面向清扫车自动寻路的轻量化路沿感知算法研究  

On Lightweight Road Edge Perception Algorithm for Autonomous Path Finding of Street Sweeping Vehicles

作　　者：凌基 尚正阳 刘跃 黄伟[1] LING Ji;SHANG Zhengyang;LIU Yue;HUANG Wei(School of Mechanical Engineering,Anhui Polytechnic University,Wuhu 241060,Anhui;School of Energy and Power Engineering,Jiangsu University,Zhenjiang 212016,Jiangsu;Y&C.Engine Co.,Ltd.,Wuhu 241070,Anhui;Hefei Zhongke Zhichi Technology Co.,Ltd.,Hefei 230094,China)

机构地区：[1]安徽工程大学机械工程学院,安徽芜湖241060 [2]江苏大学能源与动力工程学院,江苏镇江212016 [3]玉柴联合动力股份有限公司,安徽芜湖241070 [4]合肥中科智驰科技有限公司,合肥230094

出　　处：《合肥大学学报》2024年第5期119-127,共9页Journal of Hefei University

基　　金：汽车新技术安徽省工程技术研究中心项目“基于智能物流的车辆路径规划关键技术研究”(QCKJ202104);安徽工程大学校级科研项目“常态化疫情管控区域内无人物流配置与其载运耦合调度研究”(Xjky2022001)。

摘　　要：无人驾驶垃圾清扫车通常通过路沿检测实现自主路径选择。传统深度学习方法虽然具有较好识别效果,但计算量过大不符合实际应用需求。为此,提出一种基于YOLOv5轻量化的改进GDFE-YOLO算法。采用Ghostconv和C3Ghost对原网络模型主干进行替换;再引入可变形卷积替代Neck部分中的传统Conv卷积模块;最后将损失函数替换为Focal-EIOU Loss。实验结果表明,GDFE-YOLO算法在参数量、计算量和模型大小上分别较原模型降低了16.2%、15%和19.4%,检测速度提高12%;路沿识别均值精度为96.1%。GDFE-YOLO相较于YOLOv5s算法的识别精度仅下降0.9%,同时基于整体路沿的线性拟合检测策略,其单点的精度下降影响较小,因此所提出算法能够实现清扫车的轻量化路沿检测要求。Driverless garbage sweepers often achieve autonomous path selection through curb detection.Although the traditional deep learning method has a good recognition effect,the amount of computation is too large and does not meet the practical application requirements.Therefore,an improved GDFE-YOLO algorithm based on YOLOv5 lightweight was proposed.Ghostconv and C3Ghost are used to replace the backbone of the original network model,and then the deformable convolution DCNv2 is introduced to replace the traditional Conv convolution module in the Neck part,and finally the loss function is replaced by Focal-EIOU Loss.Experimental results show that the GDFE-YOLO algorithm reduces the number of parameters,the amount of computation and the size of the model by 16.2%,15%and 19.4%,respectively,and the detection speed is increased by 12%,and the average accuracy of curb recognition is 96.1%.Compared with the YOLOv5s algorithm,the recognition accuracy of GDFE-YOLO is only reduced by 0.9%,and based on the linear fitting detection strategy of the overall curb,the accuracy of a single point has little impact,so the proposed algorithm can realize the lightweight curb detection requirements of sweepers.

关 键 词：清扫车 路沿识别 机器视觉 改进YOLO 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]