Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/86004
Title: Adobe Boxes: Locating Object Proposals using Object Adobes
Authors: Xiao, Yang
Fang, Zhiwen
Cao, Zhiguo
Zhu, Lei
Yuan, Junsong
Keywords: Object Proposal
Adobe Boxes
Issue Date: 2016
Source: Fang, Z., Cao, Z., Xiao, Y., Zhu, L., & Yuan, J. Adobe Boxes: Locating Object Proposals using Object Adobes. IEEE Transactions on Image Processing, 25(9), 4116-4128.
Series/Report no.: IEEE Transactions on Image Processing
Abstract: Despite the previous efforts of object proposals, the detection rates of the existing approaches are still not satisfactory enough. To address this, we propose Adobe Boxes to efficiently locate the potential objects with fewer proposals, in terms of searching the object adobes that are the salient object parts easy to be perceived. Because of the visual difference between the object and its surroundings, an object adobe obtained from the local region has a high probability to be a part of an object, which is capable of depicting the locative information of the proto-object. Our approach comprises of three main procedures. First, the coarse object proposals are acquired by employing randomly sampled windows. Then, based on local-contrast analysis, the object adobes are identified within the enlarged bounding boxes that correspond to the coarse proposals. The final object proposals are obtained by converging the bounding boxes to tightly surround the object adobes. Meanwhile, our object adobes can also refine the detection rate of most state-of-the-art methods as a refinement approach. The extensive experiments on four challenging datasets (PASCAL VOC2007, VOC2010, VOC2012, and ILSVRC2014) demonstrate that the detection rate of our approach generally outperforms the state-of-the-art methods, especially with relatively small number of proposals. The average time consumed on one image is about 48 ms, which nearly meets the real-time requirement.
URI: https://hdl.handle.net/10356/86004
http://hdl.handle.net/10220/43908
ISSN: 1057-7149
DOI: 10.1109/TIP.2016.2579311
Rights: © 2016 IEEE.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:EEE Journal Articles

SCOPUSTM   
Citations 20

18
checked on Aug 31, 2020

WEB OF SCIENCETM
Citations 20

17
checked on Oct 18, 2020

Page view(s) 20

201
checked on Oct 25, 2020

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.