Motion Segmentation of Articulated Structures by Integration of Visual Perception Criteria

  title={Motion Segmentation of Articulated Structures by Integration of Visual Perception Criteria},
  author={Hilde Kuehne and Annika W{\"o}rner},
The correct segmentation of articulated motion is an import ant factor to extract and understand the functional structures of complex, articulated objects. Segmenting su ch body motion without additional appearance information is still a challenging task, because articulated obj ects as e.g. the human body are mainly based on fine, connected structures. The proposed approach combines cons ensus based motion segmentation with biological inspired visual perception criteria. This allows the group… 

Figures from this paper


Articulated Motion Segmentation Using RANSAC with Priors
A novel algorithm for articulated motion segmentation called RANSAC with priors is proposed, which is both robust and efficient and applies to independent motions which can be regarded as a special case and treated uniformly.
Visual perception of biological motion and a model for its analysis
The kinetic-geometric model for visual vector analysis originally developed in the study of perception of motion combinations of the mechanical type was applied to biological motion patterns and the results turned out to be highly positive.
Real-Time Motion Segmentation of Sparse Feature Points at Any Speed
A real-time incremental approach to motion segmentation operating on sparse feature points that allows for a variable number of image frames to affect the segmentation process, thus enabling an arbitrary number of objects traveling at different relative speeds to be detected.
A Benchmark for the Comparison of 3-D Motion Segmentation Algorithms
  • Roberto Tron, R. Vidal
  • Computer Science
    2007 IEEE Conference on Computer Vision and Pattern Recognition
  • 2007
This paper compares four 3D motion segmentation algorithms for affine cameras on a benchmark of 155 motion sequences of checkerboard, traffic, and articulated scenes.
Good features to track
  • Jianbo Shi, Carlo Tomasi
  • Computer Science
    1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition
  • 1994
A feature selection criterion that is optimal by construction because it is based on how the tracker works, and a feature monitoring method that can detect occlusions, disocclusions, and features that do not correspond to points in the world are proposed.
Motion segmentation by consensus
A method for merging multiple partitions into a single partition, by minimising the ratio of pairwise agreements and contradictions between the equivalence relations corresponding to the partitions, which is advantageous when merging segmentations obtained independently.
Computational Studies in the Interpretation of Structure and Motion: Summary and Extension
Abstract : Computational studies of the interpretation of structure from notion examine the conditions under which three-dimensional structure can be recovered from motion in the image. The first
Pyramidal implementation of the lucas kanade feature tracker
It is essential to define the notion of similarity in a 2D neighborhood sense and the image velocity d is defined as being the vector that minimizes the residual function defined as follows.
Cognitive neuroscience: Neural mechanisms for the recognition of biological movements
A learning-based, feedforward model provides a neurophysiologically plausible and consistent summary of many key experimental results, and is used as a tool for organizing and making sense of the experimental data, despite their growing size and complexity.
Ransac toolbox for matlab
  • change/18555.
  • 2008