摘要 针对目前仓储货物分类速度慢、易出错、灵活性差等问题，提出了一种改进YOLOv5s的货物检测算法，对仓储货物进行预分类。首先，根据仓储货物的外形特征，将其分为包装箱与包装袋两大类，形成训练数据集；其次，将骨干网络更换为具有更小模型尺寸的MobileNetV3，加快推理；再次，添加SE注意力机制模块，旨在提高模型的检测精度；最后，结合α_CIoU损失函数，增强模型的灵活度。通过实验验证，改进后的算法相较于原始算法在精确率（Precision，P）、平均类别精度（mean Average Precision，mAP）和帧率（Frames Per Second，FPS）三方面分别提升2.1%、0.5%和10.6%，能够高效地完成对仓储货物的预分类工作。
Abstract: A modified YOLOv5s detection algorithm has been proposed to address the issues of slow classification speed, error-proneness, and low flexibility in warehouse goods categorization. The algorithm aims to pre-classify warehouse goods. Firstly, based on the external characteristics of warehouse goods, they are divided into two main categories: packaging boxes and packaging bags, forming a training dataset. Secondly, the backbone network is replaced with MobileNetV3, a smaller-sized model, to accelerate inference. Additionally, an SE attention mechanism module is added to enhance the detection accuracy of the model. Finally, the α_CIoU loss function is incorporated to improve the flexibility of the model. Experimental results demonstrate that the improved algorithm achieves a 2.1% increase in precision (P), a 0.5% increase in mean Average Precision (mAP), and a 10.6% increase in Frames Per Second (FPS) compared to the original algorithm. It enables efficient pre-classification of warehouse goods.
王 影, 王 晨, 贾永涛, 刘 麒. 基于改进YOLOv5s的仓储货物检测算法研究[J]. 吉林化工学院学报, 2024, 41(1): 51-58.
WANG Ying , WANG Chen , JIA Yongtao , LIU Qi. Research on an Improved YOLOv5s-based Algorithm for Warehouse Goods Detection. Journal of Jilin Institute of Chemical Technology, 2024, 41(1): 51-58.
