Sciweavers

BMVC
2010
13 years 3 months ago
Calibration of Non-Overlapping Cameras---Application to Vision-Based Robotics
Multi-camera systems are more and more used in vision-based robotics. An accurate extrinsic calibration is usually required. In most of cases, this task is done by matching featur...
Pierre Lébraly, Eric Royer, Omar Ait-Aider,...
BMVC
2010
13 years 3 months ago
Large-scale Dictionary Learning For Local Coordinate Coding
Local coordinate coding has recently been introduced to learning visual feature dictionary and achieved top level performance for object recognition. However, the computational co...
Bo Xie, Mingli Song, Dacheng Tao
BMVC
2010
13 years 3 months ago
Insect Species Recognition using Sparse Representation
Insect species recognition is a typical application of image categorization and object recognition. Unlike generic image categorization datasets (such as the Caltech 101 dataset) ...
An Lu, Xin Hou, Chen Lin, Cheng-Lin Liu
BMVC
2010
13 years 3 months ago
FAST: Fast Adaptive Silhouette Area based Template Matching
Template matching is a well-proven approach in the area of articulated object tracking. Matching accuracy and computation time of template matching are essential and yet often con...
Daniel Mohr, Gabriel Zachmann
BMVC
2010
13 years 3 months ago
Diffusion-based Regularisation Strategies for Variational Level Set Segmentation
Variational level set methods are formulated as energy minimisation problems, which are often solved by gradient-based optimisation methods, such as gradient descent. Unfortunatel...
Maximilian Baust, Darko Zikic, Nassir Navab
BMVC
2010
13 years 3 months ago
Three-step image rectification
Image stereo-rectification is the process by which two images of the same solid scene undergo homographic transforms, so that their corresponding epipolar lines coincide and becom...
Pascal Monasse, Jean-Michel Morel, Zhongwei Tang
BMVC
2010
13 years 3 months ago
Accounting for the Relative Importance of Objects in Image Retrieval
We introduce a method for image retrieval that leverages the implicit information about object importance conveyed by the list of keyword tags a person supplies for an image. We p...
Sung Ju Hwang, Kristen Grauman
BMVC
2010
13 years 3 months ago
Inferring Image Transformation and Structure from Motion-Blurred Images
This paper deals with the problem of estimating structure of 3D scenes and image transformations from observations that are blurred due to unconstrained camera motion. Initially, ...
Paramanand Chandramouli, Rajagopalan Ambasamudram
BMVC
2010
13 years 3 months ago
Segmentation using Deformable Spatial Priors with Application to Clothing
We present a method for segmenting the parts of multiple instances of a known object category exhibiting large variations in projected shape and colour. The method builds on an ex...
Basela Hasan, David Hogg