基于改进YOLOv2模型的驾驶辅助系统实时行人检测*

doi:10.19562/j.chinasae.qcgc.2019.012.010

摘要/Abstract

摘要： 为解决驾驶辅助系统(ADAS)对复杂背景行人和小尺寸行人检测精度较低的问题,基于深度神经网络模型YOLOv2建立了ADAS实时行人检测模型YOLOv2-P。首先在特征提取网络中采用参数化修正线性单元激活函数,以从训练数据中自适应地学习参数,并在行人检测网络中采用多层特征图融合方法,将低层特征图信息与高层特征图信息进行融合;然后使用交叉熵损失函数替代YOLOv2模型中的sigmoid激活函数,并对宽度、高度损失函数进行归一化处理;最后采用迭代自组织数据分析算法对行人数据集中行人边界框尺寸进行聚类。试验结果表明:相比于YOLOv2,YOLOv2-P对复杂背景行人及小尺寸行人的检测精度有明显提升,能够满足ADAS行人检测准确性和实时性需要。

关键词: 行人检测, 驾驶辅助系统, 参数化修正线性单元, 交叉熵损失函数, 迭代自组织数据分析算法

Abstract: In order to solve the problem of low detection accuracy of pedestrians with small stature or in complex background in advanced driver assistance systems (ADAS), a real-time pedestrian detection model named YOLOv2-P for ADAS is established based on a deep neural network model YOLOv2. Firstly, the parametric rectified linear unit activation function in feature extraction network is adopted to adaptively learn parameters from training data, and the multi-feature map fusion method is used to fusion low-layer feature map and high-layer feature map in feature extraction network. Next, cross entropy loss function is used instead of sigmoid activation function in model YOLOv2, and the width and height loss functions are normalized. Finally, a clustering is performed on the pedestrian boundary frame size in pedestrian data set by utilizing iterative self-organizing data analysis algorithm. The results of test show that the detection accuracy of the pedestrians with small stature or in complex background with YOLOv2-P model has a significant rise, compare with that with YOLOv2 model, meeting the requirements in accuracy and real-time performance for the pedestrian detection in ADAS.

Key words: pedestrian detection, advanced driver assistance system, parametric rectified linear unit, cross entropy loss function, iterative self-organizing data analysis algorithm

白中浩, 李智强, 蒋彬辉, 王鹏辉. 基于改进YOLOv2模型的驾驶辅助系统实时行人检测^*[J]. 汽车工程, 2019, 41(12): 1416-1423.

Bai Zhonghao, Li Zhiqiang, Jiang Binhui, Wang Penghui. Real-time Pedestrian Detection in Advanced Driver Assistance Systems Based on Improved YOLOv2 Model[J]. Automotive Engineering, 2019, 41(12): 1416-1423.

参考文献

[1] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE,2005:886-893.
[2] 蔡英凤,王海,陈小波,等.驾驶辅助系统基于融合显著性的行人检测算法[J].汽车工程,2015,37(10):1215-1220.
[3] 郭烈,葛平淑,赵一兵,等.基于人体典型部位特征组合的行人检测方法[J].汽车工程,2014,36(4):496-502.
[4] LUO P, TIAN Y, WANG X, et al. Switchable deep network for pedestrian detection[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2014:899-906.
[5] OUYANG W, WANG X. Joint deep learning for pedestrian detection[C]. Computer Vision (ICCV),2013 IEEE International Conference on. IEEE,2013:2056-2063.
[6] LI J, LIANG X, SHEN S M, et al. Scale-aware fast R-CNN for pedestrian detection[J]. IEEE Transactions on Multimedia,2018,20(4):985-996.
[7] 陈文强,熊辉,李克强,等.基于深度神经网络的行人及骑车人联合检测[J].汽车工程,2018,40(6):726-732,725.
[8] TIAN Y, LUO P, WANG X, et al. Deep learning strong parts for pedestrian detection[C]. Proceedings of the IEEE International Conference on Computer Vision,2015:1904-1912.
[9] PAISITKRIANGKRAI S, SHEN C, Van Den HENGEL A. Strengthening the effectiveness of pedestrian detection with spatially pooled features[C]. European Conference on Computer Vision. Springer, Cham,2014:546-561.
[10] DONG P, WANG W. Better region proposals for pedestrian detection with R-CNN[C]. Visual Communications and Image Processing (VCIP),2016. IEEE,2016:1-4.
[11] OUYANG W, ZHOU H, LI H, et al. Jointly learning deep features,deformable parts,occlusion and classification for pedestrian detection[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence,2017,99:1.
[12] ZHANG S, BENENSON R, OMRAN M, et al. Towards reaching human performance in pedestrian detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2018,40(4):973-986.
[13] 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.
[14] MOLCHANOV V V, VISHNYAKOV B V, VIZILTER Y V, et al. Pedestrian detection in video surveillance using fully convolutional YOLO neural network[C]. Automated Visual Inspection and Machine Vision II. International Society for Optics and Photonics,2017,10334:103340Q.
[15] WANG L, LI W, ZHANG Y, et al. Pedestrian detection based on YOLOv2 with skip structure in underground coal mine[C]. Information Technology and Mechatronics Engineering Conference (ITOEC),2017 IEEE 3^rd. IEEE,2017:1216-1220.
[16] PENG Q, LUO W, HONG G, et al. Pedestrian detection for transformer substation based on gaussian mixture model and YOLO[C]. Intelligent Human Machine Systems and Cybernetics (IHMSC),2016 8th International Conference on. IEEE,2016,2:562-565.
[17] MEMARSADEGHI N, MOUNT D M, NETANYAHU N S, et al. A fast implementation of the ISODATA clustering algorithm[J]. International Journal of Computational Geometry & Applications,2007,17(1):71-103.
[18] HE K, ZHANG X, REN S, et al. Delving deep into rectifiers: surpassing human-level performance on imagenet classification[C]. Proceedings of the IEEE International Conference on Computer Vision,2015:1026-1034.
[19] DOLLAR P, WOJEK C, SCHIELE B, et al. Pedestrian detection: an evaluation of the state of the art[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(4):743-761.
[20] ESS A, LEIBE B, SCHINDLER K, et al. A mobile vision system for robust multi-person tracking[C]. Computer Vision and Pattern Recognition,2008.IEEE Conference on. IEEE,2008:1-8.
[21] GEIGER A, LENZ P, URTASUN R. Are we ready for autonomous driving? the KITTI vision benchmark suite[C]. IEEE Conference on Computer Vision and Pattern Recognition. IEEE,2012:3354-3361.

基于改进YOLOv2模型的驾驶辅助系统实时行人检测^*

Real-time Pedestrian Detection in Advanced Driver Assistance Systems Based on Improved YOLOv2 Model

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

Metrics

本文评价

推荐阅读 10

[1]	吴桐,王宇宁,关艺搏,田韶鹏. 基于改进门控上下文聚合网络的雾天实时行人检测方法[J]. 汽车工程, 2023, 45(5): 796-806.
[2]	肖艳秋,周坤,崔光珍,房占鹏,孙启迪,刘燕旗. 基于差异性区域预测的行人与骑车人联合检测[J]. 汽车工程, 2021, 43(1): 77-85.
[3]	董汉, 舒伟, 陈超, 孙灿, 尤超. 危险驾驶工况场景的复杂度评估方法研究[J]. 汽车工程, 2020, 42(6): 808-814.
[4]	朱波, 黄茂飞, 谈东奎, 胡旭东, 顾家鑫. 基于神经网络与数据融合的行人检测方法^*[J]. 汽车工程, 2020, 42(11): 1482-1489.
[5]	熊晓夏, 陈龙, 梁军, 蔡英凤, 江浩斌. 基于驾驶员避撞行为的行车风险判别方法的仿真研究^*[J]. 汽车工程, 2019, 41(2): 153-160.