[Show abstract][Hide abstract] ABSTRACT: This paper proposes a novel method for integrating multiple local cues, i.e. lo- cal region detectors as well as descriptors, in the context o f object detection. Rather than to fuse the outputs of several distinct classifie rs in a fixed setup, our approach implements a highly flexible combination schem e, where the con- tributions of all individual cues are flexibly recombined de pending on their ex- planatory power for each new test image. The key idea behind our approach is to integrate the cues over an estimated top-down segmentation, which allows to quantify how much each of them contributed to the object hypothesis. By combining those contributions on a per-pixel level, our approach ensures that each cue only contributes to object regions for which it is confident and that potential correlations between cues are effectively facto red out. Experimental results on several benchmark data sets show that the proposed multi-cue combi- nation scheme significantly increases detection performan ce compared to any of its constituent cues alone. Moreover, it provides an intere sting evaluation tool to analyze the complementarity of local feature detectors and descriptors.
Proceedings of the British Machine Vision Conference 2006, Edinburgh, UK, September 4-7, 2006; 01/2006
[Show abstract][Hide abstract] ABSTRACT: Object recognition systems aiming to work in real world settings should use multiple cues in order to achieve robustness. We present a new cue integration scheme, which extends the idea of cue accumulation to discriminative classifiers. We derive and test the scheme for support vector machines (SVMs), but we also show that it is easily extendible to any large margin classifier. In the case of one-class SVMs the scheme can be interpreted as a new class of Mercer kernels for multiple cues. Experimental comparison with a probabilistic accumulation scheme is favorable to our method. Comparison with voting scheme shows that our method may suffer as the number of object classes increases. Based on these results, we propose a recognition algorithm consisting of a decision tree where decisions at each node are taken using our accumulation scheme. Results obtained using this new algorithm compare very favorably to accumulation (both probabilistic and discriminative) and voting scheme.
Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on; 01/2004
[Show abstract][Hide abstract] ABSTRACT: This paper describes techniques for fusing the output of multiple cues to robustly and accurately segment foreground objects from the background in image sequences. Two different methods for cue integration are presented and tested. The first is a probabilistic approach which at each pixel computes the likelihood of observations over all cues before assigning pixels to foreground or back-ground layers using Bayes Rule. The second method allows each cue to make a decision independent of the other cues before fusing their outputs with a weighted sum. A further important contribution of our work concerns demonstrating how models for some cues can be learnt and subsequently adapted online. In particular, regions of coherent motion are used to train distributions for colour and for a simple texture descriptor. An additional aspect of our framework is in providing mechanisms for suppressing cues when they are believed to be unreliable, for instance during training or when they disagree with the general consensus. Results on extended video sequences are presented.
Data provided are for informational purposes only. Although carefully collected, accuracy cannot be guaranteed. The impact factor represents a rough estimation of the journal's impact factor and does not reflect the actual current impact factor. Publisher conditions are provided by RoMEO. Differing provisions from the publisher's actual policy or licence agreement may be applicable.