Enhancing Underwater Imagery using Generative Adversarial Networks

Fabbri, Cameron; Islam, Md Jahidul; Sattar, Junaed

doi:10.48550/arxiv.1801.04011

Cited by 7 publications

(24 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There exist a number of hand gesturebased HRI frameworks [17], [18], [19] for terrestrial robots. In addition, recent visual hand gesture recognition techniques [26], [27] based on CNNs have been shown to be highly accurate and robust to noise and visual distortions [8]. A number of such visual recognition and tracking techniques have been successfully used for underwater tracking [16] and have proven to be more robust than other purely featurebased methods [3].…”

Section: B Underwater Human-robot Communicationmentioning

confidence: 99%

See 1 more Smart Citation

Understanding human motion and gestures for underwater human–robot collaboration

Islam

Sattar³

2018

Journal of Field Robotics

Self Cite

View full text Add to dashboard Cite

In this paper, we present a number of robust methodologies for an underwater robot to visually detect, follow, and interact with a diver for collaborative task execution. We design and develop two autonomous diver-following algorithms, the first of which utilizes both spatial-and frequency-domain features pertaining to human swimming patterns in order to visually track a diver. The second algorithm uses a convolutional neural network-based model for robust tracking-by-detection. In addition, we propose a hand gesture-based human-robot communication framework that is syntactically simpler and computationally more efficient than the existing grammar-based frameworks. In the proposed interaction framework, deep visual detectors are used to provide accurate hand gesture recognition; subsequently, a finite-state machine performs robust and efficient gesture-to-instruction mapping. The distinguishing feature of this framework is that it can be easily adopted by divers for communicating with underwater robots without using artificial markers or requiring memorization of complex language rules. Furthermore, we validate the performance and effectiveness of the proposed methodologies through extensive field experiments in closed-and open-water environments. Finally, we perform a user interaction study to demonstrate the usability benefits of our proposed interaction framework compared to existing methods.

show abstract

Section: B Underwater Human-robot Communicationmentioning

confidence: 99%

“…The trained model is invariant to the scale and appearance of divers (e.g., the color of the suit/flippers, swimming directions, etc.) and robust to noise and image distortions [8].…”

Section: Introductionmentioning

confidence: 99%

Understanding human motion and gestures for underwater human–robot collaboration

Islam

Sattar³

2018

Journal of Field Robotics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recently, Underwater Generative adversarial network (UGAN) [12] is proposed to improve the underwater image quality. For discriminator, UGAN chose WGAN-GP (Wasserstein GAN with gradient penalty) [14] to enforces the soft constraint on the output concerning its input via the Lipschitz on the gradients norms instead of clipping the gradients in some range.…”

Section: Uganmentioning

confidence: 99%

“…The generator is motivated by CycleGAN [66], comparable to the encoder-decoder network of UNET [48]. The encoder of UGAN [12] is composed of convolutional layers having filter sizes of 4 × 4 with a stride of two followed by batch normalization [22] and leaky ReLU (slope of 0.2). Similarly, the decoder portion consists of deconvolutional layers followed by ReLU [42] only except the last layer where TanH is used to restrict distribution between -1 and 1.…”

Section: Uganmentioning

confidence: 99%

Diving Deeper into Underwater Image Enhancement: A Survey

Anwar

2019

Preprint

View full text Add to dashboard Cite

The powerful representation capacity of deep learning has made it inevitable for the underwater image enhancement community to employ its potential. The exploration of deep underwater image enhancement networks is increasing over time, and hence; a comprehensive survey is the need of the hour. In this paper, our main aim is two-fold, 1): to provide a comprehensive and in-depth survey of the deep learning-based underwater image enhancement, which covers various perspectives ranging from algorithms to open issues, and 2): to conduct a qualitative and quantitative comparison of the deep algorithms on diverse datasets to serve as a benchmark, which has been barely explored before.To be specific, we first introduce the underwater image formation models, which are the base of training data synthesis and design of deep networks, and also helpful for understanding the process of underwater image degradation. Then, we review deep underwater image enhancement algorithms, and a glimpse of some of the aspects of the current networks is presented including network architecture, network parameters, training data, loss function, and training configurations. We also summarize the evaluation metrics and underwater image datasets. Following that, a systematically experimental comparison is carried out to analyze the robustness and effectiveness of deep algorithms.

show abstract

“…These problems are exacerbated underwater since both the robot and diver are suspended in a six-degrees-of-freedom (6DOF) environment. Consequently, classical model-based detection algorithms fail to achieve good generalization performance [3,4]. On the other hand, model-free algorithms incur significant target drift [5] under such noisy conditions.…”

mentioning

confidence: 99%

Toward a Generic Diver-Following Algorithm: Balancing Robustness and Efficiency in Deep Visual Detection

Islam

Fulton

Sattar

2019

IEEE Robot. Autom. Lett.

Self Cite

View full text Add to dashboard Cite

This paper explores the design and development of a class of robust diver-following algorithms for autonomous underwater robots. By considering the operational challenges for underwater visual tracking in diverse real-world settings, we formulate a set of desired features of a generic diver following algorithm. We attempt to accommodate these features and maximize general tracking performance by exploiting the state-of-the-art deep object detection models. We fine-tune the building blocks of these models with a goal of balancing the trade-off between robustness and efficiency in an on-board setting under real-time constraints. Subsequently, we design an architecturally simple Convolutional Neural Network (CNN)-based diver-detection model that is much faster than the state-of-the-art deep models yet provides comparable detection performances. In addition, we validate the performance and effectiveness of the proposed diver-following modules through a number of field experiments in closed-water and open-water environments.

show abstract

Enhancing Underwater Imagery using Generative Adversarial Networks

Cited by 7 publications

References 0 publications

Understanding human motion and gestures for underwater human–robot collaboration

Understanding human motion and gestures for underwater human–robot collaboration

Diving Deeper into Underwater Image Enhancement: A Survey

Toward a Generic Diver-Following Algorithm: Balancing Robustness and Efficiency in Deep Visual Detection

Contact Info

Product

Resources

About