Soft Hough Forest-ERTs: Generalized Hough Transform based object detection from soft-labelled training data

Liu, Y; Wang, Y; Sowmya, A; Chen, F

Soft Hough Forest-ERTs: Generalized Hough Transform based object detection from soft-labelled training data

Liu, Y Wang, Y

Sowmya, A Chen, F

Permalink

Publisher:: ELSEVIER SCI LTD
Publication Type:: Journal Article
Citation:: Pattern Recognition, 2016, 60, pp. 145-156
Issue Date:: 2016-12-01

Closed Access

	Filename	Description	Size
	1-s2.0-S0031320316300905-main.pdf	Published version	1.69 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Liu, Y
dc.contributor.author	Wang, Y https://orcid.org/0000-0002-6815-0879
dc.contributor.author	Sowmya, A
dc.contributor.author	Chen, F https://orcid.org/0000-0003-4971-8729
dc.date.accessioned	2022-07-07T22:05:42Z
dc.date.available	2022-07-07T22:05:42Z
dc.date.issued	2016-12-01
dc.identifier.citation	Pattern Recognition, 2016, 60, pp. 145-156
dc.identifier.issn	0031-3203
dc.identifier.issn	1873-5142
dc.identifier.uri	http://hdl.handle.net/10453/158722
dc.description.abstract	Classical supervised object detection methods learn object models from labelled training data. This is tedious to create especially when the training dataset is large. Detection methods such as background subtraction and headlight detection can detect potential positive blobs that may contain the object without labelled training data. However, such blobs are not always accurate. They may include noise such as part of an object, multiple objects and other types of objects. Therefore, soft labels that indicate their probability of being positive may be more useful. A modified soft label estimation method based on Maximum Mean Discrepancy is introduced in this work. Based on it, a Generalized Hough Transform based object detection method from soft-labelled training data is proposed to utilize potential detections and their estimated soft labels. Experimental results show that the method can achieve comparable performance to supervised methods. It outperforms both Generalized Hough Transform based object detection with hard-labelled training blobs, and a state-of-the-art weakly supervised method.
dc.language	English
dc.publisher	ELSEVIER SCI LTD
dc.relation.ispartof	Pattern Recognition
dc.relation.isbasedon	10.1016/j.patcog.2016.04.023
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0801 Artificial Intelligence and Image Processing, 0806 Information Systems, 0906 Electrical and Electronic Engineering
dc.subject.classification	Artificial Intelligence & Image Processing
dc.title	Soft Hough Forest-ERTs: Generalized Hough Transform based object detection from soft-labelled training data
dc.type	Journal Article
utslib.citation.volume	60
utslib.for	0801 Artificial Intelligence and Image Processing
utslib.for	0806 Information Systems
utslib.for	0906 Electrical and Electronic Engineering
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/A/DRsch The Data Science Institute
utslib.copyright.status	closed_access	*
dc.date.updated	2022-07-07T22:05:40Z
pubs.publication-status	Published
pubs.volume	60

Abstract:

Classical supervised object detection methods learn object models from labelled training data. This is tedious to create especially when the training dataset is large. Detection methods such as background subtraction and headlight detection can detect potential positive blobs that may contain the object without labelled training data. However, such blobs are not always accurate. They may include noise such as part of an object, multiple objects and other types of objects. Therefore, soft labels that indicate their probability of being positive may be more useful. A modified soft label estimation method based on Maximum Mean Discrepancy is introduced in this work. Based on it, a Generalized Hough Transform based object detection method from soft-labelled training data is proposed to utilize potential detections and their estimated soft labels. Experimental results show that the method can achieve comparable performance to supervised methods. It outperforms both Generalized Hough Transform based object detection with hard-labelled training blobs, and a state-of-the-art weakly supervised method.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/158722