VNR Vignana Jyothi Institute of Engineering and Technology

(Affiliated to J.N.T.U, Hyderabad)

Bachupally(v), Hyderabad, Telangana, India

CRIME DETECTION SYSTEM

A course project submitted in complete requirements for the award of the degree of

BACHELOR OF TECHNOLOGY

IN

COMPUTER SCIENCE AND ENGINEERING -

ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING

Submitted By

A. K. Ram Mohan 22071A6667

Ch. Prateeka 22071A6677
G. Dharaneesh 22071A6683
J.V.S. Chandradithya 22071A6688
J. Oliviya 22071A6692
K. Rutvik 22071A6698

Under the Guidance of

Ms. V. Manjula (Assistant Proffesor)

Department of Computer Science and Engineering

Artificial Intelligence and Machine Learning & Internet of Things
VNR Vignana Jyothi Institute of Engineering and Technology
(Affiliated to J.N.T.U, Hyderabad)
Bachupally(v), Hyderabad, Telangana, India

CERTIFICATE

This is to certify that 22071A6667, 22071A6677, 22071A6683, 22071A6688,

22071A6692, 22071A6698 have completed their course project work at CSE-AIML
Department of VNR VJIET, Hyderabad entitled "CRIME DETECTION SYSTEM"
in complete fulfilment of the requirements for the award of B.Tech degree during the
academic year 2023-2024. This work is carried out under my supervision and has not
been submitted to any other University/Institute for award of any degree/diploma.

Ms. V.Manjula Dr. N. Sandhya

Assistant Proffesor Head of The Department
Dept of CSE - AIML & IoT Dept of CSE - AIML & IoT
VNR VJIET VNR VJIET
 DECLARATION

This is to certify that our project report titled “ CRIME DETECTION SYSTEM "
submitted to Vallurupalli Nageswara Rao Vignana Jyothi Institute of Engineering and
Technology in complete fulfilment of requirement for the award of Bachelor of
Technology in Computer Science and Engineering – Internet of Things is a bona fide
report to the work carried out by us under the guidance and supervision of
Ms.V.Manjula, Assistant Professor, Department of Computer Science and
Engineering – AIML&IoT, Vallurupalli Nageswara Rao Vignana Jyothi Institute of
Engineering and Technology. To the best of our knowledge, this has not been
submitted in any form to other university or institution for the award of any degree or
diploma
 ACKNOWLEDGEMENT

Over a span of two years, VNRVJIET has helped us transform ourselves from mere
amateurs in the field of Computer Science into skilled engineers capable of handling
any given situation in real time. We are highly indebted to the institute for everything
that it has given us. We would like to express our gratitude towards the principal of
our institute, Dr. Challa Dhanunjaya Naidu and the Head of the Computer Science
& Engineering – AIML & IoT Department, Dr.N.Sandhya for their kind co-
operation and encouragement which helped us complete the project in the stipulated
time. Although we have spent a lot of time and put in a lot effort into this project, it
would not have been possible without the motivating support and help of our project
guide Ms V. Manjula. We thank for her guidance, constant supervision and for
providing necessary information to complete this project. Our thanks and
appreciations also go to all the faculty members, staff members of VNRVJIET, and
all our friends who have helped us put this project together
 INDEX

Problem Statement.............................................................................6

SRS Document.................................................................................... 7

System Design....................................................................................11

Testing............................................................................................... 20

Conclusion......................................................................................... 21

References......................................................................................... 26
Problem Statement for Crime Detection System Using Live
Video Feed from CCTV Cameras
Background:

Crime detection systems are essential tools for maintaining public safety and security. CCTV
cameras are widely used for surveillance in various public and private spaces, providing real-time
monitoring capabilities. However, the manual monitoring of these video feeds is labor-intensive and
prone to human error. With advancements in artificial intelligence and machine learning, there is a
significant opportunity to develop an automated crime detection system that utilizes live video feeds
from CCTV cameras to identify and alert authorities of suspicious activities in real-time.

Objective:

To design and develop an intelligent, scalable, and real-time crime detection system that leverages
live video feeds from CCTV cameras. This system aims to automatically detect and report suspicious
activities, enhancing the effectiveness of surveillance efforts and improving public safety.
 Software Requirements Specification (SRS)

CRIME DETECTION SYSTEM

1. Introduction

1.1 Purpose

The purpose of this document is to define the requirements for the Crime
Detection System Using Live Video Feed from CCTV Cameras. This
document will provide a detailed description of the system's functionality,
user interface, and overall performance.

1.2 Scope

The Crime Detection System will enable real-time monitoring and

automated detection of suspicious activities using live video feeds from
CCTV cameras. The system will be accessible via web and mobile
applications for security personnel.

1.3 Definitions, Acronyms, and Abbreviations

- CDS: Crime Detection System

- CCTV: Closed-Circuit Television
- AI: Artificial Intelligence
- UI: User Interface

2. Overall Description

2.1 Product Perspective

The CDS is a standalone system designed to be user-friendly and scalable.

It interfaces with existing CCTV camera infrastructure and security alert
systems.
 2.2 Product Functions

- Real-time monitoring of live video feeds

- Automated detection of suspicious activities
- Immediate alert notifications to security personnel
- Review and management of detected incidents
- Analytical tools for security trends and performance

2.3 User Classes and Characteristics

- Security Personnel: Users who monitor live feeds and respond to alerts
- Administrators: Users who manage system settings, user accounts, and
camera feeds
- Investigators: Users who review recorded incidents and analyze data

2.4 Operating Environment

The system will operate on modern web browsers (Chrome, Firefox, Safari)
and mobile operating systems (iOS, Android).

2.5 Design and Implementation Constraints

- The system must comply with privacy laws and regulations.

- The system must integrate with existing CCTV camera networks and
security infrastructure.

2.6 Assumptions and Dependencies

- Reliable internet connectivity is assumed for users.

- Dependency on external services for video storage and alert notifications.
3. Specific Requirements

3.1 Functional Requirements

3.1.1 User Registration and Authentication

- Users must be able to register and log in to the system.

- Users must be able to reset their passwords.

3.1.2 Real-Time Monitoring

- The system must continuously monitor live video feeds from multiple
CCTV cameras.
- Users must be able to view live feeds from selected cameras.

3.1.3 Automated Detection

- The system must use AI algorithms to detect suspicious activities.

- The system must log detected incidents with timestamps and camera
details.

3.1.4 Alert Notifications

- The system must send immediate alerts to designated security personnel

upon detection of suspicious activities.
- Alerts must be sent via multiple channels (e.g., email, SMS, push
notifications).

3.1.5 Incident Management

- Users must be able to review and manage detected incidents.

- Users must be able to add notes and classify the incidents.

3.2 Non-Functional Requirements

3.2.1 Performance
- The system should support a minimum of 5,000 concurrent camera feeds.
- Alerts should be generated within 2 seconds of detecting suspicious
activity.

3.2.2 Reliability

- The system should have an uptime of 99.9%.

3.2.3 Usability

- The system should have an intuitive and easy-to-navigate interface.

- Users should be able to review an incident in less than 2 minutes.

3.3 External Interface Requirements

3.3.1 User Interfaces

- Web-based user interface compatible with major browsers.

- Mobile application interface for iOS and Android.

3.3.2 Hardware Interfaces

- The system must be compatible with standard CCTV cameras and

networking equipment.

3.3.3 Software Interfaces

- Integration with video storage systems for archiving footage.

- Integration with alert notification systems for real-time alerts.

3.4 System Features

3.4.1 Analytical Tools

- Users should be able to generate reports on security trends and system

performance.
 3.4.2 Customizable Alerts

- Users should be able to configure alert criteria and notification settings.

4. Other Requirements

4.1 Performance Requirements

The system should be able to handle peak loads during high traffic periods
without performance degradation.

4.2 Safety Requirements

The system must comply with safety standards for data handling and
storage.

4.3 Security Requirements

- The system must use encryption for data transmission.

- The system must comply with GDPR for user data protection.

4.4 Software Quality Attributes

- Maintainability The system should be designed for easy updates and

maintenance.
- Scalability: The system should be scalable to accommodate future
growth.

4.5 Business Rules

- All detected incidents must be logged and stored for a minimum of 6

months.
- Users must agree to the terms and conditions before accessing the system.
SYSTEM DESIGN

UML: Unified Modeling Language (UML) is a general-purpose modeling language.

The main aim of UML is to define a standard way to visualize the way a system has
been designed. It is quite similar to blueprints used in other fields of engineering.
UML is not a programming language; it is rather a visual language.

UML diagrams are classified into two types:

1. Structural Diagrams
1.1. Class diagram
1.2. Component diagram
1.3. Deployment diagram
2. Behavioral Diagrams
2.1. Use case diagram
2.2. Sequence diagram
2.3. Communication diagram
2.4. Activity diagram
2.5. Statechart diagram
1. Structural Diagrams

1.1. Class diagram:

A class diagram is a diagram that shows a set of classes, interfaces, and
collaborations and their relationships.

Class diagram commonly contain the following things:

 Classes
 Interfaces
 Collaborations
 Dependency, generalization and association relationships
1.2. Component diagram:
Component diagrams are used to model the physical aspects of a system. Physical
aspects are the elements such as executables, libraries, files, documents, etc. which
reside in a node. Component diagrams are used to visualize the organization and
relationships among components in a system.

Component diagram commonly contain:

 Components
 Interfaces
 Relationships
1.3. Deployment diagram:
The deployment diagram is mostly employed by network engineers, system
administrators, etc. with the purpose of representing the deployment of software on
the hardware system. It envisions the interaction of the software with the hardware
to accomplish the execution. The selected hardware must be of good quality so that
the software can work more efficiently at a faster rate by producing accurate results
in no time.

The deployment diagram consists of the following notations:

 A component
 An artifact
 An interface
 A node
2. Behavioral Diagrams

2.1. Use Case diagram:

A use case diagram is a diagram that shows a set of use cases and actors and their
relationships.

Use case diagrams commonly contain:

 Use cases
 Actors
 Dependency, generalization, and association relationships
2.2. Sequence diagram:
A sequence diagram emphasizes the time ordering of messages. Sequence diagram is
formed by first placing the objects that participate in the interaction at the top of
your diagram, across the X axis. Typically, you place the object that initiates the
interaction at the left, and increasingly more subordinate objects to the right. Next,
you place the messages that these objects send and
receive along the Y axis, in order of increasing time from top to bottom. This gives the
reader a clear visual cue to the flow of control over time.

Sequence diagrams commonly contain:

 Objects
 Links
Messages
2.3. Communication diagram:
The collaborations are used when it is essential to depict the relationship between
the object. Both the sequence and communication diagrams represent the same
information, but the way of portraying it quite different. The communication
diagrams are best suited for analyzing use cases.

Communication diagrams commonly contain:

 Objects
 Associations
 Messages
2.4. Activity diagram:
An activity diagram shows the flow from activity to activity. An activity is an ongoing
non atomic execution within a state machine. Activities ultimately result in some
action, which is made up of executable atomic computations that result in a change
in state of the system or the return of a value. Actions encompass calling another
operation, sending a signal, creating or destroying an object, or some pure
computation, such as evaluating an expression. Graphically, an activity diagram is a
collection of vertices and arcs.

Activity diagrams commonly contain:

 Activity states and action states
 Transitions
 Objects
2.5. Statechart diagram:
The statechart diagram implements the real-world models as well as the object-
oriented systems. It records the dynamic behavior of the system, which is used to
differentiate between the dynamic and static behavior of a system.

Statechart diagrams commonly contain:

 States
 Transitions
Events and Action
TESTING

Test Cases :
TEST CASE ID DESCRIPTION EXPECTED OUTCOME PASS/FAIL
User Registration Successful creation of user Successful creation
accounts with secure storage of user accounts with
TC001
of credentials and verification verified credentials
of user identity.
User Login Secure authentication process Secure authentication
ensuring only authorized with logged attempts
TC002
users access the system with
logged login attempts.
Live Feed Real-time monitoring and Real-time monitoring
Montoring analysis of incoming data and analysis of data
TC003
feeds for immediate insights feeds
and actions.
Automated Automated recognition of Automated
Detection patterns or anomalies to recognition of
TC004
trigger timely responses and patterns or anomalies
actions.
Alert Notifications Timely and accurate alerts to Timely and accurate
relevant stakeholders based alerts to stakeholders
TC005
on detected events or
anomalies.
Incident Review Comprehensive review and Comprehensive
analysis of incidents for analysis and
TC006
accurate assessment and assessment of
follow-up actions incidents
Incident Effective handling and Effective handling
Management resolution of incidents and resolution of
TC007
through structured workflows incidents
and timely responses
Report Generation Generation of detailed and Detailed and
TC008 actionable reports based on actionable reports
monitored data and incidents. generated
CONCLUSION

Crime detection through CCTV cameras developed for police involves advanced
technology that enhances public safety and law enforcement capabilities. These
systems are designed to monitor public spaces, identify criminal activities in real-time,
and trigger alerts to law enforcement agencies. By leveraging machine learning
algorithms and computer vision, CCTV systems can autonomously detect suspicious
behaviors such as theft, vandalism, or violence, thereby enabling proactive response
measures. This proactive approach not only aids in crime prevention but also
facilitates quicker apprehension of perpetrators, ultimately contributing to a safer
community environment.
REFERENCES

1) Smith, J. (2020). "Advancements in CCTV Technology for Law Enforcement."

Police Technology Journal.

2) Johnson, R. (2019). "Machine Learning Applications in Crime Detection."

International Journal of Law Enforcement Technology.

3) Anderson, M. (2021). "Real-time Surveillance Systems for Public Safety."

Journal of Public Safety Technology.

4) Brown, A. et al. (2018). "Computer Vision in Crime Prevention." Proceedings

of the International Conference on Cyber Security and Protection.

5) Davis, S. (2022). "Artificial Intelligence in Policing: Enhancing Surveillance

Capabilities." Journal of Law and Technology.