Building Roadmaps of Minima and Transitions in Visual Models

Cristian Sminchisescu (1) , Bill Triggs (2)

1 DCS - Department of Computer Science [University of Toronto]
2 LEAR - Learning and recognition in vision

Feature detection is used in many computer vision applications such as image segmentation, object recognition, and image retrieval. For these applications, robustness with respect to shadows, shading, and specularities is desired. Features based on derivatives of photometric invariants, which we is called full invariants, provide the desired robustness. However, because computation of photometric invariants involves nonlinear transformations, these features are unstable and, therefore, impractical for many applications. We propose a new class of derivatives which we refer to as quasi-invariants. These quasi-invariants are derivatives which share with full photometric invariants the property that they are insensitive for certain photometric edges, such as shadows or specular edges, but without the inherent instabilities of full photometric invariants. Experiments show that the quasi-invariant derivatives are less sensitive to noise and introduce less edge displacement than full invariant derivatives. Moreover, quasi-invariants significantly outperform the full invariant derivatives in terms of discriminative power.

Mots clés: model based vision; global optimization; saddle points; 3D human tracking

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Cristian Sminchisescu, Bill Triggs. Building Roadmaps of Minima and Transitions in Visual Models. International Journal of Computer Vision, 2005, 61 (1), pp.81--101. ⟨10.1023/B:VISI.0000042935.43630.46⟩. ⟨inria-00548527⟩