改进YOLOv5的复杂道路目标检测算法

doi:10.3778/j.issn.1002-8331.2205-0158

摘要/Abstract

摘要： 针对复杂道路背景下的密集遮挡目标和小目标导致的误检、漏检问题，提出一种基于改进YOLOv5的复杂道路目标检测算法。引入Quality Focal Loss，将分类得分与位置的质量预测结合，提高了对密集遮挡目标的定位精度；增加一层浅层检测层作为更小目标的检测层，将原始算法的三尺度检测改为四尺度，特征融合部分也作相应改进，提高了算法对小目标特征的学习能力；借鉴加权双向特征金字塔网络（BiFPN）的特征融合思想，提出了去权重的BiFPN，充分利用深层、浅层以及原始的特征信息，加强了特征融合，减少了卷积过程中特征信息的丢失，提高了检测精度；引入卷积块注意模块（CBAM），进一步提升了算法的特征提取能力，让算法更关注有用的信息。实验结果表明，该改进算法在公开的自动驾驶数据集KITTI和自制的骑乘人员头盔数据集Helmet上的检测精度分别达到了94.9%和96.8%，相比原始算法分别提高了1.9个百分点和2.1个百分点的检测精度，检测速度分别达到了69 FPS和68 FPS，具有较好的检测精度与实时性，同时与一些主流的目标检测算法相比，该改进算法也有一定的优越性。

关键词: 复杂道路, YOLOv5, Quality Focal Loss, 双向特征金字塔网络（BiFPN）, 卷积块注意模块（CBAM）, 遮挡目标, 小目标

Abstract: Aiming at the problem of false detection and missed detection caused by dense occluded targets and small targets in complex road background, a complex road target detection algorithm based on improved YOLOv5 is proposed. Firstly, Quality Focal Loss is introduced, which combines the classification score with the quality prediction of location to improve the positioning accuracy of dense occluded targets. Secondly, a shallow detection layer is added as the detection layer of smaller targets, the three-scale detection of the original algorithm is changed to four-scale detection, and the feature fusion part is also improved accordingly, which improves the learning ability of the algorithm to the features of small targets. Then, based on the feature fusion idea of weighted bidirectional feature pyramid network（BiFPN）, a de-weighted BiFPN is proposed, which makes full use of deep, shallow and original feature information, strengthens feature fusion, reduces the loss of feature information in the process of convolution, and improves the detection accuracy. Finally, the convolution block attention module（CBAM） is introduced to further improve the feature extraction ability of the algorithm and make the algorithm pay more attention to useful information. The experimental results show that the detection accuracy of the improved algorithm in this paper on the public autopilot data set KITTI and the self-made rider helmet data set Helmet reaches 94.9% and 96.8% respectively, which is 1.9 percentage points and 2.1 percentage points higher than the original algorithm, and the detection speed reaches 69 FPS and 68 FPS respectively. It has better detection accuracy and real-time performance. At the same time, compared with some mainstream target detection algorithms, the improved algorithm in this paper also has some advantages.

Key words: complex road, YOLOv5, Quality Focal Loss, bidirectional feature pyramid network（BiFPN）, convolution block attention module（CBAM）, occluded target, small target

王鹏飞, 黄汉明, 王梦琪. 改进YOLOv5的复杂道路目标检测算法[J]. 计算机工程与应用, 2022, 58(17): 81-92.

WANG Pengfei, HUANG Hanming, WANG Mengqi. Complex Road Target Detection Algorithm Based on Improved YOLOv5[J]. Computer Engineering and Applications, 2022, 58(17): 81-92.

参考文献

[1] 彭育辉，江铭，马中原，等.汽车自动驾驶关键技术研究进展[J].福州大学学报（自然科学版），2021，49（5）：691-703.
PENG Yuhui，JIANG Ming，MA Zhongyuan，et al.Research progress on key technologies of auto driving[J].Journal of Fuzhou University（Natural Science Edition），2021，49（5）：691-703.
[2] LIENHART R，MAYDT J.An extended set of haar-like features for rapid object detection[C]//Proceedings of International Conference on Image Processing，2002.
[3] LOWE D G.Object recognition from local scale-invariant features[C]//Proceedings of the Seventh IEEE International Conference on Computer Vision，1999：1150-1157.
[4] OJALA T，PIETIKAINEN M，MAENPAA T.Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2002，24（7）：971-987.
[5] DALAL N，TRIGGS B.Histograms of oriented gradients for human detection[C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition（CVPR’05），2005：886-893.
[6] CORTES C，VAPNIK V.Support-vector networks[J].Machine Learning，1995，20（3）：273-297.
[7] FREUND Y，SCHAPIRE R E.A desicion-theoretic generali-zation of on-line learning and an application to boosting[C]//European Conference on Computational Learning Theory.Berlin，Heidelberg：Springer，1995：23-37.
[8] 钱伍，王国中，李国平.改进YOLOv5的交通灯实时检测鲁棒算法[J].计算机科学与探索，2022，16（1）：231-241.
QIAN Wu，WANG Guozhong，LI Guoping.Improved YOLOv5 traffic light real-time detection robust algorithm[J].Journal of Frontiers of Computer Science and Technology，2022，16（1）：231-241.
[9] GIRSHICK R，DONAHUE J，DARRELL T，et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2014：580-587.
[10] GIRSHICK R.Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision，2015：1440-1448.
[11] REN S，HE K，GIRSHICK R，et al.Faster R-CNN：towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems，2015.
[12] REDMON J，DIVVALA S，GIRSHICK R，et al.You only look once：unified，real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2016：779-788.
[13] LIU W，ANGUELOV D，ERHAN D，et al.SSD：single shot multibox detector[C]//European Conference on Computer Vision.Cham：Springer，2016：21-37.
[14] REDMON J，FARHADI A.YOLO9000：better，faster，stronger[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：7263-7271.
[15] REDMON J，FARHADI A.Yolov3：an incremental improvement[J].arXiv：1804.02767，2018.
[16] BOCHKOVSKIY A，WANG C Y，LIAO H Y M.Yolov4：optimal speed and accuracy of object detection[J].arXiv：2004.10934，2020.
[17] AGARWAL S，TERRAIL J O D，JURIE F.Recent advances in object detection in the age of deep convolutional neural networks[J].arXiv：1809.03193，2018.
[18] 刘昌华.复杂交通场景下自动驾驶道路目标检测[D].大连：大连理工大学，2021.
LIU Changhua.Automatic driving road target detection in complex traffic scenes[D].Dalian：Dalian University of Technology，2021.
[19] CAI Z，VASCONCELOS N.Cascade R-CNN：delving into high quality object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：6154-6162.
[20] 陈幻杰，王琦琦，杨国威，等.多尺度卷积特征融合的SSD目标检测算法[J].计算机科学与探索，2019，13（6）：1049-1061.
CHEN Huanjie，WANG Qiqi，YANG Guowei，et al.SSD object detection algorithm with multi-scale convolution feature fusion[J].Journal of Frontiers of Computer Science and Technology，2019，13（6）：1049-1061.
[21] 李轩，李静，王海燕.密集交通场景的目标检测算法研究[J].计算机技术与发展，2020，30（7）：46-50.
LI Xuan，LI Jing，WANG Haiyan.Research on target detection algorithm in dense traffic scene[J].Computer Technology and Development，2020，30（7）：46-50.
[22] CHU X，ZHENG A，ZHANG X，et al.Detection in crowded scenes：one proposal，multiple predictions[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2020：12214-12223.
[23] LI X，WANG W，WU L，et al.Generalized focal loss：learning qualified and distributed bounding boxes for dense object detection[C]//Advances in Neural Information Processing Systems，2020.
[24] 汪雷，黄剑，段涛，等.基于气压肌动图和改进神经模糊推理系统的手势识别研究[J].自动化学报，2022，48（5）：1220-1233.
WANG Lei，HUANG Jian，DUAN Tao，et al.Research on gesture recognition based on pressure-based mechanomyogram and improved neural fuzzy inference system[J].Acta Automatica Sinica，2022，48（5）：1220-1233.
[25] LIN T Y，GOYAL P，GIRSHICK R，et al.Focal loss for dense object detection[C]//Proceedings of the IEEE International Conference on Computer Vision，2017：2980-2988.
[26] LIN T Y，DOLLáR P，GIRSHICK R，et al.Feature pyramid networks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：2117-2125.
[27] LIU S，QI L，QIN H，et al.Path aggregation network for instance segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：8759-8768.
[28] TAN M，PANG R，LE Q V.Efficientdet：scalable and efficient object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2020：10781-10790.
[29] WOO S，PARK J，LEE J Y，et al.Cbam：convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision（ECCV），2018：3-19.
[30] LIN T Y，MAIRE M，BELONGIE S，et al.Microsoft coco：common objects in context[C]//European Conference on Computer Vision.Cham：Springer，2014：740-755.
[31] HU J，SHEN L，SUN G.Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：7132-7141.
[32] GEIGER A，LENZ P，STILLER C，et al.Vision meets robotics：the kitti dataset[J].The International Journal of Robotics Research，2013，32（11）：1231-1237.
[33] MELEKHOV I，TIULPIN A，SATTLER T，et al.Dgc-net：dense geometric correspondence network[C]//2019 IEEE Winter Conference on Applications of Computer Vision（WACV），2019：1034-1042.
[34] ZHANG H，WANG Y，DAYOUB F，et al.Varifocalnet：an iou-aware dense object detector[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2021：8514-8523.
[35] WANG Q，WU B，ZHU P，et al.ECA-Net：efficient channel attention for deep convolutional neural networks[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR），2020.
[36] HOU Q，ZHOU D，FENG J.Coordinate attention for efficient mobile network design[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2021：13713-13722.
[37] GE Z，LIU S，WANG F，et al.YOLOX：exceeding YOLO series in 2021[J].arXiv：2107.08430，2021.