Kalman filter based multiple objects detection-tracking algorithm robust to occlusion

Jong Min Jeong, Tae Sung Yoon, Jin Bae Park

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

13 Citations (Scopus)

Abstract

Visual target tracking is one of the major fields in computer vision system. Object tracking has many practical applications such as automated surveillance system, military guidance, traffic management system, fault detection system, artificial intelligence and robot vision system. But it is difficult to track objects with image sensor. Especially, multiple objects tracking is harder than single object tracking. This paper proposes multiple objects tracking algorithm based on the Kalman filter. Our algorithm uses the Kalman filter as many as the number of moving objects in the image frame. If many moving objects exist in the image, however, we obtain multiple measurements. Therefore, precise data association is necessary in order to track multiple objects correctly. Another problem of multiple objects tracking is occlusion that causes merge and split. For solving these problems, this paper defines the cost function using some factors. Experiments using Matlab show that the performance of the proposed algorithm is appropriate for multiple objects tracking in real-time.

Original languageEnglish
Title of host publicationProceedings of the SICE Annual Conference
PublisherSociety of Instrument and Control Engineers (SICE)
Pages941-946
Number of pages6
ISBN (Electronic)9784907764463
DOIs
Publication statusPublished - 2014 Oct 23
Event2014 53rd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2014 - Sapporo, Japan
Duration: 2014 Sep 92014 Sep 12

Other

Other2014 53rd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2014
CountryJapan
CitySapporo
Period14/9/914/9/12

Fingerprint

Kalman filters
Computer vision
Target tracking
Fault detection
Image sensors
Cost functions
Artificial intelligence
Object detection
Experiments

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Jeong, J. M., Yoon, T. S., & Park, J. B. (2014). Kalman filter based multiple objects detection-tracking algorithm robust to occlusion. In Proceedings of the SICE Annual Conference (pp. 941-946). [6935235] Society of Instrument and Control Engineers (SICE). https://doi.org/10.1109/SICE.2014.6935235
Jeong, Jong Min ; Yoon, Tae Sung ; Park, Jin Bae. / Kalman filter based multiple objects detection-tracking algorithm robust to occlusion. Proceedings of the SICE Annual Conference. Society of Instrument and Control Engineers (SICE), 2014. pp. 941-946
@inproceedings{adb0b4b79e1c46daa8efc4502da3bc07,
title = "Kalman filter based multiple objects detection-tracking algorithm robust to occlusion",
abstract = "Visual target tracking is one of the major fields in computer vision system. Object tracking has many practical applications such as automated surveillance system, military guidance, traffic management system, fault detection system, artificial intelligence and robot vision system. But it is difficult to track objects with image sensor. Especially, multiple objects tracking is harder than single object tracking. This paper proposes multiple objects tracking algorithm based on the Kalman filter. Our algorithm uses the Kalman filter as many as the number of moving objects in the image frame. If many moving objects exist in the image, however, we obtain multiple measurements. Therefore, precise data association is necessary in order to track multiple objects correctly. Another problem of multiple objects tracking is occlusion that causes merge and split. For solving these problems, this paper defines the cost function using some factors. Experiments using Matlab show that the performance of the proposed algorithm is appropriate for multiple objects tracking in real-time.",
author = "Jeong, {Jong Min} and Yoon, {Tae Sung} and Park, {Jin Bae}",
year = "2014",
month = "10",
day = "23",
doi = "10.1109/SICE.2014.6935235",
language = "English",
pages = "941--946",
booktitle = "Proceedings of the SICE Annual Conference",
publisher = "Society of Instrument and Control Engineers (SICE)",

}

Jeong, JM, Yoon, TS & Park, JB 2014, Kalman filter based multiple objects detection-tracking algorithm robust to occlusion. in Proceedings of the SICE Annual Conference., 6935235, Society of Instrument and Control Engineers (SICE), pp. 941-946, 2014 53rd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2014, Sapporo, Japan, 14/9/9. https://doi.org/10.1109/SICE.2014.6935235

Kalman filter based multiple objects detection-tracking algorithm robust to occlusion. / Jeong, Jong Min; Yoon, Tae Sung; Park, Jin Bae.

Proceedings of the SICE Annual Conference. Society of Instrument and Control Engineers (SICE), 2014. p. 941-946 6935235.

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

TY - GEN

T1 - Kalman filter based multiple objects detection-tracking algorithm robust to occlusion

AU - Jeong, Jong Min

AU - Yoon, Tae Sung

AU - Park, Jin Bae

PY - 2014/10/23

Y1 - 2014/10/23

N2 - Visual target tracking is one of the major fields in computer vision system. Object tracking has many practical applications such as automated surveillance system, military guidance, traffic management system, fault detection system, artificial intelligence and robot vision system. But it is difficult to track objects with image sensor. Especially, multiple objects tracking is harder than single object tracking. This paper proposes multiple objects tracking algorithm based on the Kalman filter. Our algorithm uses the Kalman filter as many as the number of moving objects in the image frame. If many moving objects exist in the image, however, we obtain multiple measurements. Therefore, precise data association is necessary in order to track multiple objects correctly. Another problem of multiple objects tracking is occlusion that causes merge and split. For solving these problems, this paper defines the cost function using some factors. Experiments using Matlab show that the performance of the proposed algorithm is appropriate for multiple objects tracking in real-time.

AB - Visual target tracking is one of the major fields in computer vision system. Object tracking has many practical applications such as automated surveillance system, military guidance, traffic management system, fault detection system, artificial intelligence and robot vision system. But it is difficult to track objects with image sensor. Especially, multiple objects tracking is harder than single object tracking. This paper proposes multiple objects tracking algorithm based on the Kalman filter. Our algorithm uses the Kalman filter as many as the number of moving objects in the image frame. If many moving objects exist in the image, however, we obtain multiple measurements. Therefore, precise data association is necessary in order to track multiple objects correctly. Another problem of multiple objects tracking is occlusion that causes merge and split. For solving these problems, this paper defines the cost function using some factors. Experiments using Matlab show that the performance of the proposed algorithm is appropriate for multiple objects tracking in real-time.

UR - http://www.scopus.com/inward/record.url?scp=84911932944&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84911932944&partnerID=8YFLogxK

U2 - 10.1109/SICE.2014.6935235

DO - 10.1109/SICE.2014.6935235

M3 - Conference contribution

AN - SCOPUS:84911932944

SP - 941

EP - 946

BT - Proceedings of the SICE Annual Conference

PB - Society of Instrument and Control Engineers (SICE)

ER -

Jeong JM, Yoon TS, Park JB. Kalman filter based multiple objects detection-tracking algorithm robust to occlusion. In Proceedings of the SICE Annual Conference. Society of Instrument and Control Engineers (SICE). 2014. p. 941-946. 6935235 https://doi.org/10.1109/SICE.2014.6935235