| 386 | 1 | 28 |
| 下载次数 | 被引频次 | 阅读次数 |
在复杂道路环境下，自动驾驶系统在目标检测过程中仍然面临误检与漏检的挑战，难以兼顾精度和实时性。本文提出一种基于YOLOv11的轻量化改进道路目标检测方法。首先应用深度可分离卷积(SPD-Conv)替换部分传统卷积，以增强特征之间的关联性，提高卷积操作的表达能力。其次对C2PSA结构中的PSABlock模块进行优化，引入结合空间与通道的注意力机制SCSA,实现更全面的特征融合，有效捕捉多语义信息，降低关键信息遗漏的风险。最后将传统上采样模块替换为动态上采样(DySample)模块，既保持检测精度，又提高整体推理速度，实现模型的轻量化。实验结果表明，该方法在KITTI数据集上相比于原模型参数量降低18.9%,平均精度均值提升1.04%,推理速度提升16.9%,有效提升了检测性能与推理效率。
Abstract：In complex road environments, automatic driving systems still face the challenges of misdetection and omission in the target detection process, which makes it difficult to balance accuracy and real-time performance.A lightweight improved road target detection method based on YOLOv11 is proposed.Firstly, a depth-separable convolution(SPD-Conv)is applied to replace part of the traditional convolution to enhance the correlation between features and improve the expressiveness of the convolution operation.Secondly, the PSABlock module in the C2PSA structure is optimized, and the SCSA attention mechanism combining space and channel is introduced to achieve more comprehensive feature fusion, effectively capture multi-semantic information, and reduce the risk of omitting key information.Finally, the traditional up-sampling module is replaced by the DySample module, which maintains the detection accuracy and improves the overall inference speed, realizing the lightweight of the model.The experimental results show that on the KITTI dataset, the method reduces the number of parameters of the original model by 18.9%,improves the average accuracy by 1.04%,and increases the inference speed by 16.9%,which effectively raises the detection performance and inference efficiency.
[1] 胡满江，杨智元，李洋，等.智能汽车人机协同决策关键技术综述[J].中国公路学报，2024,37(3):98-116.HU M J,YANG Z Y,LI Y,et al.Review on the human-machine collaborative decision-making in intelligent vehicles[J].China Journal of Highway and Transport,2024,37(3):98-116.(in Chinese)
[2] 张奕博，张雅丽.基于改进YOLOv5网络模型的夜间车辆检测研究[J].现代计算机，2024,30(2):18-25.ZHANG Y B,ZHANG Y L.Research on night target detection based on improved YOLOv5 model[J].Modern Computer,2024,30(2):18-25.(in Chinese)
[3] 张浩晨，张竹林，史瑞岩，等.YOLO-CDC:优化改进YOLOv8的车辆目标检测算法[J/OL].计算机工程与应用，2025:1-15[2025-03-13].https://kns.cnki.net/kcms/detail/11.2127.TP.20250312.1726.022.html.ZHANG H C,ZHANG Z L,SHI R Y,et al.YOLO-CDC:optimizing and improving YOLOv8 vehicle target detection algorithm[J/OL].Computer Engineering and Applications,2025:1-15[2025-03-13].https://kns.cnki.net/kcms/detail/11.2127.TP.20250312.1726.022.html.(in Chinese)
[4] 郑玉珩，黄德启.改进MobileViT与YOLOv4的轻量化车辆检测网络[J].电子测量技术，2023,46(2):175-183.ZHENG Y H,HUANG D Q.Lightweight vehicle detection network based on MobileViT and YOLOv4[J].Electronic Measurement Technology,2023,46(2):175-183.(in Chinese)
[5] 李东宇，王绪娜，高宏伟.基于驾驶场景的高效多模态融合检测方法[J].沈阳理工大学学报，2024,43(3):18-25.LI D Y,WANG X N,GAO H W.Efficient multi-modal fusion detection method based on driving scenes[J].Journal of Shenyang Ligong University,2024,43(3):18-25.(in Chinese)
[6] 张张详，陈宁.改进的YOLOv8n在复杂环境下的车辆识别算法[J].浙江科技大学学报，2024,36(5):404-416.ZHANG Z X,CHEN N.Improved YOLOv8n vehicle recognition algorithm under complex circumstances[J].Journal of Zhejiang University of Science and Technology,2024,36(5):404-416.(in Chinese)
[7] SI Y Z,XU H Y,ZHU X Z,et al.SCSA:Exploring the synergistic effects between spatial and channel attention[J].Neurocomputing,2025,634:129866.
[8] GU Z C,ZHU K,YOU S T.YOLO-SSFS:a method combining SPD-Conv/STDL/IM-FPN/SIoU for outdoor small target vehicle detection[J].Electronics,2023,12(18):3744.
[9] LAN Y S,CHEN M,LI C,et al.Research on small target detection method for industrial safety helmets based on improved YOLOv8[J].Journal of Computing and Information Technology,2024,31(2):123-136.
[10] SHI H W,YANG W Z,CHEN D N,et al.CPA-YOLOv7:contextual and pyramid attention-based improvement of YOLOv7 for drones scene target detection [J].Journal of Visual Communication and Image Representation,2023,97:103965.
[11] 于贺婷，刘思萌，文峰.基于CBAM注意力机制的智能交通信号控制[J].沈阳理工大学学报，2024,43(5):34-40.YU H T,LIU S M,WEN F.Intelligent traffic control technology based on CBAM attention mechanism[J].Journal of Shenyang Ligong University,2024,43(5):34-40.(in Chinese).
[12] HUANG H J,CHEN Z G,ZOU Y,et al.Channel prior convolutional attention for medical image segmentation[J].Computers in Biology and Medicine,2024,178:108784.
[13] LIU W Z,LU H,FU H T,et al.Learning to upsample by learning to sample[C]//2023 IEEE/CVF International Conference on Computer Vision(ICCV).Paris,France:IEEE,2023:6004-6014.
[14] GEIGER A,LENZ P,STILLER C,et al.Vision meets robotics:the KITTI dataset[J].The International Joural of Robotics Research,2013,32(11):1231-1237
[15] REN S Q,HE K M,GIRSHICK R,et al.Faster R-CNN:towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149.
基本信息:
中图分类号:U463.6;TP391.41
引用信息:
[1]张熙函,刘军,齐向晶.基于轻量化YOLOv11的道路目标检测[J].沈阳理工大学学报,2026,45(02):61-66.
基金信息:
辽宁省教育厅高等学校基本科研项目(LJKMZ20220610)