Abstract—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.
Index Terms—underwater robot vision, gesture recognition, convolutional neural networks, feature extraction
Cite: Mygel Andrei M. Martija, Jakov Ivan S. Dumbrique, and Prospero C. Naval, Jr, "Underwater Gesture Recognition Using Classical Computer Vision and Deep Learning Techniques," Journal of Image and Graphics, Vol. 8, No. 1, pp. 9-14, March 2020. doi: 10.18178/joig.8.1.9-14
Copyright © 2020 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.
Copyright © 2012-2020 Journal of Image and Graphics, All Rights Reserved