Semantic Segmentation of Underwater Imagery: Dataset and Benchmark

Islam, Md Jahidul; Edge, Chelsey; Xiao, Yanjie; Luo, Peigen; Mehtaz, Muntaqim; Morse, Christopher R.; Enan, Sadman Sakib; Sattar, Junaed

doi:10.48550/arxiv.2004.01241

Cited by 3 publications

(11 citation statements)

References 44 publications

(98 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, we employ two additional loss functions, a smooth loss and auxiliary loss, to help train the network reach even higher accuracies. On both the Seagrass [1] and SUIM [2] datasets, our network respectively reaches 89.74 and 51.87 mIoU (mean Intersection Over Union), which are at the state-of-art level.…”

Section: Introductionmentioning

confidence: 86%

“…[11] developed a fast seagrass segmentation network running on GPU Desktop platform and, as well as, compared the existing state-of-art methods against a public seagrass dataset [1]. Instead, for general underwater segmentation on various semantic classes, [2] presented a light-end segmentation network and published its companion generalist underwater segmentation dataset, the SUIM dataset. Our proposed network is an end2end deep learning network optimised for embedded GPU platforms.…”

Section: Related Workmentioning

confidence: 99%

“…Semantic Segmentation Network Although current state-of-art segmentation networks have been originally proposed for medical image analysis, driverless cars or other surface applications, those successful networks could be applied as well to underwater segmentation tasks. The authors of [2] and [11] already proved that segmentation networks such as U-Net [12], deeplab [13], SegNet [14], PSPNet [3], FCN [15] can achieve excellent segmentation accuracy on different underwater datasets, while [16], [17], [18], [19] and [20] proposed a fast inference segmentation networks for real time use on Desktop GPU, which could be potentially deployed on AUVs while still achieve high accuracy.…”

Section: Related Workmentioning

confidence: 99%

“…The first row presents the underwater images and the second row presents their corresponding segmentation ground truth. The first three columns from the left are related to the seagrasses segmentation task [1] while the others comes from SUIM dataset [2] for general underwater segmentation task.…”

Section: Introductionmentioning

confidence: 99%

“…This approach helps also to optimize network training, as well as to improve the segmentation accuracy. We evaluated the proposed network on two datasets,the Seagrass [1] and SUIM [2] datesets, against which we validated its accuracy, and measured its inference speed on two Nvidia embedded platforms.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Compact and Fast Underwater Segmentation Network for Autonomous Underwater Vehicles

Wang

Zhou

et al. 2021

Computer Vision – ACCV 2020

View full text Add to dashboard Cite

Reliable and real-time semantic segmentation is crucial for vision-based navigation tasks undertaken by AUVs (Autonomous Underwater Vehicles). However state-of-art deep learning segmentation networks could not be deployed on embedded devices with limited onboard resources, due to the required high computation capacity and the lack of capability to deal with poor underwater image quality. In this work we present a new deep underwater segmentation network, featured by a compact encoder and a lightweight decoder. We use only one step upsampling block to recover features maps from the encoder to significantly speed up the inference time. Furthermore, we adopt three strategies to improve the network accuracy. Firstly, in parallel with the main decoder path, we introduce a branch path to extract additional low-level features. Secondly, we use position attention module to enhance the high-level semantic information and use channel attention module to introduce extra global context as well as refine the inter-dependencies of each features. Thirdly, we proposed to use two additional auxiliary loss and smooth loss functions to better train the network, such that it will be more robust in segmenting images at varying resolutions and generating smooth boundaries. We validate our network accuracy on two different underwater segmentation datasets, a generalistic and a specialist one, and our model achieves the same level of accuracy of state-of-art networks. We also tested the network speed on different embedded platforms, and we showed it reaches real-time inference speed on both Nvidia Jetson GPU platforms TX2 and Nano, with respectively around 24 and 18 FPS (Frame Per Second). The proposed network inference is up to 27 times faster than other considered networks. Its high accuracy and speed will so pave the way for its deployment and application on AUVs systems.

show abstract

Section: Introductionmentioning

confidence: 86%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Compact and Fast Underwater Segmentation Network for Autonomous Underwater Vehicles

Wang

Zhou

et al. 2021

Computer Vision – ACCV 2020

View full text Add to dashboard Cite

show abstract

Underwater image saliency detection based on refined attentional feedback mechanism

Liu,

2023

Third International Conference on Computer Graphics, Image, and Virtualization (ICCGIV 2023)

View full text Add to dashboard Cite

Underwater image saliency detection makes the terrestrial saliency detection model less effective in the application of underwater vehicles due to factors such as turbid water and unstable light, resulting in a degradation of the model's performance. We offer a model for underwater saliency detection based on an improved attentional feedback mechanism to overcome the aforementioned issues. The features at the top and bottom levels are effectively fused by forming a cascaded feedback decoder through the cross feature module and adding channel space attention, after which the residual refinement module is added for further refinement. The training and testing process uses underwater open datasets. The experimental findings demonstrate that our method is superior to other ways in comparative analysis with four general saliency detection methods and two underwater saliency detection methods on four underwater image datasets, proving the model's viability and efficacy.

show abstract

PSS-net: Parallel semantic segmentation network for detecting marine animals in underwater scene

Kim

Park²

2022

Front. Mar. Sci.

View full text Add to dashboard Cite

Marine scene segmentation is a core technology in marine biology and autonomous underwater vehicle research. However, it is challenging from the perspective of having a different environment from that of the conventional traffic segmentation on roads. There are two major challenges. The first is the difficulty of searching for objects under seawater caused by the relatively low-light environment. The second problem is segmenting marine animals with protective colors. To solve such challenges, in previous research, a method of simultaneously segmenting the foreground and the background was proposed based on a simple modification of the conventional model; however, it has limitations in improving the segmentation accuracy. Therefore, we propose a parallel semantic segmentation network to solve the above issues in which a model and a loss are employed to locate the foreground and the background separately. The training task to locate the foreground and the background is reinforced in the proposed method by adding an attention technique in a parallel model. Furthermore, the final segmentation is performed by aggregating two feature maps obtained by separately locating the foreground and the background.The test results using an open dataset for marine animal segmentation reveal that the proposed method achieves performance of 87%, 97.3%, 88%, 95.2%, and 0.029 in the mean intersection of the union, structure similarities, weighted F-measure, enhanced-alignment measure, and mean absolute error, respectively. These findings confirm that the proposed method has higher accuracy than the state-of-the-art methods. The proposed model and code are publicly available via Github1.

show abstract

Semantic Segmentation of Underwater Imagery: Dataset and Benchmark

Cited by 3 publications

References 44 publications

Compact and Fast Underwater Segmentation Network for Autonomous Underwater Vehicles

Compact and Fast Underwater Segmentation Network for Autonomous Underwater Vehicles

Underwater image saliency detection based on refined attentional feedback mechanism

PSS-net: Parallel semantic segmentation network for detecting marine animals in underwater scene

Contact Info

Product

Resources

About