Underwater Image Super-Resolution using Deep Residual Multipliers

Islam, Jahidul; Enan, Sadman Sakib; Luo, Peigen; Sattar, Junaed

doi:10.1109/icra40945.2020.9197213

Cited by 72 publications

(76 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These images are carefully chosen from a large pool of samples collected during oceanic explorations and human-robot cooperative experiments in several locations of various water types. We also utilize a few images from large-scale datasets named EUVP [10], USR-248 [27], and UFO-120 [15], which we previously proposed for underwater image enhancement and super-resolution problems. The images are chosen to accommodate a diverse set of natural underwater scenes and various setups for human-robot collaborative experiments.…”

Section: The Suim Datasetmentioning

confidence: 99%

Semantic Segmentation of Underwater Imagery: Dataset and Benchmark

Islam¹,

Edge²,

Xiao³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

In this paper, we present the first large-scale dataset for semantic Segmentation of Underwater IMagery (SUIM). It contains over 1500 images with pixel annotations for eight object categories: fish (vertebrates), reefs (invertebrates), aquatic plants, wrecks/ruins, human divers, robots, and sea-floor. The images are rigorously collected during oceanic explorations and human-robot collaborative experiments, and annotated by human participants. We also present a comprehensive benchmark evaluation of several state-of-the-art semantic segmentation approaches based on standard performance metrics. Additionally, we present SUIM-Net, a fully-convolutional deep residual model that balances the tradeoff between performance and computational efficiency. It offers competitive performance while ensuring fast end-to-end inference, which is essential for its use in the autonomy pipeline by visuallyguided underwater robots. In particular, we demonstrate its usability benefits for visual servoing, saliency prediction, and detailed scene understanding. With a variety of use cases, the proposed model and benchmark dataset open up promising opportunities for future research on underwater robot vision.

show abstract

Section: The Suim Datasetmentioning

confidence: 99%

Semantic Segmentation of Underwater Imagery: Dataset and Benchmark

Islam¹,

Edge²,

Xiao³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…It contains 300 natural underwater images which we exhaustively compiled to ensure diversity in the objects categories, waterbody, optical distortions, and aspect ratio of the salient objects. We collect these images from two major sources: (i) Existing unlabeled datasets: we utilize benchmark datasets that are generally used for underwater image enhancement and superresolution tasks; specifically, we select subsets of images from datasets named USR-248 [87], UIEB [88], and EUVP [23]. II).…”

Section: B Evaluation Data Preparationmentioning

confidence: 99%

“…[38] on the salient image RoI is potentially more useful for detailed perception rather than SESR on the entire image. Moreover, as seen on the right, SVAM-Net Light -generated saliency maps can also be used to determine the scale for super-resolution; here, we use 2× and 4× SRDRM [87] on two salient RoIs based on their respective resolutions.…”

Section: Generalization Performancementioning

confidence: 99%

SVAM: Saliency-guided Visual Attention Modeling by Autonomous Underwater Robots

Islam¹,

Wang²,

Sattar³

2020

Preprint

Self Cite

View full text Add to dashboard Cite

This paper presents a holistic approach to saliencyguided visual attention modeling (SVAM) for use by autonomous underwater robots. Our proposed model, named SVAM-Net, integrates deep visual features at various scales and semantics for effective salient object detection (SOD) in natural underwater images. The SVAM-Net architecture is configured in a unique way to jointly accommodate bottom-up and top-down learning within two separate branches of the network while sharing the same encoding layers. We design dedicated spatial attention modules (SAMs) along these learning pathways to exploit the coarselevel and fine-level semantic features for SOD at four stages of abstractions. The bottom-up branch performs a rough yet reasonably accurate saliency estimation at a fast rate, whereas the deeper top-down branch incorporates a residual refinement module (RRM) that provides fine-grained localization of the salient objects. Extensive performance evaluation of SVAM-Net on benchmark datasets clearly demonstrates its effectiveness for underwater SOD. We also validate its generalization performance by several ocean trials' data that include test images of diverse underwater scenes and waterbodies, and also images with unseen natural objects. Moreover, we analyze its computational feasibility for robotic deployments and demonstrate its utility in several important use cases of visual attention modeling.

show abstract

“…e experiment shows that the proposed network can learn the image deblurring from a large amount of images and the corresponding sharp image and effectively improve the quality of the underwater image. Islam et al [5] provided a deep residual network-based generation model for single-image super-resolution (SISR) of underwater images and a countertraining pipeline for learning SISR from the paired data. At the same time, an objective function is also developed in order to supervise the training, which evaluates the perceptive quality of the image according to the overall content, color, and local style information of the image.…”

Section: Introductionmentioning

confidence: 99%

Super-Resolution Reconstruction of Underwater Image Based on Image Sequence Generative Adversarial Network

Fan

Zhao

et al. 2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Since the underwater image is not clear and difficult to recognize, it is necessary to obtain a clear image with the super-resolution (SR) method to further study underwater images. The obtained images with conventional underwater image super-resolution methods lack detailed information, which results in errors in subsequent recognition and other processes. Therefore, we propose an image sequence generative adversarial network (ISGAN) method for super-resolution based on underwater image sequences collected by multifocus from the same angle, which can obtain more details and improve the resolution of the image. At the same time, a dual generator method is used in order to optimize the network architecture and improve the stability of the generator. The preprocessed images are, respectively, passed through the dual generator, one of which is used as the main generator to generate the SR image of sequence images, and the other is used as the auxiliary generator to prevent the training from crashing or generating redundant details. Experimental results show that the proposed method can be improved on both peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) compared to the traditional GAN method in underwater image SR.

show abstract

Underwater Image Super-Resolution using Deep Residual Multipliers

Cited by 72 publications

References 37 publications

Semantic Segmentation of Underwater Imagery: Dataset and Benchmark

Semantic Segmentation of Underwater Imagery: Dataset and Benchmark

SVAM: Saliency-guided Visual Attention Modeling by Autonomous Underwater Robots

Super-Resolution Reconstruction of Underwater Image Based on Image Sequence Generative Adversarial Network

Contact Info

Product

Resources

About