial leaf blight. First, the lightweight feature extraction network MobileNetV3_Large (MV3L) was adopted as the backbone of the model. Second, based on Haar wavelet downsampling, a multi-scale detail enhancement (MSDE) module was proposed to improve decision-making ability of the model in transitional regions such as spot gaps, and to improve the sticking and blurring problems at the boundary of spot segmentation. Meanwhile, the PagFm-Ghostconv Feature Fusion (PGFF) module was proposed to significantly reduce the computational overhead of the model. Furthermore, coordinate attention (CA) mechanism was incorporated before the PGFF module to improve robustness of the model in complex environments. A hybrid loss function integrating Focal Loss and Dice Loss was ultimately proposed to mitigate class imbalance between disease and background pixels in rice disease imagery.
Validated on rice disease images captured under natural illumination conditions, the MMCP-DeepLabv3+ model achieved a mean intersection over union (MIoU) of 81.23% and mean pixel accuracy (MPA) of 89.79%, with floating-point operations (Flops) and the number of model parameters (Params) reduced to 9.695 G and 3.556 M, respectively. Compared to the baseline DeepLabv3+, this represents a 1.89% improvement in MIoU, a 0.83% increase in MPA, alongside 93.1% and 91.6% reductions in Flops and Params.
The MMPC-DeepLabv3+ model demonstrated superior performance over DeepLabv3+, U-Net, PSPNet, HRNetV2, and SegFormer, achieving an optimal balance between recognition accuracy and computational efficiency, which establishes a novel paradigm for rice lesion segmentation in precision agriculture.
水稻是一种重要的粮食作物，但易受病害影响。然而，目前可用的斑点分割模型计算开销大，难以在田间环境中部署。
为解决这些局限性，针对三种常见的水稻叶部病害：稻瘟病、褐斑病和白叶枯病，开发了一种轻量级水稻叶斑分割模型（MV3L-MSDE-PGFF-CA-DeepLabv3+，MMPC-DeepLabv3+）。首先，采用轻量级特征提取网络MobileNetV3_Large（MV3L）作为模型的骨干。其次，基于哈尔小波下采样，提出了一种多尺度细节增强（MSDE）模块，以提高模型在斑点间隙等过渡区域的决策能力，并改善斑点分割边界处的粘连和模糊问题。同时，提出了PagFm-Ghostconv特征融合（PGFF）模块，以显著降低模型的计算开销。此外，在PGFF模块之前引入坐标注意力（CA）机制，以提高模型在复杂环境中的鲁棒性。最终提出了一种融合焦点损失和骰子损失的混合损失函数，以减轻水稻病害图像中病害像素与背景像素之间的类别不平衡。
在自然光照条件下采集的水稻病害图像上进行验证，MMCP-DeepLabv3+模型的平均交并比（MIoU）达到81.23%，平均像素准确率（MPA）达到89.79%，浮点运算次数（Flops）和模型参数数量（Params）分别降至9.695 G和3.556 M。与基线DeepLabv3+相比，MIoU提高了1.89%，MPA提高了
