Adaptive Weighted Multi-Discriminator CycleGAN for Underwater Image Enhancement

Park, Jaihyun; Han, David K.; Ko, Hanseok

doi:10.3390/jmse7070200

Cited by 22 publications

(17 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In certain cases, Cycle-GAN models could also introduce undesired effects. Jaihyun et al find that performance of CycleGAN is highly dependent on the dataset, potentially resulting in unrealistic images with less information content than the original images 34 . Finally, because real domain data is being used in both domain adaptation paradigms, adjustments to the real data target domain, e. g., use of a different C-arm X-ray imaging device or design changes to surgical hardware, may require de novo acquisition of real data and re-training of the models.…”

Section: Discussionmentioning

confidence: 99%

SyntheX: Scaling Up Learning-based X-ray Image Analysis Through In Silico Experiments

Cong¹,

Killeen²,

Yi-cheng³

et al. 2022

Preprint

View full text Add to dashboard Cite

Artificial intelligence (AI) now enables automated interpretation of medical images for clinical use. However, AI's potential use for interventional images (versus those involved in triage or diagnosis), such as for guidance during surgery, remains largely untapped. This is because surgical AI systems are currently trained using post hoc analysis of data collected during live surgeries, which has fundamental and practical limitations, including ethical considerations, expense, scalability, data integrity, and a lack of ground truth. Here, we demonstrate that creating realistic simulated images from human models is a viable alternative and complement to large-scale in situ data collection. We show that training AI image analysis models on realistically synthesized data, combined with contemporary domain generalization or adaptation techniques, results in models that on real data perform comparably to models trained on a precisely matched real data training set. Because synthetic generation of training data from human-based models scales easily, we find that our model transfer paradigm for X-ray image analysis, which we refer to as SyntheX, can even outperform real data-trained models due to the effectiveness of training on a larger dataset. We demonstrate the potential of SyntheX on three clinical tasks: Hip image analysis, surgical robotic tool detection, and COVID-19 lung lesion segmentation. SyntheX provides an opportunity to drastically accelerate the conception, design, and evaluation of intelligent systems for X-ray-based medicine. In addition, simulated image environments provide the opportunity to test novel instrumentation, design complementary surgical approaches, and envision novel techniques that improve outcomes, save time, or mitigate human error, freed from the ethical and practical considerations of live human data collection.

show abstract

Section: Discussionmentioning

confidence: 99%

SyntheX: Scaling Up Learning-based X-ray Image Analysis Through In Silico Experiments

Cong¹,

Killeen²,

Yi-cheng³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…When it comes to more project specific tasks, the standard data augmentation method cannot generate images that are close to the preferred real-world data, and it requires a significant amount of time and trial and error to produce the desired results. Therefore, DL models such as Generative Adversarial Networks (GANs), CycleGAN, and U-Nets are the current state-of-theart methods used to augment datasets and increase their size [18][19][20]. GAN are mainly used to produce synthetic images that follow the same probability distribution as the real images.…”

Section: Related Workmentioning

confidence: 99%

Virtual Underwater Datasets for Autonomous Inspections

Polymenis

Haroutunian

Norman

et al. 2022

JMSE

View full text Add to dashboard Cite

Underwater Vehicles have become more sophisticated, driven by the off-shore sector and the scientific community’s rapid advancements in underwater operations. Notably, many underwater tasks, including the assessment of subsea infrastructure, are performed with the assistance of Autonomous Underwater Vehicles (AUVs). There have been recent breakthroughs in Artificial Intelligence (AI) and, notably, Deep Learning (DL) models and applications, which have widespread usage in a variety of fields, including aerial unmanned vehicles, autonomous car navigation, and other applications. However, they are not as prevalent in underwater applications due to the difficulty of obtaining underwater datasets for a specific application. In this sense, the current study utilises recent advancements in the area of DL to construct a bespoke dataset generated from photographs of items captured in a laboratory environment. Generative Adversarial Networks (GANs) were utilised to translate the laboratory object dataset into the underwater domain by combining the collected images with photographs containing the underwater environment. The findings demonstrated the feasibility of creating such a dataset, since the resulting images closely resembled the real underwater environment when compared with real-world underwater ship hull images. Therefore, the artificial datasets of the underwater environment can overcome the difficulties arising from the limited access to real-world underwater images and are used to enhance underwater operations through underwater object image classification and detection.

show abstract

“…solve this problem by using a 'cycle consistency loss' that allows learning the mutual mappings between two domains from unpaired data. Such models have been effectively used for unpaired learning of perceptual image enhancement [53,54] as well. Furthermore, Ignatov et al [55] showed that additional lossterms for preserving the image-based content and texture information improve the performance of image quality enhancement using GANs.…”

Section: Automatic Image Enhancementmentioning

confidence: 99%

Machine Vision for Improved Human-Robot Cooperation in Adverse Underwater Conditions

Islam

2019

Preprint

View full text Add to dashboard Cite

Visually-guided underwater robots are widely used in numerous autonomous exploration and surveillance applications alongside humans for cooperative task execution. However, underwater visual perception is challenging due to marine artifacts such as poor visibility, lighting variation, scattering, etc. Additionally, chromatic distortions and scarcity of salient visual features make it harder for an underwater robot to visually interpret its surroundings to effectively assist its companion diver during an underwater mission. In this paper, we delineate our attempts to address these challenges by designing novel and improved vision-based solutions. Specifically, we present robust methodologies for autonomous diver following, human-robot communication, automatic image enhancement, and image super-resolution. We depict their algorithmic details and describe relevant design choices to meet the real-time operating constraints on single-board embedded machines. Moreover, through extensive simulation and field experiments, we demonstrate how an autonomous robot can exploit these solutions to understand human motion and hand gesture-based instructions even in adverse visual conditions. As an immediate next step, we want to focus on relative pose estimation and visual attention modeling of an underwater robot based on its companion humans' body-pose and temporal activity recognition. We believe that these autonomous capabilities will facilitate a faster and better interpretation of visual scenes and enable more effective underwater human-robot cooperation.

show abstract

Adaptive Weighted Multi-Discriminator CycleGAN for Underwater Image Enhancement

Cited by 22 publications

References 28 publications

SyntheX: Scaling Up Learning-based X-ray Image Analysis Through In Silico Experiments

SyntheX: Scaling Up Learning-based X-ray Image Analysis Through In Silico Experiments

Virtual Underwater Datasets for Autonomous Inspections

Machine Vision for Improved Human-Robot Cooperation in Adverse Underwater Conditions

Contact Info

Product

Resources

About