Dealing with occlusions in the eigenspace approach

@article{Leonardis1996DealingWO,
  title={Dealing with occlusions in the eigenspace approach},
  author={Ale{\vs} Leonardis and Horst Bischof},
  journal={Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition},
  year={1996},
  pages={453-458}
}
  • A. Leonardis, H. Bischof
  • Published 18 June 1996
  • Computer Science
  • Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition
The basic limitations of the current appearance-based matching methods using eigenimages are non-robust estimation of coefficients and inability to cope with problems related to occlusions and segmentation. In this paper we present a new approach which successfully solves these problems. The major novelty of our approach lies in the way how the coefficients of the eigenimages are determined. Instead of computing the coefficients by a projection of the data onto the eigenimages, we extract them… 

Figures from this paper

Robust Recognition Using Eigenimages
TLDR
This paper presents a new approach which successfully solves problems related to outliers, occlusions, and varying background in appearance-based matching methods using eigenimages using a robust hypothesize-and-test paradigm.
Computational Complexity Reduction in Eigenspace Approaches
TLDR
This paper proposes to use a focus-of-attention (FOA) detector which is intended to select candidate areas of interest with minimal computational effort and employs a multiresolution approach to alleviate the problems related to complexity.
Robust localization using eigenspace of spinning-images
  • M. Jogan, A. Leonardis
  • Computer Science
    Proceedings IEEE Workshop on Omnidirectional Vision (Cat. No.PR00704)
  • 2000
TLDR
This paper proposes a representation-eigenspace of spinning-images-which enables a straightforward application of the robust estimation of eigenimage coefficients which is directly related to the localization.
Robust recognition of scaled eigenimages through a hierarchical approach
  • H. Bischof, A. Leonardis
  • Computer Science
    Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231)
  • 1998
TLDR
It is shown that the method for estimating the coefficients of eigenimages can be applied to convolved and subsampled images yielding the same value of the coefficients, which enables an efficient multiresolution approach, where the values of the coefficient can directly be propagated through the scales.
Translation , Scale and Occlusion-Tolerant Recognition with Multiple Eigenspace Models
TLDR
A method for estimating the position and scale of occluder objects present in images of any of a number of modeled scenes and locating, segment, de-occlude and recognize each object individually is presented.
2 The Proposed Method : Image Segmentation and Occluder Removal using Multiple Eigenspaces
TLDR
A method that uses eigenspace models to segment an input image into a foreground and a background component and yields segments that correspond to meaningful real-world objects even in the presence of occlusions, and these segments can be directly used for other tasks like object recognition.
Multiple Eigenspace Models for Scene Segmentation and Occlusion Removal
TLDR
A method that uses eigenspace models to segment an input image into a foreground and a background component and yields segments that correspond to meaningful real-world objects even in the presence of occlusions, and these segments can be directly used for other tasks like object recognition.
Object recognition using appearance-based parts and relations
TLDR
This paper proposes a representation using appearance-based parts and relations to overcome problems of recognition of general three-dimensional objects in cluttered scenes and its design has been a stumbling block in achieving success.
EigenTracking: Robust Matching and Tracking of Articulated Objects Using a View-Based Representation
TLDR
A “subspace constancy assumption” is defined that allows techniques for parameterized optical flow estimation to simultaneously solve for the view of an object and the affine transformation between the eigenspace and the image.
View-Based Recognition Using an Eigenspace Approximation to the Hausdorff Measure
TLDR
This paper has developed a view matching technique based on an eigenspace approximation to the generalized Hausdorff measure that achieves compact storage and fast indexing that are the main advantages of eIGenspace view matching techniques, while also being tolerant of partial occlusion and background clutter.
...
...

References

SHOWING 1-10 OF 16 REFERENCES
Fast template matching based on the normalized correlation by using multiresolution eigenimages
  • S. Yoshimura, T. Kanade
  • Computer Science
    Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'94)
  • 1994
Presents a fast computation method of the normalized correlation for multiple rotated templates by using multiresolution eigenimages. This method allows the authors to accurately detect both location
Illumination Planning for Object Recognition Using Parametric Eigenspaces
TLDR
The illumination planner presents a novel approach to the problem of illumination planning for robust object recognition in structured environments and has been used to enhance the performance of an object recognition system.
View-based and modular eigenspaces for face recognition
TLDR
A modular eigenspace description technique is used which incorporates salient features such as the eyes, nose and mouth, in an eigenfeature layer, which yields higher recognition rates as well as a more robust framework for face recognition.
Eigenfaces for Recognition
TLDR
A near-real-time computer system that can locate and track a subject's head, and then recognize the person by comparing characteristics of the face to those of known individuals, and that is easy to implement using a neural network architecture.
Learning, positioning, and tracking visual appearance
  • S. Nayar, H. Murase, S. Nene
  • Computer Science
    Proceedings of the 1994 IEEE International Conference on Robotics and Automation
  • 1994
TLDR
A general learning algorithm is presented for determining the mapping between robot position and object appearance, which enables accurate visual control without any prior hand-eye calibration.
ExSel++: A General Framework to Extract Parametric Models
TLDR
A framework for accurate and robust extraction of parametric models of different types is presented and the robust fitting technique, which increases the accuracy of the selected models, may change the classification of data elements which requires the final selection.
Face recognition from one example view
  • D. Beymer, T. Poggio
  • Computer Science
    Proceedings of IEEE International Conference on Computer Vision
  • 1995
TLDR
Oar experiments suggest that among the techniques for expressing prior knowledge of faces, 2D example-based approaches should be considered alongside the more standard 3D modeling techniques.
Neural networks for optimization and signal processing
TLDR
A guide to the fundamental mathematics of neurocomputing, a review of neural network models and an analysis of their associated algorithms, and state-of-the-art procedures to solve optimization problems are explained.
Modern heuristic techniques for combinatorial problems
Part 1 Introduction: combinatorial problems local and global optima heuristics. Part 2 Simulated annealing: the basic method enhancements and modifications applications conclusions. Part 3 Tabu
Robust Regression and Outlier Detection
  • Wiley Series in Probability and Statistics
  • 1987
...
...