Underwater image segmentation in the wild using deep learning

Drews-Jr, Paulo L. J.; Souza, Isadora de; Maurell, Igor P.; Protas, Églen; Botelho, Silvia S. C.

doi:10.1186/s13173-021-00117-7

Cited by 28 publications

(5 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They also propose an encoderdecoder model (SUIM-Net) to balance the performance and computational efficiency. In [23], a dataset of images of real and simulated environments is presented, and explores different strategies of segmentation, fine-tuning, and image restoration. Complementarily, [24] presents the DeepFish benchmark for classification, counting, location, and segmentation tasks, allowing the training of multitasking models.…”

Section: Related Workmentioning

confidence: 99%

Semantic Segmentation of Fish and Underwater Environments Using Deep Convolutional Neural Networks and Learned Active Contours

et al. 2023

View full text Add to dashboard Cite

The conservation of marine resources requires constant monitoring of the underwater environment by researchers. For this purpose, visual automated monitoring systems are of great interest, especially those that can describe the environment using semantic segmentation based on deep learning. Although they have been successfully used in several applications, such as biomedical ones, obtaining optimal results in underwater environments is still a challenge due to the heterogeneity of water and lighting conditions, and the scarcity of labeled datasets. Even more, the existing deep learning techniques oriented to semantic segmentation only provide low resolution results, lacking the enough spatial details for a high performance monitoring. To address these challenges, a combined loss function based on the active contour theory and level set methods is proposed to refine the spatial segmentation resolution and quality. To evaluate the method, a new underwater dataset with pixel annotations for three classes (fish, seafloor, and water) was created using images from publicly accessible datasets like SUIM, RockFish, and DeepFish. The performance of architectures of convolutional neural networks (CNNs), such as UNet and DeepLabV3+, trained with different loss functions (cross entropy, dice, and active contours) was compared, finding that the proposed combined loss function improved the segmentation results by around 3%, both in the metric Intercept Over Union (IoU) as in Hausdorff Distance (HD).

show abstract

Section: Related Workmentioning

confidence: 99%

Semantic Segmentation of Fish and Underwater Environments Using Deep Convolutional Neural Networks and Learned Active Contours

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Deep learning methods have also been used to apply image segmentation to underwater datasets (Liu and Fang, 2020;Drews Jr et al, 2021;Nezla et al, 2021). However, a lack of properly labelled datasets for underwater imaging applications has been a notable challenge in this area.…”

Section: Related Workmentioning

confidence: 99%

Image Feature Extraction Methods for Structure Detection From Underwater Imagery

Roberts,

Helmholz,

Parnum

et al. 2023

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. The use of autonomous underwater vehicles (AUVs) for surveying underwater infrastructure presents a potential cost saving in comparison to remotely operated vehicles (ROVs). One of the challenges when processing images of underwater structures captured by an AUV, is that vast number of images captured during the mission usually do not show the structure. For instance, images captured during the dive to the structure or of the sea floor, or of the deep sea facing away from the structure. Too many images captured, without relevant information for a 3D reconstruction of the structure, leads to increased processing time and issues during the reconstruction process. There are two solutions to reduce the images to only images showing the structure. Firstly, only images of the structure are captured in the first place or remove images that are not useful after the capture and before further processing. This study developed and evaluated techniques that would enable the first strategy to be applied in an AUV. To apply this strategy in an AUV, would require an on-board structure detection system to ensure that they are correctly orientated for capturing useful footage during a survey mission. However, the marine environment poses several challenges to image-based object detection. Furthermore, small AUVs have limited power and computational resources available while deployed on a mission. To investigate the suitability of creating a lightweight structure detection model for the purpose of image evaluation, three computationally efficient image feature extraction methods (colour moments, local binary patterns (LBP), and Haar wavelet decomposition) were evaluated for their ability to distinguish underwater structures from background areas using unsupervised k-means models. LBP was found to be an effective method for identifying underwater structures in open water conditions. For identifying a structure against the seabed, colour moments were identified as the most effective method.

show abstract

“…an adaptive threshold. Adaptive segmentation features: Adaptive thresholds calculate thresholds for a small portion of each image, so that the thresholds for different areas of the picture are not the same, suitable for unevenly distributed pictures [6]. Figure 4 is a comparison of adaptive threshold segmentation and fixed threshold segmentation, the first is the original picture, the second is the fixed threshold segmentation, and the last two are adaptive threshold segmentation, which can be seen to be better handled.…”

Section: Adaptive Threshold Segmentationmentioning

confidence: 99%