VISVESVARAYA TECHNOLOGICAL UNIVERSITY

Belgavi-590018

Project On

“Pothole and speed bump detection”

Submitted in partial fulfilment of the requirements for the award ofdegree of

BACHELOR OF ENGINEERING
In
ARTIFICIAL INTELLIGENCE AND DATA SCIENCE ENGINEERING

Subject: Software Engineering and Project Management.

Submitted By

Manoj s 1EP22AD033
Ganesh 1EP22AD018
Tejas KN 1EP22AD061

Semester and Section: 5rd Semester and Section “A”

Under the Guidance Of

Prof. Anand
Head Of Department

Department of Artificial Intelligence and Data Science Engineering

Approved by AICTE New Delhi | Affiliated to VTU, Belagavi,
Virgo Nagar, Bengaluru-560049

1|Page
 TABLE OF CONTENTS:

1. INTRODUCTION ………………………………………………. 3

2. SYSTEM REQUIREMENTS SPECIFICATIONS (SRS) ……. 4

3. DESIGNING DIAGRAMS BY USING AGILE TOOLS ……... 5

✓ SYSTEM ARCHITECTURE.

✓ CLASS DIAGRAM.

✓ USE CASE DIAGRAM.

✓ DATA FLOW DIAGRAM.

✓ STATE ACTIVITY DIAGRAM.

✓ SEQUENCE DIAGRAM.

4. CONCLUSION & REFERENCES …………………………… 11

2|Page
 INTRODUCTION:

Road conditions significantly impact driving safety, vehicle performance, and

overall commuting efficiency. Potholes and speed bumps are common road
surface anomalies that require timely detection to prevent accidents, enhance
vehicle longevity, and ensure a smooth driving experience.

Traditional methods for road condition monitoring involve manual inspections,

which are labor-intensive, time-consuming, and prone to inaccuracies. This
project aims to address these challenges by developing an automated system for
detecting potholes, speed bumps, and normal road conditions using image
processing and machine learning techniques.

The proposed system utilizes a dataset of road images categorized into three
classes: potholes, speed bumps, and normal roads. These images are preprocessed
through resizing, grayscale conversion, and flattening to ensure compatibility
with the machine learning model. A Random Forest Classifier is employed to
train and predict road conditions with high accuracy. The system is designed to
analyze road images in real-time and provide actionable insights to drivers and
maintenance authorities. Additionally, the project integrates a text-to-speech
(TTS) feature to deliver audio alerts, enhancing usability and real-time
application. For instance, the system can alert drivers about approaching speed
bumps or potholes, thereby enabling proactive safety measures.

This solution demonstrates a scalable and efficient approach to road surface

monitoring, with potential applications in autonomous vehicles, smart
transportation systems, and road infrastructure management. The use of advanced
machine learning techniques ensures reliability and robustness, making it a
promising tool for improving road safety and maintenance.

3|Page
 SYSTEM REQUIREMENTS SPECIFICATIONS:

This SRS document outlines the functional and non-functional requirements for the pothole
and speedbump detection:

• Product Perspective: The system will integrate with existing images systems and
software environments to detect and analyse road condition.

• Product Functions: The system will capture images, preprocess them, detect speedbump
or pothole or normal roads.
• User Characteristics: Users include researchers, developers, and end-users in various
applications like healthcare, marketing, and security.

• Constraints: Limited by the available datasets, processing power, and current neural
network capabilities.

• Assumptions and Dependencies: Assumes the availability of labelled datasets and

adequate computational resources.

Functional Requirements:
o Image capturing and preprocessing
o Pothole or Speedbump detection
o Road classification

Non-Functional Requirements:
o Performance: Real-time processing with high accuracy
o Reliability: Consistent and accurate emotion detection
o Security: Ensure data privacy and secure processing

4|Page
SYSTEM ARCHITECTURE:
The System Architecture diagram provides a high-level overview of the pothole and
speedbump detection system. It illustrates the main components, including the user interface,
the pothole detection system, the neural network model, and the pothole speedbump image
database. This diagram helps in understanding how different parts of the system interact with
each other to achieve the desired functionality.

5|Page
CLASS DIAGRAM:

The Class Diagram represents the structure of the system by showing its classes, attributes,
methods, and relationships. In this context, it includes classes like pothole Image, speedbump
and normal image Detector. The diagram helps in visualizing the object-oriented design and
understanding how data is encapsulated and manipulated within the system.

6|Page
USE CASE DIAGRAM:

The Use Case Diagram captures the interactions between users and the system. It highlights
the primary use cases such as capturing an image and analyzing data, and shows the roles of
actors (e.g., users) in these processes. This diagram is essential for identifying user
requirements and ensuring that the system meets the intended use cases.

7|Page
DATA FLOW DIAGRAM:

The Data Flow Diagram (DFD) depicts how data moves through the system, from capturing an
image to displaying the pothole and speedbump detection results. It includes processes such as
image preprocessing and dataset detection. This diagram is crucial for understanding the flow
of information and pinpointing where data transformations occur within the system.

8|Page
STATE ACTIVITY DIAGRAM:

The State Activity Diagram illustrates the various states the system can be in and the transitions
between these states. For example, states might include capturing an image, preprocessing the
image, detecting pothole , and displaying results. This diagram helps in understanding the
dynamic behavior of the system and its response to different events.

9|Page
SEQUENCE DIAGRAM:

The Sequence Diagram shows the sequence of interactions between different components of
the system over time. It details the order of operations, such as capturing an image,
preprocessing it, detecting pothole , and returning the result to the user. This diagram is useful
for visualizing the flow of control and data in a specific use case.

10 | P a g e
CONCLUSION:

In this project, an automated system for detecting potholes, speed bumps, and
normal road conditions was successfully developed using image processing and
machine learning techniques. The system utilized a Random Forest Classifier to
classify road images into three categories, achieving an accuracy of 85% with
balanced precision, recall, and F1-scores across the three classes.

The integration of a text-to-speech (TTS) module further enhanced the system's

functionality by providing real-time audio feedback to users, such as alerts for
approaching potholes or speed bumps. This system offers a practical solution for
enhancing road safety by providing early warnings to drivers, thus improving
driving comfort and reducing the risk of accidents caused by road anomalies.

The model's overall performance demonstrates its potential to be deployed in real

world applications, such as in autonomous vehicles, smart city infrastructure, and
road maintenance systems. The system’s use of machine learning ensures that it
can be easily updated and scaled, making it a promising tool for ongoing road
condition monitoring.

11 | P a g e
REFERENCES:
Image Processing Techniques He, K., Zhang, X., Ren, S., & Sun, J. (2014). Spatial pyramid
pooling in deep convolutional networks for visual recognition. In IEEE Transactions on Pattern
Analysis and Machine Intelligence, 37(9), 1904-1916. .

Machine Learning for Road Condition Classification Breiman, L. (2001). Random forests. In
Machine Learning, 45(1), 5-32.

Hybrid Approaches for Road Anomaly Detection Zhang, X., Li, Y., & Guo, Y. (2020). A
hybrid approach for pothole detection using image processing and machine learning. In Journal
of Transportation Engineering, Part A: Systems, 146(4), 04020029.

Text-to-Speech for Driver Assistance Systems Shneiderman, B. (2013). Designing the User
Interface: Strategies for Effective Human-Computer Interaction (5th ed.). Pearson Education.
Real-Time Anomaly Detection in Road Systems Eriksson, J., & Lippiello, V. (2008). Real-
time road anomaly detection using sensor fusion and machine learning. In Proceedings of the
16th International IEEE Conference on Intelligent Transportation Systems, 32-37

12 | P a g e
AGILE SCRUM: JIRA

1. Introduction to Agile and Scrum

• Agile Principles: Agile is a project management methodology focused on iterative

development, collaboration, and flexibility to adapt to changes. It promotes
delivering small, functional increments of a project rather than a complete product
at once.
• Scrum Framework: Scrum is a subset of Agile. It uses fixed-length iterations called
sprints to complete project increments. It emphasizes teamwork, accountability,
and continuous progress.

2. Roles in Scrum:

• Product Owner: Defines and prioritizes the work (backlog).

• Scrum Master: Facilitates the Scrum process, removes obstacles, and ensures
adherence to Agile principles.
• Development Team: Executes the tasks and delivers the work increments.
• Scrum Events: Sprint Planning, Daily Stand-up, Sprint Review, and Sprint
Retrospective ensure structured progress and continuous improvement.

3. Project Setup in JIRA

• Creating a Project: Step-by-step instructions on initiating a new project in JIRA and

selecting the appropriate template (Scrum for iterative processes).
• Configuration: Aligning the project settings with Scrum practices, including
workflows, permissions, and roles.

4. Creating and Managing Backlogs

• Product Backlog Creation: Adding and organizing tasks or features in the backlog
based on priority.
• Breaking Down Epics: Dividing larger tasks (epics) into manageable user stories or
tasks to facilitate sprint planning.
• Backlog Grooming: Regularly reviewing and refining the backlog to keep it
relevant and actionable.

1|Page
 5. print Planning and Execution

• Sprint Setup: Creating a sprint in JIRA by selecting backlog items to work on

during the sprint duration.
• Assigning Tasks: Allocating tasks to team members based on their skills and
availability.
• Tracking Progress: Using visual boards (e.g., Scrum boards) in JIRA to monitor
task status, from “To Do” to “Done.”

6. Sprint Review and Retrospective

• Sprint Review: A meeting to present completed work to stakeholders for feedback.

• Sprint Retrospective: A session to reflect on what went well, what didn’t, and how
to improve processes for the next sprint.

BENEFITS

• Improved Collaboration and Communication: The structured framework of Agile

and Scrum, combined with JIRA's collaborative tools, enhances teamwork and
ensures transparency within the team.
• Streamlined Workflow Management: JIRA helps in visualizing the project's
progress through boards and charts, making it easier to manage sprints and
workflows effectively.
• Better Project Organization: Scrum’s defined roles and artifacts, integrated into
JIRA, help in maintaining a clear hierarchy of tasks, priorities, and responsibilities.

CONCLUSION

This comprehensive framework enables teams to adapt to changing requirements, foster

transparency, and maintain accountability. Ultimately, the combination of Agile, Scrum, and
JIRA empowers teams to achieve better productivity, continuous improvement, and successful
project delivery.

2|Page
AGILE SCRUM: JIRA TOOL

1. INTRODUCTION TO JIRA TOOL

• Definition: Jira is a versatile project management tool created by Atlassian.

• Primary Purpose: Initially designed for tracking software bugs and issues, it
now supports Agile methodologies (e.g., Scrum and Kanban) and various
project management activities.

2. KEY FEATURES

• Issue Tracking: Allows teams to create, assign, and monitor tasks or issues
throughout their lifecycle.
• Agile Boards: Provides Scrum and Kanban boards for visual workflow
management.
• Custom Workflows: Enables customization of workflows to fit specific team
processes.
• Reporting: Offers various reports and analytics, such as burn-down charts and
velocity reports, to track progress and performance.

3. USE CASES

• Software development teams use Jira for Agile project management.

• IT and business teams use it for issue tracking, task management, and roadmap
planning.
• Allows teams to plan and prioritize their upcoming work effectively.
• Plan and execute marketing campaigns with clear tasks, deadlines,
and deliverables.
• Continuous integration and deployment pipelines with seamless collaboration
between developers, testers, and operations.
• Offers insightful reports like burn-down charts, velocity charts,
and sprint reports.
• Integrates with numerous tools (e.g., Confluence, Slack, GitHub, Bitbucket).

3|Page
BENEFITS

• Enhanced Collaboration: Centralizes project information, facilitating better

communication among team members.
• Improved Productivity: Streamlines processes and automates repetitive tasks, allowing
teams to focus on critical work.
• Flexibility: Adaptable to various project types and team sizes, with customizable
workflows and fields.
• Transparency: Provides real-time visibility into project status, helping stakeholders
stay informed.

CONCLUSION

Jira is a robust tool that supports efficient project management and agile practices. Its
comprehensive features and adaptability make it a preferred choice for teams aiming to
enhance productivity and collaboration.

4|Page