Projective Kalman Filter: Multiocular Tracking of 3D Locations Towards Scene Understanding thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Projective Kalman Filter: Multiocular Tracking of 3D Locations Towards Scene Understanding

Published on Feb 25, 20077630 Views

This paper presents a novel approach to the problem of estimating and tracking 3D locations of multiple targets in a scene using measurements gathered from multiple calibrated cameras. Estimation and

Related categories

Chapter list

Projective Kalman Filter: Multiocular Tracking of 3D Locations Towards Scene Understanding00:05
Outline00:27
Introduction01:00
Problem statement01:59
Objective02:55
Example03:29
Kalman Filter (KF) Model03:46
Projective Kalman Filter (I)04:51
Projective Kalman Filter (II) Modelling non-linearity05:26
Projective Kalman Filter (III) Noise model06:19
Data association on P3→P2 (I)07:04
Data association on P3→P2 (II)07:22
Results08:30
Results on Synthetic Data (I)08:57
Results on Synthetic Data (II)10:26
Results on Real Data (I)10:48
Results on Real Data (II)11:16
Conclusions & Future Work11:54
The End12:40