Real-time RGB-D Tracking with Depth Scaling Kernelised Correlation Filters and Occlusion Handling

Massimo Camplani; Sion Hannuna; Majid Mirmehdi; Dima Damen (Aldamen); Lili Tao; Tilo Burghardt; Adeline Paiement

doi:10.5244/C.29.145

Real-time RGB-D Tracking with Depth Scaling Kernelised Correlation Filters and Occlusion Handling

Massimo Camplani, Sion Hannuna, Majid Mirmehdi, Dima Damen (Aldamen), Lili Tao, Tilo Burghardt, Adeline Paiement

SPHERE

Research output: Contribution to conference › Conference Paper

132 Downloads (Pure)

Abstract

We present a real-time RGB-D object tracker which manages occlusions and scale changes in a wide variety of scenarios. Its accuracy matches, and in many cases outperforms, state-of-the-art algorithms for precision and it far exceeds most in speed. We build our algorithm on the existing colour-only KCF tracker which uses the `kernel trick' to extend correlation filters for fast tracking. We fuse colour and depth cues as the tracker's features, and furthermore, exploit the depth data to both adjust a given target's scale, and detect and manage occlusions in such a way as to maintain real-time performance, exceeding on average 40~fps. We benchmark our approach using 2 publicly available datasets and make our easy-to-extend modularised code available to other researchers.

Original language	English
Pages	145.1-145.11
Number of pages	11
DOIs	https://doi.org/10.5244/C.29.145
Publication status	Published - Sep 2015

Structured keywords

Digital Health

Keywords

RGB-D tracking
Kernelised Correlation Filters
Depth and Color Fusion
Digital Health

Access to Document

10.5244/C.29.145

Fingerprint Dive into the research topics of 'Real-time RGB-D Tracking with Depth Scaling Kernelised Correlation Filters and Occlusion Handling'. Together they form a unique fingerprint.

Projects

1 Finished

SPHERE (EPSRC IRC)

Craddock, I. J., Coyle, D. T., Flach, P. A., Kaleshi, D., Mirmehdi, M., Piechocki, R. J., Stark, B. H., Ascione, R., Ashburn, A. M., Burnett, M. E., Aldamen, D., Gooberman-Hill, R. J. S., Harwin, W. S., Hilton, G., Holderbaum, W., Holley, A. P., Manchester, V. A., Meller, B. J., Stack, E. & Gilchrist, I. D.

1/10/13 → 30/09/18

Project: Research, Parent

Cite this

Camplani, M., Hannuna, S., Mirmehdi, M., Damen (Aldamen), D., Tao, L., Burghardt, T., & Paiement, A. (2015). Real-time RGB-D Tracking with Depth Scaling Kernelised Correlation Filters and Occlusion Handling. 145.1-145.11. https://doi.org/10.5244/C.29.145

@conference{ffd3c82e77d847d79eae669d31a5cddf,

title = "Real-time RGB-D Tracking with Depth Scaling Kernelised Correlation Filters and Occlusion Handling",

abstract = "We present a real-time RGB-D object tracker which manages occlusions and scale changes in a wide variety of scenarios. Its accuracy matches, and in many cases outperforms, state-of-the-art algorithms for precision and it far exceeds most in speed. We build our algorithm on the existing colour-only KCF tracker which uses the `kernel trick' to extend correlation filters for fast tracking. We fuse colour and depth cues as the tracker's features, and furthermore, exploit the depth data to both adjust a given target's scale, and detect and manage occlusions in such a way as to maintain real-time performance, exceeding on average 40~fps. We benchmark our approach using 2 publicly available datasets and make our easy-to-extend modularised code available to other researchers. ",

keywords = "RGB-D tracking, Kernelised Correlation Filters, Depth and Color Fusion, Digital Health",

author = "Massimo Camplani and Sion Hannuna and Majid Mirmehdi and {Damen (Aldamen)}, Dima and Lili Tao and Tilo Burghardt and Adeline Paiement",

year = "2015",

month = sep,

doi = "10.5244/C.29.145",

language = "English",

pages = "145.1--145.11",

}

TY - CONF

T1 - Real-time RGB-D Tracking with Depth Scaling Kernelised Correlation Filters and Occlusion Handling

AU - Camplani, Massimo

AU - Hannuna, Sion

AU - Mirmehdi, Majid

AU - Damen (Aldamen), Dima

AU - Tao, Lili

AU - Burghardt, Tilo

AU - Paiement, Adeline

PY - 2015/9

Y1 - 2015/9

N2 - We present a real-time RGB-D object tracker which manages occlusions and scale changes in a wide variety of scenarios. Its accuracy matches, and in many cases outperforms, state-of-the-art algorithms for precision and it far exceeds most in speed. We build our algorithm on the existing colour-only KCF tracker which uses the `kernel trick' to extend correlation filters for fast tracking. We fuse colour and depth cues as the tracker's features, and furthermore, exploit the depth data to both adjust a given target's scale, and detect and manage occlusions in such a way as to maintain real-time performance, exceeding on average 40~fps. We benchmark our approach using 2 publicly available datasets and make our easy-to-extend modularised code available to other researchers.

AB - We present a real-time RGB-D object tracker which manages occlusions and scale changes in a wide variety of scenarios. Its accuracy matches, and in many cases outperforms, state-of-the-art algorithms for precision and it far exceeds most in speed. We build our algorithm on the existing colour-only KCF tracker which uses the `kernel trick' to extend correlation filters for fast tracking. We fuse colour and depth cues as the tracker's features, and furthermore, exploit the depth data to both adjust a given target's scale, and detect and manage occlusions in such a way as to maintain real-time performance, exceeding on average 40~fps. We benchmark our approach using 2 publicly available datasets and make our easy-to-extend modularised code available to other researchers.

KW - RGB-D tracking

KW - Kernelised Correlation Filters

KW - Depth and Color Fusion

KW - Digital Health

U2 - 10.5244/C.29.145

DO - 10.5244/C.29.145

M3 - Conference Paper

SP - 145.1-145.11

ER -