Arbitrary-shape object localization using adaptive image grids

Sliding-window based search is a widely used technique for object localization. However, for objects of non-rectangle shapes, noises in windows may mislead the localization, causing unsatisfactory results. In this paper, we propose an efficient bottom-up approach for detecting arbitrary-shape object...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuan, Junsong, Zhou, Chunluan
Other Authors: School of Electrical and Electronic Engineering
Format: Conference or Workshop Item
Language:English
Published: 2013
Subjects:
Online Access:https://hdl.handle.net/10356/100685
http://hdl.handle.net/10220/17895
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-100685
record_format dspace
spelling sg-ntu-dr.10356-1006852020-03-07T13:24:50Z Arbitrary-shape object localization using adaptive image grids Yuan, Junsong Zhou, Chunluan School of Electrical and Electronic Engineering Asian Conference on Computer Vision (11th : 2012 : Daejeon, Korea) DRNTU::Engineering::Electrical and electronic engineering Sliding-window based search is a widely used technique for object localization. However, for objects of non-rectangle shapes, noises in windows may mislead the localization, causing unsatisfactory results. In this paper, we propose an efficient bottom-up approach for detecting arbitrary-shape objects using image grids as basic components. First, a test image is partitioned into n×n grids and the object is localized by finding a set of connected grids which maximize the classifier's response. Then, graph cut segmentation is used to improve the object boundary by utilizing local image context. Instead of using bounding boxes, the proposed approach searches connected regions of any shapes. With the graph cut refinement, our approach can start with coarse image grids and is robust to noises. To make image grids better cover the object of arbitrary shape, we also propose a fast adaptive grid partition method which takes image content into account and can be efficiently implemented by dynamic programming. The use of adaptive partition further improves the localization accuracy of our approach. Experiments on PASCAL VOC 2007 and VOC 2008 datasets demonstrate the effectiveness of our approach. Accepted version 2013-11-29T03:12:32Z 2019-12-06T20:26:36Z 2013-11-29T03:12:32Z 2019-12-06T20:26:36Z 2013 2013 Conference Paper Zhou, C., & Yuan, J. (2013). Arbitrary-shape object localization using adaptive image grids. Proceedings of the 11th Asian conference on Computer Vision (ACCV12), pp.71-84. https://hdl.handle.net/10356/100685 http://hdl.handle.net/10220/17895 10.1007/978-3-642-37331-2_6 en © 2013 Springer-Verlag Berlin Heidelberg. This is the author created version of a work that has been peer reviewed and accepted for publication by Proceedings of the 11th Asian conference on Computer Vision (ACCV12), Springer-Verlag Berlin Heidelberg. It incorporates referee’s comments but changes resulting from the publishing process, such as copyediting, structural formatting, may not be reflected in this document. The published version is available at: [http://dx.doi.org/10.1007/978-3-642-37331-2_6]. 14 p. application/pdf
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic DRNTU::Engineering::Electrical and electronic engineering
spellingShingle DRNTU::Engineering::Electrical and electronic engineering
Yuan, Junsong
Zhou, Chunluan
Arbitrary-shape object localization using adaptive image grids
description Sliding-window based search is a widely used technique for object localization. However, for objects of non-rectangle shapes, noises in windows may mislead the localization, causing unsatisfactory results. In this paper, we propose an efficient bottom-up approach for detecting arbitrary-shape objects using image grids as basic components. First, a test image is partitioned into n×n grids and the object is localized by finding a set of connected grids which maximize the classifier's response. Then, graph cut segmentation is used to improve the object boundary by utilizing local image context. Instead of using bounding boxes, the proposed approach searches connected regions of any shapes. With the graph cut refinement, our approach can start with coarse image grids and is robust to noises. To make image grids better cover the object of arbitrary shape, we also propose a fast adaptive grid partition method which takes image content into account and can be efficiently implemented by dynamic programming. The use of adaptive partition further improves the localization accuracy of our approach. Experiments on PASCAL VOC 2007 and VOC 2008 datasets demonstrate the effectiveness of our approach.
author2 School of Electrical and Electronic Engineering
author_facet School of Electrical and Electronic Engineering
Yuan, Junsong
Zhou, Chunluan
format Conference or Workshop Item
author Yuan, Junsong
Zhou, Chunluan
author_sort Yuan, Junsong
title Arbitrary-shape object localization using adaptive image grids
title_short Arbitrary-shape object localization using adaptive image grids
title_full Arbitrary-shape object localization using adaptive image grids
title_fullStr Arbitrary-shape object localization using adaptive image grids
title_full_unstemmed Arbitrary-shape object localization using adaptive image grids
title_sort arbitrary-shape object localization using adaptive image grids
publishDate 2013
url https://hdl.handle.net/10356/100685
http://hdl.handle.net/10220/17895
_version_ 1681049161146826752