AJAY KUMAR GARG ENGINEERING COLLEGE,
GHAZIABAD
PROJECT PRESENTATION ON
INTELLIGENT VIDEO SURVE I LLANCE SYSTEM
Guided By, Presented By,
Ms. Shilpi Gupta Aman (2100270119001)
Danish Husain (2100270119003)
Jay Kumar Sharma
CSIT- 1
10 (2100270119004)
OutLine of the Project
I. Abstract
II. Objective
III. Literature Review
IV. Research Gap
V. Design
a)DFD
b)Use case
c)Class Diagram
d)Collaboration Diagram
e)Data Schema
f)ER Diagram
VI. ScreenShots
VII. GhatChatt
VIII. Refrences
Abstract
2
• Our project, the "Intelligent Video Surveillance System," leverages
cutting-edge technologies in computer vision and artificial
intelligence to enhance traditional video surveillance capabilities.
Key features include real-time object detection and tracking,
behavior analysis, anomaly detection, IoT device integration, cloud
support, and a user-friendly interface. This system provides
advanced security through intelligent video analytics, ensuring
efficient monitoring, rapid response to threats, and comprehensive
situational awareness.
CSIT-
10
3
Objective
Current Video Surveillance Systems Provide Real-time Footage But Struggle To Identify
Suspicious Incidents In Crowded Areas. Manual Monitoring Is Both Challenging And Labor-
intensive. Our Proposed System Aims To Enhance Surveillance With Key Features:
1. Object Detection.
2. Monitoring And Tracking Of Individuals.
3. PPE kit Detection.
4. Car counter.
Our Project Employs Convolutional Neural Networks (Cnns) To Detect Falls, Crashes, Crowd
Anomalies, And Objects In Live Video Streams, Leveraging Tensorflow For Implementation.
This Innovation Aims To Significantly Improve Surveillance Capabilities.
CSIT-
10
TECHNICAL
5
REQUIREMENTS
HARDWARE REQUIREMENTS
• INTEL(R) CORE(TM) I5-7300U CPU @ 2.60GHZ 2.71 GHZ
• 8GB RAM
SOFTWARE REQUIREMENTS
• PYTHON(V3.9): LANGUAGE IN WHICH CODE IS WRITTEN
• CMAKE(V3.25.2): FOR COMPILING OPENCV
• VISUAL STUDIO CODE: FOR BUILDING OPENCV AND DARKNET CODE
• NVIDIA GPU DRIVER: FOR FASTER GPU PERFORMANCE
• CUDA(V12.0): FOR PARALLEL COMPUTING USING GPU
• CUDNN(8.8.0): A GPU-ACCELERATED LIBRARY OF PRIMITIVES FOR DEEP NEURAL
NETWORKS
• OPENCV(V4.7.0): FOR WORKING ON IMAGES/ VIDEOS IN PYTHON
CSIT-
10
Literature Review
Literature Review
6
SYSTEM OVER ALL
ARCHITECTURE
CSIT-
10
8
DATA FLOW
DIAGRAM
CSIT-
10
USE CASE
DIAGRAM
CSIT- 7
10
9
FLOW CHART
CSIT-
10
Activity Trace Diagram
Class Diagram
Collabration Diagram
E.R Diagram
OBJECT
DETECTION VEHICLE COUNTER
CSIT- 10
10
PERSON DETECTION
11
METHODOLGIES USED
While Talking About Methodology, It Divided As Per The
Modules
1. WEB GUI
• HTML5, CSS3
• Flask
• PYTHON
2. TECHNOLOGIES
Y.O.L.O V3
CSIT-
10
12
GANTT
CHART
2n 3rd 4t
8/9 /2 023 d18/1 0/2 023 11/12/2023 h04/04/2024
CSIT-
10
CONCLUSIO
N
In conclusion, our machine learning-based surveillance projec
demonstrates video the potential security t
monitoring. for revolutionizing
harnessing and real-timesafet
advanced algorithms and
By data effectively detects falls, crashes, and ycrowd
analysis, the system
anomalies. It offers a proactive approach to security and provides
actionable insights for prompt responses. As technology continues to
advance, this project showcases the promising future of intelligent
surveillance systems, contributing to enhanced security across diverse
domains and applications.
CSIT- 13
10
14
REFERENCES
1. Arunnehru J, Chamundeeswari G, Prasanna Bharathi S. Human action recognition
using 3D convolutional neural networks with 3D motion cuboids in surveillance
videos. Procedia Comput Sci. 2018;133:471–7 (ISSN 1877-0509). 4
2. Li Y. A deep spatiotemporal perspective for understanding crowd behavior. IEEE Trans Multimedia.
2018;20(12):3289–97
3. Min W, Yao L, Lin Z, Liu L. Support vector machine approach to fall recognition based on simplified
expression of human skeleton action and fast detection of start key frame using torso angle. IET
Comput Vision. 2018
4. Min W, Yao L, Lin Z, Liu L. Support vector machine approach to fall recognition based on simplified
expression of human skeleton action and fast detection of start key frame using torso angle. IET
Comput Vision. 2018;12(8):1133–40.
CSIT-
10
15
REFERENCES
5. Ching-Kai Huang and Tsuhan Chen, “Motion Activated Video Surveillance Using TI DSP”, DSPS
FEST
'99, Houston, Texas, August 4-6, 1999
6. K. Srinivasan K. Porkumaran, G. Sainarayanan, “Intelligent human body tracking, modeling, and
activity analysis of video surveillance system: A survey”, Journal of Convergence in Engineering,
Technology and Science Vol.1 December 2009, pp. 1-4
7. Yigithan Dedeoglu, “Moving Object Detection, Tracking And Classification For Smart
Video
Surveillance” 2004.
CSIT-
10
CSIT- 16
10
