Marine Animal Segmentation

Li, Lin; Dong, Bo; Rigall, Eric; Zhou, Tao; Dong, Junyu; Chen, Geng

doi:10.1109/tcsvt.2021.3093890

Cited by 28 publications

(8 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This type of segmentation is particularly useful for a more accurate estimation of animal sizes, as it provides the exact image area occupied by the animal. Various deep learning models have been applied successfully for free-swimming animals, such as cod and jellyfish, captured by stationary underwater cameras [ 46 ], up to 37 different marine animals, including those with camouflage, as part of the MAS3K dataset [ 47 , 48 , 49 ], fish passing through a camera chamber in a fish trawl [ 40 ] and multiple fish species in a tropical habitat [ 50 ].…”

Section: Related Workmentioning

confidence: 99%

A Deep-Learning Based Pipeline for Estimating the Abundance and Size of Aquatic Organisms in an Unconstrained Underwater Environment from Continuously Captured Stereo Video

Böer

Gröger

Badri-Höher

et al. 2023

Sensors

View full text Add to dashboard Cite

The utilization of stationary underwater cameras is a modern and well-adapted approach to provide a continuous and cost-effective long-term solution to monitor underwater habitats of particular interest. A common goal of such monitoring systems is to gain better insight into the dynamics and condition of populations of various marine organisms, such as migratory or commercially relevant fish taxa. This paper describes a complete processing pipeline to automatically determine the abundance, type and estimate the size of biological taxa from stereoscopic video data captured by the stereo camera of a stationary Underwater Fish Observatory (UFO). A calibration of the recording system was carried out in situ and, afterward, validated using the synchronously recorded sonar data. The video data were recorded continuously for nearly one year in the Kiel Fjord, an inlet of the Baltic Sea in northern Germany. It shows underwater organisms in their natural behavior, as passive low-light cameras were used instead of active lighting to dampen attraction effects and allow for the least invasive recording possible. The recorded raw data are pre-filtered by an adaptive background estimation to extract sequences with activity, which are then processed by a deep detection network, i.e., Yolov5. This provides the location and type of organisms detected in each video frame of both cameras, which are used to calculate stereo correspondences following a basic matching scheme. In a subsequent step, the size and distance of the depicted organisms are approximated using the corner coordinates of the matched bounding boxes. The Yolov5 model employed in this study was trained on a novel dataset comprising 73,144 images and 92,899 bounding box annotations for 10 categories of marine animals. The model achieved a mean detection accuracy of 92.4%, a mean average precision (mAP) of 94.8% and an F1 score of 93%.

show abstract

Section: Related Workmentioning

confidence: 99%

A Deep-Learning Based Pipeline for Estimating the Abundance and Size of Aquatic Organisms in an Unconstrained Underwater Environment from Continuously Captured Stereo Video

Böer

Gröger

Badri-Höher

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…The aim of COD is to identify objects that are "seamlessly" embedded in their background surroundings. This is a very challenging task due to the high intrinsic similarities between the target object and the background [100][101][102]. Recent research [103] suggests that depth can provide useful spatial information to improve COD results.…”

Section: Application To Rgb-d Camouflaged Object Detectionmentioning

confidence: 99%

Specificity-preserving RGB-D saliency detection

Zhou¹,

Fu²,

Chen³

et al. 2023

Comp. Visual Media

Self Cite

View full text Add to dashboard Cite

Salient object detection (SOD) in RGB and depth images has attracted increasing research interest. Existing RGB-D SOD models usually adopt fusion strategies to learn a shared representation from RGB and depth modalities, while few methods explicitly consider how to preserve modality-specific characteristics. In this study, we propose a novel framework, the specificity-preserving network (SPNet), which improves SOD performance by exploring both the shared information and modality-specific properties. Specifically, we use two modality-specific networks and a shared learning network to generate individual and shared saliency prediction maps. To effectively fuse cross-modal features in the shared learning network, we propose a cross-enhanced integration module (CIM) and propagate the fused feature to the next layer to integrate cross-level information. Moreover, to capture rich complementary multi-modal information to boost SOD performance, we use a multi-modal feature aggregation (MFA) module to integrate the modality-specific features from each individual decoder into the shared decoder. By using skip connections between encoder and decoder layers, hierarchical features can be fully combined. Extensive experiments demonstrate that our SPNet outperforms cutting-edge approaches on six popular RGB-D SOD and three camouflaged object detection benchmarks. The project is publicly available at https://github.com/taozh2017/SPNet.

show abstract

“…Recently, detecting marine creatures has also become favorable (X. Liu [22], Merencilla et al [23], Li et al [24]). Shark-EYE was developed by Merencilla [23] by using the YOLOv3 algorithm to detect single shark fish, including multi-scale prediction and bounding box prediction-based logistic regression.…”

Section: Deep Learning-basedmentioning

confidence: 99%

“…However, this work focuses on classifying individual or close objects. Similar motivation by Li et al [24] created the world's first large-scale Marine Animal Segmentation (MAS) dataset, MAS3K, using an ECD-Net-based MAS model. Their MAS3K collection contains several photos of marine animals with high-quality annotations, covering complicated underwater environments and the camouflage properties of marine animals.…”

Section: Deep Learning-basedmentioning

confidence: 99%

Underwater Fish Detection and Counting Using Mask Regional Convolutional Neural Network

Khai

Abdullah

Hasan

et al. 2022

Water

View full text Add to dashboard Cite

Fish production has become a roadblock to the development of fish farming, and one of the issues encountered throughout the hatching process is the counting procedure. Previous research has mainly depended on the use of non-machine learning-based and machine learning-based counting methods and so was unable to provide precise results. In this work, we used a robotic eye camera to capture shrimp photos on a shrimp farm to train the model. The image data were classified into three categories based on the density of shrimps: low density, medium density, and high density. We used the parameter calibration strategy to discover the appropriate parameters and provided an improved Mask Regional Convolutional Neural Network (Mask R-CNN) model. As a result, the enhanced Mask R-CNN model can reach an accuracy rate of up to 97.48%.

show abstract

Marine Animal Segmentation

Cited by 28 publications

References 68 publications

A Deep-Learning Based Pipeline for Estimating the Abundance and Size of Aquatic Organisms in an Unconstrained Underwater Environment from Continuously Captured Stereo Video

A Deep-Learning Based Pipeline for Estimating the Abundance and Size of Aquatic Organisms in an Unconstrained Underwater Environment from Continuously Captured Stereo Video

Specificity-preserving RGB-D saliency detection

Underwater Fish Detection and Counting Using Mask Regional Convolutional Neural Network

Contact Info

Product

Resources

About