山东大学学报 (工学版) ›› 2024, Vol. 54 ›› Issue (5): 34-41.doi: 10.6040/j.issn.1672-3961.0.2023.232
• 交通工程——智慧交通专题 • 上一篇
薛健,赵琳,张浩,杨璐,郝凡昌*
XUE Jian, ZHAO Lin, ZHANG Hao, YANG Lu, HAO Fanchang
摘要： 针对目前交通标志检测方法受光照影响较大,模型精度低等问题,提出一种更快基于区域卷积神经网络(faster region-based convolutional neural network, Faster R-CNN)的交通标志检测算法。针对图像中天空与非天空区域的光照不均匀现象,引入伽马变换增强交通标志在模型中的特征表达能力;利用基于卷积注意力模块的高效网络(convolutional block attention module-based an efficient network, CBAM-EfficientNet)解决网络深度退化问题,提高浅层网络的特征获取能力,降低参数量;在网络中引入特征金字塔网络以检测不同尺寸目标,增强网络对不同尺寸交通标志的感知能力,解决交通标志尺寸差异问题。试验结果表明,该算法在GTSDB数据集上的平均准确率均值PmA达到99.79%,在CCTSDB2021数据集上的PmA达到87.62%。为光照不均匀图像的交通标志检测提供一种高准确性的方法。
中图分类号:
| [1] HECHRI A, MTIBAA A. Two-stage traffic sign detection and recognition based on SVM and convolutional neural networks[J]. Iet Image Processing, 2020, 14(5): 939-946. [2] XU X H, JIN J C, ZHANG S Q, et al. Smart data driven traffic sign detection method based on adaptive color threshold and shape symmetry[J]. Future Generation Computer Systems-the International Journal of Escience, 2019, 94: 381-391. [3] SHAO F M, WANG X Q, MENG F J, et al. Improved Faster R-CNN traffic sign detection based on a second region of interest and highly possible regions proposal network[J]. Sensors, 2019, 19(10): 2288. [4] YU J, YE X J, TU Q. Traffic sign detection and recognition in multi images using a fusion model with YOLO and VGG network[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(9): 16632-16642. [5] LIU Y C, SHI G, LI Y X, et al. M-YOLO: traffic sign detection algorithm applicable to complex scenarios[J]. Symmetry-Basel, 2022, 14(5): 952. [6] ZHANG J M, XIE Z P, SUN J, et al. A cascaded R-CNN with multiscale attention and imbalanced samples for traffic sign detection[J]. IEEE Access, 2020, 8: 29742-29754. [7] ZHAO Z Y, YANG X X, ZHOU Y C, et al. Real-time detection of particleboard surface defects based on improved YOLOV5 target detection[J]. Scientific Reports, 2021, 11(1): 21777. [8] YAN Y, DENG C, MA J J, et al. A traffic sign recognition method under complex illumination conditions[J]. IEEE Access, 2023, 11: 39185-39196. [9] ZHANG C G, XU D L, ZHANG L F, et al. Rail surface defect detection based on image enhancement and improved YOLOX[J]. Electronics, 2023, 12(12): 2672. [10] GHOSH R. On-road vehicle detection in varying weather conditions using Faster R-CNN with several region proposal networks[J]. Multimedia Tools and App-lications, 2021, 80(17): 25985-25999. [11] 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. [12] LIN T Y, DOLLAR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C] //Proceedings of the 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Honolulu, USA: IEEE, 2017: 936-944. [13] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C] // Proceedings of the Pro-ceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Columbus, USA: IEEE, 2014: 580-587. [14] GIRSHICK R. Fast R-CNN[C] //Proceedings of the Proceedings of the IEEE International Conference on Computer Vision(ICCV). Boston, USA: IEEE, 2015: 1440-1448. [15] TAN M, LE Q. Efficientnet: rethinking model scaling for convolutional neural networks[C] //Proceedings of the International Conference on Machine Learning. Long Beach, USA: PMLR, 2019: 6105-6114. [16] TAN M, LE Q. EfficientNetV2: smaller models and faster training[C] //Proceedings of the International Conference on Machine Learning. [S.l.] : PMLR, 2021: 10096-10106. [17] WOO S H, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C] //Proceedings of the 15th European Conference on Computer Vision(ECCV). Munich, Germany: Springer, 2018: 3-19. [18] HOUBEN S, STALLKAMP J, SALMEN J, et al. Detection of traffic signs in real-world images: the German traffic sign detection benchmark[C] //Proceedings of the International Joint Conference on Neural Networks(IJCNN). Dallas, USA: IEEE, 2013: 1-8. [19] ZHANG J M, ZOU X, KUANG L D, et al. CCTSDB2021: a more comprehensive traffic sign detection benchmark[J]. Human-Centric Computing and Information Sciences, 2022, 12: 23. [20] SERNA C G, RUICHEK Y. Traffic signs detection and classification for European urban environments[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 21(10): 4388-4399. [21] ZHANG J M, YE Z, JIN X K, et al. Real-time traffic sign detection based on multiscale attention and spatial information aggregator[J]. Journal of Real-Time Image Processing, 2022, 19(6): 1155-1167. [22] LEE H S, KIM K. Simultaneous traffic sign detection and boundary estimation using convolutional neural network[J]. IEEE Transactions on Intelligent Transportation Systems, 2018, 19(5): 1652-1663. [23] WEI H Y, ZHANG Q Q, LI X, et al. YOLOF-F: you only look one-level feature fusion for traffic sign detection[J]. Visual Computer, 2023, 39(3): 1-14. [24] WANG W, WU B, LÜ J, et al. Regular and small target detection[C] //Multi Media Modeling: 25th International Conference(MMM). Thessaloniki, Greece: Springer, 2019: 453-464. [25] 李厚杰,王法胜,贺建军,等. 基于伪样本正则化Faster R-CNN的交通标志检测[J]. 吉林大学学报(工学版), 2021, 51(4): 1251-1260. LI Houjie, WANG Fasheng, HE Jianjun, et al. Pseudo sample regularization Faster R-CNN for traffic sign detection[J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(4): 1251-1260. [26] 李翔宇, 王倩影. 基于改进YOLOv5的复杂背景下交通标志识别研究[J]. 现代信息科技, 2023, 7(10): 30-32. LI Xiangyu, WANG Qianying. Research on traffic sign recognition in complex background based on improved YOLOv5[J]. Modern Information Technology, 2023, 7(10): 30-32. [27] WANG Q Y, LI X Y, LU M. An improved traffic sign detection and recognition deep model based on YOLOv5[J]. IEEE Access, 2023, 11: 54679-54691. |
| [1] | 张宪红,张春蕊. 基于六维前馈神经网络模型的图像增强算法[J]. 山东大学学报(工学版), 2018, 48(4): 10-19. |
| [2] | 肖乔,裴继红,王荔霞,龚志成. 基于多通道Gabor滤波模糊融合的遥感图像舰船检测[J]. 山东大学学报 (工学版), 2015, 45(5): 29-35. |
| [3] | 潘晟旻1,2,钟毅1*,王建华2. 基于改进Canny算子的坯料挤压变形边缘提取[J]. 山东大学学报(工学版), 2013, 43(5): 19-23. |
|
||
