PROJECT NAME: Helmet Safety Detector

SCHOOL NAME: Viraj International School

YEAR/CLASS: 2024-25 / Grade XII

TEACHER NAME: Mr. Yogesh Mishra

TEACHER EMAIL: [email protected]

TEAM MEMBER NAMES AND GRADES:

1. Aditya Singh Rathore

2. Ayush Shetty

3. Darsh Kalpesh Prajapati

4. Rishika Rahul Chaudhary

1. Introduction

1
Our team focuses on various sectors of society to solve their problems and
provide the best solutions. The project name is helmet safety detector. It is in
high demand to use it on a regular basis and it is still essential in many places.
Also, it is important to spread awareness about wearing a helmet and seat belt
while driving.

As students and citizens of this society, we are responsible for the upcoming
future and for that, we have come up with something that will be resourceful
for the society and economy.

2. Team Roles

2
2.1 Who is in your team and what are their roles?

Role Role description Team Member

Name

● Schedules and allocates tasks among the team

● Ensures tasks are completed on time
Project Leader ● Acts as the point of contact between the team
and the teacher, users and stakeholders
Aditya Rathore
● Resolves team issues

● Decide on type of data needed to train an AI

model
● Collects data
● Ensures data is in a format that the team can
Data Expert work with
● Ensures data is ethically sourced and unfair bias Darsh Prajapati
is eliminated  Works with prototype builder
to train the AI model

● Collects questions from the team that need

answers
● Identifies where answers can be located
Information (source) Rishika Rahul
Researcher
● Searches for answers, writes up a report and Chaudhary
passes information to the project reporter

● Works with the team and the user to create a

process flow for the new user experience
Rishika Rahul
● Plans the user interface for the prototype Chaudhary
Designer

● Works with data expert to train/teach

computer
● Creates the prototype and codes if necessary
Prototype
Builder Darsh Prajapati

3
 ● Works with users to tests the prototype
● Gets feedback from users and user sign-off
when they prototype has met user requirements
Tester Ayush Shetty
● Creates an action plan on what needs to be fixed
and prioritises requests for future
improvements

● Collates the team Project Logbook submission

and creates the content for the video pitch
Marketing/ Aditya Rathore
Communicatio ● Selects spokespeople within the team for
ns leader various matters relating to the project

● Films the activities of the team and edits these

into a presentation for submission
Video
producer Ayush Shetty

2.2 Project plan

The following table is a guide for your project plan. You may use this or create your own
version using a spreadsheet which you can paste into this section. You can expand the
‘Notes’ section to add reminders, things that you need to follow up on, problems that need to
be fixed urgently, etc.

Phase Task Planned Planne Planned Actual Actual Actual Who is Notes/Remarks
d end duration start end date duration responsible
start date (hours, date (hours,
date minutes) minutes)

Preparing for Coursework,

the project readings

Set up a
team folder
on a shared
drive

Defining the Background

problem reading

Research
issues in our
community

Team

meeting to
discuss
issues and

4
 select an
issue for the
project

Complete

section 3 of
the Project

Logbook

Rate
yourselves

Understandin Identify
g the users users

Meeting with
users to
observe
them

Interview
with user (1)

Interview
with user
(2), etc…

Complete

section 4 of
the Project
Logbook

Rate
yourselves

Brainstorming Team

meeting to
generate
ideas for a
solution

Complete

section 5 of
the Project

Logbook

Rate
yourselves

Designing Team
your solution
meeting to
design the
solution

Complete

section 6 of
the logbook

Rate
yourselves

Collecting and Team

preparing data
meeting to
discuss data

5
 requirement
s

Collecting and Data

preparing data collection
Prototyping

Data
preparation
and labelling

Complete

Section 6 of
the Project
Logbook

Team

meeting to
plan
prototyping
phase

Prototyping Train your

Testing model with
input
dataset

Test your
model and
keep training
with more
data until you
think your
model is
accurate

Write a
program to

initiate
actions
based on the
result of your
model

Complete

section 8 of
the Project

Logbook

Rate
yourselves

Team

meeting to
discuss
testing
plan

Testing Invite users

Creating the to test your
video prototype

Conduct

testing with
users

Complete

6
 section 9 of

the Project

Logbook

Rate
yourselves

Team

meeting to
discuss
video
creation

Write your
script

Film your
video

Edit your
video

Completing Reflect on
the logbook the project

with your
team

Complete
sections 10
and 11 of the

Project

Logbook

Review
your Project
logbook
and video

Submission Submit your

entries on
the IBM

2.3 Communications plan

Will you meet face-to-face, online or a mixture of each to communicate?

- Yes, meeting face-to-face for regular meetings and updates on projects is quite
more frequent however, during weekends and holidays the team leader conducts
an online meet to assign work.

How often will you come together to share your progress?

- Twice a week to share the progress done so far, if an important and urgent task is
assigned then meeting right after its completion to implement other interrelated
activities.

Who will set up online documents and ensure that everyone is contributing?

7
 - Our team leader will prepare the online folder for data collected by information
researchers and data experts. Also, he makes sure that everyone is contributing
according to their role without delays.
-

What tools will you use for communication?

- Using google meet, zoom, email, social media to check on updates from other team
members.

2.4 Team meeting minutes (create one for each meeting held)

Date of meeting :8/7/24

attended: Aditya, Darsh, Rishika
Who wasn’t able to attend: Ayush

Purpose of meeting: Decide the agenda

Items discussed:
1. Topic
2. Project requirement
3. Data sources

Things to do (what, by whom, by when)

1. Preparation of data sources and information by the information researcher
2. Assigning tasks for data expert and prototype builder by the team leader
3. Start making the project logbook according to team leader’s instructions.

8
Date of meeting :9/9/24
attended: Aditya, Darsh, Rishika
Who wasn’t able to attend: Ayush

Purpose of meeting: Discussion on the elements of project logbook

Items discussed:
1. Problem Definition
2. Empathy map
3. Progress update

Things to do (what, by whom, by when)

1. Preparation for prototype interface for user.
2. Discussion on various matters related to marketing.
3. Video producing

9
3. Problem Definition
3.1 List important local issues faced by your school or community

● Increased death rate due to health hazards and diseases.

● poverty and unemployment due to less opportunity for a large population.
● weak education sector, low literacy rate which also leads to unemployment and puts
a setback for the society and economy.
● Gender inequality, many perks of living are not provided the same for all genders.
● Some set of work and sectors are discouraged or unrecognized by the economy and
government.
● Corruption and scams, leads to inequality for the general public.
● Lack of facilities for weaker sections, different age categories, economically weak
people, illiterates and many more groups of people.
● ill-treatment of animals, lack of animal shelters, excessive animal husbandry,
insufficient animal doctors and keepers.
● Increase in accidents due to lack of road safety.

3.2 Which issues matter to you and why?

● Health issues faced by different generations whether young or old, as they may
contribute less towards the society.
● Weak education system and illiteracy of the population which becomes a root cause for
various other problems faced in an economy.
● Lack of facilities for weaker section and older age groups as they may have potential to
work and earn but are not given an opportunity to do so.
● Youngsters dying at a young age due to carelessness.
● Ignorance of rules, regulations and laws made by the government for road safety.

10
3.3 Which issue will you focus on?

Many youngsters nowadays are being careless by making mistakes which can endanger their life.
These mistakes include not wearing a helmet, which is a major issue for accidents these days.

3.4 Write your team’s problem statement in the format below.

How can we help DRIVERS find a way to WEAR HELMETS so that they can STAY SAFE
AND SPREAD AWARENESS FOR ROAD SAFETY

11
4. The Users
4.1 Who are the users and how are they affected by the problem?

TWO WHEELER DRIVERS -Many times among such drivers there are youngsters and careless
men who are not realizing the value of their life and endangering their life by not wearing a
helmet for their comfort.
Road accidents are very common and in such cases not wearing a helmet can put the person
under the worst circumstances.

TRAFFIC POLICE - It also becomes and essential tool for traffic police to handle on road
vehicles along with reducing their work of fining the rule violators. As the system will detect
the people not wearing helmets. It is not only a tool to teach the motorbike drivers but also
reduce the burden of traffic officers.

4.2 What have you actually observed about the users and how the problem affects
them?

Observing people riding without helmets highlights a critical safety issue that can lead to
severe consequences. Helmets are proven to reduce the risk of head injuries and fatalities in
road accidents, yet many individuals avoid wearing them due to perceived discomfort, style
preferences, or a lack of awareness about their importance. This negligence endangers not
only the riders themselves but also impacts families and the wider community, as head
injuries often lead to long-term disabilities, requiring extensive medical care and
rehabilitation. Additionally, the financial burden on healthcare systems rises significantly with
each preventable injury. Raising public awareness, improving helmet comfort and design, and
enforcing helmet laws could foster a stronger culture of road safety, ultimately saving lives
and reducing the strain on medical resources.

Traffic police face too many responsibilities, managing road safety, laws, and maintaining
order in busy streets. They often handle multiple tasks, from directing traffic to addressing
accidents and ensuring regular updates with traffic regulations. One of the biggest challenges
they face is drivers who ignore safety measures like wearing helmets. These individuals put
themselves at significant risk, complicating the police’s job. Traffic officers must constantly
monitor for violations, conduct checks, and issue fines, all while ensuring public safety. The
disregard for helmet laws not only endangers lives but also increases the workload for traffic
police, making their job even more demanding.

12
4.3 Record your interview questions here as well as responses from users.

Here are six interview questions to gauge public opinion and awareness about the issue of
not wearing helmets while riding:

1. How often do you see people riding without helmets in your area, and why do you think
this happens?
2. Do you think wearing a helmet can significantly reduce the risk of serious injury in
accidents? Why or why not?
3. What, in your opinion, are the main reasons some people avoid wearing helmets while
riding?
4. Have you or someone you know experienced a situation where wearing a helmet made
a difference in an accident? Can you share more about it?
5. What would encourage more people to wear helmets? Do you think stricter laws, better
helmet designs, or awareness campaigns would help?
6. Do you believe it should be mandatory for all riders to wear helmets? How would you
feel about penalties for not wearing one?

13
 4.4 Empathy Map

Map what the users say, think, do and feel about the problem in this table

What our users are saying What our users thinking

"I don’t think "It’s just a "I’m invincible;

it’s necessary; I quick ride; I it won’t happen
ride slowly and won’t need to me."
only on local it for such a
"I’ve been
streets." short
riding for years
distance."
without a
helmet or seat "It’s just a quick
"Everyone else
belt and never ride; I won’t
around here had an need it for such a
rides without accident." short distance."
helmets or seat
belt, so I don’t
feel out of place."

What our users are doing How our users feel

14
Riding Aggressively:
Rebellion:
Ignoring Safety Guidelines:
Fear of Judgment:
Taking Risks:

Denial:
Resisting Authority:

Confidence:

4.5 What are the usual steps that users currently take related to the problem and
where are the difficulties?

Steps taken
1. Checking the Bike : Before starting, a rider ensures that the bike/car is in good working
condition, including checking tire pressure, fuel levels, brakes, and lights.

2. Wearing Protective Gear: Safety gear is essential, with the helmet being the most
crucial. Other protective items like gloves, jackets, and knee/elbow pads are also advisable
for safety.

3. Wearing the Helmet/Seat belt: The helmet is one of the most important protective
pieces, designed to protect the rider's head in case of accidents.

4.Road Hazards and Traffic Risks: Two-wheeler riders are highly vulnerable to road
conditions (potholes, debris) and risky driving behaviors from other road users (e.g., cars
cutting them off, poor visibility). Traffic congestion and the need to maneuver through
narrow gaps also pose significant challenges.

15
 5. Weather and Environmental Conditions: Riders must contend with extreme weather
conditions like rain (slippery roads), heat (discomfort from helmets), cold (reduced
mobility), and wind (which can destabilize the bike), all of which can affect safety and
comfort.

6. Safety and Vulnerability: Unlike cars, motorcycles offer little protection in crashes.
Riders are exposed to serious injuries in accidents and face additional risks like accidents
caused by lack of visibility and inadequate protective gear.

7. Maintenance and Physical Strain: Drivers require frequent maintenance (e.g., tire care,
oil changes), and long rides can cause physical discomfort, such as neck and back pain,
wrist fatigue, and overall strain.

4.6 Write your team’s problem statement in the format below.

__DRIVERS___ [a specific user or group of users]

are experiencing issues with ___ROAD ACCIDENTS___ [problem] today

because of ___NOT WEARING HELMET FOR SAFETY___ [cause]

16
5. Brainstorming
5.1 Ideas

How might you use the power of AI/machine learning to solve the users’ problem by
increasing their knowledge or improving their skills?

AI Idea #1 Conducting computer based programmes including animated videos to

showcase importance of road safety

AI Idea #2 Placing speed meter cameras that detect vehicles driving faster than speed
limit.

AI Idea #3 Building a program that detects whether two wheeler drivers are wearing safety
helmets or not.

17
 AI Idea #4 making drones to be used as traffic police at busy areas for reducing jams and
increasing time efficiency.

AI Idea #5 Generating an air traffic police that works faster and gives desirable results.

AI idea #6 Making a seat belt detector to ensure safety for drivers.

5.2 Priority Grid

Evaluate your five AI ideas based on value to users and ease of creation and
implementation.

High value to users, easy to create High value to users, hard to create

Making a seat
belt detector Generating air traffic
for safety. police and drones.

Making a seat belt

detector for safety.

18
Low value to users, Low value to users,
easy to create hard to create

Animated videos
telling traffic safety
importance.

Speed limit
cameras

19
5.3 Based on the priority grid, which AI solution is the best fit for your users and for
your team to create and implement?

Briefly summarize the idea for your solution in a few sentences and be sure to identify the
tool that you will use.

20
6. Design
6.1 What are the steps that users will now do using your AI solution to address the
problem?

1. Drivers of motorcycles or scooters would start checking if they and their passengers have
securely fastened their helmets before starting the engine, ensuring both are properly
adjusted.

2. In the case of motorcycle riders, they would make sure the helmet fits properly — no
loose straps, correct size, and snug on the head — to avoid detection alerts from the
helmet detector.

3. Drivers might remind passengers to buckle up or wear their helmets before the vehicle
starts moving, to prevent the detector system from issuing an alert or a warning..

4. Drivers would avoid trying to drive without the proper safety gear in place, as some
systems could prevent the bike from moving unless the helmet is detected as being worn.

5. If the helmet or detector is malfunctioning or gives false alarms, drivers may stop to
check the systems and ensure that the detectors are working properly. They may report it
to service centers if necessary.

6. Drivers may adapt their driving behavior to ensure that they always follow the rules about
safety gear, as violating helmet regulations could result in fines, points on a license, or
penalties.

21
 7. Drivers could take on the role of educating other road users about the importance of
wearing helmets, especially for passengers, so that everyone is more aware of the
detection systems and the potential consequences of not complying.

7. Data
7.1 What data will you need to train your AI solution?

To train a helmet detection AI, you'll need images with and without helmets, annotated with
bounding boxes and labels. Ensure diversity in environments, lighting, and poses for better
model accuracy.

7.2 Where or how will you source your data?

Where will the Do you have

Data data come permission to use Ethical
Who owns the
from? the data? considerations
needed data?

Avoid using
Public
Have Dataset owners Yes identifiable
datasets
personal data.

Ensure consent
Real-world Permission
Want/Need Collaborators/Yo and follow
images required
u privacy laws.

Reflect real-
Synthetic You/Software
Nice to have Yes world diversity
data tools owners
accurately.

22
8. Prototype
8.1 Which AI tool(s) will you use to build your prototype?

To build your helmet detection prototype, use YOLO or Faster R-CNN for object detection with
TensorFlow or PyTorch. Annotate data using LabelImg or Roboflow and train models in Google
Colab or Jupyter Notebook. Deploy with OpenCV or TensorFlow Lite for edge devices.

8.2 Which AI tool(s) will you use to build your solution?

1. TensorFlow/PyTorch: For training AI models.

2. OpenCV: For image/video processing.
3. Detectron2: For object detection with high performance.
4. YOLO: For real-time helmet detection.
5. LabelImg: For annotating your dataset.
6. TensorFlow Lite/ONNX: For deploying models on edge devices.

23
8.3 What decisions or outputs will your tool generate and what further action needs to
be taken after a decision is made?

1.Detect Helmet: Output if a helmet is worn. Action: Alert or log the result.
2 Confidence Level: Provide a confidence score. Action: Flag low-confidence results for review
or improve the model.
3 Bounding Box/Segmentation: Show detected helmets with a bounding box. Action: Use for
visualization or tracking.
4.Real-time Monitoring: Continuously detect helmets. Action: Trigger alerts or safety actions if
necessary.

9. Testing
9.1 Who are the users who tested the prototype?

1. Traffic Enforcement Authorities (Police)

● Role: Monitor and enforce road safety laws.

● Use: They can use helmet and seatbelt detectors as part of automated traffic
enforcement systems to identify non-compliance and issue fines or warnings.

2. Vehicle Manufacturers

● Role: Design and produce vehicles with built-in safety features.

● Use: Incorporate helmet and seatbelt detection technologies in vehicles (motorcycles,
cars, etc.) to ensure compliance with safety regulations and improve consumer safety.

3. Motorcycle Rental Services

● Role: Rent out motorcycles or scooters to customers.

● Use: Use helmet detectors to ensure that renters wear helmets before riding, which
helps reduce accidents and ensures safety compliance.

24
 4. Road Safety and Research Organizations

● Role: Conduct research and promote road safety awareness.

● Use: Collect data from helmet and seatbelt detection systems to analyze trends,
identify high-risk behaviors, and create better safety policies and awareness
campaigns.

5. Insurance Companies

● Role: Provide vehicle insurance coverage to individuals and businesses.

● Use: Use data from helmet and seatbelt detectors to assess risk, adjust premiums,
and incentivize safer driving behaviors through discounts or lower premiums for
compliant drivers.

6. Ride-Sharing Services (e.g., Uber, Lyft)

● Role: Offer ride-sharing and ride-hailing services.

● Use: Monitor and ensure that both drivers and passengers comply with safety
regulations, such as wearing seatbelts, for safer rides and to reduce liability in case of
accidents.

7. Vehicle Maintenance & Service Centers

● Role: Provide vehicle repair and maintenance services.

● Use: Detect any issues or malfunctions in helmet and seatbelt detection systems and
ensure they are working properly during routine inspections and maintenance.

8. Government Regulatory Bodies (Transport Authorities)

● Role: Set and enforce traffic laws and safety standards.

● Use: Implement regulations requiring helmet and seatbelt detectors in certain
vehicles, monitor their effectiveness in reducing accidents, and use data from
detectors to inform policy decisions.

9.2 List your observations of your users as they tested your solution.

25
 1.Ease of Use: Simple or complex navigation depending on the interface.
2.Accuracy: Missed detections or false positives in varying conditions.
3.Real-time Performance: Delays or lags with video processing.
4.Confidence Threshold: Confusion with low confidence scores.
5.User Interactions: Manual corrections or confirmations.
6.Alert Responses: Satisfaction or frustration with how alerts trigger.
7.Data Accuracy: Issues with specific helmet types or environments, suggesting model
improvements.

9.3 Complete the user feedback grid

26
 What works What needs to change

Questions? Ideas

9.4 Refining the prototype: Based on user testing, what needs to be acted on now so
that the prototype can be used?

27
 To refine your helmet detection prototype based on user testing:

1. Improve Accuracy: Address false positives/negatives and handle edge cases like poor
visibility or different helmet types.
2. Enhance Usability: Simplify the UI and ensure real-time processing meets user
expectations.
3. Expand Dataset: Include diverse helmet types, lighting conditions, and user scenarios
for better model generalization.

9.5 What improvements can be made later?

Future improvements could include:

1. Model Optimization: Enhance accuracy and speed.

2. Multi-object Detection: Improve handling of multiple helmets in complex scenes.
3. Contextual Awareness: Recognize when helmets are required.
4. Real-time Alerts: Add notifications for immediate action.
5. Cross-platform Support: Extend compatibility to mobile and edge devices.

10. Team collaboration

28
10.1 How did you actively work with others in your team and with stakeholders?

In your helmet detection project, actively working with your team and stakeholders can
involve:

1. Regular Communication: Hold frequent meetings to align on goals, progress, and

challenges. This ensures everyone is on the same page and can provide feedback.

2. Collaborative Development: Share responsibilities—such as data collection, model

training, and UI design—to leverage each team member's strengths.
3. Stakeholder Involvement: Gather feedback from stakeholders regularly to ensure the
project meets their needs, especially regarding user requirements and deployment
contexts.
4. Iterative Testing: Conduct user testing sessions and gather feedback to refine the
prototype. Discuss findings with the team and adjust the approach as needed.

5. Documentation & Transparency: Maintain clear documentation so all team members

and stakeholders understand the project's progress, challenges, and next steps.

29
11. Individual learning reflection
11.1. Team Reflections

A good way to identify what you have learned is to ask yourself what surprised you during
the project. List the things that surprised you and any other thoughts you might have on
issues in your local community.

Team member name:

Team member name:

Team member name:

Team member name:

30
 Rate
yourself

Individual Learning
Reflection

1 point –
2 points Some team members present an account of their learning during the project.
-E3 ach team presents an account of their learning during the project.
points - Each team member presents a reflective and insightful account of their learning during
project. the

12. Video link

Enter the URL of your team video:

Enter the password (if any):

31
Appendix
Recommended Assessment Rubric (for Teachers)
LOGBOOK AND VIDEO CONTENT
Steps 3 points 2 points 1 point Points
Given

Problem A local problem which has not A local problem which has not A local problem is
been fully solved before is been fully solved before is
definition explained in detail with described. described
supporting research.

The Users Understanding of the user group Understanding of the user The user group is
is evidenced by completion of group is evidenced by described but it is unclear
all of the steps in Section 4 The completion of most of the how they are affected by
Users and thorough steps in Section 4 The Users. the problem.
investigation.

Brainstorming A brainstorming session was A brainstorming session was A brainstorming session

conducted using creative and conducted using creative and was conducted. A solution
critical thinking. A compelling critical thinking. A solution was was selected.
solution was selected with selected with supporting
supporting arguments from arguments in Section 5
Section 5 Brainstorming. Brainstorming.

Design The use of AI is a good fit for the The use of AI is a good fit for The use of AI is a good fit
the solution and there is some for the solution.
solution. The new user documentation about how it
experience is clearly meets the needs of users.
documented showing how users
will be better served than they
are today.

Data Relevant data to train the AI Relevant data to train the AI Relevant data to train the
model have been identified as model have been identified as AI model have been
well as how the data will be well as how the data will be identified as well as how
sourced or collected. There is sourced or collected. There is the data will be sourced or
evidence that the dataset is evidence that the dataset is collected.
balanced, and that safety and balanced.
privacy have been considered.

Prototype A prototype for the solution has A prototype for the solution A concept for a prototype
been created and successfully has been created and trained.
trained to meet users’ shows how the AI model
requirements. will work

Testing A prototype has been tested A prototype has been tested A concept for a
with a fair representation of with users and improvements prototype shows how it
users and all tasks in Section 9 have been identified to meet will be tested.
Testing have been completed. user requirements.

Team Effective team collaboration and Team collaboration among There is some evidence
communication among peers peers and stakeholders is of team interactions
collaboration and stakeholders is clearly clearly documented in Section among peers and
documented in Section 10 stakeholders.
Team collaboration. 10 Team collaboration.

32
Individual Each team member presents a Each team presents an Some team members
learning reflective and insightful account account of their learning
of their learning during the during the project. present an account of their
project. learning during the project.

Total points

VIDEO PRESENTATION
Points Given

3 – excellent
Criteria
2 – very good

1 – satisfactory

Communicatio
n The video is well-paced and communicated, following a clear
and logical sequence.

Demonstrations and/or visuals are used to illustrate

Illustrative
examples, where appropriate.

Accurate The video presents accurate science and technology and

language uses appropriate language.

Passion The video demonstrates passion from team members about

their chosen topic/idea.

Sound and
The video demonstrates good sound and image quality.
image quality

Length
The content is presented in the video within a 3-minute

33
 timeframe.

Total points

34