Tiny-ML based person identification in dynamic motion
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2024.
| Автори: | , , , |
|---|---|
| Інші автори: | |
| Формат: | Дисертація |
| Мова: | English |
| Опубліковано: |
Brac University
2024
|
| Предмети: | |
| Онлайн доступ: | http://hdl.handle.net/10361/24359 |
| id |
10361-24359 |
|---|---|
| record_format |
dspace |
| spelling |
10361-243592024-10-21T21:05:17Z Tiny-ML based person identification in dynamic motion Ahmed, Mirza Raiyan Nokib, Shahed Pervez Nafee, Shadman Ahmad Khondaker, Jannatus Sakira Chakrabarty, Amitabha Department of Computer Science and Engineering, Brac University TinyML Tiny machine learning Object detection Dynamic motion Person identification Image analysis Pattern recognition. Signal processing--Digital techniques. Microcontrollers. Motion perception (Vision). Computer vision. This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2024. Cataloged from PDF version of thesis. Includes bibliographical references (pages 54-57). TinyML, short for Tiny Machine Learning, focuses on small, low-power machine learning systems, with a significant emphasis on human identification. This capability is crucial in areas like access control, security, and law enforcement. Traditional methods like fingerprint and face recognition often require costly hardware and software, whereas TinyML offers a more economical and efficient alternative. TinyML models can be trained using various sensors, such as cameras, microphones, and accelerometers, making them suitable for devices like smartphones and smartwatches. Techniques such as gait and voice recognition are also viable with TinyML, with computer vision playing a crucial role in processing visual data for human identification. Despite the challenges in facial recognition, such as the need for extensive data and computational resources, TinyML models paired with computer vision hold promise for improving effectiveness, affordability, and security.Our analysis of CNN architectures (SqueezeNet, ResNet50, VGG16, MobileNetV2, and MobileFaceNet) for human identification in dynamic motion reveals significant performance improvements with data augmentation. ResNet50 and MobileNetV2 showed the most notable enhancements, with accuracy improvements to 96%, demonstrating robust generalization with enriched data. MobileNetV2 achieved a precision of 97% and an F1 score of 94%, highlighting its effectiveness. While all models benefited from data augmentation, VGG16 and MobileFaceNet also exhibited significant enhancements. These findings underscore the critical role of data augmentation in bolstering model performance and suggest that deploying ResNet50 and MobileNetV2 on devices like the ESP32-CAM could yield highly effective human identification systems. This analysis highlights the interplay between model architecture, dataset characteristics, and data augmentation in shaping model efficacy for real-world applications. Mirza Raiyan Ahmed Shahed Pervez Nokib Shadman Ahmad Nafee Jannatus Sakira Khondaker B.Sc. in Computer Science 2024-10-21T06:02:31Z 2024-10-21T06:02:31Z ©2024 2024-05 Thesis ID 20101188 ID 20301123 ID 20341033 ID 20301468 http://hdl.handle.net/10361/24359 en Brac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. 64 pages application/pdf Brac University |
| institution |
Brac University |
| collection |
Institutional Repository |
| language |
English |
| topic |
TinyML Tiny machine learning Object detection Dynamic motion Person identification Image analysis Pattern recognition. Signal processing--Digital techniques. Microcontrollers. Motion perception (Vision). Computer vision. |
| spellingShingle |
TinyML Tiny machine learning Object detection Dynamic motion Person identification Image analysis Pattern recognition. Signal processing--Digital techniques. Microcontrollers. Motion perception (Vision). Computer vision. Ahmed, Mirza Raiyan Nokib, Shahed Pervez Nafee, Shadman Ahmad Khondaker, Jannatus Sakira Tiny-ML based person identification in dynamic motion |
| description |
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2024. |
| author2 |
Chakrabarty, Amitabha |
| author_facet |
Chakrabarty, Amitabha Ahmed, Mirza Raiyan Nokib, Shahed Pervez Nafee, Shadman Ahmad Khondaker, Jannatus Sakira |
| format |
Thesis |
| author |
Ahmed, Mirza Raiyan Nokib, Shahed Pervez Nafee, Shadman Ahmad Khondaker, Jannatus Sakira |
| author_sort |
Ahmed, Mirza Raiyan |
| title |
Tiny-ML based person identification in dynamic motion |
| title_short |
Tiny-ML based person identification in dynamic motion |
| title_full |
Tiny-ML based person identification in dynamic motion |
| title_fullStr |
Tiny-ML based person identification in dynamic motion |
| title_full_unstemmed |
Tiny-ML based person identification in dynamic motion |
| title_sort |
tiny-ml based person identification in dynamic motion |
| publisher |
Brac University |
| publishDate |
2024 |
| url |
http://hdl.handle.net/10361/24359 |
| work_keys_str_mv |
AT ahmedmirzaraiyan tinymlbasedpersonidentificationindynamicmotion AT nokibshahedpervez tinymlbasedpersonidentificationindynamicmotion AT nafeeshadmanahmad tinymlbasedpersonidentificationindynamicmotion AT khondakerjannatussakira tinymlbasedpersonidentificationindynamicmotion |
| _version_ |
1814309670560464896 |