DESCRIPTION:
A hierarchical algorithm to detect cast shadows and objects such as vehicles, airplanes and people in single, overhead, color images. The inventive method is illumination and brightness independent.
POTENTIAL APPLICATIONS:
Technology can be integrated into systems and programs fielded by military / homeland security / intelligence / law enforcement and risk management, for example, unmanned aerial vehicles (UAVs) / drones, and smart acquisition and tracking of targets.
ADVANTAGES:
Homeland security and defense
- Aerial surveillance analysis
- Automated target recognition and tracking
- Battlefield planning
3-D scene reconstruction and virtual environment construction
- Simulation-based pilot training
PATENT STATUS:
U.S. Patent 7,366,323 and patent pending.
KEYWORDS:
Shadow detection; static shadow; image segmentation; pixel level classification; Markov Random Field (MRF); Expectation Maximization (EM) algorithm; reliable lattice
ADDITIONAL REFERENCE INFORMATION:
Professor Zhang’s homepage is http://www.cs.binghamton.edu/~zhongfei/ with additional information accessible via the link to the Multimedia Research Lab which he directs http://www.fortune.binghamton.edu/
See also RB-142, Linear System Based Qualitative Indpendent Motion Detection From Compressed MPEG Surveillance Video.
|
