A dynamic approach and a new dataset for hand-detection in first person vision

A. Betancourt Arango, P. Morerio, E.I. Barakova, L. Marcenaro, G.W.M. Rauterberg, C.S. Regazzoni

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademic

12 Citations (Scopus)
1 Downloads (Pure)

Abstract

Hand detection and segmentation methods stand as two of the most most prominent objectives in First Person Vision. Their popularity is mainly explained by the importance of a reliable detection and location of the hands to develop human-machine interfaces for emergent wearable cameras. Current developments have been focused on hand segmentation problems, implicitly assuming that hands are always in the field of view of the user. Existing methods are commonly presented with new datasets. However, given their implicit assumption, none of them ensure a proper composition of frames with and without hands, as the hand-detection problem requires. This paper presents a new dataset for hand-detection, carefully designed to guarantee a good balance between positive and negative frames, as well as challenging conditions such as illumination changes, hand occlusions and realistic locations. Additionally, this paper extends a state-of-the-art method using a dynamic filter to improve its detection rate. The improved performance is proposed as a baseline to be used with the dataset.
Original languageEnglish
Title of host publicationComputer Analysis of Images and Patterns : 16th International Conference, CAIP 2015, Valletta, Malta, September 2-4, 2015 Proceedings, Part I
EditorsG. Azzopardi, N. Petkov
Place of PublicationBerlin
PublisherSpringer
Pages274-287
ISBN (Print)978-3-319-23191-4
DOIs
Publication statusPublished - 2015

Publication series

NameLecture Notes in Computer Science
Volume9256
ISSN (Print)0302-9743

Fingerprint

Lighting
Cameras
Chemical analysis

Cite this

Betancourt Arango, A., Morerio, P., Barakova, E. I., Marcenaro, L., Rauterberg, G. W. M., & Regazzoni, C. S. (2015). A dynamic approach and a new dataset for hand-detection in first person vision. In G. Azzopardi, & N. Petkov (Eds.), Computer Analysis of Images and Patterns : 16th International Conference, CAIP 2015, Valletta, Malta, September 2-4, 2015 Proceedings, Part I (pp. 274-287). (Lecture Notes in Computer Science; Vol. 9256). Berlin: Springer. https://doi.org/10.1007/978-3-319-23192-1_23
Betancourt Arango, A. ; Morerio, P. ; Barakova, E.I. ; Marcenaro, L. ; Rauterberg, G.W.M. ; Regazzoni, C.S. / A dynamic approach and a new dataset for hand-detection in first person vision. Computer Analysis of Images and Patterns : 16th International Conference, CAIP 2015, Valletta, Malta, September 2-4, 2015 Proceedings, Part I. editor / G. Azzopardi ; N. Petkov. Berlin : Springer, 2015. pp. 274-287 (Lecture Notes in Computer Science).
@inproceedings{3342b57b58674d6b9ea551169aed6ad4,
title = "A dynamic approach and a new dataset for hand-detection in first person vision",
abstract = "Hand detection and segmentation methods stand as two of the most most prominent objectives in First Person Vision. Their popularity is mainly explained by the importance of a reliable detection and location of the hands to develop human-machine interfaces for emergent wearable cameras. Current developments have been focused on hand segmentation problems, implicitly assuming that hands are always in the field of view of the user. Existing methods are commonly presented with new datasets. However, given their implicit assumption, none of them ensure a proper composition of frames with and without hands, as the hand-detection problem requires. This paper presents a new dataset for hand-detection, carefully designed to guarantee a good balance between positive and negative frames, as well as challenging conditions such as illumination changes, hand occlusions and realistic locations. Additionally, this paper extends a state-of-the-art method using a dynamic filter to improve its detection rate. The improved performance is proposed as a baseline to be used with the dataset.",
author = "{Betancourt Arango}, A. and P. Morerio and E.I. Barakova and L. Marcenaro and G.W.M. Rauterberg and C.S. Regazzoni",
year = "2015",
doi = "10.1007/978-3-319-23192-1_23",
language = "English",
isbn = "978-3-319-23191-4",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "274--287",
editor = "G. Azzopardi and N. Petkov",
booktitle = "Computer Analysis of Images and Patterns : 16th International Conference, CAIP 2015, Valletta, Malta, September 2-4, 2015 Proceedings, Part I",
address = "Germany",

}

Betancourt Arango, A, Morerio, P, Barakova, EI, Marcenaro, L, Rauterberg, GWM & Regazzoni, CS 2015, A dynamic approach and a new dataset for hand-detection in first person vision. in G Azzopardi & N Petkov (eds), Computer Analysis of Images and Patterns : 16th International Conference, CAIP 2015, Valletta, Malta, September 2-4, 2015 Proceedings, Part I. Lecture Notes in Computer Science, vol. 9256, Springer, Berlin, pp. 274-287. https://doi.org/10.1007/978-3-319-23192-1_23

A dynamic approach and a new dataset for hand-detection in first person vision. / Betancourt Arango, A.; Morerio, P.; Barakova, E.I.; Marcenaro, L.; Rauterberg, G.W.M.; Regazzoni, C.S.

Computer Analysis of Images and Patterns : 16th International Conference, CAIP 2015, Valletta, Malta, September 2-4, 2015 Proceedings, Part I. ed. / G. Azzopardi; N. Petkov. Berlin : Springer, 2015. p. 274-287 (Lecture Notes in Computer Science; Vol. 9256).

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademic

TY - GEN

T1 - A dynamic approach and a new dataset for hand-detection in first person vision

AU - Betancourt Arango, A.

AU - Morerio, P.

AU - Barakova, E.I.

AU - Marcenaro, L.

AU - Rauterberg, G.W.M.

AU - Regazzoni, C.S.

PY - 2015

Y1 - 2015

N2 - Hand detection and segmentation methods stand as two of the most most prominent objectives in First Person Vision. Their popularity is mainly explained by the importance of a reliable detection and location of the hands to develop human-machine interfaces for emergent wearable cameras. Current developments have been focused on hand segmentation problems, implicitly assuming that hands are always in the field of view of the user. Existing methods are commonly presented with new datasets. However, given their implicit assumption, none of them ensure a proper composition of frames with and without hands, as the hand-detection problem requires. This paper presents a new dataset for hand-detection, carefully designed to guarantee a good balance between positive and negative frames, as well as challenging conditions such as illumination changes, hand occlusions and realistic locations. Additionally, this paper extends a state-of-the-art method using a dynamic filter to improve its detection rate. The improved performance is proposed as a baseline to be used with the dataset.

AB - Hand detection and segmentation methods stand as two of the most most prominent objectives in First Person Vision. Their popularity is mainly explained by the importance of a reliable detection and location of the hands to develop human-machine interfaces for emergent wearable cameras. Current developments have been focused on hand segmentation problems, implicitly assuming that hands are always in the field of view of the user. Existing methods are commonly presented with new datasets. However, given their implicit assumption, none of them ensure a proper composition of frames with and without hands, as the hand-detection problem requires. This paper presents a new dataset for hand-detection, carefully designed to guarantee a good balance between positive and negative frames, as well as challenging conditions such as illumination changes, hand occlusions and realistic locations. Additionally, this paper extends a state-of-the-art method using a dynamic filter to improve its detection rate. The improved performance is proposed as a baseline to be used with the dataset.

U2 - 10.1007/978-3-319-23192-1_23

DO - 10.1007/978-3-319-23192-1_23

M3 - Conference contribution

SN - 978-3-319-23191-4

T3 - Lecture Notes in Computer Science

SP - 274

EP - 287

BT - Computer Analysis of Images and Patterns : 16th International Conference, CAIP 2015, Valletta, Malta, September 2-4, 2015 Proceedings, Part I

A2 - Azzopardi, G.

A2 - Petkov, N.

PB - Springer

CY - Berlin

ER -

Betancourt Arango A, Morerio P, Barakova EI, Marcenaro L, Rauterberg GWM, Regazzoni CS. A dynamic approach and a new dataset for hand-detection in first person vision. In Azzopardi G, Petkov N, editors, Computer Analysis of Images and Patterns : 16th International Conference, CAIP 2015, Valletta, Malta, September 2-4, 2015 Proceedings, Part I. Berlin: Springer. 2015. p. 274-287. (Lecture Notes in Computer Science). https://doi.org/10.1007/978-3-319-23192-1_23