Toward a sentient environment: real-time wide area multiple human tracking with identities

  • Authors:
  • Tao Zhao;Manoj Aggarwal;Thomas Germano;Ian Roth;Alexandar Knowles;Rakesh Kumar;Harpreet Sawhney;Supun Samarasekera

  • Affiliations:
  • Sarnoff Corporation, 201 Washington Rd, 08543, Princeton, NJ, USA;Sarnoff Corporation, 201 Washington Rd, 08543, Princeton, NJ, USA;Sarnoff Corporation, 201 Washington Rd, 08543, Princeton, NJ, USA;Sarnoff Corporation, 201 Washington Rd, 08543, Princeton, NJ, USA;Sarnoff Corporation, 201 Washington Rd, 08543, Princeton, NJ, USA;Sarnoff Corporation, 201 Washington Rd, 08543, Princeton, NJ, USA;Sarnoff Corporation, 201 Washington Rd, 08543, Princeton, NJ, USA;Sarnoff Corporation, 201 Washington Rd, 08543, Princeton, NJ, USA

  • Venue:
  • Machine Vision and Applications
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, we presented a fully integratedreal-time computer vision system that can detect and track multiple humans in a wide-area using a network of stereo cameras. Continuous human identities are achieved by fusing video tracking with different kinds of biometric devices. The system also provides immersive visualization which enables the users to conveniently navigate through space and time and query useful events. The key innovations include stereo-based multi-object detection and tracking, a unified approach for fusing multiple sensors of different modalities, visualization and user interface design.