Evaluation of object detection proposals under condition variations

Fahimeh Rezazadegan; Sareh Shirazi; Michael Milford; Ben Upcroft

Evaluation of object detection proposals under condition variations

Fahimeh Rezazadegan, Sareh Shirazi, Michael Milford, Ben Upcroft

Research output: Contribution to conference › Paper › peer-review

Abstract

Object detection is a fundamental task in many computer vision applications, therefore the importance of evaluating the quality of object detection is well
acknowledged in this domain. This process gives insight into the capabilities of methods in handling environmental changes. In this paper, a new method for object detection is introduced that combines the Selective Search and EdgeBoxes. We tested these three methods under environmental variations. Our experiments demonstrate the outperformance of the combination method under illumination and view point variations.

Original language	English
Pages	1-2
Number of pages	2
Publication status	Submitted - 10 Dec 2015
Externally published	Yes
Event	2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015) Workshops - Boston, United States Duration: 7 Jun 2015 → 12 Jun 2015

Conference

Conference	2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015) Workshops
Country/Territory	United States
City	Boston
Period	7/06/15 → 12/06/15

Cite this

@conference{95227a7faa564de0b55b531db60d666c,

title = "Evaluation of object detection proposals under condition variations",

abstract = "Object detection is a fundamental task in many computer vision applications, therefore the importance of evaluating the quality of object detection is wellacknowledged in this domain. This process gives insight into the capabilities of methods in handling environmental changes. In this paper, a new method for object detection is introduced that combines the Selective Search and EdgeBoxes. We tested these three methods under environmental variations. Our experiments demonstrate the outperformance of the combination method under illumination and view point variations.",

author = "Fahimeh Rezazadegan and Sareh Shirazi and Michael Milford and Ben Upcroft",

year = "2015",

month = dec,

day = "10",

language = "English",

pages = "1--2",

note = "2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015) Workshops ; Conference date: 07-06-2015 Through 12-06-2015",

}

TY - CONF

T1 - Evaluation of object detection proposals under condition variations

AU - Rezazadegan, Fahimeh

AU - Shirazi, Sareh

AU - Milford, Michael

AU - Upcroft, Ben

PY - 2015/12/10

Y1 - 2015/12/10

N2 - Object detection is a fundamental task in many computer vision applications, therefore the importance of evaluating the quality of object detection is wellacknowledged in this domain. This process gives insight into the capabilities of methods in handling environmental changes. In this paper, a new method for object detection is introduced that combines the Selective Search and EdgeBoxes. We tested these three methods under environmental variations. Our experiments demonstrate the outperformance of the combination method under illumination and view point variations.

AB - Object detection is a fundamental task in many computer vision applications, therefore the importance of evaluating the quality of object detection is wellacknowledged in this domain. This process gives insight into the capabilities of methods in handling environmental changes. In this paper, a new method for object detection is introduced that combines the Selective Search and EdgeBoxes. We tested these three methods under environmental variations. Our experiments demonstrate the outperformance of the combination method under illumination and view point variations.

UR - http://arXiv.org/abs/1512.03424

M3 - Paper

SP - 1

EP - 2

T2 - 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015) Workshops

Y2 - 7 June 2015 through 12 June 2015

ER -

Evaluation of object detection proposals under condition variations

Abstract

Conference

Other files and links

Fingerprint

Cite this