Unsupervised clustering in Hough space for recognition of multiple instances of the same object in a cluttered scene

Aragon Camarasa, G. and Siebert, J.P. (2010) Unsupervised clustering in Hough space for recognition of multiple instances of the same object in a cluttered scene. Pattern Recognition Letters, 31(11), pp. 1274-1284. (doi: 10.1016/j.patrec.2010.03.003)

Abstract

We describe an active binocular vision system that is capable of localising multiple instances of objects of the same-class in different settings within a covert, pre-attentive, visual search strategy. By clustering SIFT-feature matches that have been projected into a non-quantised (i.e. continuous) Hough space we are able to detect up to 6 same-class object instances simultaneously while tolerating up to ∼ 66% of each object’s surface being occluded by another object instance of the same-class. Our findings are based on using a database of ∼ 2300 images of synthetically composited and real-world images.

• Item Type: Articles
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Siebert, Dr Paul and Aragon Camarasa, Dr Gerardo
• Authors: Aragon Camarasa, G., and Siebert, J.P.
• Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
• College/School: College of Science and Engineering > School of Computing Science
• Journal Name: Pattern Recognition Letters
• Publisher: Elsevier BV
• ISSN: 0167-8655
• ISSN (Online): 1872-7344
• Published Online: 06 March 2010