Adaptive scene dependent filters for segmentation and online learning of visual objects

NEUROCOMPUTING

卷:70

Article; Proceedings Paper

Steil, J. J. ; Goetting, M. ; Wersing, H. ; Koerner, E. ; Ritter, H.

关键词: visual online learning;    unsupervised image segmentation;    vector quantization;    cognitive vision;    object recognition;    human-machine interaction;   

DOI  :  10.1016/j.neucom.2006.11.020

来源: Elsevier

【 摘 要 】

We propose the adaptive scene dependent filter (ASDF) hierarchy for unsupervised learning of image segmentation, which integrates several processing pathways into a flexible, highly dynamic, and real-time capable vision architecture. It is based on forming a combined feature space from basic feature maps like, color, disparity, and pixel position. To guarantee real-time performance, we apply an enhanced vector quantization method to partition this feature space. The learned codebook defines corresponding best-match segments for each prototype and yields an over-segmentation of the object and the surround. The segments are recombined into a final object segmentation mask based on a relevance map, which encodes a coarse bottom-up hypothesis where the object is located in the image. We apply the ASDF hierarchy for preprocessing input images in a feature-based biologically motivated object recognition learning architecture and show experiments with this real-time vision system running at 6 Hz including the online learning of the segmentation. Because interaction with user is not perfect, the real-world system acquires useful views effectively only at about 1.5 Hz, but we show that for training a new object one hundred views taking only one minute of interaction time is sufficient. (c) 2007 Elsevier B.V. All rights reserved.

【 授权许可】

Free