Deep learning algorithm based on MobileNet for multi-target tracking

被引：0
|
作者：
Xue J.-T. [1 ]
Ma R.-H. [1 ]
Hu C.-F. [1 ,2 ]
机构：
[1] School of Electrical and Information Engineering, Tianjin University, Tianjin
[2] Key Laboratory of Micro Opto-electro Mechanical System Technology of Ministry of Education, Tianjin University, Tianjin
来源：
Kongzhi yu Juece/Control and Decision | 2021年 / 36卷 / 08期
关键词：
Deep learning; Deep-SORT; MobileNet; Multi-target tracking; Object detection; YOLOv3;
D O I：
10.13195/j.kzyjc.2019.1424
中图分类号：
学科分类号：
摘要：
For the real-time problem of deep learning algorithm in multi-target tracking, a multi-target tracking algorithm based on MobileNet is proposed. Using the principle that deepwise separable convolution of MobileNet can compress deep network models, the YOLOv3 backbone network is replaced by MobileNet, but multiscale predictions are remained, which reduces effectively the amount of parameters by factorizing a standard convolution into a depthwise convolution and a pointwise convolution. For the detected bounding box information, the tracking task is performed using the Deep-SORT algorithm. The experimental results show that the processing speed is improved by nearly 50% under the condition of maintaining the tracking result. Copyright ©2021 Control and Decision.
引用
收藏
页码：1991 / 1996
页数：5
相关论文
共 24 条
  • [1] Luo W, Xing J, Milan A, Et al., Multiple object tracking: A literature review, (2014)
  • [2] Liu W, Anguelov D, Erhan D, Et al., SSD: Single shot multi box detector, Proceedings of European Conference on Computer Vision (ECCV), pp. 21-37, (2016)
  • [3] Girshick R., Fast R-CNN, Proceedings of International Conference on Computer Vision(ICCV), pp. 1440-1448, (2015)
  • [4] Ren S, He K, Girshick R, Et al., Faster R-CNN: Towards real-time object detection with region proposal networks, IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 6, pp. 1137-1149, (2017)
  • [5] Redmon J, Divvala S, Girshick R, Et al., You only look once: Unified, real-time object detection, Proceedings of Computer Vision and Pattern Recognition (CVPR), pp. 779-788, (2015)
  • [6] Redmon J, Farhadi A., YOLO9000: Better, faster, stronger, Proceedings of Computer Vision and Pattern Recognition (CVPR), pp. 6517-6525, (2017)
  • [7] Redmon J, Farhadi A., YOLOv3: An incremental improvement, Proceedings of Computer Vision and Pattern Recognition(CVPR), pp. 1-6, (2018)
  • [8] Lei Wu, Han Yue, Peng Chen, Et al., A novel dynamic network pruning via smooth initialization and its potential applications in machine learning based security solutions, IEEE Access, 7, pp. 91667-91678, (2019)
  • [9] Wang S S, Wang M, Wang G Y., Deep neural network pruning based two-stage remote sensing image object detection, Journal of Northeastern University: Natural Science, 40, 2, pp. 174-179, (2019)
  • [10] Polyak Adam, Wolf Lior, Channel-level acceleration of deep face representations, IEEE Access, 3, pp. 2163-2175, (2015)
123