143
click to vote
ICPR
2006
IEEE
16 years 7 months ago
2006
IEEE
This paper introduces an efficient 3D segmentation concept, which is based on extending the well-known Maximally Stable Extremal Region (MSER) detector to the third dimension. The...
172
click to vote
ICPR
2006
IEEE
16 years 7 months ago
2006
IEEE
We propose an object detection method using particle filters. Our approach estimates the probability of object presence in the current image given the history of observations up t...
153
click to vote
ICPR
2006
IEEE
16 years 7 months ago
2006
IEEE
The quantization parameter (QP) has a very important impact on the compression rate in H.264. In this paper we show that in order to achieve efficient rate-control coding a good e...
158
click to vote
ICPR
2006
IEEE
16 years 7 months ago
2006
IEEE
Laser based people tracking systems have been developed for mobile robotic or intelligent surveillance areas. Existing systems rely on laser point clustering to extract object loc...
168
click to vote
ICPR
2006
IEEE
16 years 7 months ago
2006
IEEE
Images obtained with catadioptric sensors contain significant deformations which prevent the direct use of classical image treatments. Thus, Markov Random Fields (MRF) whose usefu...
185
click to vote
ICPR
2006
IEEE
16 years 7 months ago
2006
IEEE
In this paper, a novel unsupervised approach for the segmentation of unorganized 3D points sets is proposed. The method derives by the mean shift clustering paradigm devoted to se...
171
click to vote
ICPR
2006
IEEE
16 years 7 months ago
2006
IEEE
This paper restates the shape from shading problem regarding both surface modeling and optimization. We combine the use of a B-spline as 3D model for the scene surface and the use...
146
click to vote
ICPR
2006
IEEE
16 years 7 months ago
2006
IEEE
We introduce the `No Panacea Theorem' for classifier combination in the two-classifier, two-class case. It states that if the combination function is continuous and diverse, ...
121
click to vote
ICPR
2006
IEEE
16 years 7 months ago
2006
IEEE
We propose a criterion, called `maximal redundancy', for onset detection in time series. The concept redundancy is adopted from information theory and indicates how well a si...
161
click to vote
ICPR
2006
IEEE
16 years 7 months ago
2006
IEEE
K-Nearest Neighbors relies on the definition of a global metric. In contrast, Discriminant Adaptive Nearest Neighbor (DANN) computes a different metric at each query point based o...