Automated Analysis of Marine Video with Limited Data

Levy, Deborah L.; Belfer, Yuval; Osherov, Elad; Bigal, Eyal; Scheinin, Aviad; Nativ, Hagai; Tchernov, Dan; Treibitz, Tali

doi:10.1109/cvprw.2018.00187

Cited by 24 publications

(21 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, a variety of other DL frameworks and data sets exist that users can use easily. In particular, because of its strong support for graphical processing unit (GPU), the PyTorch framework has been used extensively in relatively recent literature (Ketkar 2017;Liu et al 2019).In fact, much of the research reviewed here (9/ 41) uses transfer learning (Siddiqui et al 2017;Levy et al 2018;Sun et al 2018), which involves using existing knowledge from related tasks or fields to improve model learning efficiency. The most common transfer learning technique is to use pretrained DL models that have been trained on related data sets with different categories.…”

Section: Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning for smart fish farming: applications, opportunities and challenges

Yang

Zhang

Liu

et al. 2020

Reviews in Aquaculture

209

View full text Add to dashboard Cite

The rapid emergence of deep learning (DL) technology has resulted in its successful use in various fields, including aquaculture. DL creates both new opportunities and a series of challenges for information and data processing in smart fish farming. This paper focuses on applications of DL in aquaculture, including live fish identification, species classification, behavioural analysis, feeding decisions, size or biomass estimation, and water quality prediction. The technical details of DL methods applied to smart fish farming are also analysed, including data, algorithms and performance. The review results show that the most significant contribution of DL is its ability to automatically extract features. However, challenges still exist; DL is still in a weak artificial intelligence stage and requires large amounts of labelled data for training, which has become a bottleneck that restricts further DL applications in aquaculture. Nevertheless, DL still offers breakthroughs for addressing complex data in aquaculture. In brief, our purpose is to provide researchers and practitioners with a better understanding of the current state of the art of DL in aquaculture, which can provide strong support for implementing smart fish farming applications.

show abstract

Section: Algorithmsmentioning

confidence: 99%

“…2017; Levy et al . 2018; Sun et al . 2018), which involves using existing knowledge from related tasks or fields to improve model learning efficiency.…”

Section: Technical Details and Overall Performancementioning

confidence: 99%

Deep learning for smart fish farming: applications, opportunities and challenges

Yang

Zhang

Liu

et al. 2020

Reviews in Aquaculture

209

View full text Add to dashboard Cite

show abstract

“…6. in these cases, estimating the location of the acoustic source and tracking it over time typically yields significantly valuable information, and may likely be the ultimate task of the sensing process. Common solutions for this challenging task include image-and video-based monitoring [98], LiDAR systems [3], as well as acoustic systems [47].…”

Section: Direction Of Arrival Estimation and Localization Through 3d Acoustic Arrays Of Arbitrary Shapementioning

confidence: 99%

Underwater Direction of Arrival Estimation using Wideband Arrays of Opportunity

Dubrovinskaya

Casari

2019

OCEANS 2019 - Marseille

View full text Add to dashboard Cite

Casari knows no boundaries. He believed in me to allow me to work independently while providing all the possible support and was by my side when needed. His high standards both in research and communication have become my constant beacon in my personal and professional growth. His assistance in every aspect of research work was absolutely invaluable.Another thank you should definitely go to my tutor Prof. Albert Banchs Roca for all his help with the paperwork from the very first days of my Ph.D. I would also like to say thanks to Dr. Ivor Nissen for his introduction to the world of underwater acoustic localization research, and for always keeping an eye on my progress. I am grateful to Dr. Diamant for welcoming and hosting me at Haifa University and enduring me during numerous sea trials. All the field experience I got during my trips to Israel is still one of the most unforgettable go through during my Ph.D.Furthermore, I would like to say many thanks to Dr. Konstantin Kebkal and Evologics GmbH colleagues for hosting me at their premises in Berlin and for all the invaluable help in organizing lab and field experiments. Special thanks to Veronika Kebkal who pushed everyone to make it possible (and fun!) Also, I would like to thank Dr. Fraser Dalgleish who hosted me at Florida Atlantic University and for sharing experimental data even after I left.A huge bunch of thanks goes to all my colleagues at IMDEA Networks for all the coffee break talks, dinner drinks, board games battles, and barbeque parties. Special thanks go to the "ground-floor" team for all the evening gossip times and fun we had.Last but not least thank you goes to my wonderful family. Thanks to my parents for teaching me to value knowledge and for giving me everything I need. And the most important thanks -to my husband Sergey Samodov, who was solving all my life problems, listened to my nagging during the hardest days saying, "this too shall pass", waiting for me to come back. I couldn't have done this journey without you.

show abstract

“…Getting to determine where objects are located in a given image (object localization) and which category each object belongs to (object classification) can be useful in a multitude of scenarios and implemented for multiple applications. In the marine environment object detection and classification has been used among others to record fish presence and recognition [16][17][18][19], to monitor marine turtles [20] or in the classification of planktonic organisms [21].…”

Section: Introductionmentioning

confidence: 99%

Jellytoring: Real-Time Jellyfish Monitoring Based on Deep Learning Object Detection

Martin‐Abadal

Ruiz‐Frau

Hinz

et al. 2020

Sensors

View full text Add to dashboard Cite

During the past decades, the composition and distribution of marine species have changed due to multiple anthropogenic pressures. Monitoring these changes in a cost-effective manner is of high relevance to assess the environmental status and evaluate the effectiveness of management measures. In particular, recent studies point to a rise of jellyfish populations on a global scale, negatively affecting diverse marine sectors like commercial fishing or the tourism industry. Past monitoring efforts using underwater video observations tended to be time-consuming and costly due to human-based data processing. In this paper, we present Jellytoring, a system to automatically detect and quantify different species of jellyfish based on a deep object detection neural network, allowing us to automatically record jellyfish presence during long periods of time. Jellytoring demonstrates outstanding performance on the jellyfish detection task, reaching an F1 score of 95.2%; and also on the jellyfish quantification task, as it correctly quantifies the number and class of jellyfish on a real-time processed video sequence up to a 93.8% of its duration. The results of this study are encouraging and provide the means towards a efficient way to monitor jellyfish, which can be used for the development of a jellyfish early-warning system, providing highly valuable information for marine biologists and contributing to the reduction of jellyfish impacts on humans.

show abstract

Automated Analysis of Marine Video with Limited Data

Cited by 24 publications

References 36 publications

Deep learning for smart fish farming: applications, opportunities and challenges

Deep learning for smart fish farming: applications, opportunities and challenges

Underwater Direction of Arrival Estimation using Wideband Arrays of Opportunity

Jellytoring: Real-Time Jellyfish Monitoring Based on Deep Learning Object Detection

Contact Info

Product

Resources

About