Upload
arvind-krishnaa
View
980
Download
5
Embed Size (px)
DESCRIPTION
Citation preview
SMART CAMERA MONITORING SYSTEMENVIRONMENTAL ANALYSIS, MONITORING AND CONTROL
Akshay SArvind Krishnaa.JBhargavi RBalamurugan SDivya PSarang B
Third Year, Computer Science and Engineering
Objective
To develop
1.An effective monitoring system
2.Analyze its environment
3.Recognize entities
4.Track their motion paths and characteristics
5.Process above data to obtain identifiable patterns
6.Apply or interpret these patterns to suitable applications
Motivations
• Casino Surveillance System• Security monitoring and analysis• Geriatric Surveillance• Child Care Monitoring• Industrial Surveillance• Traffic Management System
System Model- Various Modules
ENTITY DETECTION
ENTITY RECOGNITION
MOTIONTRACKING
STORING SPATIO-TEMPORAL DATA
IN DATABASE
MINING DATA TO FORM
PATTERNS
COMPARE INPUT TO
AVAILABLE PATTERNS
SELECTQUERY
INSERT QUERY
ACTION
Overview
1. Real-Time Face Detection
2. Facial Recognition and object tagging
3. Motion path tracking using SIFT
4. Continuously stream processed data from surveillance equipment(cameras) to database residing in the server.
5. Form recognizable patterns from the data based on fuzzy logic.
6. Use the patterns as a template for future monitoring.
Salient Features
1. Fully automated system with minimal manual monitoring of surveillance footage.
2. Ability to scale from very large or medium-small applications
3. Integrating existing technologies and building upon the fundamentals.
4. Distributed processing of captured data on “smart” cameras instead of on a server
Challenges Faced
1. Detecting individual faces in a densely populated area
2. Constructing patterns when subjects are only partially visible
3. Monitoring in hostile environments
4. Cost and design feasibility
References Viola Paul, Jones Michael, “Rapid Object Detection Using a Boosted Cascade of Simple
Features” ; ACCEPTED CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION 2001
Henry A. Rowley, Shumeet Baluja, and Takeo Kanade, “Neural Network-Based Face Detection” ; PAMI, January 1998
“FPGAs Provide Reconfigurable DSP Solutions”, White Paper developed by ALTERA International,
“FPGA Vs. DSP Design Reliability and Maintenance” , White Paper developed by ALTERA International.
Henry Schneiderman, Takeo Kanade, "A Statistical Method for 3D Object Detection Applied to Faces and Cars" cvpr, vol. 1, pp.1746, 2000 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'00) - Volume 1, 2000
Jiyong Zhang , “Spatio-Temporal Databases”, Spatio-temporal database research at the University of Melbourne
Laptev, Ivan and Lindeberg, Tony (2004). ”Local descriptors for spatio-temporal recognition”. ECCV'04 Workshop on Spatial Coherence for Visual Motion Analysis, Springer Lecture Notes in Computer Science, Volume 3667. pp. 91–103.
Zhen Liang, Hong Fu, Zheru Chi, David Dagan Feng , “Salient-SIFT for Image Retrieval” ACIVS (1) 2010:pages 62-71