Tracking Sponge Size and Behaviour with Fixed Underwater Observatories

Möller, Torben; Nilssen, Ingunn; Nattkemper, Tim Wilhelm

doi:10.1007/978-3-030-05792-3_5

Cited by 8 publications

(14 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Within this context, high‐definition still and video image data constitute a key non‐destructive approach for the non‐invasive monitoring of aquatic marine environments (Aguzzi et al, 2019; Bicknell et al, 2016; Jahanbakht et al, 2021). Many studies in the literature contributed to the analysis of benthic fauna outside the Antarctic region (Lopez‐Vazquez et al, 2020; Möller & Nattkemper, 2021), including the analysis of corals (Osterloff et al, 2019; Zuazo et al, 2020) and sponge dynamics (Harrison et al, 2021; Möller et al, 2019).…”

Section: Discussionmentioning

confidence: 99%

Long‐term automated visual monitoring of Antarctic benthic fauna

et al. 2022

View full text Add to dashboard Cite

The rapid changes in the climate of Antarctica are likely to pose challenges to living communities, which makes monitoring of Antarctic fauna an urgent necessity. Benthos is particularly difficult to monitor, and is sensitive to local environmental changes. At the same time, long‐term monitoring is complicated by logistical factors. It is therefore urgent to develop advanced instruments to set up autonomous and long‐term monitoring programmes to obtain the lacking biological knowledge needed to understand this complex and remote marine environment. We present a pilot study to set up a non‐invasive and sustainable autonomous monitoring activity in Antarctica, leveraging on a specifically designed automated camera recording, computer vision and machine learning image processing techniques. We also present and analyse the high‐resolution image dataset acquired for an extended period of time encompassing both the summer and the Antarctic night and the corresponding transition periods. The results of this study demonstrate both the effectiveness of such an autonomous imaging devices for acquiring relevant long‐term visual data and the effectiveness of the proposed image analysis algorithms for extracting relevant scientific knowledge from such data. The presented results show how the extracted knowledge discloses dynamics of the observed ecosystems that can be obtained only through continuous observations extended in time, not achievable with the state‐of‐the‐art monitoring approaches commonly implemented in Antarctica. The success of this pilot study is a step towards the collection of continuous data near shore in Antarctic areas and in general in all the remote and extreme underwater habitats. Moreover, the presented stand‐alone and autonomous imaging device can be used for increasing the number of the monitoring sites in remote environments and when complemented with the acquisition of physical and bio‐chemical variables it can be used for obtaining data collections of great scientific value difficult to acquire otherwise.

show abstract

Section: Discussionmentioning

confidence: 99%

Long‐term automated visual monitoring of Antarctic benthic fauna

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Results from Models 1 and 2 demonstrated the utility of RootPainter to temporal changes in species behaviour. Sponge contractions have previously been studied in both shallow and deep-water using manual and bespoke machine learning methods [2,21,28,29]. 'Intrinsic' contractions observed in shallow-water sponges likely serve to clear the aquiferous system, where blocked canals may disrupt filter-feeding [63,64].…”

Section: Rootpainter Applicationsmentioning

confidence: 99%

New Interactive Machine Learning Tool for Marine Image Analysis

Clark,

Smith,

Fletcher

et al. 2023

Preprint

View full text Add to dashboard Cite

Due to advances in imaging technologies, the rate of marine video and image data collection is drastically increasing. Often these datasets are not analysed to their full potential as extracting information for multiple species, such as their presence and surface area, is incredibly time-consuming. This study demonstrates the potential of a new open-source interactive machine learning tool, RootPainter, to analyse large marine image datasets quickly and accurately. The tool was initially developed to measure plant roots, but here was tested on its ability to measure the presence and surface area of the cold-water coral reef associate sponge species,Mycale lingua, in two types of underwater image data: 18,346 time-lapse images and 1,420 remotely operated vehicle video frames. New corrective annotation metrics integrated with RootPainter, such as dice score and species area error, allow for the objective assessment of when to stop model training and reduce the need for manual model validation. Three highly accurateMycale linguamodels were created using RootPainter, as indicated by their average dice score of 0.94 ± 0.06. Model transfer and optimisation aided in the production of two of these models, increasing analysis efficiency from 6 to 16 times faster than manual annotation in Photoshop, for underwater observatory images. Sponge and surface area measurements were extracted from both datasets allowing future investigation of sponge behaviours and distributions. This study demonstrates that interactive machine learning tools and model sharing have the potential to dramatically increase image analysis speeds, collaborative research, and our collective knowledge on spatiotemporal patterns in biodiversity.

show abstract

“…After upsampling with four layers and concatenating with the low-level feature of the same spatial resolution from the Xception structure of the backbone network, the channel is reduced by 1 × 1 convolution before concatenating. Then, a 3 × 3 convolution fine-tuning feature is used and finally, upsampled with four layers to get the final prediction map [13].…”

Section: Related Workmentioning

confidence: 99%

“…The entry flow contains 11 convs, the middle flow contains 48 convs and the exit flow contains 6 convs, giving a total of 65 layers. We refer to this network as Xception_65 [13]. The Xception_65 network structure reduces the computational complexity, accelerates model training and guarantees its learning ability.…”

Section: Network Backbonementioning

confidence: 99%

“…The U-net network also has related applications in the underwater field and has achieved good performance. For examples, Möller et al [13] proposed an automated process based on convolutional networks (the U-Net) for high temporal coverage and resolution monitoring of specific regions of interest (such as coral reefs). This process can automatically generate a series of sponge sizes from an image series.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Semantic Segmentation of Underwater Images Based on Improved Deeplab

Liu

Fang

2020

JMSE

View full text Add to dashboard Cite

Image semantic segmentation technology has been increasingly applied in many fields, for example, autonomous driving, indoor navigation, virtual reality and augmented reality. However, underwater scenes, where there is a huge amount of marine biological resources and irreplaceable biological gene banks that need to be researched and exploited, are limited. In this paper, image semantic segmentation technology is exploited to study underwater scenes. We extend the current state-of-the-art semantic segmentation network DeepLabv3 + and employ it as the basic framework. First, the unsupervised color correction method (UCM) module is introduced to the encoder structure of the framework to improve the quality of the image. Moreover, two up-sampling layers are added to the decoder structure to retain more target features and object boundary information. The model is trained by fine-tuning and optimizing relevant parameters. Experimental results indicate that the image obtained by our method demonstrates better performance in improving the appearance of the segmented target object and avoiding its pixels from mingling with other class’s pixels, enhancing the segmentation accuracy of the target boundaries and retaining more feature information. Compared with the original method, our method improves the segmentation accuracy by 3%.

show abstract

Tracking Sponge Size and Behaviour with Fixed Underwater Observatories

Cited by 8 publications

References 14 publications

Long‐term automated visual monitoring of Antarctic benthic fauna

Long‐term automated visual monitoring of Antarctic benthic fauna

New Interactive Machine Learning Tool for Marine Image Analysis

Semantic Segmentation of Underwater Images Based on Improved Deeplab

Contact Info

Product

Resources

About