一种新的结合卷积神经网络的隧道内停车检测方法
作者:
中图分类号:

TP751

基金项目:

国家自然科学基金项目(61604105)。


A new tunnel vehicle stopping detection methodology combined with convolutional neural network
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [20]
  • |
  • 相似文献
  • | | |
  • 文章评论
    摘要:

    为了更准确地检测高速公路隧道内停车行为,将传统的图像处理技术与深度学习相结合。首先,通过基于混合高斯模型(Gaussian mixture model,GMM)的背景差分法提取出运动目标。接着通过meanshift算法跟踪这些运动目标,计算运动目标的速度以及在相邻视频帧中运动目标的相关性,通过与速度阈值和相似度阈值的比较得到静止目标。最后,结合卷积神经网络(convolutional neural network,CNN)分类模型识别静止目标是否为车辆。文中方法在高速公路隧道视频上进行测试,达到至少84%的准确率。另外,与没有结合卷积神经网络的传统图像处理方法相比,文中方法至少提高了63%的准确率。

    Abstract:

    In order to more accurately detect the vehicle stopping in highway tunnels, this paper proposes a new methodology that combines the traditional image processing technology with deep learning. Firstly, the foreground moving targets are extracted using the background difference method based on Gaussian mixture model (GMM). Then the meanshift algorithm is applied to track these foreground moving targets. By calculating the speed of the moving targets and the correlation of the moving targets between the neighboring video frames, and comparing the results with the speed threshold and correlation threshold, the static target is detected. Finally, combined with the convolutional neural network (CNN) classification model, whether the static target is vehicle is identified. The method proposed in this paper is validated using the real highway tunnel vehicle stopping video and achieves an accuracy of at least 84%. Compared with the traditional image processing method without CNN, our method improves at least 63% accuracy.

    参考文献
    [1] Gazzah S, Mhalla A, Amara N E B. Vehicle detection on a video traffic scene:review and new perspectives[C/OL]//2016 7th International Conference on Sciences of Electronics, Technologies of Information and Telecommunications (SETIT). New York, USA:IEEE, 2017(2017-06-08)[2020-01-01]. https://doi.org/10.1109/SETIT.2016.7939912
    [2] Guler S, Silverstein J A, Pushee I H. Stationary objects in multiple object tracking[C/OL]//2007 IEEE Conference on Advanced Video and Signal Based Surveillance. New York, USA:IEEE, 2008(2008-07-07)[2020-01-01]. https://doi.org/10.1109/AVSS.2007.4425318
    [3] Porikli F. Detection of temporarily static regions by processing video at different frame rates[C]//2007 IEEE Conference on Advanced Video and Signal Based Surveillance, September 5-7, 2007, London, UK. IEEE, 2007:236-241.
    [4] 赵敏, 张波, 唐毅, 等. 露天场景下高速公路违章停车视频检测算法[J].计算机测量与控制,2014,22(2):489-492.Zhao M, Zhang B, Tang Y, et al. Detection algorithm for highway lllegal parking in open-air scenes[J]. Computer Measurement & Control, 2014, 22(2):489-492. (in Chinese)
    [5] 隋靓, 党建武. 基于运动目标轨迹的高速公路异常事件检测算法研究[J]. 计算机应用与软件,2018,35(1):246-252.Sui J, Dang J W. Traffic anomaly detection based on moving object trajectory[J]. Computer Applications and Software, 2018, 35(1):246-252. (in Chinese)
    [6] 胡煦, 黄俊, 袁梅. 基于视频的路侧停驶事件实时检测算法[J]. 信息通信,2019(3):4-7.Hu X, Huang J, Yuan M. Real-time detection of roadside parking events based on video[J]. Information & Communications,2019(3):4-7. (in Chinese)
    [7] Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks[C]//NIPS'12:Proceedings of the 25th International Conference on Neural Information Processing Systems. New York, USA:Curran Associates Inc, 2012,1:1097-1105.
    [8] Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions[C/OL]//2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). New York, USA:IEEE,2015(2018-08-15)[2020-01-01]. https://doi.org/10.1109/CVPR.2015.7298594.
    [9] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//IEEE Conference on Computer Vision & Pattern Recognition. New York, USA:IEEE Computer Society, 2016,1:770-778.
    [10] Hu J, Shen L, Albanie S, et al. Squeeze-and-excitation networks[C]//Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), June 18-22, 2018, Salt Lake City. IEEE, 2018:7132-7141.
    [11] Cui B, Créput J C. Moving object detection and tracking based on three-frame difference and background subtraction with laplace filter[M]. Artificial Intelligence and Soft Computing. Berlin, Germany:Springer, 2018:3-13.
    [12] Peng Y, Chen Z, Liu C, et al. Moving human detection and extraction via improved optical flow and adjacent region merger[C/OL]//2017 Chinese Automation Congress (CAC). New York, USA:IEEE, 2017(2017-10-01)[2020-01-01]. https://doi.org/10.1109/CAC.2017.8244112.
    [13] Ahmad J, Larijani H, Emmanuel R, et al. An intelligent real-time occupancy monitoring system with enhanced encryption and privacy[C/OL]//2018 IEEE 17th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC). New York, USA:IEEE, 2018(2018-10-08)[2020-01-01] https://doi.org/10.1109/ICCI-CC.2018.8482047.
    [14] Fan Y X, Wen G J, Li D, et al. Video anomaly detection and localization via gaussian mixture fully convolutional variational autoencoder[J]. Computer Vision and Image Understanding, 2020, 195:102920.
    [15] 高海壮, 段先华. 基于帧差法和混合高斯的海上运动目标检测[J].计算机与数字工程,2019,47(5):1140-1144.Gao H Z, Duan X H. A method for detecting maritime moving targets based on three-frame difference method and improved hybrid gaussian background model[J]. Computer and Digital Engineering, 2019,47(5):1140-1144. (in Chinese)
    [16] Cheng Y, Hongyu W, Xiaohong W. Positioning method research for unmanned aerial vehicles based on Meanshift tracking algorithm[C/OL]//Control & Decision Conference. New York, USA:IEEE, 2017(2017-07-17)[2020-01-01]. https://doi.org/10.1109/CCDC.2017.7978663.
    [17] Liu J, Zhong X. An object tracking method based on mean shift algorithm with HSV color space and texture features[J]. Cluster Computing,2019,22(3):6079-6090.
    [18] Wang B, Feng K, Yang W, et al. Study on multiple targets tracking algorithm based on multiple sensors[J]. Cluster Computing,2019,22(6):13283-13291.
    [19] Ioffe S, Szegedy C. Batch normalization:accelerating deep network training by reducing internal covariate shift[C]//ICML'15:Proceedings of the 32nd International Conference on International Conference on Machine Learning,New York,USA:JMLR.org. 2015, 37:448-456.
    [20] Hinton G E, Srivastava N, Krizhevsky A, et al. Improving neural networks by preventing co-adaptation of feature detectors[J]. Computer Science,2012,3(4):212-223.
    相似文献
    引证文献
引用本文

杨祖莨,丁洁,刘晋峰.一种新的结合卷积神经网络的隧道内停车检测方法[J].重庆大学学报,2021,44(6):49-59.

复制
分享
文章指标
  • 点击次数:466
  • 下载次数: 870
  • HTML阅读次数: 666
  • 引用次数: 0
历史
  • 收稿日期:2020-01-07
  • 在线发布日期: 2021-06-10
文章二维码