Wang Yi, Ouyang Cheng, Peng Hao, Deng Jingtao, Yang Lin, Chen Hailin, Luo Yahui, Jiang Ping
College of Information and Intelligence, Hunan Agricultural University, Changsha 410128, China.
College of Mechanical and Electrical Engineering, Hunan Agricultural University, Changsha 410128, China.
Sensors (Basel). 2025 Feb 25;25(5):1405. doi: 10.3390/s25051405.
Chili pepper, a widely cultivated and consumed crop, faces challenges in accurately determining maturity due to issues such as occlusion, small target size, and similarity between fruit color and background. This study presents an enhanced YOLOv8n-based object detection model, YOLO-ALW, designed to address these challenges. The model introduces the AKConv (Alterable Kernel Convolution) module in the head section, which adaptively adjusts the convolution kernel shape and size based on the target and scene, improving detection performance under occlusion and dense environments. In the backbone, the SPPF_LSKA (Spatial Pyramid Pooling Fast-Large Separable Kernel Attention) module enhances the integration of multi-scale features, facilitating accurate differentiation of peppers at various maturity stages while maintaining low computational complexity. Additionally, the Wise-IoU (Wise Intersection over Union) loss function optimizes bounding box learning, further improving the detection of peppers in occluded or background-similar scenarios. Experimental results demonstrate that YOLO-ALW achieves a mean average precision (mAP) of 99.1%, with precision and recall rates of 98.3% and 97.8%, respectively, outperforming the original YOLOv8n by 3.4%, 5.1%, and 9.0%, respectively. Grad-CAM feature visualization highlights the model's improved focus on key fruit features. YOLO-ALW shows significant promise for high-precision chili pepper detection and maturity recognition, offering valuable support for automated harvesting applications.
辣椒是一种广泛种植和食用的作物，由于存在遮挡、目标尺寸小以及果实颜色与背景相似等问题，在准确确定成熟度方面面临挑战。本研究提出了一种基于YOLOv8n的增强型目标检测模型YOLO-ALW，旨在应对这些挑战。该模型在头部引入了AKConv（可变内核卷积）模块，该模块根据目标和场景自适应调整卷积核的形状和大小，提高了在遮挡和密集环境下的检测性能。在主干部分，SPPF_LSKA（空间金字塔池化快速-大分离内核注意力）模块增强了多尺度特征的融合，有助于在保持低计算复杂度的同时准确区分不同成熟阶段的辣椒。此外，Wise-IoU（明智交并比）损失函数优化了边界框学习，进一步提高了在遮挡或背景相似场景下辣椒的检测效果。实验结果表明，YOLO-ALW的平均精度均值（mAP）达到99.1%，精确率和召回率分别为98.3%和97.8%，分别比原始YOLOv8n高出3.4%、5.1%和9.0%。Grad-CAM特征可视化突出了模型对关键果实特征的改进关注。YOLO-ALW在高精度辣椒检测和成熟度识别方面显示出巨大潜力，为自动化收获应用提供了有价值的支持。
