<XML><RECORDS><RECORD><REFERENCE_TYPE>0</REFERENCE_TYPE><REFNUM>9303</REFNUM><AUTHORS><AUTHOR>Aragon-Camarasa,G.</AUTHOR><AUTHOR>Siebert,J.P.</AUTHOR></AUTHORS><YEAR>2010</YEAR><TITLE>Unsupervised clustering in Hough space for recognition of multiple instances of the same object in a cluttered scene</TITLE><PLACE_PUBLISHED>Pattern Recognition Letters, in press</PLACE_PUBLISHED><PUBLISHER>Elsevier Science</PUBLISHER><LABEL>Aragon-Camarasa:2010:9303</LABEL><KEYWORDS><KEYWORD>Generalised Hough transform; Unsupervised clustering; Active vision; Robot head; Multiple localisation</KEYWORD></KEYWORDS<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.</ABSTRACT><NOTES>Manuscript accpted for publication and now in press.</NOTES></RECORD></RECORDS></XML>