Two layer network flow for fast data association on multi object tracking

Bariqi Abdillah; Grafika Jati; Wisnu Jatmiko; Adi Nurhadiyatna

doi:10.1109/ICACSIS.2018.8618161

Two layer network flow for fast data association on multi object tracking

Bariqi Abdillah, Grafika Jati, Wisnu Jatmiko, Adi Nurhadiyatna

Department of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Multi object tracking is one interesting topics of computer science that has many applications, such as surveillance system, navigation robot, sports analysis, autonomous driving car, and others. One of the main task of multi-object tracking is data association. This study discusses data association on multi-object tracking and its completion with a two-layer network flow approach. Notice that each object on a frame as a node, then there is an edge connecting each node from one frame to other frame and then finding for the set of edges that provide the greatest probability of transition from one frame to the next, or in the optimization problem better known as max-cost network flow. The probability calculation is based on position distance and similarity feature between objects. The data used in this research is 2DMOT2015. The proposed method obtains highly competitive MOTA of 20.1% compared to existing method with fast computation speed by 215.8 fps.

Original language	English
Title of host publication	2018 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	373-378
Number of pages	6
ISBN (Electronic)	9781728101354
DOIs	https://doi.org/10.1109/ICACSIS.2018.8618161
Publication status	Published - 2 Jul 2018
Event	10th International Conference on Advanced Computer Science and Information Systems, ICACSIS 2018 - Yogyakarta, Indonesia Duration: 27 Oct 2018 → 28 Oct 2018

Publication series

Name	2018 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2018

Conference

Conference	10th International Conference on Advanced Computer Science and Information Systems, ICACSIS 2018
Country/Territory	Indonesia
City	Yogyakarta
Period	27/10/18 → 28/10/18

Keywords

Convolutional Neural Network
Data Association
Multi Object Tracking
Network Flow

Access to Document

10.1109/ICACSIS.2018.8618161

Cite this

Abdillah, B., Jati, G., Jatmiko, W., & Nurhadiyatna, A. (2018). Two layer network flow for fast data association on multi object tracking. In 2018 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2018 (pp. 373-378). Article 8618161 (2018 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICACSIS.2018.8618161

Abdillah, Bariqi ; Jati, Grafika ; Jatmiko, Wisnu et al. / Two layer network flow for fast data association on multi object tracking. 2018 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 373-378 (2018 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2018).

@inproceedings{156b1ef34e0441138783eed17b99fcdf,

title = "Two layer network flow for fast data association on multi object tracking",

abstract = "Multi object tracking is one interesting topics of computer science that has many applications, such as surveillance system, navigation robot, sports analysis, autonomous driving car, and others. One of the main task of multi-object tracking is data association. This study discusses data association on multi-object tracking and its completion with a two-layer network flow approach. Notice that each object on a frame as a node, then there is an edge connecting each node from one frame to other frame and then finding for the set of edges that provide the greatest probability of transition from one frame to the next, or in the optimization problem better known as max-cost network flow. The probability calculation is based on position distance and similarity feature between objects. The data used in this research is 2DMOT2015. The proposed method obtains highly competitive MOTA of 20.1% compared to existing method with fast computation speed by 215.8 fps.",

keywords = "Convolutional Neural Network, Data Association, Multi Object Tracking, Network Flow",

author = "Bariqi Abdillah and Grafika Jati and Wisnu Jatmiko and Adi Nurhadiyatna",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 10th International Conference on Advanced Computer Science and Information Systems, ICACSIS 2018 ; Conference date: 27-10-2018 Through 28-10-2018",

year = "2018",

month = jul,

day = "2",

doi = "10.1109/ICACSIS.2018.8618161",

language = "English",

series = "2018 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "373--378",

booktitle = "2018 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2018",

address = "United States",

}

Abdillah, B, Jati, G, Jatmiko, W & Nurhadiyatna, A 2018, Two layer network flow for fast data association on multi object tracking. in 2018 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2018., 8618161, 2018 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2018, Institute of Electrical and Electronics Engineers Inc., pp. 373-378, 10th International Conference on Advanced Computer Science and Information Systems, ICACSIS 2018, Yogyakarta, Indonesia, 27/10/18. https://doi.org/10.1109/ICACSIS.2018.8618161

Two layer network flow for fast data association on multi object tracking. / Abdillah, Bariqi; Jati, Grafika; Jatmiko, Wisnu et al.
2018 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 373-378 8618161 (2018 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2018).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Two layer network flow for fast data association on multi object tracking

AU - Abdillah, Bariqi

AU - Jati, Grafika

AU - Jatmiko, Wisnu

AU - Nurhadiyatna, Adi

PY - 2018/7/2

Y1 - 2018/7/2

N2 - Multi object tracking is one interesting topics of computer science that has many applications, such as surveillance system, navigation robot, sports analysis, autonomous driving car, and others. One of the main task of multi-object tracking is data association. This study discusses data association on multi-object tracking and its completion with a two-layer network flow approach. Notice that each object on a frame as a node, then there is an edge connecting each node from one frame to other frame and then finding for the set of edges that provide the greatest probability of transition from one frame to the next, or in the optimization problem better known as max-cost network flow. The probability calculation is based on position distance and similarity feature between objects. The data used in this research is 2DMOT2015. The proposed method obtains highly competitive MOTA of 20.1% compared to existing method with fast computation speed by 215.8 fps.

AB - Multi object tracking is one interesting topics of computer science that has many applications, such as surveillance system, navigation robot, sports analysis, autonomous driving car, and others. One of the main task of multi-object tracking is data association. This study discusses data association on multi-object tracking and its completion with a two-layer network flow approach. Notice that each object on a frame as a node, then there is an edge connecting each node from one frame to other frame and then finding for the set of edges that provide the greatest probability of transition from one frame to the next, or in the optimization problem better known as max-cost network flow. The probability calculation is based on position distance and similarity feature between objects. The data used in this research is 2DMOT2015. The proposed method obtains highly competitive MOTA of 20.1% compared to existing method with fast computation speed by 215.8 fps.

KW - Convolutional Neural Network

KW - Data Association

KW - Multi Object Tracking

KW - Network Flow

UR - http://www.scopus.com/inward/record.url?scp=85062428312&partnerID=8YFLogxK

U2 - 10.1109/ICACSIS.2018.8618161

DO - 10.1109/ICACSIS.2018.8618161

M3 - Conference contribution

AN - SCOPUS:85062428312

T3 - 2018 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2018

SP - 373

EP - 378

BT - 2018 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2018

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 10th International Conference on Advanced Computer Science and Information Systems, ICACSIS 2018

Y2 - 27 October 2018 through 28 October 2018

ER -

Abdillah B, Jati G, Jatmiko W, Nurhadiyatna A. Two layer network flow for fast data association on multi object tracking. In 2018 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 373-378. 8618161. (2018 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2018). doi: 10.1109/ICACSIS.2018.8618161

Two layer network flow for fast data association on multi object tracking

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this