Vision based real-time fish detection using convolutional neural network

Sung, Minsung; Yu, Son-Cheol; Girdhar, Yogesh

doi:10.1109/oceanse.2017.8084889

Cited by 114 publications

(47 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These values show a high detection capacity of objects that have been previously trained for a height of approximately 100 meters. Note that the detection models implemented by other authors [20], [21], [22], [23], have been trained for heights of 5, 10, 20 and 30 meters, and the estimates reach a sensitivity of approximately 77 %; while the specificity reached is close to 72%. These results show the effectiveness of the implementation carried out in this investigation.…”

Section: A Results Of Video Analyticsmentioning

confidence: 95%

Multipurpose unmanned system: an efficient solution to increase the capabilities of the UAVs

et al. 2020

View full text Add to dashboard Cite

The results of this research propose the implementation of a system that significantly increases the capacity of unmanned vehicles, turning them into multifunctional vehicles. The system has a logistics dispatch module and a video analytics module. The first module allows the delivery of medical, food, smoke, disinfectant, etc. The module is practical, safe and economical, features that denote the feasibility of immediate implementation in unmanned vehicles of any rank and / or classification. Note that the implementation of the dispatch module does not require additional radio frequency systems. The second module includes a video analysis process in real time, an aspect that constitutes a significant contribution to the proposed solution, since it allows obtaining important information during the flight; it also reduces the risk in air operations and simultaneously increases the efficiency of themselves. Note that video analytics optimizes resources and avoids jeopardizing the lives of aircraft pilots and crews who traditionally should carry out these activities. In times of pandemic, this innovation avoids direct contact with an infected population and can guarantee the sanitary conditions required in certain circumstances. The solution increases the capabilities of unmanned vehicles and makes them useful tools in various scenarios, whether caused by natural or man-made disasters. Our proposal is very flexible, reliable, and scalable and can be adapted to various models and makes of unmanned vehicles. The system has been implemented on fixed-wing and rotary-wing unmanned vehicles, showing satisfactory results.

show abstract

Section: A Results Of Video Analyticsmentioning

confidence: 95%

Multipurpose unmanned system: an efficient solution to increase the capabilities of the UAVs

et al. 2020

View full text Add to dashboard Cite

show abstract

“…However, one of the most timeconsuming aspects of biological observation has been identifying species, historically requiring taxonomic experts. Deep learning techniques enable automated classification of species from a variety of platforms, including: opportunistic citizen science visual observations (e.g., redmap.org.au; iNaturalist.org; Pimm et al, 2015); benthic photo quadrats (BisQue; Rahimi et al, 2014, Fedorov et al, 2017; cabled video observatories (Marini et al, 2018); unmanned underwater vehicles (Qin et al, 2015;Sung et al, 2017); acoustic-sensing hydrophones (Dugan et al, 2015;McQuay et al, 2017); plankton-sensing flow cytometers (Göröcs et al, 2018); and satellite imagery (Guirado et al, 2018). Taxonomic experts are still very much needed for developing datasets as inputs to this modeling approach.…”

Section: Artificial Intelligencementioning

confidence: 99%

Global Observational Needs and Resources for Marine Biodiversity

et al. 2019

View full text Add to dashboard Cite

The diversity of life in the sea is critical to the health of ocean ecosystems that support living resources and therefore essential to the economic, nutritional, recreational, and health needs of billions of people. Yet there is evidence that the biodiversity of many marine habitats is being altered in response to a changing climate and human activity. Understanding this change, and forecasting where changes are likely to occur, requires monitoring of organism diversity, distribution, abundance, and health. It requires a minimum of measurements including productivity and ecosystem function, species composition, allelic diversity, and genetic expression. These observations need to be complemented with metrics of environmental change and socioeconomic drivers. However, existing global ocean observing infrastructure and programs often do not explicitly consider observations of marine biodiversity and associated processes. Much effort has focused on physical, chemical and some biogeochemical measurements.

show abstract

“…where λ is a scale factor, introducing the constraint condition r 1 × r 2 = 0, |r 1 | = |r 2 | = 1, the solution of the internal parameter can be expressed as Equations (7) and (8).…”

Section: Camera Calibrationmentioning

confidence: 99%

“…Lu et al [7] used the deep neural network vgg-16 to identify tuna with an accuracy of 96%. Sung et al [8] made use of the YOLO architecture for real-time detection. Ammar et al [9] proposed a Symmetric Positive Definite (SPD) algorithm to generate synthetic data for the automatic detection of western lobsters, and the YOLO network is used for lobster detection.…”

Section: Introductionmentioning

confidence: 99%

Underwater Fish Body Length Estimation Based on Binocular Image Processing

Cheng

Zhang

et al. 2020

Information

View full text Add to dashboard Cite

Recently, the information analysis technology of underwater has developed rapidly, which is beneficial to underwater resource exploration, underwater aquaculture, etc. Dangerous and laborious manual work is replaced by deep learning-based computer vision technology, which has gradually become the mainstream. The binocular cameras based visual analysis method can not only collect seabed images but also construct the 3D scene information. The parallax of the binocular image was used to calculate the depth information of the underwater object. A binocular camera based refined analysis method for underwater creature body length estimation was constructed. A fully convolutional network (FCN) was used to segment the corresponding underwater object in the image to obtain the object position. A fish’s body direction estimation algorithm is proposed according to the segmentation image. The semi-global block matching (SGBM) algorithm was used to calculate the depth of the object region and estimate the object body length according to the left and right views of the object. The algorithm has certain advantages in time and accuracy for interest object analysis by the combination of FCN and SGBM. Experiment results show that this method effectively reduces unnecessary information, improves efficiency and accuracy compared to the original SGBM algorithm.

show abstract

Vision based real-time fish detection using convolutional neural network

Cited by 114 publications

References 2 publications

Multipurpose unmanned system: an efficient solution to increase the capabilities of the UAVs

Multipurpose unmanned system: an efficient solution to increase the capabilities of the UAVs

Global Observational Needs and Resources for Marine Biodiversity

Underwater Fish Body Length Estimation Based on Binocular Image Processing

Contact Info

Product

Resources

About