People Image Analysis Consortium
 

Home -> Projects ->Master-Slave Distant Human Identification (DHID) Member Login  

Jump to: Components | Demos | Publications | Releases

 Description

Distant Human Identification (DHID) System is a master-slave real-time surveillance system to detect, track, and acquire biometric imagery of humans at distance.

A stationary wide field of view master camera is used to monitor an environment at distance. When the master camera detects a moving person, a narrow field of view slave camera is commanded to turn to that direction, acquire the target human, and track them while recording zoomed-in images. These zoomed-in views provide meaningful biometric imagery of the distant humans, who are not recognizable in the master view.

 Components

The system include the following three control compoents. Details are described in the published paper below.
1. Master Camera Processing: This module controls motion detection and object classification at master camera.
2. Slave Camera Processing: This module controls object detection and tracking at slave camera.
3. Pan-Tilt-Zoom Control: This module controls the Pan-Tilt head and slave camera zooming in real time.

 Demos

4 View Combined Video Example
A four view combined video clip to show how the system works. It includs system view, master camera view, slave camera view, and slave camera tracking view. The tracking here is based on human head.
Download: mpg [17.1MB]
2 View Combined Video Example
A two view combined video clip to show an example of master camera view and slave camera view. In the slave camera view, the target is detected, tracked, and zoomed in. The slave camera tracking here is based on human body.
Download: avi [2.0MB]
Master Camera Video Example
A master view video clip to show an example of motion detection and tracking in master camera. In this example, whenever two objects move across each other, the focus (red crossing) moves to the object on the top.
Download: mpg [27.4MB]
Slave Camera Video Example
A slave camera view video clip to show an example of slave camera tracking based on human head.
Download: avi [39.8MB]

 Selected Publications

We grant permission to use and publish all data and results from this site, provided the following paper is referenced:

 Releases [ Members Only ]



PIA Consortium is a part of Robotics Institute, School of Computer Science, Carnegie Mellon University