Dense scale selection over space, time and space-time

Abstract

Scale selection methods based on local extrema over scale of scale-normalized derivatives have been primarily developed to be applied sparsely --- at image points where the magnitude of a scale-normalized differential expression additionally assumes local extrema over the domain where the data are defined. This paper presents a methodology for performing dense scale selection, so that hypotheses about local characteristic scales in images, temporal signals and video can be computed at every image point and every time moment. A critical problem when designing mechanisms for dense scale selection is that the scale at which scale-normalized differential entities assume local extrema over scale can be strongly dependent on the local order of the locally dominant differential structure. To address this problem, we propose a methodology where local extrema over scale are detected of a quasi quadrature measure involving scale-space derivatives up to order two and propose two independent mechanisms to reduce the phase dependency of the local scale estimates by: (i) introducing a second layer of post-smoothing prior to the detection of local extrema over scale and (ii) performing local phase compensation based on a model of the phase dependency of the local scale estimates depending on the relative strengths between first- vs. second-order differential structure. This general methodology is applied over three types of domains: (i) spatial images, (ii) temporal signals and (iii) spatio-temporal video. Experiments show that the proposed methodology leads to intuitively reasonable results with local scale estimates that reflect variations in the characteristic scales of locally dominant structures over space and time.

43 pages, 14 figures, 3 tables

References in corpus (3)

• Dense Correspondences Across Scenes and Scales
• Time-causal and time-recursive spatio-temporal receptive fields
• Temporal scale selection in time-causal scale space

Cited by in corpus (9)

• Scale-covariant and scale-invariant Gaussian derivative networks
• A Principled Design of Image Representation: Towards Forensic Tasks
• Provably scale-covariant continuous hierarchical networks based on scale-normalized differential expressions coupled in cascade
• Dynamic texture recognition using time-causal and time-recursive spatio-temporal receptive fields
• A time-causal and time-recursive scale-covariant scale-space representation of temporal signals and past time
• Feature-Centered First Order Structure Tensor Scale-Space in 2D and 3D
• Provably scale-covariant networks from oriented quasi quadrature measures in cascade
• Orientation selectivity properties for the affine Gaussian derivative and the affine Gabor models for visual receptive fields
• Go with the Flow: Perception-refined Physics Simulation