基于改进YOLO v8模型的南方农田障碍物检测方法

Obstacle Detection Method for Southern Farmlands Based on Improved YOLO v8 Model

摘要:

障碍物检测是无人农机实现自主作业的关键技术之一。针对南方非结构化农田复杂环境下障碍物检测，本文实地采集并标注了一个南方非结构化农田障碍物数据集，并通过数据增强技术提升数据多样性。基于YOLO v8模型，引入Shuffle Attention注意力机制至C2f模块，提出改进的C2f?ATT模块，以增强特征表达能力。同时，采用全新卷积神经网络构建块替换部分常规模块，形成YO?STNet模型，并用增强型交并比（EIoU）损失函数替换原有损失函数，以平衡模型复杂性增加带来的收敛速度下降。试验结果表明，在检测精度，尤其是在小目标检测和模糊目标识别方面，提出模型表现出显著优势，网络收敛速度也显著加快。与原始YOLO v8模型相比，改进模型平均检测精度提高3.67个百分点。与YOLO v5、YOLO v7、YOLO v10、Faster R?CNN、SSD等的对比结果表明，本文提出模型性能更优越，精度更高。研究结果为无人农机在复杂农田环境下自主避障提供了重要技术参考与实践支撑。

Abstract:

Obstacle detection is one of the key technologies for enabling autonomous operation of unmanned agricultural machinery. To address obstacle detection in the complex environments of unstructured farmland in southern China, a dataset of obstacles in such farmlands was collected and annotated，and data diversity was enhanced through data augmentation techniques. Based on the YOLO v8 model, the Shuffle Attention mechanism was introduced into the C2f module, proposing an improved C2f?ATT module to enhance feature representation. Simultaneously, a convolutional neural network building block was used to replace some conventional modules, forming the YO?STNet model. The enhanced intersection over union (EIoU) loss function was adopted to replace the original loss function, balancing the decreased convergence speed caused by increased model complexity. Experimental results showed that the proposed model exhibited significant advantages in detection accuracy, particularly in small object detection and blurred object recognition, while network convergence speed was also markedly accelerated. Compared with the original YOLO v8 model, the improved model achieved a 3.67 percentage points increase in average detection accuracy. Comparative results with models such as YOLO v5, YOLO v7, YOLO v10, Faster R?CNN, and SSD demonstrated that the proposed model offered superior performance and higher precision. The findings can provide important technical reference and practical support for autonomous obstacle avoidance of unmanned agricultural machinery in complex farmland environments.