Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/105524
Citations
Scopus Web of Science® Altmetric
?
?
Type: Conference paper
Title: Efficient point process inference for large-scale object detection
Author: Pham, T.
Rezatofighi, S.
Reid, I.
Chin, T.
Citation: Proceedings of the 29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), 2016 / vol.2016-January, pp.2837-2845
Publisher: IEEE
Issue Date: 2016
Series/Report no.: IEEE Conference on Computer Vision and Pattern Recognition
ISBN: 9781467388511
ISSN: 1063-6919
Conference Name: 29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016) (26 Jun 2016 - 01 Jul 2016 : Las Vegas, NV)
Statement of
Responsibility: 
Trung T. Pham, Seyed Hamid Rezatofighi, Ian Reid and Tat-Jun Chin
Abstract: We tackle the problem of large-scale object detection in images, where the number of objects can be arbitrarily large, and can exhibit significant overlap/occlusion. A successful approach to modelling the large-scale nature of this problem has been via point process density functions which jointly encode object qualities and spatial interactions. But the corresponding optimisation problem is typically difficult or intractable, and many of the best current methods rely on Monte Carlo Markov Chain (MCMC) simulation, which converges slowly in a large solution space. We propose an efficient point process inference for largescale object detection using discrete energy minimization. In particular, we approximate the solution space by a finite set of object proposals and cast the point process density function to a corresponding energy function of binary variables whose values indicate which object proposals are accepted. We resort to the local submodular approximation (LSA) based trust-region optimisation to find the optimal solution. Furthermore we analyse the error of LSA approximation, and show how to adjust the point process energy to dramatically speed up the convergence without harming the optimality. We demonstrate the superior efficiency and accuracy of our method using a variety of large-scale object detection applications such as crowd human detection, birds, cells counting/localization.
Rights: © 2016 IEEE
RMID: 0030056387
DOI: 10.1109/CVPR.2016.310
Grant ID: http://purl.org/au-research/grants/arc/CE140100016
http://purl.org/au-research/grants/arc/FL130100102
http://purl.org/au-research/grants/arc/DP160103490
Appears in Collections:Computer Science publications

Files in This Item:
File Description SizeFormat 
RA_hdl_105524.pdfRestricted Access1.54 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.