Deep learning based human presence detection
Human detection and tracking have been progressively demanded in various industries. The concern over human safety has inhibited the deployment of advanced and collaborative robotics, mainly attributed to the dimensionality limitation of present safety sensing. This study entails developing a deep l...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Penerbit UMP
2020
|
Subjects: | |
Online Access: | http://umpir.ump.edu.my/id/eprint/33638/1/Deep%20learning%20based%20human%20presence%20detection.pdf http://umpir.ump.edu.my/id/eprint/33638/ https://doi.org/10.15282/mekatronika.v2i2.6768 https://doi.org/10.15282/mekatronika.v2i2.6768 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Universiti Malaysia Pahang |
Language: | English |
id |
my.ump.umpir.33638 |
---|---|
record_format |
eprints |
spelling |
my.ump.umpir.336382022-04-06T06:40:41Z http://umpir.ump.edu.my/id/eprint/33638/ Deep learning based human presence detection Venketaramana, Balachandran Muhammad Nur Aiman, Shapiee Ahmad Fakhri, Ab. Nasir Mohd Azraai, Mohd Razman Anwar P. P., Abdul Majeed TK Electrical engineering. Electronics Nuclear engineering Human detection and tracking have been progressively demanded in various industries. The concern over human safety has inhibited the deployment of advanced and collaborative robotics, mainly attributed to the dimensionality limitation of present safety sensing. This study entails developing a deep learning-based human presence detector for deployment in smart factory environments to overcome dimensionality limitations. The objective is to develop a suitable human presence detector based on state-of-the-art YOLO variation to achieve real-time detection with high inference accuracy for feasible deployment at TT Vision Holdings Berhad. It will cover the fundamentals of modern deep learning based object detectors and the methods to accomplish the human presence detection task. The YOLO family of object detectors have truly revolutionized the Computer Vision and object detection industry and have continuously evolved since its development. At present, the most recent variation of YOLO includes YOLOv4 and YOLOv4 - Tiny. These models are acquired and pre-evaluated on the public CrowdHuman benchmark dataset. These algorithms mentioned are pre-trained on the CrowdHuman models and benchmarked at the preliminary stage. YOLOv4 and YOLOv4 – Tiny are trained on the CrowdHuman dataset for 4000 iterations and achieved a mean Average Precision of 78.21% at 25FPS and 55.59% 80FPS, respectively. The models are further fine-tuned on a Custom CCTV dataset and achieved significant precision improvements up to 88.08% at 25 FPS and 77.70% at 80FPS, respectively. The final evaluation justified YOLOv4 as the most feasible model for deployment. Penerbit UMP 2020 Article PeerReviewed pdf en cc_by_nc_4 http://umpir.ump.edu.my/id/eprint/33638/1/Deep%20learning%20based%20human%20presence%20detection.pdf Venketaramana, Balachandran and Muhammad Nur Aiman, Shapiee and Ahmad Fakhri, Ab. Nasir and Mohd Azraai, Mohd Razman and Anwar P. P., Abdul Majeed (2020) Deep learning based human presence detection. Mekatronika - Journal of Intelligent Manufacturing & Mechatronics, 2 (2). pp. 55-61. ISSN 2637-0883 https://doi.org/10.15282/mekatronika.v2i2.6768 https://doi.org/10.15282/mekatronika.v2i2.6768 |
institution |
Universiti Malaysia Pahang |
building |
UMP Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Malaysia Pahang |
content_source |
UMP Institutional Repository |
url_provider |
http://umpir.ump.edu.my/ |
language |
English |
topic |
TK Electrical engineering. Electronics Nuclear engineering |
spellingShingle |
TK Electrical engineering. Electronics Nuclear engineering Venketaramana, Balachandran Muhammad Nur Aiman, Shapiee Ahmad Fakhri, Ab. Nasir Mohd Azraai, Mohd Razman Anwar P. P., Abdul Majeed Deep learning based human presence detection |
description |
Human detection and tracking have been progressively demanded in various industries. The concern over human safety has inhibited the deployment of advanced and collaborative robotics, mainly attributed to the dimensionality limitation of present safety sensing. This study entails developing a deep learning-based human presence detector for deployment in smart factory environments to overcome dimensionality limitations. The objective is to develop a suitable human presence detector based on state-of-the-art YOLO variation to achieve real-time detection with high inference accuracy for feasible deployment at TT Vision Holdings Berhad. It will cover the fundamentals of modern deep learning based object detectors and the methods to accomplish the human presence detection task. The YOLO family of object detectors have truly revolutionized the Computer Vision and object detection industry and have continuously evolved since its development. At present, the most recent variation of YOLO includes YOLOv4 and YOLOv4 - Tiny. These models are acquired and pre-evaluated on the public CrowdHuman benchmark dataset. These algorithms mentioned are pre-trained on the CrowdHuman models and benchmarked at the preliminary stage. YOLOv4 and YOLOv4 – Tiny are trained on the CrowdHuman dataset for 4000 iterations and achieved a mean Average Precision of 78.21% at 25FPS and 55.59% 80FPS, respectively. The models are further fine-tuned on a Custom CCTV dataset and achieved significant precision improvements up to 88.08% at 25 FPS and 77.70% at 80FPS, respectively. The final evaluation justified YOLOv4 as the most feasible model for deployment. |
format |
Article |
author |
Venketaramana, Balachandran Muhammad Nur Aiman, Shapiee Ahmad Fakhri, Ab. Nasir Mohd Azraai, Mohd Razman Anwar P. P., Abdul Majeed |
author_facet |
Venketaramana, Balachandran Muhammad Nur Aiman, Shapiee Ahmad Fakhri, Ab. Nasir Mohd Azraai, Mohd Razman Anwar P. P., Abdul Majeed |
author_sort |
Venketaramana, Balachandran |
title |
Deep learning based human presence detection |
title_short |
Deep learning based human presence detection |
title_full |
Deep learning based human presence detection |
title_fullStr |
Deep learning based human presence detection |
title_full_unstemmed |
Deep learning based human presence detection |
title_sort |
deep learning based human presence detection |
publisher |
Penerbit UMP |
publishDate |
2020 |
url |
http://umpir.ump.edu.my/id/eprint/33638/1/Deep%20learning%20based%20human%20presence%20detection.pdf http://umpir.ump.edu.my/id/eprint/33638/ https://doi.org/10.15282/mekatronika.v2i2.6768 https://doi.org/10.15282/mekatronika.v2i2.6768 |
_version_ |
1729703440584540160 |