A Fast Working System for Tracking Multiple Objects in a Confined View Space |
![]() |
Stan Sexton, UNR Department of CS. Dr. Jim Gattiker, Los Alamos National Laboratory Dr. George Bebis, UNR Department of CS. Dr. Dwight Egbert, UNR Department of CS. |
|
Home Abtract Problem Statement Results Methodology Conclusion & Future Work Acknowledgements ![]() |
The following results were obtained using a single person inside a confined view space. The person enters the space from the bottom and exits near the top through a hidden door way. Figure. 1 shows a frame which has had the foreground separated from the background using a mean and standard deviation of pixel values. By examining the resulting data we can make accurate estimations of what occurred in the mpeg sequence. For example: Figure. 2 shows a graphical representation of the mean size of an object as it is tracked across the field of view. From this data we can tell that the object is moving away from the camera. Figure 3 shows that the mean gray value of an object is going to be relatively uniform. This is an obvious aid when trying to differentiate between objects within close proximity. |
UNR Homepage | UNR Department of Computer Science | UNR-CVL | UNR CRCD | LANL Homepage | LANL NIS-7 | NSF