Sciweavers

355 search results - page 38 / 71
» A Background Model Initialization Algorithm for Video Survei...
Sort
View
121
Voted
ICASSP
2008
IEEE
15 years 9 months ago
Joint tracking and video registration by factorial Hidden Markov models
Tracking moving objects from image sequences obtained by a moving camera is a difficult problem since there exists apparent motion of the static background. It becomes more dif...
Xue Mei, Fatih Murat Porikli
149
Voted
CVPR
2012
IEEE
13 years 5 months ago
Understanding collective crowd behaviors: Learning a Mixture model of Dynamic pedestrian-Agents
In this paper, a new Mixture model of Dynamic pedestrian-Agents (MDA) is proposed to learn the collective behavior patterns of pedestrians in crowded scenes. Collective behaviors ...
Bolei Zhou, Xiaogang Wang, Xiaoou Tang
114
Voted
ICPR
2008
IEEE
16 years 3 months ago
Segmentation by combining parametric optical flow with a color model
We present a simple but efficient model for object segmentation in video scenes that integrates motion and color information in a joint probabilistic framework. Optical flow is mo...
Adrian Ulges, Thomas M. Breuel
89
Voted
DAGM
2007
Springer
15 years 8 months ago
WarpCut - Fast Obstacle Segmentation in Monocular Video
Abstract. Autonomous collision avoidance in vehicles requires an accurate seperation of obstacles from the background, particularly near the focus of expansion. In this paper, we p...
Andreas Wedel, Thomas Schoenemann, Thomas Brox, Da...
122
Voted
IROS
2006
IEEE
134views Robotics» more  IROS 2006»
15 years 8 months ago
A Novel Self Organizing Network to Perform Fast Moving Object Extraction from Video Streams
— Image segmentation is a critical task in computer vision. In the context of motion detection, a very popular segmentation approach is background substraction which consists in ...
Dizan Vasquez, Thierry Fraichard