A novel SURF-based algorithm for tracking a 'Human' in a dynamic environment

Meenakshi Gupta; Swagat Kumar; Sourav Garg; Nishant Kejriwal; Laxmidhar Behera

doi:10.1109/ICARCV.2014.7064443

A novel SURF-based algorithm for tracking a 'Human' in a dynamic environment

Meenakshi Gupta, Swagat Kumar, Sourav Garg, Nishant Kejriwal, Laxmidhar Behera

Computer Science

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

2 Citations (Scopus)

Abstract

© 2014 IEEE. Detecting and tracking a human from a mobile robot platform has several applications in service robotics where a robot is expected to assist humans. In this paper, we propose a novel interest point-based algorithm that can track a human reliably under several challenging situations like variation in illumination, pose change, scaling, camera motion and occlusion. The limitations of point-based methods are overcome using colour information and imposing a structure on the colour blobs. Whenever sufficient number of SURF matching points are not available for a given frame, the presence of human is detected using Markov random field based graph matching algorithm. Imposition of structure on coloured blobs helps in eliminating background objects having similar colour distribution. The stability-versus-plasticity dilemma inherent in tracking over long run is resolved by selecting new templates on-line and maintaining a tree of templates which is updated with new information. The performance of the algorithm is demonstrated through simulation on standard datasets and the computation time is found to be comparable with existing SURF-based tracking methods.

Original language	English
Title of host publication	2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1004-1009
Number of pages	6
ISBN (Print)	9781479951994
DOIs	https://doi.org/10.1109/ICARCV.2014.7064443
Publication status	Published - 12 Dec 2014
Event	13th International Conference on Control Automation Robotics and Vision - Marina Bay Sands, Singapore, Singapore Duration: 10 Dec 2014 → 12 Dec 2014

Publication series

Name	2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014

Conference

Conference	13th International Conference on Control Automation Robotics and Vision
Country/Territory	Singapore
City	Singapore
Period	10/12/14 → 12/12/14

Keywords

Binary Search Tree
Graph Matching
Human-Tracking
Mobile Robot
SURF

Access to Document

10.1109/ICARCV.2014.7064443

Cite this

Gupta, M., Kumar, S., Garg, S., Kejriwal, N., & Behera, L. (2014). A novel SURF-based algorithm for tracking a 'Human' in a dynamic environment. In 2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014 (pp. 1004-1009). (2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICARCV.2014.7064443

Gupta, Meenakshi ; Kumar, Swagat ; Garg, Sourav et al. / A novel SURF-based algorithm for tracking a 'Human' in a dynamic environment. 2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 1004-1009 (2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014).

@inbook{6eac0ee55f1144c296686344da9cf061,

title = "A novel SURF-based algorithm for tracking a 'Human' in a dynamic environment",

abstract = "{\textcopyright} 2014 IEEE. Detecting and tracking a human from a mobile robot platform has several applications in service robotics where a robot is expected to assist humans. In this paper, we propose a novel interest point-based algorithm that can track a human reliably under several challenging situations like variation in illumination, pose change, scaling, camera motion and occlusion. The limitations of point-based methods are overcome using colour information and imposing a structure on the colour blobs. Whenever sufficient number of SURF matching points are not available for a given frame, the presence of human is detected using Markov random field based graph matching algorithm. Imposition of structure on coloured blobs helps in eliminating background objects having similar colour distribution. The stability-versus-plasticity dilemma inherent in tracking over long run is resolved by selecting new templates on-line and maintaining a tree of templates which is updated with new information. The performance of the algorithm is demonstrated through simulation on standard datasets and the computation time is found to be comparable with existing SURF-based tracking methods.",

keywords = "Binary Search Tree, Graph Matching, Human-Tracking, Mobile Robot, SURF",

author = "Meenakshi Gupta and Swagat Kumar and Sourav Garg and Nishant Kejriwal and Laxmidhar Behera",

year = "2014",

month = dec,

day = "12",

doi = "10.1109/ICARCV.2014.7064443",

language = "English",

isbn = "9781479951994",

series = "2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014",

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

pages = "1004--1009",

booktitle = "2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014",

address = "United States",

note = "13th International Conference on Control Automation Robotics and Vision ; Conference date: 10-12-2014 Through 12-12-2014",

}

Gupta, M, Kumar, S, Garg, S, Kejriwal, N & Behera, L 2014, A novel SURF-based algorithm for tracking a 'Human' in a dynamic environment. in 2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014. 2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014, Institute of Electrical and Electronics Engineers Inc., pp. 1004-1009, 13th International Conference on Control Automation Robotics and Vision, Singapore, Singapore, 10/12/14. https://doi.org/10.1109/ICARCV.2014.7064443

A novel SURF-based algorithm for tracking a 'Human' in a dynamic environment. / Gupta, Meenakshi; Kumar, Swagat; Garg, Sourav et al.
2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 1004-1009 (2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014).

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

TY - CHAP

T1 - A novel SURF-based algorithm for tracking a 'Human' in a dynamic environment

AU - Gupta, Meenakshi

AU - Kumar, Swagat

AU - Garg, Sourav

AU - Kejriwal, Nishant

AU - Behera, Laxmidhar

PY - 2014/12/12

Y1 - 2014/12/12

N2 - © 2014 IEEE. Detecting and tracking a human from a mobile robot platform has several applications in service robotics where a robot is expected to assist humans. In this paper, we propose a novel interest point-based algorithm that can track a human reliably under several challenging situations like variation in illumination, pose change, scaling, camera motion and occlusion. The limitations of point-based methods are overcome using colour information and imposing a structure on the colour blobs. Whenever sufficient number of SURF matching points are not available for a given frame, the presence of human is detected using Markov random field based graph matching algorithm. Imposition of structure on coloured blobs helps in eliminating background objects having similar colour distribution. The stability-versus-plasticity dilemma inherent in tracking over long run is resolved by selecting new templates on-line and maintaining a tree of templates which is updated with new information. The performance of the algorithm is demonstrated through simulation on standard datasets and the computation time is found to be comparable with existing SURF-based tracking methods.

AB - © 2014 IEEE. Detecting and tracking a human from a mobile robot platform has several applications in service robotics where a robot is expected to assist humans. In this paper, we propose a novel interest point-based algorithm that can track a human reliably under several challenging situations like variation in illumination, pose change, scaling, camera motion and occlusion. The limitations of point-based methods are overcome using colour information and imposing a structure on the colour blobs. Whenever sufficient number of SURF matching points are not available for a given frame, the presence of human is detected using Markov random field based graph matching algorithm. Imposition of structure on coloured blobs helps in eliminating background objects having similar colour distribution. The stability-versus-plasticity dilemma inherent in tracking over long run is resolved by selecting new templates on-line and maintaining a tree of templates which is updated with new information. The performance of the algorithm is demonstrated through simulation on standard datasets and the computation time is found to be comparable with existing SURF-based tracking methods.

KW - Binary Search Tree

KW - Graph Matching

KW - Human-Tracking

KW - Mobile Robot

KW - SURF

UR - http://www.mendeley.com/research/novel-surfbased-algorithm-tracking-human-dynamic-environment

U2 - 10.1109/ICARCV.2014.7064443

DO - 10.1109/ICARCV.2014.7064443

M3 - Chapter

SN - 9781479951994

T3 - 2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014

SP - 1004

EP - 1009

BT - 2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 13th International Conference on Control Automation Robotics and Vision

Y2 - 10 December 2014 through 12 December 2014

ER -

Gupta M, Kumar S, Garg S, Kejriwal N, Behera L. A novel SURF-based algorithm for tracking a 'Human' in a dynamic environment. In 2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 1004-1009. (2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014). doi: 10.1109/ICARCV.2014.7064443

A novel SURF-based algorithm for tracking a 'Human' in a dynamic environment

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this