Semantic Segmentation of Underwater Imagery: Dataset and Benchmark

Islam, Jahidul; Edge, Chelsey; Xiao, Yuyang; Luo, Peigen; Mehtaz, Muntaqim; Morse, Christopher; Enan, Sadman Sakib; Sattar, Junaed

doi:10.1109/iros45743.2020.9340821

Cited by 108 publications

(81 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These tasks are mainly designed to extract knowledge from underwater videos and images. Despite the recent use of CNNs for various visual analysis tasks such as segmentation [55][56][57][58], localisation [59][60][61], and counting [62][63][64], the most common and the widest studied CV task in underwater fish habitat monitoring has been classification. Therefore, in this paper, we focus mainly on classification of underwater fish images.…”

Section: Applications Of Deep Learning In Fish-habitat Monitoringmentioning

confidence: 99%

Computer Vision and Deep Learning for Fish Classification in Underwater Habitats: A Survey

Saleh,

Sheaves,

Azghadi

2022

Preprint

View full text Add to dashboard Cite

Marine scientists use remote underwater video recording to survey fish species in their natural habitats. This helps them understand and predict how fish respond to climate change, habitat degradation, and fishing pressure. This information is essential for developing sustainable fisheries for human consumption, and for preserving the environment. However, the enormous volume of collected videos makes extracting useful information a daunting and time-consuming task for a human. A promising method to address this problem is the cutting-edge Deep Learning (DL) technology.DL can help marine scientists parse large volumes of video promptly and efficiently, unlocking niche information that cannot be obtained using conventional manual monitoring methods. In this paper, we provide an overview of the key concepts of DL, while presenting a survey of literature on fish habitat monitoring with a focus on underwater fish classification. We also discuss the main challenges faced when developing DL for underwater image processing and propose approaches to address them. Finally, we provide insights into the marine habitat monitoring research domain and shed light on what the future of DL for underwater image processing may hold. This paper aims to inform a wide range of readers from marine scientists who would like to apply DL in their research to computer scientists who would like to survey state-of-the-art DL-based underwater fish habitat monitoring literature.

show abstract

Section: Applications Of Deep Learning In Fish-habitat Monitoringmentioning

confidence: 99%

Computer Vision and Deep Learning for Fish Classification in Underwater Habitats: A Survey

Saleh,

Sheaves,

Azghadi

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Obviously, this simple network design is outdated and ineffective, and requires very large computational resources. The work [21] proposes an optional residual skip block consisting of three convolutional layers with batch normalisation and ReLU non‐linearity after each convolutional layer. Furthermore, they embed this residual skip block module in an end‐to‐end architecture to extract multi‐scale features.…”

Section: Related Workmentioning

confidence: 99%

DPANet: Dual Pooling‐aggregated Attention Network for fish segmentation

Zhang

Bao

2021

IET Computer Vision

View full text Add to dashboard Cite

The sustainable development of marine fisheries depends on the accurate measurement of data on fish stocks. Semantic segmentation methods based on deep learning can be applied to automatically obtain segmentation masks of fish in images to obtain measurement data. However, general semantic segmentation methods cannot accurately segment fish objects in underwater images. In this study, a Dual Pooling-aggregated Attention Network (DPANet) to adaptively capture long-range dependencies through an efficient and computing-friendly manner to enhance feature representation and improve segmentation performance is proposed. Specifically, a novel pooling-aggregate position attention module and a poolingaggregate channel attention module are designed to aggregate contexts in the spatial dimension and channel dimension, respectively. These two modules adopt pooling operations along the channel dimension and along the spatial dimension to aggregate information, respectively, thus reducing computational costs. In these modules, attention maps are generated by four different paths and are aggregated into one. The authors conduct extensive experiments to validate the effectiveness of the DPANet and achieve new state-ofthe-art segmentation performance on the well-known fish image dataset DeepFish as well as on the underwater image dataset SUIM, achieving a Mean IoU score of 91.08% and 85.39% respectively, while significantly reducing FLOPs of attention modules by about 93%.

show abstract

“…As its low-resolution predictions generally result in poor performance, we create a higher-resolution version by incorporating two ideas from [10,70]. First, we [20] Consumer 22 10K ADE20K [76] Consumer 150 20K COCO Panoptic [9,34,43] Consumer 134 118K KITTI [1] Driving 30 150 CamVid [7] Driving 23 367 CityScapes [14] Driving 33 3K India Driving Dataset (IDD) [64] Driving 35 7K Berkeley Deep Drive (BDD) [74] Driving 20 7K Mapillary Vista Dataset [51] Driving 66 18K ISPRS [57] Aerial 6 4K iSAID [68,71] Aerial 16 27K SUN RGB-D [60] Indoor 37 5K ScanNet [15] Indoor 41 19K SUIM [33] Underwater 8 1525 vKITTI2 [8,23] Synthetic driving 9 43K vGallery [69] Synthetic indoor 8 44K…”

Section: Model Architecturesmentioning

confidence: 99%

Transferability Metrics for Selecting Source Model Ensembles

Agostinelli¹,

Uijlings²,

Mensink³

et al. 2021

Preprint

View full text Add to dashboard Cite

We address the problem of ensemble selection in transfer learning: Given a large pool of source models we want to select an ensemble of models which, after fine-tuning on the target training set, yields the best performance on the target test set. Since fine-tuning all possible ensembles is computationally prohibitive, we aim at predicting performance on the target dataset using a computationally efficient transferability metric. We propose several new transferability metrics designed for this task and evaluate them in a challenging and realistic transfer learning setup for semantic segmentation: we create a large and diverse pool of source models by considering 17 source datasets covering a wide variety of image domain, two different architectures, and two pre-training schemes. Given this pool, we then automatically select a subset to form an ensemble performing well on a given target dataset. We compare the ensemble selected by our method to two baselines which select a single source model, either (1) from the same pool as our method; or (2) from a pool containing large source models, each with similar capacity as an ensemble. Averaged over 17 target datasets, we outperform these baselines by 6.0% and 2.5% relative mean IoU, respectively.

show abstract

Semantic Segmentation of Underwater Imagery: Dataset and Benchmark

Cited by 108 publications

References 26 publications

Computer Vision and Deep Learning for Fish Classification in Underwater Habitats: A Survey

Computer Vision and Deep Learning for Fish Classification in Underwater Habitats: A Survey

DPANet: Dual Pooling‐aggregated Attention Network for fish segmentation

Transferability Metrics for Selecting Source Model Ensembles

Contact Info

Product

Resources

About