A novel approach for people counting and tracking from crowd video

M. Ayyuce Kizrak Sagun; Bulent Bolat

doi:10.1109/INISTA.2017.8001170

A novel approach for people counting and tracking from crowd video

M. Ayyuce Kizrak Sagun
, Bulent Bolat

Halic University
Yildiz Technical University

Araştırma çıktısı: Kitap/Rapor/Konferans Bildirisinde Bölüm › Konferans katkısı › Hakem

6 Atıf (Scopus)

Özet

Crowd analysis on video recordings is an important research area currently. In this work, a combined crowd density estimation method is presented to overcome this problem. To improve the accuracy of the system two different estimators run simultaneously and a blob is marked as a person only if both estimators mark it as person. One of the main problems in crowd density estimation is occlusion. To overcome this problem we tracked the trajectories of blobs by using a Kalman filter. The method was applied to three common benchmark data which are PETS2009, UCSD and Grand Central. The results confirm the proposed method's success.

Orijinal dil	İngilizce
Ana bilgisayar yayını başlığı	Proceedings - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017
Editörler	Tulay Yildirim, Ireneusz Czarnowski, Piotr Jedrzejowicz
Yayınlayan	Institute of Electrical and Electronics Engineers Inc.
Sayfalar	277-281
Sayfa sayısı	5
ISBN (Elektronik)	9781509057955
DOI'lar	https://doi.org/10.1109/INISTA.2017.8001170
Yayın durumu	Yayınlandı - 3 Ağu 2017
Harici olarak yayınlandı	Evet
Etkinlik	2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017 - Gdynia, Poland Süre: 3 Tem 2017 → 5 Tem 2017

Yayın serisi

Adı	Proceedings - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???	2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017
Ülke/Bölge	Poland
Şehir	Gdynia
Periyot	3/07/17 → 5/07/17

Bibliyografik not

Publisher Copyright:
© 2017 IEEE.

Belgeye Erişim

10.1109/INISTA.2017.8001170

Diğer Dosyalar ve Linkler

Link to publication in Scopus

Alıntı Yap

Sagun, M. A. K., & Bolat, B. (2017). A novel approach for people counting and tracking from crowd video. In T. Yildirim, I. Czarnowski, & P. Jedrzejowicz (Eds.), Proceedings - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017 (pp. 277-281). Makale 8001170 (Proceedings - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/INISTA.2017.8001170

Sagun, M. Ayyuce Kizrak ; Bolat, Bulent. / A novel approach for people counting and tracking from crowd video. Proceedings - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017. editör / Tulay Yildirim ; Ireneusz Czarnowski ; Piotr Jedrzejowicz. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 277-281 (Proceedings - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017).

@inproceedings{24e58c2f142b47f0afd7f84b8eb39e16,

title = "A novel approach for people counting and tracking from crowd video",

abstract = "Crowd analysis on video recordings is an important research area currently. In this work, a combined crowd density estimation method is presented to overcome this problem. To improve the accuracy of the system two different estimators run simultaneously and a blob is marked as a person only if both estimators mark it as person. One of the main problems in crowd density estimation is occlusion. To overcome this problem we tracked the trajectories of blobs by using a Kalman filter. The method was applied to three common benchmark data which are PETS2009, UCSD and Grand Central. The results confirm the proposed method's success.",

keywords = "Crowd density, Kalman filtering, Optical flow, SIFT, Video processing, complex wavelet transform",

author = "Sagun, \{M. Ayyuce Kizrak\} and Bulent Bolat",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017 ; Conference date: 03-07-2017 Through 05-07-2017",

year = "2017",

month = aug,

day = "3",

doi = "10.1109/INISTA.2017.8001170",

language = "English",

series = "Proceedings - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017",

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

pages = "277--281",

editor = "Tulay Yildirim and Ireneusz Czarnowski and Piotr Jedrzejowicz",

booktitle = "Proceedings - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017",

address = "United States",

}

Sagun, MAK & Bolat, B 2017, A novel approach for people counting and tracking from crowd video. in T Yildirim, I Czarnowski & P Jedrzejowicz (eds), Proceedings - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017., 8001170, Proceedings - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017, Institute of Electrical and Electronics Engineers Inc., pp. 277-281, 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017, Gdynia, Poland, 3/07/17. https://doi.org/10.1109/INISTA.2017.8001170

A novel approach for people counting and tracking from crowd video. / Sagun, M. Ayyuce Kizrak; Bolat, Bulent.
Proceedings - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017. ed. / Tulay Yildirim; Ireneusz Czarnowski; Piotr Jedrzejowicz. Institute of Electrical and Electronics Engineers Inc., 2017. p. 277-281 8001170 (Proceedings - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017).

Araştırma çıktısı: Kitap/Rapor/Konferans Bildirisinde Bölüm › Konferans katkısı › Hakem

TY - GEN

T1 - A novel approach for people counting and tracking from crowd video

AU - Sagun, M. Ayyuce Kizrak

AU - Bolat, Bulent

PY - 2017/8/3

Y1 - 2017/8/3

N2 - Crowd analysis on video recordings is an important research area currently. In this work, a combined crowd density estimation method is presented to overcome this problem. To improve the accuracy of the system two different estimators run simultaneously and a blob is marked as a person only if both estimators mark it as person. One of the main problems in crowd density estimation is occlusion. To overcome this problem we tracked the trajectories of blobs by using a Kalman filter. The method was applied to three common benchmark data which are PETS2009, UCSD and Grand Central. The results confirm the proposed method's success.

AB - Crowd analysis on video recordings is an important research area currently. In this work, a combined crowd density estimation method is presented to overcome this problem. To improve the accuracy of the system two different estimators run simultaneously and a blob is marked as a person only if both estimators mark it as person. One of the main problems in crowd density estimation is occlusion. To overcome this problem we tracked the trajectories of blobs by using a Kalman filter. The method was applied to three common benchmark data which are PETS2009, UCSD and Grand Central. The results confirm the proposed method's success.

KW - Crowd density

KW - Kalman filtering

KW - Optical flow

KW - SIFT

KW - Video processing

KW - complex wavelet transform

UR - https://www.scopus.com/pages/publications/85030249867

U2 - 10.1109/INISTA.2017.8001170

DO - 10.1109/INISTA.2017.8001170

M3 - Conference contribution

AN - SCOPUS:85030249867

T3 - Proceedings - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017

SP - 277

EP - 281

BT - Proceedings - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017

A2 - Yildirim, Tulay

A2 - Czarnowski, Ireneusz

A2 - Jedrzejowicz, Piotr

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017

Y2 - 3 July 2017 through 5 July 2017

ER -

Sagun MAK, Bolat B. A novel approach for people counting and tracking from crowd video. In Yildirim T, Czarnowski I, Jedrzejowicz P, editörler, Proceedings - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 277-281. 8001170. (Proceedings - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017). doi: 10.1109/INISTA.2017.8001170

A novel approach for people counting and tracking from crowd video

Özet

Yayın serisi

???event.eventtypes.event.conference???

Bibliyografik not

Belgeye Erişim

Diğer Dosyalar ve Linkler

Parmak izi

Alıntı Yap