Professional Documents
Culture Documents
VRS Final (Compatibility Mode)
VRS Final (Compatibility Mode)
VRS Final (Compatibility Mode)
Session (2006-2010)
Presented by:
Introduction Literature Review SDLC Phases Inception El b Elaboration ti Construction Transition Conclusion and Future Enhancements References
Introduction
Video Reporting System
Videos are taken from the CC CCTV camera for further processing
After processing a report is generated for the top management for necessary actions
Introduction Literature Review SDLC Phases Inception El b Elaboration ti Construction Transition Conclusion and Future Enhancements References
Literature Review
It is any form of signal processing for which the input is an Start image, such as photographs or frames of video; the output of History Databases consist of software-based image processing can be either an image or a set of "containers" Purpose characteristics that are structured to collect and store information so or parameters related to the image Object Detection users Implementation can retrieve, add, update or remove such Reduce Theft Electronics Engineering Computer C Componentsinformation in an automatic fashion Science t Enhance Productivity Hardware Aspects Movie Viewable Stop Provide Internetstorage CCTV in Monitor Multiple Locations Image processing Tracking Study multiplecameras Sensors Peace of Mind Introduction about Surveillance System y techniques, techniquesdatabase Software and algorithms Aspects tools Algorithms Advantages of Surveillance System Databases Activities For contain the reports y Surveillance System of the in analysis Research Aspects system
Introduction Literature Review SDLC Phases Inception El b Elaboration ti Construction Transition Conclusion and Future Enhancements References
SDLC Phases
RUP (Rational Unified Process)
Video Reporting System Project Model Project schedule and Mile stones Inception Deliverables Development Plan Requirement Change Management Plan Configuration Plan TheVideo reporting System is a desktop system in which CCTV camera is used Quality Plan y for taking(Rational Unified Process) Phase I:body in the form of reports for Resource Plan RUP the suspicious activity of the human Inception necessary actions. Plan Infrastructure Risk identification Plan Scope
SDLC Phases
P bl Problem Statement St t t The Video Reporting System is surveillance system that works for reporting the suspicious human scope of the Architecture action. TheSystemproject is: Project Plan It is a desktop based application and deployed on a single system system. Video is capture through CCTV camera. Requirements Human actions are recognizing in the live video. of human actions is Report Functional generated for management. Our system cannot detect any abnormal action outside the cameras lenss boundary. Non Functional Our system only deploy at main gate of any building for the purpose of security reason containing barrier. and Software Requirements Hardware
Only Normal human body is detected e.g. children, animals detection is not part of our project. The video should be clear so that images can be taken easily easily. Humans which stay more then 5 seconds in the targeted boundary will be treated as suspicious. Purchasing, installation and deployment of any Hardware, Software & caballing installation, is not part of our project.
Hardware Requirements CCTV Camera or Webcam Intel Processor 2.0GHz Video Capturing 2 GB RAM RUP (Rational Unified Process) Phase I: Inception Object Detection Software Requirements Maintainability Scope Documentation: Microsoft Office tH Human t d T ki B Body Tracking Rational rose P bl Problem Statement St Usability Visio System Architecture Reporting Coding: C #.net frame work Project Plan Efficiency MS Access Requirements Operating System: Windows XP
SDLC Phases
SDLC Phases
Scenario I: Object Detection RUP (Rational Unified Process) Phase II: Elaboration
SDLC Phases
RUP (Rational Unified Process) Phase II: Elaboration
Sequence Diagram
Scenario I: Object Detection
SDLC Phases
RUP (Rational Unified Process) Phase II: Elaboration
Sequence Diagram
Scenario II: Tracking
SDLC Phases
RUP (Rational Unified Process) Phase II: Elaboration
Sequence Diagram
Scenario III: Reporting
SDLC Phases
RUP (Rational Unified Process) Phase II: Elaboration
User Interfaces
SDLC Phases
RUP (Rational Unified Process) Phase II: Elaboration
User Interfaces
SDLC Phases
RUP (Rational Unified Process) Phase II: Elaboration
User Interfaces
SDLC Phases
RUP (Rational Unified Process) Phase II: Elaboration
User Interfaces
SDLC Phases
RUP (Rational Unified Process) Phase II: Elaboration
User Interfaces
SDLC Phases
RUP (Rational Unified Process) Phase II: Elaboration
User Interfaces
SDLC Phases
RUP (Rational Unified Process) Phase II: Elaboration
User Interfaces
SDLC Phases
RUP (Rational Unified Process) Phase II: Elaboration
User Interfaces
SDLC Phases
RUP (Rational Unified Process) Phase II: Elaboration
User Interfaces
SDLC Phases
RUP (Rational Unified Process) Phase II: Elaboration
User Interfaces
SDLC Phases
RUP (Rational Unified Process) Phase II: Elaboration
User Interfaces
SDLC Phases
RUP (Rational Unified Process) Phase II: Elaboration
User Interfaces
SDLC Phases
RUP (Rational Unified Process) Phase II: Elaboration
User Interfaces
SDLC Phases
RUP (Rational Unified Process) Phase III: Construction Project Demo:
Test Cases:
Object Detection Test Case Human Body Tracking Test Case Reporting Test Case
SDLC Phases
RUP (Rational Unified Process) Phase IV: Transition
Deployment Diagram
Introduction Literature Review SDLC Phases Inception El b Elaboration ti Construction Transition Conclusion and Future Enhancements References
Conclusion
Our project is about the reporting of suspicious human actions. This system facilitates management as no particular person is required to monitor human actions at the place where surveillance is required. The system reports automatically to management about suspicious actions.
Future Enhancements
Our system achieves human activity but still requires g some enhancements e.g. To make tracking of people through multiple cameras. To recognize covered faces people To enhance the tracking algorithm so that it did not slow down the system processing To incorporate Artificial Intelligence so that system identify and recognize human body by itself. To incorporate more actions like bending, jumping fighting etc etc.
Introduction Literature Review SDLC Phases Inception El b Elaboration ti Construction Transition Current Status Conclusion and Future Enhancements References
References
Saad Ali, Arslan Basharat and Mubarak Shah Chaotic g Invariants for Human Action Recognition, 2007. N. Dalal and B. Triggs. Histogram of oriented gradients for human detection. In CVPR, 2005. A. Farhadi and M. K. Tabrizi. Learning to recognize activities from the wrong view point. In ECCV, 2008. M. Valera and S.A. Velastin, Intelligent distributed surveillance systems: a review, IEE Proc.-Vis. Image Signal Process., Vol. 152, No. 2 152 No 2, April 2005 Neeti A. Ogale, A survey of techniques for human detection from video, 2006
References
ArnoldWiliem, Vamsi Madasu, Wageeh Boles, and Prasad Yarlagadda, 2009, Adaptive Unsupervised Learning of Human Adaptive Actions, in Computer Vision and Pattern Recognition Weilong Yang, Yang Wang, and Greg Mori, 2008, Human Action Recognition from a Single Clip per Action, in Computer Action , Vision and Pattern Recognition Wei Niu, Jiao Long, Dan Han, and Yuan-Fang Wang, 2004, Human Activity Detection and Recognition for Video Human Surveillance, in Computer Vision and Pattern Recognition Neeti A. Ogale, A survey of techniques for human detection from video, IEEE, 2005 video ,
References
P. Peixoto, J. Goncalves, and H. Araujo. Real-time gesture g y g recognition system based on contour signatures, ICPR, volume 1, pages 447-450, 2002. A. Fathi and G. Mori. Action recognition by learning mid-level motion features. In CVPR, 2008. D.Weinland and E. Boyer. Action recognition using exemplar-based embedding. In CVPR, 2008. Henry Schneiderman and Takeo Kanade. Object detection using the statistics of parts. IJCV 56(3):151 177 2004 parts IJCV, 56(3):151.177, 2004. G. Gordon, T. Darrell, M. Harville, and J. Woodfill, Background Estimation and Removal based on Range and Color, in Proceedings p g , of IEEE Conference on Computer Vision and Pattern Recognition, Vol.2, pp.2459-2464, Fort Collins, CO., USA, Jun. 1999.
References
Qiang Zhu, Shai Avidan, Mei-Chen Yeh, and Kwang-Ting Cheng, g g Fast Human Detection Using a Cascade of Histograms of Oriented Gradients , 2005. H. Zhong, J. Shi, and M. Visontai, Detecting Unusual Activity in Video, Proc. IEEE Conf. CVPR, vol. 2, pp. 819-826, 2004. F. Lv, J. Kang, R. Nevatia, I. Cohen and G. Medioni, Automatic Tracking and Labeling of Human Activities in a Video Sequence, Intl Workshop on Performance Evaluation of Tracking and Surveillance, 2004. 2004 P.C. Ribeiro and J. Santos-Victor, Human Activity Recognition from Video: modeling, feature selection and classification architecture, Intl Workshop on Human Activity Recognition and Modeling, pp. 6170, 2005.
References
Anant Madabhushi and J. K. Aggarwal , 1999, A Bayesian Approach to Human Activity Recognition, Computer Vision and Recognition , Image Understanding. Aaron F. Bobick, James W. Davis, The Recognition of Human Movement Using emporal Templates, IEEE Transactions on Templates , Pattern Analysis and Machine Intelligence, Vol. 23, No. 3, March 2001. Somboon Hongeng, Ram Nevatia, Francois Bremond, VideoVideo based event recognition: activity representation and probabilistic recognition methods, Computer Vision and Image Understanding 96, (2004) 129-162 . g ( )