Abstract
The paper addresses the problem of registering regions of interest in two video sequences. Potential applications include blob fusion and target tracking in blurry sequences. It is assumed that the moving target is tracked successfully in one of the two sequences and is represented by a bounding box in each frame of the first sequence. The goal is to find the corresponding bounding box for each frame of the second video sequence. The registration algorithm developed is based on mutual information. To facilitate the registration process, the two cameras are assumed to be calibrated such that the geometrical transformation required to register the corresponding bounding boxes is a 2D rigid body transformation without rotation. Visual and IR video sequences are used to test the proposed approach.
Original language | English (US) |
---|---|
Title of host publication | Proceedings - IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2003 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 313-318 |
Number of pages | 6 |
ISBN (Print) | 0769519717, 9780769519715 |
DOIs | |
State | Published - 2003 |
Event | IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2003 - Miami, United States Duration: Jul 21 2003 → Jul 22 2003 |
Other
Other | IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2003 |
---|---|
Country | United States |
City | Miami |
Period | 7/21/03 → 7/22/03 |
Keywords
- Cameras
- Humans
- Image sensors
- Millimeter wave technology
- Mutual information
- Sensor fusion
- Surveillance
- Target tracking
- Video sequences
- Weapons
ASJC Scopus subject areas
- Computer Networks and Communications
- Signal Processing