Video Sensor Architecture for Surveillance Applications

Autor: Jordi Sanchez, José Simó, G. Benet
Jazyk: angličtina
Rok vydání: 2012
Předmět:
Artificial intelligence
Domain-specific architectures
Computer science
Visual sensor network
Video Recording
Cloud computing
lcsh:Chemical technology
Biochemistry
computer vision
Pattern Recognition
Automated
Analytical Chemistry
Software
Organization and management
Photography
lcsh:TP1-1185
Instrumentation
Hardware architecture
Computer network
domain-specific architectures
Transducer
Distributed smart cameras
Equipment Design
Surveillance systems
Automated pattern recognition
Atomic and Molecular Physics
and Optics
Computer assisted diagnosis
Video tracking
Sensor node
Component-based software engineering
Equipment design
surveillance systems
Transducers
Real-time computing
Equipment
Computer program
Article
Security Measures
distributed smart cameras
Computer Communication Networks
Image processing
Artificial Intelligence
Image Interpretation
Computer-Assisted
Electrical and Electronic Engineering
Real-time systems
business.industry
Node (networking)
Methodology
image processing
ARQUITECTURA Y TECNOLOGIA DE COMPUTADORES
Equipment Failure Analysis
real-time systems
Computer vision
Software architecture
business
Videorecording
Zdroj: Sensors, Vol 12, Iss 2, Pp 1509-1528 (2012)
Sensors
Volume 12
Issue 2
Pages 1509-1528
Sensors (Basel, Switzerland)
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
instname
ISSN: 1424-8220
Popis: This paper introduces a flexible hardware and software architecture for a smart video sensor. This sensor has been applied in a video surveillance application where some of these video sensors are deployed, constituting the sensory nodes of a distributed surveillance system. In this system, a video sensor node processes images locally in order to extract objects of interest, and classify them. The sensor node reports the processing results to other nodes in the cloud (a user or higher level software) in the form of an XML description. The hardware architecture of each sensor node has been developed using two DSP processors and an FPGA that controls, in a flexible way, the interconnection among processors and the image data flow. The developed node software is based on pluggable components and runs on a provided execution run-time. Some basic and application-specific software components have been developed, in particular: acquisition, segmentation, labeling, tracking, classification and feature extraction. Preliminary results demonstrate that the system can achieve up to 7.5 frames per second in the worst case, and the true positive rates in the classification of objects are better than 80%. © 2012 by the authors; licensee MDPI, Basel, Switzerland.
This work has been partially supported by SENSE project (Specific Targeted Research Project within the thematic priority IST 2.5.3 of the 6th Framework Program of the European Commission: IST Project 033279), and has been also co-funded by the Spanish research projects SIDIRELI: DPI2008-06737-C02-01/02 and COBAMI: DPI2011-28507-C02-02, both partially supported with European FEDER funds.
Databáze: OpenAIRE
Externí odkaz: