I s a a c  C O H E N 

Unmanned Aerial Vehicles

Back to home

Students

Publications

Miscellaneous

Biography

D e s c r i p t i o n 

The detection and tracking of moving objects in a video stream acquired by a UAV is a challenging problem, as it requires estimating the camera motion, detecting independent moving objects in the scene, and finally tracking these objects by associating blob features across frames. We address these specific problems in our research effort and we have developed a system capable of detecting and tracking moving objects in UAV video. The system modules are: image stabilization, image mosaicing, detection and tracking of moving objects.

S t u d e n t s 

• Elaine Kang
• Jinman Kang

R e s u l t s 

Motion Stabilization

Motion Stabilization of IR video

Detection of Moving Objects

Detection and Tracking of moving objects

P u b l i c a t i o n s 

• Continuous Tracking Within and across Camera Streams, IEEE, Conference on Computer Vision and Pattern Recognition, CVPR'2003, Madison, Wisconsin. June 16-22, 2003.
• Robust Affine Motion Estimation in Joint Image Space using Tensor Voting, International Conference on Pattern Recognition. August 2002.
  
• Event Detection and Analysis from Video Streams, IEEE Transaction on Pattern Analysis and Machine Intelligence, 8(23) pages 873-889, August 2001
• A Graph-Based Global Registration for 2D Mosaics, 15th International Conference on Pattern Recognition(ICPR), 2000, Barcelrona, Spain
• Detecting and Tracking Objects in Video Surveillance, Proc. of the IEEE Computer Vision and Pattern Recognition 99, Fort Collins, June 1999.
• Detecting and Tracking Moving Objects in Video from an Airborne Observer, DARPA Image Understanding Workshop, IUW98, Monterey, November 1998.
• Event Detection and Analysis from Video Streams, DARPA Image Understanding Workshop, IUW98, Monterey, November 1998.
• Detecting and Tracking Moving Objects in Video from an Airborne Observer, DARPA Image Understanding Workshop, IUW98, Monterey, November 1998.