Underwater Gesture Recognition Using Classical Computer Vision and Deep Learning Techniques

Underwater Gesture Recognition is a challenging task since conditions which are normally not an issue in gesture recognition on land must be considered. Such issues include low visibility, low contrast, and unequal spectral propagation. In this work, we explore the underwater gesture recognition pro...

Full description

Saved in:
Bibliographic Details
Main Authors: Martija, Mygel Andrei M, Dumbrique, Jakov Ivan S, Naval, Prospero C, Jr.
Format: text
Published: Archīum Ateneo 2020
Subjects:
Online Access:https://archium.ateneo.edu/mathematics-faculty-pubs/177
https://archium.ateneo.edu/cgi/viewcontent.cgi?article=1187&context=mathematics-faculty-pubs
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Ateneo De Manila University
id ph-ateneo-arc.mathematics-faculty-pubs-1187
record_format eprints
spelling ph-ateneo-arc.mathematics-faculty-pubs-11872022-02-18T08:11:51Z Underwater Gesture Recognition Using Classical Computer Vision and Deep Learning Techniques Martija, Mygel Andrei M Dumbrique, Jakov Ivan S Naval, Prospero C, Jr. Underwater Gesture Recognition is a challenging task since conditions which are normally not an issue in gesture recognition on land must be considered. Such issues include low visibility, low contrast, and unequal spectral propagation. In this work, we explore the underwater gesture recognition problem by taking on the recently released Cognitive Autonomous Diving Buddy Underwater Gestures dataset. The contributions of this paper are as follows: (1) Use traditional computer vision techniques along with classical machine learning to perform gesture recognition on the CADDY dataset; (2) Apply deep learning using a convolutional neural network to solve the same problem; (3) Perform confusion matrix analysis to determine the types of gestures that are relatively difficult to recognize and understand why; (4) Compare the performance of the methods above in terms of accuracy and inference speed. We achieve up to 97.06% accuracy with our CNN. To the best of our knowledge, our work is one of the earliest attempts, if not the first, to apply computer vision and machine learning techniques for gesture recognition on the said dataset. As such, we hope this work will serve as a benchmark for future work on the CADDY dataset. 2020-03-01T08:00:00Z text application/pdf https://archium.ateneo.edu/mathematics-faculty-pubs/177 https://archium.ateneo.edu/cgi/viewcontent.cgi?article=1187&context=mathematics-faculty-pubs Mathematics Faculty Publications Archīum Ateneo underwater robot vision gesture recognition convolutional neural networks feature extraction Computer Sciences Mathematics
institution Ateneo De Manila University
building Ateneo De Manila University Library
continent Asia
country Philippines
Philippines
content_provider Ateneo De Manila University Library
collection archium.Ateneo Institutional Repository
topic underwater robot vision
gesture recognition
convolutional neural networks
feature extraction
Computer Sciences
Mathematics
spellingShingle underwater robot vision
gesture recognition
convolutional neural networks
feature extraction
Computer Sciences
Mathematics
Martija, Mygel Andrei M
Dumbrique, Jakov Ivan S
Naval, Prospero C, Jr.
Underwater Gesture Recognition Using Classical Computer Vision and Deep Learning Techniques
description Underwater Gesture Recognition is a challenging task since conditions which are normally not an issue in gesture recognition on land must be considered. Such issues include low visibility, low contrast, and unequal spectral propagation. In this work, we explore the underwater gesture recognition problem by taking on the recently released Cognitive Autonomous Diving Buddy Underwater Gestures dataset. The contributions of this paper are as follows: (1) Use traditional computer vision techniques along with classical machine learning to perform gesture recognition on the CADDY dataset; (2) Apply deep learning using a convolutional neural network to solve the same problem; (3) Perform confusion matrix analysis to determine the types of gestures that are relatively difficult to recognize and understand why; (4) Compare the performance of the methods above in terms of accuracy and inference speed. We achieve up to 97.06% accuracy with our CNN. To the best of our knowledge, our work is one of the earliest attempts, if not the first, to apply computer vision and machine learning techniques for gesture recognition on the said dataset. As such, we hope this work will serve as a benchmark for future work on the CADDY dataset.
format text
author Martija, Mygel Andrei M
Dumbrique, Jakov Ivan S
Naval, Prospero C, Jr.
author_facet Martija, Mygel Andrei M
Dumbrique, Jakov Ivan S
Naval, Prospero C, Jr.
author_sort Martija, Mygel Andrei M
title Underwater Gesture Recognition Using Classical Computer Vision and Deep Learning Techniques
title_short Underwater Gesture Recognition Using Classical Computer Vision and Deep Learning Techniques
title_full Underwater Gesture Recognition Using Classical Computer Vision and Deep Learning Techniques
title_fullStr Underwater Gesture Recognition Using Classical Computer Vision and Deep Learning Techniques
title_full_unstemmed Underwater Gesture Recognition Using Classical Computer Vision and Deep Learning Techniques
title_sort underwater gesture recognition using classical computer vision and deep learning techniques
publisher Archīum Ateneo
publishDate 2020
url https://archium.ateneo.edu/mathematics-faculty-pubs/177
https://archium.ateneo.edu/cgi/viewcontent.cgi?article=1187&context=mathematics-faculty-pubs
_version_ 1726158633346007040