优化EfficientDet深度学习的车辆检测
作者:
中图分类号:

TP391.41

基金项目:

国家自然科学基金(42171428);湖北省安全生产专项资金科技项目(SJIX 20211006);重庆市技术创新与应用发展专项(cstc2019jscx-msxmX0051)


Optimized EfficientDet deep learning model for vehicle detection
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    针对深度学习EfficientDet模型的车辆检测性能进行分析, 基于训练过程中容易陷入局部最优进行优化改进, 构建分阶段自适应的训练模型, 利用该训练模型对短距离和远距离车辆进行检测, 并将检测结果与基于Cascade R-CNN和CenterNet方法进行比较, 从计算复杂度、耗时及检测精度三方面分析显示本文方法优于其他两种方法.同时, 对不同角度和不同距离车辆检测结果进行分析, 确定了检测的最优距离和角度.最后, 通过实例验证了本文方法可以用于大范围车辆的检测.

    Abstract:

    At present, deep learning has been widely applied in object detection, such as vehicle detection.In this paper, the deep learning EfficientDet model was analyzed, and its advantages in vehicle detection were confirmed.A phased adaptive training model was constructed to avoid local optimum in training process, then it was used to detect vehicles from both short and long distance.The detection results showed that compared with detection methods based on Cascade R-CNN and CenterNet, the proposed model was superior in terms of computational complexity, time consumption and detection accuracy.Meanwhile, further analysis figured out the optimal detection distance and angle.Finally, an example is given to verify that the proposed method can be applied to a large range of vehicle detection.

    参考文献
    [1] 张家旭, 杨雄, 施正堂, 等. 汽车紧急换道避障的路径规划与跟踪控制[J]. 华南理工大学学报(自然科学版), 2020, 48(9): 86-93, 106 ZHANG Jiaxu, YANG Xiong, SHI Zhengtang, et al. Path planning and tracking control for emergency lane change and obstacle avoidance of vehicles[J]. Journal of South China University of Technology (Natural Science Edition), 2020, 48(9): 86-93, 106
    [2] 赵娜, 袁家斌, 徐晗. 智能交通系统综述[J]. 计算机科学, 2014, 41(11): 7-11, 45 ZHAO Na, YUAN Jiabin, XU Han. Survey on intelligent transportation system[J]. Computer Science, 2014, 41(11): 7-11, 45
    [3] Aarthi R, Padmavathi S, Amudha J. Vehicle detection in static images using color and corner map[C]//2010 International Conference on Recent Trends in Information, Telecommunication and Computing. March 12-13, 2010, Kerala, India. IEEE, 2010: 244-246
    [4] Matos F M D S, Souza R M C R D. An image vehicle classification method based on edge and PCA applied to blocks[C]//2012 IEEE International Conference on Systems, Man, and Cybernetics (SMC). October 14-17, 2012, Seoul, Korea (South). IEEE, 2012: 1688-1693
    [5] Iqbal U, Zamir S W, Shahid M H, et al. Image based vehicle type identification[C]//2010 International Conference on Information and Emerging Technologies. June 14-16, 2010, Karachi, Pakistan. IEEE, 2010: 1-5
    [6] 裴明涛, 沈家峻, 杨敏, 等. 复杂光照环境下的车辆检测方法[J]. 北京理工大学学报, 2016, 36(4): 393-398 PEI Mingtao, SHEN Jiajun, YANG Min, et al. Vehicle detection method in complex illumination environment[J]. Transactions of Beijing Institute of Technology, 2016, 36(4): 393-398
    [7] Ghaffarian S, Gökaşar I. Automatic vehicle detection based on automatic histogram-based fuzzy C-means algorithm and perceptual grouping using very high-resolution aerial imagery and road vector data[J]. Journal of Applied Remote Sensing, 2016, 10(1): 015011
    [8] Li Y, Li B, Tian B, et al. Vehicle detection based on the AND-OR graph for congested traffic conditions[J]. IEEE Transactions on Intelligent Transportation Systems, 2013, 14(2): 984-993
    [9] 申铉京, 沈哲, 黄永平, 等. 基于非局部操作的深度卷积神经网络车位占用检测算法[J]. 电子与信息学报, 2020, 42(9): 2269-2276 SHEN Xuanjing, SHEN Zhe, HUANG Yongping, et al. Deep convolutional neural network for parking space occupancy detection based on non-local operation[J]. Journal of Electronics & Information Technology, 2020, 42(9): 2269-2276
    [10] Xiang X Z, Lv N, Zhai M L, et al. Real-time parking occupancy detection for gas stations based on Haar-AdaBoosting and CNN[J]. IEEE Sensors Journal, 2017, 17(19): 6360-6367
    [11] Tang T, Zhou S L, Deng Z P, et al. Vehicle detection in aerial images based on region convolutional neural networks and hard negative example mining[J]. Sensors, 2017, 17(2): 336
    [12] Wang X L, Shrivastava A, Gupta A. A-fast-RCNN: hard positive generation via adversary for object detection[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). July 21-26, 2017, Honolulu, HI, USA. IEEE, 2017: 3039-3048
    [13] Lu J Y, Ma C, Li L, et al. A vehicle detection method for aerial image based on YOLO[J]. Journal of Computer and Communications, 2018, 6(11): 98-107
    [14] Cao G M, Xie X M, Yang W Z, et al. Feature-fused SSD: fast detection for small objects[C]//Proc SPIE 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017), 2018, 1061: 381-388
    [15] Liang S D. Smart and fast data processing for deep learning in internet of things: less is more[J]. IEEE Internet of Things Journal, 2019, 6(4): 5981-5989
    [16] Cai Z W, Vasconcelos N. Cascade R-CNN: delving into high quality object detection[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. June 18-23, 2018, Salt Lake City, UT, USA. IEEE, 2018: 6154-6162
    [17] Du X Z, Lin T Y, Jin P C, et al. SpineNet: learning scale-permuted backbone for recognition and localization[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). June 13-19, 2020, Seattle, WA, USA. IEEE, 2020: 11589-11598
    [18] Zhou X, Wang D, Krähenbühl P. Objects as points[J]. arXiv e-print, 2019, arXiv: 1904.07850
    [19] Loshchilov I, Hutter F. Decoupled weight decay regularization[J]. arXiv e-print, 2017, arXiv: 1711.05101
    相似文献
    引证文献
引用本文

陈西江,安庆,班亚.优化EfficientDet深度学习的车辆检测[J].南京信息工程大学学报(自然科学版),2021,13(6):653-660
CHEN Xijiang, AN Qing, BAN Yan. Optimized EfficientDet deep learning model for vehicle detection[J]. Journal of Nanjing University of Information Science & Technology, 2021,13(6):653-660

复制
分享
文章指标
  • 点击次数:123
  • 下载次数: 1437
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 收稿日期:2021-09-28
  • 在线发布日期: 2022-01-21

地址:江苏省南京市宁六路219号    邮编:210044

联系电话:025-58731025    E-mail:nxdxb@nuist.edu.cn

南京信息工程大学学报 ® 2025 版权所有  技术支持:北京勤云科技发展有限公司