Video flashlights: real time rendering of multiple videos for immersive model visualization
EGRW '02 Proceedings of the 13th Eurographics workshop on Rendering
Counting People in Crowds with a Real-Time Network of Simple Image Sensors
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Distributed Interactive Video Arrays for Event Capture and Enhanced Situational Awareness
IEEE Intelligent Systems
Adaptive Probabilistic Tracking Embedded in a Smart Camera
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops - Volume 03
CRV '06 Proceedings of the The 3rd Canadian Conference on Computer and Robot Vision
CVPRW '06 Proceedings of the 2006 Conference on Computer Vision and Pattern Recognition Workshop
Hi-index | 0.00 |
Surveillance systems based on distributed sensor networks are massively emerging today, as the interest in enhanced safety in this ever changing world gets more actual than ever. Traditional "CCTV" surveillance systems with their centralized processing (compression) and recording architecture together with a simple multi-monitor visualization of the raw video streams bear several drawbacks and limitations. The necessary communication bandwidth to each camera and the computational requirements on the centralized servers strongly limit such systems in terms of the expandability, installation size (cable lengths) and spatial/temporal resolution of each camera. Additionally, the visualization is counter intuitive and fatiguing due to the massive load of raw video data. We present a distributed network of smart cameras and its integrated visualization. The smart cameras' tracking results are embedded in a common 3D environment as live textures and can be viewed from arbitrary perspectives. Also a georeferenced live visualization embedded in Google Earth is presented. This offers a visualization more abstract from the camera perspective yet more intuitive in terms of integration.