KNIGHT: Real Time Automated Surveillance System
A preliminary video surveillance and monitoring system, called KNIGHT, has been developed to help Orlando Police Department with electronic patrol. KNIGHT is a ‘smart’ surveillance system that detects important changes, events, and activities using computer vision techniques, flags significant events, and presents a summary in terms of key frames and textual description of activities to a monitoring officer for final analysis and response decision. The system is robust to illumination changes and weather conditions. KNIGHT has been installed at four locations in the downtown Orlando area which has Orange Avenue as its primary street, and is currently being field tested. The system employs single camera, and works in real time. KNIGHT consists of four main modules: object detection and shadow removal, tracking object classification and activity detection.
| Results for PETS sequences
|
Tracking Results for UCF Sequences ( real sequences- no actors)    |
| Results for UCF sequences
|
| Results for UCF sequences (with actors)
|
| Results for IR sequences
|
| Results for Indoor Sequences
|
| Related Publications:
Omar Javed, Khurram Shafique and Mubarak Shah, “Automated Surveillance in Realistic Scenarios“, IEEE MultiMedia, January/March 2007. Omar Javed, Khurram Shafique and Mubarak Shah, “A Hierarchical Approach to Robust Background Subtraction using Color and Gradient Information“, IEEE Workshop on Motion and Video Computing, Orlando, Dec 5-6 2002 Omar Javed and Mubrark Shah, “Tracking And Object Classification For Automated Surveillance”, The seventh European Conference on Computer Vision (ECCV 2002), Copenhagen, May 2002. Sohaib Khan, Omar Javed, Mubarak Shah, “Tracking in Uncalibrated Cameras with Overlapping Field of View”, Performance Evaluation of Tracking and Surveillance PETS 2001, (with CVPR 2001), Kauai, Hawaii, Dec 9th, 2001 Presentation: |
| Keywords: shadow removal, tracking, object classification, automated surviellance, real time system |