Professional Documents
Culture Documents
Final Manuscript
Final Manuscript
A Design Project
Presented to the
Computer Engineering Faculty
College of Computing Studies
Don Honorio Ventura State University
Villa de Bacolor, Pampanga
In Partial Fulfillment
of the Requirement for the Degree
Bachelor of Science in Computer Engineering
By:
Aldrin C. Broqueza
Jayson N. De Dios
Karl Vince P. Jimenez
Jhon Manuel T. Ocampo
Juan Carlo N. Ocampo
Marck Joshua B. Punzalan
Jambervill D. Valerio
July 2022
DON HONORIO VENTURA STATE UNIVERSITY ii
APPROVAL SHEET
THESIS COMMITTEE
JOEL D. CANLAS, MIT, MBA
Chair
JULIETA M. UMALI, MSIT, MAIE
Co-Chair
ASIL KASTLE S. DELA CRUZ, PCpE, MIT MARIA IVY M. GUESE, MIT
Member Member
PANEL OF EXAMINERS
Approved by the committee on Oral Examination with a remarks of PASSED on
July 4, 2022
Accepted and approved in partial fulfillment of the requirements for the Degree of
Bachelor of Science in Computer Engineering.
ACKNOWLEDGEMENT
This section aims to give gratitude to all of the individuals and institutions that
helped the researchers financially, emotionally and mentally and spiritually in the course
of the study:
To Asil Kastle Dela Cruz, MIT, PCpE, for being the researchers’ thesis and
academic adviser, for guiding them, giving them feedback on what improve and
supporting them in completing the project;
To Brgy. Captain Richard A. Manalili, for giving the researchers permission to
collect data inside barangay Saguin, City of San Fernando, Pampanga;
To Larry Page & Sergey Brin, for developing google that provided the
researchers guides and information they needed in completing their frameworks, tasks
and module preparations;
To the Traffic authorities, for giving the researchers answers that will help their
research paper to make more validation;
To Ms. Maribel Valerio, for providing the researchers a place to stay when they
need a overnight stay to discuss the study;
To other family and friends, for giving the researchers the emotional, moral and
emotional support they needed in completing the research paper;
Most significantly, to the Almighty God, for His ever-lasting love and grace, for
giving us the inner spiritual strength to stay on the path righteousness, for giving us
wisdom and knowledge to accomplish everything at hand.
Table of Contents
Acknowledgement -------------------------------------------------------------------- iv
Abstract -------------------------------------------------------------------- x
Introduction -------------------------------------------------------------------- 1
Objectives ---------------------------------------------------- 2
Methods -------------------------------------------------------------------- 5
Conclusions ---------------------------------------------------- 32
Recommendations ------------------------------------------- 33
References -------------------------------------------------------------------- 34
Appendices -------------------------------------------------------------------- 36
List of Figures
List of Tables
ABSTRACT
INTRODUCTION
Helmet laws are administered to lessen head injuries and avoid fatalities.
According to Liu et al., 2008, helmet-wearing riders that got involved in accidents had
decreased the risk of head injury by 69% along with a 42% decreased risk of death. This
suggests that the majority of fatal head injuries sustained in motorcycle collisions can be
mitigated or even prevented through helmet usage. However, despite the traffic laws and
years of helmets being subject to continuous improvements in terms of safety and
lifesaving qualities, as the use of helmets among riders keeps declining, the numbers of
motorcyclist fatalities keep rising.
Although there is an act in the Philippines, the Republic Act No. 10054, that
requires motorcycle riders to use standard protective motorcycle helmets while driving,
the usage of motorcycle helmets is still low due to a lack of police manpower. Moreover,
despite the penalties being provided to violators, there still are people who do not wear
helmets as even though police officials tried to regulate this problem manually through
checkpoint operations, not all of the violators can be monitored, caught, and punished by
the law. (LAWPHIL, 2010)
This study focused on this problem and proposed a system that will help law
enforcers in improving the monitoring system of checkpoint operations through the aid of
developing a device that will detect and recognize non-helmet-wearing motorcycle riders
and then notify its user using Image Processing as the main technology to be used and
the Raspberry Pi as the Microcontroller Unit.
According to Pabaharan (2020), image processing refers to a variety of operations
that examine pictures or transform one image representation into another. Although some
analog processing was used in the past, image processing is now done entirely in the
digital realm. Surveillance, medical imaging, machine vision, robotics, and computer-
generated images (CGI) are just a few of the applications. Image processing is a
technology that may be used to process pictures, 3D models, prints, and extract data from
them. While using analog visual methods, researchers employ a wide range of
fundamental picture interpretation procedures.
The researchers then opted to run the system on a Raspberry Pi as the main
processing unit, a credit-card-sized computer that connects to a computer monitor or TV
and works on a standard keyboard and mouse. It is a powerful small-sized device that
allows users to communicate with computers and learn to write in languages like Scratch
and Python. All versions include a connector for attaching a specialized camera, as well
as an array of general-purpose input/output (GPIO) pins for communicating with a broad
range of electronics, including LEDs and buttons, servos, and motors, power relays, and
a plethora of sensors. (Jolles, 2021
A similar study entitled “Machine vision techniques for motorcycle safety helmet
detection” presented a system that detects motorcycle riders and determines if they are
wearing safety helmets or not. The researchers of this study utilized K-Nearest Neighbor
(KNN) classifier. By using this classifier, the device categorized motorcycles and other
moving entities based on the features extracted from their region properties. Using KNN,
the system determines whether the rider is wearing a helmet or not based on attributes
extracted from four sections of the segmented head area. The results of the experiments
demonstrate that the average correct detection rate for the near lane, distant lane, and
both lanes is 84%, 68%, and 74%, respectively. (Waranusast, Bundon, Timtong, Tangnoi,
Pattanathaburt, 2013)
Correspondingly, Siebert and Lin (2019) created an algorithm for the automatic
registration of motorcycle helmet wear using video data. The system was trained to
recognize active motorbikes, the number and location of riders on the motorcycle, and
helmet usage using 91,000 annotated frames of video footage gathered at several
observation sites around Myanmar. An examination of the performance of the algorithm
on an annotated test data set, as well as a comparison to accessible human-registered
helmet use data, demonstrates that said technique is highly accurate. With a small amount
of training for individual observation locations, the system detects motorcycle helmet
usage with rates of 4.4% accuracy and a +2.1% accuracy when compared to a human
observer.
Moreover, a CNN-based multi-task learning (MTL) system for recognizing and
monitoring particular motorbikes, as well as registering rider-specific helmet wear was
presented in a recent study by Lin, Deng, Albers, and Siebert (2019). The study also
released the HELMET dataset, which contains 91,000 annotated frames from 10,006
unique motorbikes from 12 observation locations in Myanmar. Along with the dataset, the
researchers presented an assessment measure for helmet wear and rider detection
accuracy, that may be used as a standard for assessing future detection algorithms. The
study shows that using MTL for concurrent visual similarity learning and helmet use
classification improves the efficiency of the approach compared to previous studies,
allowing a processing speed of more than 8 FPS on consumer hardware and a weighted
average F-measure of 67.3 percent for detecting the number of riders and helmet usage
of tracked motorcycles.
With these supporting studies in mind, the researchers intend to help the
authorities by developing a system that captures images and sends notifications to the
user and that allows them to improve the strategies for capturing disobedient motorcycle
riders. By amplifying the methods of implementing the strict helmet law on two-wheeler
riders, the system helps the authorities by providing alertness and assistance to intercept
violators due to driving a motorcycle without head protection is dangerous. The
proponents want to help mitigate fatal head injuries as 90 percent of deaths caused by
motorcycle accidents were riders that are not wearing helmets (WHO Philippines 2018).
The researchers also want to learn how image processing can contribute to making the
community safer while trying to minimize the injury sustained because of accidents.
The study aims to produce a detection system for motorcycle helmets using image
processing with notifications. The system may help notify its user after it captures images
of riders who are not wearing a helmet. The captured images are stored locally and in a
database as backup data to provide evidence for traffic law violations during checkpoint
operations. The collected images are accessible by authorized personnel only through a
user-friendly webpage.
With regard to the limitation of the study, the system relies on electricity as a self-
sufficient energy source is not part of the study and the detection of ICC-certified stickers
on helmets is not included in the system due to hardware restraints. Detection of plate
numbers is not included.
The product of this study would be beneficial to motorcycle riders, checkpoint
personnel, Local Government Units, and Future Researchers. This will allow motorcycle
riders to be wary of not wearing a helmet violation when driving, for their own safety. The
system will enable the checkpoint personnel to keep track and be more aware of the
violators that drove past them. The device intends to help the Local Government Units to
impose the law in a more efficient way with regard to wearing helmets when driving a
motorcycle. Upon the completion of the study, it will serve as a supporting study for future
researchers who are looking for ideas or topics related to this study or for those who intend
to further develop, enhance, and innovate the product.
development of the system are Raspberry Pi 4, IP Camera, SIM 800L module, Internet
Cable, router, and Chassis. The Software requisite of the system are Python, PHP,
database, JavaScript, and HTML. The software development consists of software
designing, coding, training of the model, and web page development. The establishment
of the connection of components is held in the hardware development phase and the
assembly of the helmet detection and notifications functions produce the Motorcycle Rider
Helmet Detection System with conducted different tests and evaluations.
METHODS
The researchers employed a descriptive method as the methodology of this study.
The goal of descriptive research is to describe a population, situation, or phenomenon
accurately and thoroughly. To explore one or more variables, a descriptive research
design might employ a wide range of research methodologies. The researchers decided
to use this method as it fits in the collection of the needed information for this study
(McCombes, 2020).
The first stage of development is the planning phase. The researchers discussed
the design of the system to achieve its intended purpose effectively. The proponents
determined the components to acquire for the development of the system. The
researchers utilized Raspberry Pi 4 model which is the main controller unit. The Raspberry
Pi is also responsible for running the program. IP camera serves as the visual sensor of
the system that captures target entities. The proponents decided to use the internet as a
medium for notification and a GSM module to enable the device for sending a text
message as a secondary notification method.
Power Supply
IP Camera Microcontroller
Webpage
GSM module
proceed to the capturing of image. Right after the caption of the subject, the system will
save the image in the local storage of the raspberry pi and to the database. Then the
process will proceed to the sending of notifications through the GSM module and
through the web.
Figure 3. Flowchart
After the complete concept of the system was finalized, the software development
for the helmet detection was started by initializing the training phase of the model. The
researchers gathered sample data through capturing images of both positive and negative
entities on roadways. The images that are classified positive are the images that contain
motorcycle riders who do not wear a helmet and as for the negative, these are images
containing motorcycle riders who wear helmet. Positive images are annotated which is
going to be used on detecting the object desired to be captured.
The proponents utilized 1000 positive images and 2000 negative images for the
training of the model as shown in figure 3. The manually collected images are composed
of images that were captured by the proponents of themselves while riding a motorcycle
with and without a helmet and captured images of passing motorcycles through roadways.
The images collected from the internet came from websites such as Unsplash,
Stockimages, Shuttershock, and pixabay which contain photos of motorcycle riders
wearing and not wearing helmets. The images are separated in two folders: negative and
positive.
With the collection of datasets, the researchers used OpenCV to create Haar
cascades and train the program. The Haar Cascade is an object identification technique
that can recognize customized items in images or real-time video. It requires both positive
and negative pictures to function. Positive photos are those custom items the AI should
recognize. Negative pictures are those the A.I. should ignore. The Raspberry Pi was used
to run the trained model and program.
Figure 6 shows the training of the Haar cascade was initialized after the annotation
and the creation of the vector file.
Figure 7 shows the process of the training of the AI layer by layer and the duration of the
training.
Figure 8 shows the Haar Cascades that were trained and are converted to XML
file format. The files are the output model that differentiates motorcycle riders with no
helmets from motorcycle riders wearing helmets.
Following the completion of the training phase, the researchers tested the model
virtually. The virtual testing used prerecorded videos to check if the detection model is
working.
Figure 10 shows the actual testing of the Helmet detection program. It was tested
on an intersection inside Barangay Saguin, City of San Fernando, Pampanga.
As for the notification function of the system, the researchers then developed a
webpage where notifications can be received and viewed when a violator is detected and
the use of a web database as the storage of the collected images of the violators online.
HTML, PHP, and JavaScript are used to complete the web-based system.
Figure 12. Backend Processing of Files List and API for file count
The proponents conducted trial testing of the notification through the webpage on
a mobile browser and the sample notification is shown in figure 15.
be sent after a few seconds to the registered number. The message content says that a
violator has been detected which serves as an alert.
Table 1 and Table 2 are the tables for the questionnaire of End users.
Table 1. Assessment on the Ease of Operation of the Product
Indicators 4 3 2 1
A. Camera Installation
1. The camera is easy to install to desired location.
2. The camera is easy to focus and aim on desired area.
3. The lock of the camera is easy to utilize.
B. Device Controller
1. The microcontroller was easy to turn on.
2. Upon turning on the microcontroller, it was able to run the program.
3. The microcontroller runs the program/system fast.
4. The microcontroller is easy to install to desired location
C. Process of Notification Receiving
5. The user was able to receive notification.
6. The user can easily access the images on the notification.
7. The phone of the user was able to gain access to the webpage.
The 4-point Likert Scale is administered to determine the assessment of the survey
questionnaire for the end users using the following range conversion shown in Table 3.
Figure 18 shows the whole system of Motorcycle Rider Helmet Detection. This
system is designed to detect motorcycle riders who violate the R.A. 10054. The device
detects riders who do not wear helmets. It will save the image of the violator on the
webpage for remote access and it is stored in the database and locally in the raspberry pi
for protection against accidental loss of data. It will also send a notification on the webpage
and through text message indicating that a no-helmet motorcycle rider is detected. The
notification in the text message also provides a link to view the image. The hardware used
are the following:
Figure 20 shows the Raspberry Pi that was used as the main controller of the
system. It runs the detection program and sends the notifications to both SMS and Web
channels. The proponents opted for the version 4 8GB variant for wider usage capabilities
than the lower variants.
Figure 22 shows that router that was used to connect two or more packet-switched
networks or subnetworks. In this study, a router was used as an access point for both the
Raspberry Pi and the IP Camera while also providing them with an internet connection.
Figure 24 shows the content of the website includes the images saved during an
operation. The pictures are labeled with the time and date of detection for better
documentation purposes. There are functions that can be used: “Delete All” and “Export
Images”. The “Delete All” function deletes all the current images collected. The “Export
Images” function lets the user download a compressed file of all the images.
Only the admin account can add and delete user accounts as shown in Figure 26.
In creating an account, a name, an email, and a password are needed. After all the fields
are filled, there is a save button to finalize the user account creation. When deleting an
account, the admin can browse through the “View All” button and look for the account you
want to delete. Click the trashcan icon and click “Yes!” on the pop-up to delete the selected
user.
In the product development process, the structuring of the project was initiated by
conceptualizing the device and the system. After the design was finalized, the software
development was initialized. The researchers collected datasets and then trained a model
with 2000 negative images and 1000 positive images. Next, the model created was used
for the development of the program for the detection of helmets of motorcycle riders.
After finalizing the design and training of the model, the program for the detection
of motorcycle helmet is completed, the researchers proceeded in testing it virtually. The
code was tested using a laptop and a pre-made video. The researchers had a problem
with the program crashing on the first try. The process was monitored and as shown in
Figure 27, Raspberry Pi is having difficulties in running the program because of algorithm
problems. The researchers optimize the program's flow to avoid extra unnecessary steps.
After optimizing the algorithm of the program, the researchers were able fix this problem
and successfully reduced the processing power need to run the system shown in Figure
28. The researchers made changes like: isolating the image from the feed then process it
as a cropped image; processing first if the vehicle is indeed a motorcycle and using
multithreading to be able to distribute the tasks and give the Raspberry Pi easier
processing work. After these changes, the CPU usage became lower than the constant
100% from before and the program doesn’t freeze anymore.
Next, the hardware needed for the system were canvassed then procured. The
program was imported to Raspberry Pi and the actual testing begun. Tests for the
accuracy of the system in terms of ability to detect multiple entities, low –light conditions,
speed limit, SMS notification delay, and response time from capture point to the web page
notification were conducted for effectiveness and accuracy. The researchers also had
problems with the functionality of the SMS notification function. The GSM module have
power problems and burst messages. The 5V pin should not be connected by the time
Raspberry pi boot up. 5V will be reconnected once Raspberry pi has booted up. With
regard to the burst messages, the main problem was with the detection of the frames.
When the system detects a violation, it sends multiple messages if the same violator is
detected which is not supposed to happen. The problem was solved by making the system
detect a violator once and if it is still in the field of view of the camera, the GSM module
will not send any extra messages because it is considered as the same motorcycle. The
webpage is developed after the GSM was fully developed. The frontend side of the
development of the website includes HTML (Hypertext Markup Language), CSS
(Cascading Style Sheets) and JavaScript. The basic structure of the website like the head
and the title was developed using HTML. The formatting, layout and the overall
presentation of the website was managed using CSS. The backend side of the
development of the website includes PHP and the database development is done with the
use of MySQL for the storage of inputs. The researchers then added a login feature where
only the main admin have the control to add and remove user accounts for security
measures. After the total assembly of the software and hardware of the system, multiple
tests and evaluations were conducted.
The first part of the multiple detection test is to determine if the device can detect
multiple entities at once, as shown in Figure 29. A series of tests was conducted to assess
the ability of the system to detect multiple riders in a single frame. The researchers initially
determined the maximum number of motorcycles that can be detected at the same time
with consecutive tests by incrementing the number of entities visible in the same frame
by one.
1 10
2 10
3 8
4 1
The proponents conducted the second part of the multiple detection test, to identify
the accuracy of the detection with multiple entities as shown in Table 6. The first scenario
was to detect entities in the same frame with three riders not wearing helmets. The second
test was two riders with helmets and one with no helmet. Third experiment was one rider
with a helmet and the other two were not wearing helmets. The next test was three riders
were all wearing helmets. The last test conducted was to detect two riders with helmets
and two with no helmets, however as stated in the previous test, the device is having
difficulty in detecting four entities in a single frame.
3 no-helmet 8
2 with helmet,
8
1 no-helmet
1 with helmet,
9
2 no-helmet
3 with helmet 7
2 with helmet
1
2 no-helmet
Table 6 and 7 illustrate the results of the capability of the system in detecting
multiple motorcycle riders. The device can detect at most 3 motorcycle riders in the same
frame. It can also detect violations in different scenarios of three motorcycle riders passing
through the camera at the same time.
5 5
10 3
15 1
20 0
Figure 30 illustrates that the camera can detect a moving motorcycle with a very
low speed (5 kph).
As shown in figure 31, a motorcycle rider moving at 15 kph and faster was visible
but it was not a clear vision for detection.
Figure 30 shows that the system cannot detect a motorcycle rider on a high beam
because the light obstructs the vision of the camera.
In conclusion in this test, the system can detect violations in low-light conditions with
motorcycles running at a very low speed. The image of the motorcycle rider is blurred
when the speed of the motorcycle is 15kph and higher. The light from the headlights
motorcycle can obstruct the vision of the camera resulting in a failed detection.
Table 10 shows the different correct detection results of the system in each
location. Using the formula, the percentage of accuracy on Barangay Saguin, Barangay
San Roque Dau 1st, and Barangay Ascomo was 74%, 78.29%, and 76% respectively.
The proponents determined that the current accuracy of helmet detection is 76.09 percent
according to the three accuracy results in different locations.
4 4.56
5 6.26
6 4.10
7 5.06
8 6.36
9 4.40
10 5.53
11 6.13
12 4.96
13 5.45
14 5.89
15 4.86
16 6.20
17 4.98
18 5.15
19 5.54
20 5.86
Table 11 shows the results of the delay of the notification through the web server.
It was calculated as the time from the motorcycle rider entering the frame of the camera
until the time the notification is shown on the server. The computed average web
notification delay is 5.4 seconds.
17 12.59
18 11.12
19 12.79
20 14.15
As shown in Table 12, the delay of text messages is recorded in different instances.
There are 20 tests in total and the time is calculated from the time that the motorcycle rider
enters the frame until the time that the text message is received by the desired recipient.
The computed average delay of the text message notification is 12.18 seconds.
Following the development phase and system testing, the proponents conducted
the system evaluation and the results are discussed as follows:
Table 13. Respondents Assessment of the Ease of Operation of the Camera Installation
of the Product.
Weighted
Indicator Verbal Description
Mean
1. The camera is easy to install to desired location 2.8 Good
2. The camera is easy to focus on desired area. 3.7 Excellent
3. The lock of the camera is easy to utilize. 2.8 Good
Grand Mean 3.1 Good
Table 13 represents the assessment of the respondents with regard to the ease of
operation of the Camera Installation of the Motorcycle Rider Helmet Detection System.
The “camera is easy to focus and aim at desired area” got the highest weighted
mean on Camera Installation, evaluated as “Excellent” with a weighted mean of 3.7. This
implies that the camera can be easily set up in order to get the optimal angle for detection.
The “The lock of the camera is easy to utilize” and the “The camera is easy to install to
desired location” got the lowest weighted mean, evaluated as “Good” with a weighted
mean of 2.8. Stronger brackets like metal ones can be used for a stronger grip and for an
easier lock. The assessed quality of the ease of operation of Camera Installation is “Good”
as it obtained the grand mean of 3.1 and it is within the range of 2.51 – 3.50 based on the
Likert Scale. This suggests that the overall camera installation is working effectively but it
can still be improved with hardware changes.
Table 14 represents the assessment of the respondents with regard to the ease
of operation of the Device Controller of the Motorcycle Rider Helmet Detection System.
The “The microcontroller is easy to install to desired location” got the highest
weighted mean on Device Controller, evaluated as “Good” with a weighted mean of 3.2.
This indicates that the Raspberry Pi is easy to install in a specific location like a place near
a checkpoint operation. The “The microcontroller runs the program/system fast” got the
lowest weighted mean, evaluated as “Good” with a weighted mean of 2.1. This implies
that the microcontroller does not have the capability of running the program fast and better
hardware is recommended. The assessed quality of the ease of operation of the Device
Controller is “Good” as it obtained the grand mean of 2.8 and it is within the range of 2.51
– 3.50 based on the Likert Scale. This suggests that the installation and the operation of
the device controller are good but the hardware is still upgradable.
Weighted
Indicator Verbal Description
Mean
1. The user was able to receive notification. 3.7 Excellent
2. The user can easily access the images on the
3.4 Good
notification.
3. The phone of the user was able to get access to the
3.1 Good
webpage.
Grand Mean 3.4 Good
Table 15 represents the assessment of the respondents with regard to the process
of Notification Receiving of the Motorcycle Rider Helmet Detection System.
The “user was able to receive notifications” got the highest weighted mean on
Notification Receiving, evaluated as “Excellent” with a weighted mean of 3.7. This
suggests that the notification of the system is working effectively and the users are able
to receive the notifications in every detection. The “The phone of the user was able to get
access to the webpage” got the lowest weight mean, evaluated as “Good” with a weighted
mean of 3.1. This implies that the links to the images are working properly but an external
factor like the absence of internet connection can affect the viewing of images saved on
the webpage. The assessed quality of the process of Notification Receiving is “Good” as
it obtained a grand mean of 3.4 and it is within the range of 2.51 – 3.50 based on the Likert
Scale. This indicates that the notification of the system is working well and effectively meet
its objectives.
Overall, the respondents assessed the Ease of Operation of the Product as “Good”
for it obtained the overall grand mean of 3.1, and based on the Likert Scale, it is within the
range of 2.51 – 3.50. This suggests that the device is user-friendly with a simple point of
operation and the system sends notifications capably. The Raspberry Pi runs the program
with relatively low speed but it is upgradable with higher specs of a microcontroller.
Table 16. Respondents Assessment of the Effectiveness and Accuracy of the System.
Weighted
Indicator Verbal Description
Mean
1. The system captures images of riders with no
2.9 Good
helmet accurately.
2. The system does not send notifications if riders with
3.1 Good
helmets are detected.
3. The system sends notification to the user after
3.6 Excellent
capturing images of the violators.
4. The system sends notification to the users without
3.0 Good
much delay.
5. The captured images on the notifications relayed are
3.3 Good
not blurred.
6. The system can detect multiple entities. 3.1 Good
7. The results of multiple detected entities are
2.6 Good
accurate.
Grand Mean 3.09 Good
as “Good” for it obtained the grand mean of 3.09, and based on the Likert Scale, it is within
the range of 2.51 – 3.50. The system sends notifications with effectiveness and the images
sent were not blurred and are labeled with date and time.
Table 17. Experts Assessment for Motorcycle Rider Helmet Detection Using Image
Processing.
Motorcycle Rider Helmet Detection System Using Image Processing
Weighted Average Descriptive
Characteristics
Mean Rating
Functional Suitability 4.5 Satisfied
Performance 4 Satisfied
Usability 4.67 Very Satisfied
Reliability 3.56 Satisfied
Portability 4.33 Satisfied
Security 4 Satisfied
Grand Average 4.18 Satisfied
Conclusions
The researchers concluded that Motorcycle Rider Helmet Detection Using Image
Processing achieved its objectives in terms of functionality. The officers who are involved
in checkpoint operations have assessed that the system is easy to use, efficient, and able
to help keep evidence of violators. The system was able to detect no-helmet motorcycle
riders and sends a notification through a website and text message. In accordance with
the tests results and evaluations, the end-user respondents assessed the system as
“Good” and the experts were “Satisfied” with the overall function of the system with
recommended improvements in terms of optimization of the detection rate of the raspberry
pi, improvement on low-light detection capability, and webpage security.
Recommendations
The product of the study was able to meet the requirements in terms of its purpose
and features. The system can still be improved by upgrading hardware components. A
more powerful microprocessor can enhance the speed of the system. Subsequently, a
better camera will also improve the resolution of the captured photo, so other details can
be clearer, and the captured image will not be blurred. The webpage can still be improved
by further development like adding a filter function where the user can filter the date and
time of the saved images for faster navigation. The security of the website can still be
upgraded to prevent internet breaches and avoid loss or theft of data.
REFERENCES
Jolles, J. (2021). Broad-scale applications of the Raspberry Pi: A review and guide for
biologists. Methods in Ecology and Evolution. https://doi.org/10.1111/2041-
210X.13652
Lin et al. (2019). Helmet Use Detection of Tracked Motorcycles Using CNN-Based Multi-
Task Learning. https://d-nb.info/1218971762/34899X/961/1/012006/pdf
Lutkevich, B. (2019). Microcontroller. IOTAgenda.
https://internetofthingsagenda.techtarget.com/definition/microcontroller
Siebert, F., & Lin, H. (2019). Detecting motorcycle helmet use with deep learning.
https://www.researchgate.net/publication/340941340_Detecting_motorcycle_hel
met_use_with_deep_learning
Unsplash. (2022). Motorcycle rider with helmet. Retrieved from:
https://unsplash.com/s/photos/motorcycle-rider-with-helmet
Waranusast et al. (2013). Machine vision techniques for motorcycle safety helmet
detection. IEEE.
https://ieeexplore.ieee.org/abstract/document/6726989/authors#authors
APPENDICES
APPENDIX A
(GANTT CHART)
The Gantt Chart represents the schedule that the researchers followed to
complete the study.
APPENDIX B
(LETTERS)
The sample letters were used to acquire permission to test the device on these
barangays and to gather information from the respondents.
APPENDIX C
(EVALUATION
QUESTIONNAIRES)
The questionnaire was used to collect ratings as evaluation of the system, this
questionnaire answered by the end-user responders who are the officers that are involved
in checkpoint operations.
APPENDIX D
(EVALUATION FOR THE
EXPERTS)
The questionnaire was used to collect ratings as evaluation of the system, this
questionnaire answered by the experts who are in the same field of study.
APPENDIX E
(COSTING)
The costing and budgeting serve as the basis for the financial performance of the
study. Shown in the table are the quantity, unit price, and the total of the materials.
APPENDIX F
CURRICULA VITAE
The resumes serve as a proponents’ profile who contributed to the study and
worked hard to accomplish and finish the study.
Jambertvill D. Valerio
Address: Ascomo, Guagua Pampanga
Email Address: jvvalerio3066@gmail.com
Contact No: 09307558380
Technical Skills
Certificates
Certificate of Participation
About: Machine Learning
Date: March 7,2020
EDUCATIONAL ATTAINMENT
PERSONAL INFORMATION
Age: 23
Date of Birth: November 30, 1998
Place of Birth: Floridablanca, Pampanga
Sex: Male
Name of Father: Joel Y. Valerio
Occupation: Cargo Representative
Name of Mother: Maribel D. Valerio
Occupation: None
Nationality: Filipino
Aldrin C. Broqueza
Address: Del Pilar, City of San Fernando, Pampanga
Email Address: aldrinbroqueza809@gmail.com
Contact No: 09777994489
Technical Skills
Certificates
Certificate of Participation
About: Unmask Potentials Decrypting Future Professionals
Date: January 16, 2021
About: Boost your Career and Thrive in the New Normal: Application of
Machine Learning and Artificial Intelligence Amidst the Pandemic
Date: November 03, 2021
EDUCATIONAL ATTAINMENT
PERSONAL INFORMATION
Age: 23
Date of Birth: March 22, 1999
Place of Birth: San Fernando, Pampanga
Sex: Male
Name of Father: Edgar Broqueza
Occupation: Driver
Name of Mother: Lea Broqueza
Occupation: Housewife
Nationality: Filipino
Religion: Roman Catholic
Language: English, Tagalog, Kapampangan
Jayson N. De Dios
Address: Quebiawan City of San Fernando, Pampanga
Email Address: dediosjayson7@gmail.com
Contact No: 0965600092
OBJECTIVE: To be able to utilize the skills I have collected through my years of study.
To be able to improve my interpersonal skills and have a better way of interacting with the
people around me.
Technical Skills
Certificates
Certificate of Participation
About: Unmask Potentials Decrypting Future Professionals
Date: January 16, 2021
About: Boost your Career and Thrive in the New Normal: Application of
Machine Learning and Artificial Intelligence Amidst the Pandemic
Date: November 03, 2021
EDUCATIONAL ATTAINMENT
TERTIARY: Bachelor of Science in Computer Engineering
Don Honorio Ventura State University
Villa de Bacolor, Pampanga
June 2018 – Present
PERSONAL INFORMATION
Age: 22
Date of Birth: July 02, 1999
Place of Birth: San Fernando, Pampanga
Sex: Male
Name of Father: Ceferino De Dios
Occupation: Construction Worker
Name of Mother: Crisanta De Dios
Occupation: Manicurist
Nationality: Filipino
Religion: Roman Catholic
Language: English, Tagalog, Kapampangan
Technical Skills
Certificates
Certificate of Participation
About: EVOLVERE: Transforming the World Through the Evolution of
Technological Innovations
Date: January 27, 2020
About: Boost your Career and Thrive in the New Normal: Application of
Machine Learning and Artificial Intelligence Amidst the Pandemic
Date: November 03, 2021
EDUCATIONAL ATTAINMENT
PERSONAL INFORMATION
Age: 23
Date of Birth: February 23, 1999
Place of Birth: San Fernando, Pampanga
Sex: Male
Name of Father: Manuel Medina
Occupation: None
Name of Mother: Marietta Ocampo
Occupation: Housewife
Nationality: Filipino
Religion: Roman Catholic
Language: English, Tagalog, Kapampangan
OBJECTIVE: Secure a responsible career opportunity to fully utilize my training and skills,
while making a significant contribution to the success of the company.
Technical Skills
Certificates
Certificate of Participation
About: Boost your Career and Thrive in the New Normal: Application of
Machine Learning and Artificial Intelligence Amidst the Pandemic
Date: November 03, 2021
EDUCATIONAL ATTAINMENT
PERSONAL INFORMATION
Age: 22
Date of Birth: July 15, 1999
Place of Birth: Angeles City
Sex: Male
Name of Father: Francisco III Lagman Ocampo
Occupation: None
Name of Mother: Evelyn Naluz
Occupation: Housewife
Nationality: Filipino
Religion: Iglesia Ni Cristo
Language: English, Tagalog, Kapampangan
OBJECTIVE: I am a dedicated person and looking for a suitable job and opportunity where
I can use and enhance my talents, skills, and abilities in serving and dealing with people
and to grow and expand my knowledge and develop my personality as a career person.
Technical Skills
Certificates
Certificate of Participation
About: EVOLVERE: Transforming the World Through the Evolution of
Technological Innovations
Date: January 27, 2020
About: Boost your Career and Thrive in the New Normal: Application of
Machine Learning and Artificial Intelligence Amidst the Pandemic
EDUCATIONAL ATTAINMENT
ABM STRAND
City College of San Fernando, Pampanga
Heroes Hall, Magdalena St., San Juan, City of San
Fernando, Pampanga
June 2016 – March 2017
PERSONAL INFORMATION
Age: 22
Date of Birth: November 28, 1999
Place of Birth: San Fernando, Pampanga
Sex: Male
Name of Father: Rolly G. Jimenez
Occupation: None
Name of Mother: Karen P. Jimenez
Occupation: OFW
Nationality: Filipino
Religion: Roman Catholic
Language: English, Tagalog, Kapampangan
Technical Skills
Certificates
Certificate of Participation
About: Robotics Technology
Date: March 07, 2020
About: Boost your Career and Thrive in the New Normal: Application of
Machine Learning and Artificial Intelligence Amidst the Pandemic
Date: November 03, 2021
EDUCATIONAL ATTAINMENT
PERSONAL INFORMATION
Age: 22
Date of Birth: December 20, 1999
Place of Birth: San Matias, Sto. Tomas, Pampanga
Sex: Male
Name of Father: Ricardo Punzalan
Occupation: Delivery
Name of Mother: Madonna Punzalan
Occupation: Secretary
Nationality: Filipino
Religion: Roman Catholic
Language: English, Tagalog, Kapampangan