Online multiple object tracking via flow and convolutional features

Lu Wang, Lisheng Xu, Min Young Kim, Luca Rigazico, Ming Hsuan Yang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

We propose an online multiple object tracking algorithm that exploits optical flow and convolutional features to handle noisy detections as well as frequent occlusion. To achieve robust tracking, we develop a data association method that deals with tracking scenarios of increasing difficulty. For easy scenarios, we use motion affinity to associate detections with objects. For ambiguous situations, we propose to use an appearance model based on convolutional features and correlation filters to complement template matching methods. For difficult cases where objects are under heavy occlusion, we carry out occlusion analysis, which exploits the relationship between targets and occluders to predict potential object locations. To deal with noisy detections, false positives are detected and removed on both raw detection and tracklet levels, while missing and inaccurate detections are recovered or corrected via short-term tracking. Experimental results on two benchmark datasets demonstrate that the proposed online algorithm performs favorably against the state-of-the-art methods.

Original languageEnglish
Title of host publication2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings
PublisherIEEE Computer Society
Pages3630-3634
Number of pages5
ISBN (Electronic)9781509021758
DOIs
Publication statusPublished - 2018 Feb 20
Event24th IEEE International Conference on Image Processing, ICIP 2017 - Beijing, China
Duration: 2017 Sep 172017 Sep 20

Publication series

NameProceedings - International Conference on Image Processing, ICIP
Volume2017-September
ISSN (Print)1522-4880

Other

Other24th IEEE International Conference on Image Processing, ICIP 2017
CountryChina
CityBeijing
Period17/9/1717/9/20

Fingerprint

Template matching
Optical flows

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Wang, L., Xu, L., Kim, M. Y., Rigazico, L., & Yang, M. H. (2018). Online multiple object tracking via flow and convolutional features. In 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings (pp. 3630-3634). (Proceedings - International Conference on Image Processing, ICIP; Vol. 2017-September). IEEE Computer Society. https://doi.org/10.1109/ICIP.2017.8296959
Wang, Lu ; Xu, Lisheng ; Kim, Min Young ; Rigazico, Luca ; Yang, Ming Hsuan. / Online multiple object tracking via flow and convolutional features. 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. IEEE Computer Society, 2018. pp. 3630-3634 (Proceedings - International Conference on Image Processing, ICIP).
@inproceedings{665b69a047df4724bdde580c5924495e,
title = "Online multiple object tracking via flow and convolutional features",
abstract = "We propose an online multiple object tracking algorithm that exploits optical flow and convolutional features to handle noisy detections as well as frequent occlusion. To achieve robust tracking, we develop a data association method that deals with tracking scenarios of increasing difficulty. For easy scenarios, we use motion affinity to associate detections with objects. For ambiguous situations, we propose to use an appearance model based on convolutional features and correlation filters to complement template matching methods. For difficult cases where objects are under heavy occlusion, we carry out occlusion analysis, which exploits the relationship between targets and occluders to predict potential object locations. To deal with noisy detections, false positives are detected and removed on both raw detection and tracklet levels, while missing and inaccurate detections are recovered or corrected via short-term tracking. Experimental results on two benchmark datasets demonstrate that the proposed online algorithm performs favorably against the state-of-the-art methods.",
author = "Lu Wang and Lisheng Xu and Kim, {Min Young} and Luca Rigazico and Yang, {Ming Hsuan}",
year = "2018",
month = "2",
day = "20",
doi = "10.1109/ICIP.2017.8296959",
language = "English",
series = "Proceedings - International Conference on Image Processing, ICIP",
publisher = "IEEE Computer Society",
pages = "3630--3634",
booktitle = "2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings",
address = "United States",

}

Wang, L, Xu, L, Kim, MY, Rigazico, L & Yang, MH 2018, Online multiple object tracking via flow and convolutional features. in 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. Proceedings - International Conference on Image Processing, ICIP, vol. 2017-September, IEEE Computer Society, pp. 3630-3634, 24th IEEE International Conference on Image Processing, ICIP 2017, Beijing, China, 17/9/17. https://doi.org/10.1109/ICIP.2017.8296959

Online multiple object tracking via flow and convolutional features. / Wang, Lu; Xu, Lisheng; Kim, Min Young; Rigazico, Luca; Yang, Ming Hsuan.

2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. IEEE Computer Society, 2018. p. 3630-3634 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2017-September).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Online multiple object tracking via flow and convolutional features

AU - Wang, Lu

AU - Xu, Lisheng

AU - Kim, Min Young

AU - Rigazico, Luca

AU - Yang, Ming Hsuan

PY - 2018/2/20

Y1 - 2018/2/20

N2 - We propose an online multiple object tracking algorithm that exploits optical flow and convolutional features to handle noisy detections as well as frequent occlusion. To achieve robust tracking, we develop a data association method that deals with tracking scenarios of increasing difficulty. For easy scenarios, we use motion affinity to associate detections with objects. For ambiguous situations, we propose to use an appearance model based on convolutional features and correlation filters to complement template matching methods. For difficult cases where objects are under heavy occlusion, we carry out occlusion analysis, which exploits the relationship between targets and occluders to predict potential object locations. To deal with noisy detections, false positives are detected and removed on both raw detection and tracklet levels, while missing and inaccurate detections are recovered or corrected via short-term tracking. Experimental results on two benchmark datasets demonstrate that the proposed online algorithm performs favorably against the state-of-the-art methods.

AB - We propose an online multiple object tracking algorithm that exploits optical flow and convolutional features to handle noisy detections as well as frequent occlusion. To achieve robust tracking, we develop a data association method that deals with tracking scenarios of increasing difficulty. For easy scenarios, we use motion affinity to associate detections with objects. For ambiguous situations, we propose to use an appearance model based on convolutional features and correlation filters to complement template matching methods. For difficult cases where objects are under heavy occlusion, we carry out occlusion analysis, which exploits the relationship between targets and occluders to predict potential object locations. To deal with noisy detections, false positives are detected and removed on both raw detection and tracklet levels, while missing and inaccurate detections are recovered or corrected via short-term tracking. Experimental results on two benchmark datasets demonstrate that the proposed online algorithm performs favorably against the state-of-the-art methods.

UR - http://www.scopus.com/inward/record.url?scp=85045316272&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045316272&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2017.8296959

DO - 10.1109/ICIP.2017.8296959

M3 - Conference contribution

AN - SCOPUS:85045316272

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 3630

EP - 3634

BT - 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings

PB - IEEE Computer Society

ER -

Wang L, Xu L, Kim MY, Rigazico L, Yang MH. Online multiple object tracking via flow and convolutional features. In 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. IEEE Computer Society. 2018. p. 3630-3634. (Proceedings - International Conference on Image Processing, ICIP). https://doi.org/10.1109/ICIP.2017.8296959