ViSE: Visual Search Engine Using Multiple Networked Cameras
- 1 January 2006
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 1204-1207
- https://doi.org/10.1109/icpr.2006.1176
Abstract
We propose a visual search engine (ViSE) as a semi-automatic component in a surveillance system using networked cameras. The ViSE aims to assist the monitoring operation of huge amounts of captured video streams, which tracks and finds people in the video based on their primitive features with the interaction of a human operator. We address the issues of object detection and tracking, shadow suppression and color-based recognition for the proposed system. The experimental results on a set of video data with ten subjects showed that ViSE retrieves correct candidates with 83% recall at 83% precisionKeywords
This publication has 4 references indexed in Scilit:
- Detecting moving objects, ghosts, and shadows in video streamsIeee Transactions On Pattern Analysis and Machine Intelligence, 2003
- KNIGHT/spl trade/: a real time surveillance system for multiple and non-overlapping camerasPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Urban surveillance systems: from the laboratory to the commercial worldProceedings of the IEEE, 2001
- Change Detection and Tracking Using Pyramid Transform TechniquesPublished by SPIE-Intl Soc Optical Eng ,1985