Training-free moving object detection system based on hierarchical color-guided motion segmentation

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

1 Citaat (Scopus)
1 Downloads (Pure)

Uittreksel

We present a moving object detection system for surveillance based on Hierarchical Color-guided Motion segmentation (HiCoMo). The HiCoMo system does not require training and consists of two main stages: (1) hierarchical color-guided motion segmentation, and (2) motion-based verification. The first stage is a hierarchical segmentation framework, where at each level a balance is made between static and temporal features. So that groups of pixels develop into semantic object segments. In the second stage, these object segments are further analyzed in terms of motion saliency and consistency, in order to finalize the object detection results. Our proposed system is tested on real-life surveillance videos containing various scenarios. The detection results outperform a state-of-the-art training-free moving object detection algorithm in recall (90.2% compared to 81.6%) while having a competitively promising precision (96.5% compared to 97.4%). The system has a generic nature and real-time implementation potential, which makes it applicable to various applications of computer vision.

Originele taal-2Engels
TitelProceedings of the 14th IAPR International Conference on Machine Vision Applications, MVA 2015
Plaats van productiePiscataway
UitgeverijInstitute of Electrical and Electronics Engineers
Pagina's154-157
Aantal pagina's4
ISBN van elektronische versie9784901122153
DOI's
StatusGepubliceerd - 1 jan 2015
Evenement14th IAPR International Conference on Machine Vision Applications (MVA 2015) - Tokyo, Japan
Duur: 18 mei 201522 mei 2015
Congresnummer: 14
http://www.mva-org.jp/mva2015

Congres

Congres14th IAPR International Conference on Machine Vision Applications (MVA 2015)
Verkorte titelMVA 2015
LandJapan
StadTokyo
Periode18/05/1522/05/15
Internet adres

Vingerafdruk

Color
Computer vision
Pixels
Semantics
Object detection

Citeer dit

Bao, X., Dubbelman, G., Zinger, S., & de With, P. H. N. (2015). Training-free moving object detection system based on hierarchical color-guided motion segmentation. In Proceedings of the 14th IAPR International Conference on Machine Vision Applications, MVA 2015 (blz. 154-157). Piscataway: Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/MVA.2015.7153156
Bao, Xinfeng ; Dubbelman, Gijs ; Zinger, Svitlana ; de With, Peter H.N. / Training-free moving object detection system based on hierarchical color-guided motion segmentation. Proceedings of the 14th IAPR International Conference on Machine Vision Applications, MVA 2015. Piscataway : Institute of Electrical and Electronics Engineers, 2015. blz. 154-157
@inproceedings{f8cbf7488fc7474794f598d8f80b61bd,
title = "Training-free moving object detection system based on hierarchical color-guided motion segmentation",
abstract = "We present a moving object detection system for surveillance based on Hierarchical Color-guided Motion segmentation (HiCoMo). The HiCoMo system does not require training and consists of two main stages: (1) hierarchical color-guided motion segmentation, and (2) motion-based verification. The first stage is a hierarchical segmentation framework, where at each level a balance is made between static and temporal features. So that groups of pixels develop into semantic object segments. In the second stage, these object segments are further analyzed in terms of motion saliency and consistency, in order to finalize the object detection results. Our proposed system is tested on real-life surveillance videos containing various scenarios. The detection results outperform a state-of-the-art training-free moving object detection algorithm in recall (90.2{\%} compared to 81.6{\%}) while having a competitively promising precision (96.5{\%} compared to 97.4{\%}). The system has a generic nature and real-time implementation potential, which makes it applicable to various applications of computer vision.",
author = "Xinfeng Bao and Gijs Dubbelman and Svitlana Zinger and {de With}, {Peter H.N.}",
year = "2015",
month = "1",
day = "1",
doi = "10.1109/MVA.2015.7153156",
language = "English",
pages = "154--157",
booktitle = "Proceedings of the 14th IAPR International Conference on Machine Vision Applications, MVA 2015",
publisher = "Institute of Electrical and Electronics Engineers",
address = "United States",

}

Bao, X, Dubbelman, G, Zinger, S & de With, PHN 2015, Training-free moving object detection system based on hierarchical color-guided motion segmentation. in Proceedings of the 14th IAPR International Conference on Machine Vision Applications, MVA 2015. Institute of Electrical and Electronics Engineers, Piscataway, blz. 154-157, 14th IAPR International Conference on Machine Vision Applications (MVA 2015), Tokyo, Japan, 18/05/15. https://doi.org/10.1109/MVA.2015.7153156

Training-free moving object detection system based on hierarchical color-guided motion segmentation. / Bao, Xinfeng; Dubbelman, Gijs; Zinger, Svitlana; de With, Peter H.N.

Proceedings of the 14th IAPR International Conference on Machine Vision Applications, MVA 2015. Piscataway : Institute of Electrical and Electronics Engineers, 2015. blz. 154-157.

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

TY - GEN

T1 - Training-free moving object detection system based on hierarchical color-guided motion segmentation

AU - Bao, Xinfeng

AU - Dubbelman, Gijs

AU - Zinger, Svitlana

AU - de With, Peter H.N.

PY - 2015/1/1

Y1 - 2015/1/1

N2 - We present a moving object detection system for surveillance based on Hierarchical Color-guided Motion segmentation (HiCoMo). The HiCoMo system does not require training and consists of two main stages: (1) hierarchical color-guided motion segmentation, and (2) motion-based verification. The first stage is a hierarchical segmentation framework, where at each level a balance is made between static and temporal features. So that groups of pixels develop into semantic object segments. In the second stage, these object segments are further analyzed in terms of motion saliency and consistency, in order to finalize the object detection results. Our proposed system is tested on real-life surveillance videos containing various scenarios. The detection results outperform a state-of-the-art training-free moving object detection algorithm in recall (90.2% compared to 81.6%) while having a competitively promising precision (96.5% compared to 97.4%). The system has a generic nature and real-time implementation potential, which makes it applicable to various applications of computer vision.

AB - We present a moving object detection system for surveillance based on Hierarchical Color-guided Motion segmentation (HiCoMo). The HiCoMo system does not require training and consists of two main stages: (1) hierarchical color-guided motion segmentation, and (2) motion-based verification. The first stage is a hierarchical segmentation framework, where at each level a balance is made between static and temporal features. So that groups of pixels develop into semantic object segments. In the second stage, these object segments are further analyzed in terms of motion saliency and consistency, in order to finalize the object detection results. Our proposed system is tested on real-life surveillance videos containing various scenarios. The detection results outperform a state-of-the-art training-free moving object detection algorithm in recall (90.2% compared to 81.6%) while having a competitively promising precision (96.5% compared to 97.4%). The system has a generic nature and real-time implementation potential, which makes it applicable to various applications of computer vision.

UR - http://www.scopus.com/inward/record.url?scp=84941243835&partnerID=8YFLogxK

U2 - 10.1109/MVA.2015.7153156

DO - 10.1109/MVA.2015.7153156

M3 - Conference contribution

AN - SCOPUS:84941243835

SP - 154

EP - 157

BT - Proceedings of the 14th IAPR International Conference on Machine Vision Applications, MVA 2015

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

ER -

Bao X, Dubbelman G, Zinger S, de With PHN. Training-free moving object detection system based on hierarchical color-guided motion segmentation. In Proceedings of the 14th IAPR International Conference on Machine Vision Applications, MVA 2015. Piscataway: Institute of Electrical and Electronics Engineers. 2015. blz. 154-157 https://doi.org/10.1109/MVA.2015.7153156