• Corpus ID: 9386607

A Keygraph Classification Framework for Real-Time Object Detection

@article{Hashimoto2009AKC,
  title={A Keygraph Classification Framework for Real-Time Object Detection},
  author={Marcelo Hashimoto and Roberto M. Cesar},
  journal={ArXiv},
  year={2009},
  volume={abs/0901.4953}
}
In this paper, we propose a new approach for keypoint-based object detection. Traditional keypoint-based methods consist in classifying individual points and using pose estimation to discard misclassifications. Since a single point carries no relational features, such methods inherently restrict the usage of structural information to the pose estimation phase. Therefore, the classifier considers purely appearance-based feature vectors, thus requiring computationally expensive feature extraction… 

References

SHOWING 1-9 OF 9 REFERENCES
Keypoint recognition using randomized trees
  • V. Lepetit, P. Fua
  • Computer Science, Medicine
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2006
TLDR
A keypoint-based approach is developed that is effective in this context by formulating wide-baseline matching of keypoints extracted from the input images to those found in the model images as a classification problem, which shifts much of the computational burden to a training phase, without sacrificing recognition performance.
Fast Keypoint Recognition in Ten Lines of Code
TLDR
This paper shows that formulating the problem in a Naive Bayesian classification framework makes such preprocessing unnecessary and produces an algorithm that is simple, efficient, and robust, and it scales well to handle large number of classes.
Object tracking with dynamic feature graph
  • Feng Tang, Hai Tao
  • Computer Science
    2005 IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance
  • 2005
TLDR
This paper presents a novel feature based object representation attributed relational graph (ARG) for reliable object tracking and adopts a competitive and efficient dynamic model to adoptively update the object model by adding new stable features as well as deleting inactive features.
Good features to track
  • Jianbo Shi, Carlo Tomasi
  • Computer Science
    1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition
  • 1994
TLDR
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.
SURF: Speeded-Up Robust Features
In this document, the SURF detector-descriptor scheme used in the OpenSURF library is discussed in detail. First the algorithm is analysed from a theoretical standpoint to provide a detailed overview
Distinctive Image Features from Scale-Invariant Keypoints
This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene. The features are ...
A sweepline algorithm for Voronoi diagrams
  • S. Fortune
  • Computer Science, Mathematics
    SCG '86
  • 1986
TLDR
A transformation is used to obtain simple algorithms for computing the Voronoi diagram of point sites, of line segment sites, and of weighted point sites with sweepline technique.
Method and means for recognizing complex patterns
  • U. S. Patent
  • 1962
net: Open Computer Vision Library. http://sourceforge.net/projects/opencvlibrary
  • net: Open Computer Vision Library. http://sourceforge.net/projects/opencvlibrary