Adaptive Deep Multi-object Tracking Algorithm Fusing Crowd Density

被引：0
|
作者：
Liu J. [1 ,2 ,3 ]
Ren W. [4 ]
Tian J. [1 ,2 ]
机构：
[1] Robotics Laboratory, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang
[2] Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang
[3] School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing
[4] School of Mechanical Engineering and Automation, Harbin Institute of Technology(Shenzhen), Shenzhen
来源：
Moshi Shibie yu Rengong Zhineng/Pattern Recognition and Artificial Intelligence | 2021年 / 34卷 / 05期
基金：
中国国家自然科学基金;
关键词：
Crowd density map; Multi-object tracking; Person re-identification; Triplet loss;
D O I：
10.16451/j.cnki.issn1003-6059.202105001
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
Multi-object tracking technology cannot well solve the problem of multi-object tracking in the scenarios with objects severely occluded, and therefore an adaptive deep multi-object tracking algorithm fusing crowd density is proposed. Firstly, the crowd density maps and object detection results are fused, and the location and the count information of crowd density maps are utilized to correct the detector results to eliminate missing and false detections. Then, adaptive triplet loss is employed to improve the loss function of the re-identification model and thus the discrimination of the algorithm for the re-identification feature is enhanced. Finally, final tracking results are obtained using the appearance and motion information for objects association. It is verified through the experiments that the proposed algorithm effectively solves the problem of multi-object tracking in severely occluded scenes. © 2021, Science Press. All right reserved.
引用
收藏
页码：385 / 397
页数：12
相关论文
共 36 条
  • [1] FARABET C, COUPRIE C, NAJMAN L, Et al., Learning Hierarchical Features for Scene Labeling, IEEE Transactions on Pattern Analysis and Machine Intelligence, 35, 8, pp. 1915-1929, (2013)
  • [2] CHAN A B, VASCONCELOS N., Counting People with Low-Level Features and Bayesian Regression, IEEE Transactions on Image Processing, 21, 4, pp. 2160-2177, (2012)
  • [3] KONG D, GRAY D, TAO H., A Viewpoint Invariant Approach for Crowd Counting, Proc of the 18th IEEE International Conference on Pattern Recognition, pp. 1187-1190, (2006)
  • [4] RYAN D, DENMAN S, FOOKES C, Et al., Crowd Counting Using Multiple Local Features, Proc of the IEEE Conference on Digital Image Computing: Techniques and Applications, pp. 81-88, (2009)
  • [5] IDREES H, SALEEMI I, SEIBERT C, Et al., Multi-source Multi-scale Counting in Extremely Dense Crowd Images, Proc of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2547-2554, (2013)
  • [6] LEMPITSKY V, ZISSERMAN A., Learning to Count Objects in Images, Proc of the 23rd International Conference on Neural Information Processing Systems, I, pp. 1324-1332, (2010)
  • [7] BEWLEY A, GE Z Y, OTT L, Et al., Simple Online and Realtime Tracking, Proc of the IEEE International Conference on Image Processing, pp. 3464-3468, (2016)
  • [8] WOJKE N, BEWLEY A, PAULUS D., Simple Online and Realtime Tracking with a Deep Association Metric, Proc of the IEEE International Conference on Image Processing, pp. 3645-3649, (2017)
  • [9] WOJKE N, BEWLEY A., Deep Cosine Metric Learning for Person Re-identification, Proc of the IEEE Winter Conference on Applications of Computer Vision, pp. 748-756, (2018)
  • [10] RISTANI E, TOMASI C., Features for Multi-target Multi-camera Tracking and Re-identification, Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6036-6046, (2018)
1234