Robotic Visual Tracking of Relevant Cues in Underwater Environments with Poor Visibility Conditions

Maldonado-Ramírez, Alejandro; Torres-Méndez, L. Abril

doi:10.1155/2016/4265042

Cited by 13 publications

(7 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such visual attention-based cues are eventually exploited to make important navigational and other operational decisions. The classical approaches utilize features such as luminance, color, texture, and often depth information to extract salient features for enhanced object detection or template identification [39], [40], [41]. In recent years, the standard oneshot object detection models based on large-scale supervised learning are effectively applied for vision-based tracking and following [42], [24].…”

Section: B Visual Attention Modeling and Servoingmentioning

confidence: 99%

Semantic Segmentation of Underwater Imagery: Dataset and Benchmark

Islam¹,

Edge²,

Xiao³

et al. 2020

Preprint

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: B Visual Attention Modeling and Servoingmentioning

confidence: 99%

Semantic Segmentation of Underwater Imagery: Dataset and Benchmark

Islam¹,

Edge²,

Xiao³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…The early approaches date back to the work of Edgington et al [10] that uses binary morphology filters to extract salient features for automated event detection. Subsequent approaches adopt various feature contrast evaluation techniques that encode lowlevel image-based features (e.g., color, luminance, texture, object shapes) into super-pixel descriptors [33], [34], [36]. These low-dimensional representations are then exploited by heuristics or learning-based models to infer global saliency.…”

Section: B Sod and Svam By Underwater Robotsmentioning

confidence: 99%

“…To this end, traditional approaches based on various feature contrast evaluation techniques [5], [12], [33] are often practical choices for saliency estimation by visually-guided underwater robots. These techniques encode low-level image-based features (e.g., color, texture, object shapes or contours) into superpixel descriptors [34], [35], [33], [36], [9] to subsequently infer saliency by quantifying their relative distinctness on a global scale. Such bottom-up approaches are computationally light and are useful as pre-processing steps for faster visual search [34], [2] and exploration tasks [5], [11].…”

Section: Introductionmentioning

confidence: 99%

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

Islam¹,

Wang²,

Sattar³

2020

Preprint

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

“…In the underwater domain, however, existing research work mainly focuses on salient feature extraction for enhanced object detection performance [19,52,71]. Hence, they do not provide a general solution for attention modeling that can facilitate faster visual search or better scene understanding.…”

Section: Introductionmentioning

confidence: 99%

Simultaneous Enhancement and Super-Resolution of Underwater Imagery for Improved Visual Perception

Islam¹,

Luo²,

Sattar³

2020

Preprint

View full text Add to dashboard Cite

In this paper, we introduce and tackle the simultaneous enhancement and super-resolution (SESR) problem for underwater robot vision and provide an efficient solution for near real-time applications. We present Deep SESR, a residual-in-residual network-based generative model that can learn to restore perceptual image qualities at 2×, 3×, or 4× higher spatial resolution. We supervise its training by formulating a multi-modal objective function that addresses the chrominance-specific underwater color degradation, lack of image sharpness, and loss in high-level feature representation. It is also supervised to learn salient foreground regions in the image, which in turn guides the network to learn global contrast enhancement. We design an end-to-end training pipeline to jointly learn the saliency prediction and SESR on a shared hierarchical feature space for fast inference. Moreover, we present UFO-120, the first dataset to facilitate large-scale SESR learning; it contains over 1500 training samples and a benchmark test set of 120 samples. By thorough experimental evaluation on the UFO-120 and other standard datasets, we demonstrate that Deep SESR outperforms the existing solutions for underwater image enhancement and super-resolution. We also validate its generalization performance on several test cases that include underwater images with diverse spectral and spatial degradation levels, and also terrestrial images with unseen natural objects. Lastly, we analyze its computational feasibility for single-board deployments and demonstrate its operational benefits for visuallyguided underwater robots. The model and dataset information will be available at: https://github.com/ xahidbuffon/Deep-SESR.

show abstract

Robotic Visual Tracking of Relevant Cues in Underwater Environments with Poor Visibility Conditions

Cited by 13 publications

References 27 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

Simultaneous Enhancement and Super-Resolution of Underwater Imagery for Improved Visual Perception

Contact Info

Product

Resources

About