Embedded vehicle speed estimation system using an asynchronous temporal contrast vision sensor
EURASIP Journal on Embedded Systems
Customizing multiprocessor implementation of an automated video surveillance system
EURASIP Journal on Embedded Systems
MIV'06 Proceedings of the 6th WSEAS International Conference on Multimedia, Internet & Video Technologies
SEPADS'06 Proceedings of the 5th WSEAS International Conference on Software Engineering, Parallel and Distributed Systems
A content distribution network deployment over WLANs for fire detection in rural environments
UPGRADE '08 Proceedings of the third international workshop on Use of P2P, grid and agents for the development of content networks
A novel software framework for embedded multiprocessor smart cameras
ACM Transactions on Embedded Computing Systems (TECS)
Applications of trusted computing in pervasive smart camera networks
WESS '09 Proceedings of the 4th Workshop on Embedded Systems Security
Self-organizing computer vision for robust object tracking in smart cameras
ATC'10 Proceedings of the 7th international conference on Autonomic and trusted computing
HDTV compression for storage and transmission over internet
DNCOCO'06 Proceedings of the 5th WSEAS international conference on Data networks, communications and computers
Fast hough transform on GPUs: exploration of algorithm trade-offs
ACIVS'11 Proceedings of the 13th international conference on Advanced concepts for intelligent vision systems
Using compressed index structures for processing moving objects in large spatio-temporal databases
Journal of Systems and Software
PASU: A personal area situation understanding system using wireless camera sensor networks
Personal and Ubiquitous Computing
| Hi-index | 0.00 |
A smart camera combines video sensing, high-level videoprocessing and communication within a single embeddeddevice. Such cameras are key components in novel surveillancesystems.This paper reports on a prototyping development of asmart camera for traffic surveillance. We present its scalablearchitecture comprised of a CMOS sensor, digital signalprocessors (DSP), and a network processor. We furtherdiscuss the mapping of high-level video processing algorithmsto embedded DSP-based platforms and identify typicalpitfalls for the porting of software from desktops toembedded platforms. Our mapping strategies are demonstratedon an algorithm for automatic detection of stationaryvehicles. This algorithm is migrated from a Matlab-basedprototyping implementation to an embedded DSP implementationin our smart camera.Our implemented smart camera prototype streams thevideo data over an IP-network to a central monitoring stationand is able to detect stationary vehicles and blockingcargo on highways within the required real-time constraintsof six seconds.