Drones Computer Vision using Deep Learning to Support Fishing Management in Indonesia

Liawatimena, Suryadiputra; Atmadja, Wiedjaja; Abbas, Bahtiar Saleh; Trisetyarso, Agung; Wibowo, Antoni; Barlian, Erland; Hardanto, Lilik T.; Triany, Natassya Afdalena; Faisal, F.; Sulistiawan, Jaka; Yojana, Albert Cahya

doi:10.1088/1755-1315/426/1/012155

Cited by 2 publications

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These materials can be affixed with detectable sensors that allow the structures to be routinely monitored. Such data streams can now be integrated and perhaps deep learning algorithms (Fallati et al, 2019;Liawatimena et al, 2020;Meng et al, 2018;Provost et al, 2020;Yang et al, 2020) would allow such systems to become predictive, affording valuable time to circumvent an impending outbreak.…”

Section: Nano-enabled Early Warning Systems: Water Quality Monitorimentioning

confidence: 99%

Nano‐scale applications in aquaculture: Opportunities for improved production and disease control

Sabo‐Attwood

Apul

Bisesi

et al. 2021

Journal of Fish Diseases

View full text Add to dashboard Cite

Aquaculture has evolved from its earliest documented forms in the Fan Li Dynasty ca 4000 BC (Nash, 2011), to a multi-sector industry, supporting vital food production, globally. With the world's population expected to near 10 billion by 2050 (Anderson, 2010; Conforti et al., 2011), food, energy and water needs have surfaced as the most profound challenges in this new millennium. Global food shortages are exacerbated by reduced crop yields due to global warming and limited availability of water for agriculture. To ensure food security, increases in production volume of staple foods (rice, wheat, etc.), alongside with high calorie protein-based products (meat and fish) are needed. Fish are the most effective protein sources for humans with the highest edible yield (nearly 70% of the body mass utilized) and protein retention (31% vs. 18% for red meat) (Kaiser, 2012). Global production of protein from aquatic species is partially accomplished by marine and freshwater aquaculture practices with the latter producing 50 million metric tons, valued at $100 billion, annually (Bostock et al., 2010). This makes aquaculture the fastest growing food-production sector, comprising nearly 50% of the current seafood supply (Bostock et al., 2010). In addition to food security, aquaculture also plays an important role in habitat restoration, recreation, and threatened and endangered species conservation. Aquaculture is practiced on a global scale using varied approaches (i.e. intensive, extensive) and scales (i.e. high density, low density). Regardless of the application, sustainable aquaculture operations have production-specific challenges and bottlenecks. The ability to manage aquatic disease agents, monitor and maintain animal health constitutes an assemblage of notable challenges

show abstract

Section: Nano-enabled Early Warning Systems: Water Quality Monitorimentioning

confidence: 99%

Nano‐scale applications in aquaculture: Opportunities for improved production and disease control

Sabo‐Attwood

Apul

Bisesi

et al. 2021

Journal of Fish Diseases

View full text Add to dashboard Cite

show abstract

Detection and Identification of Fish Skin Health Status Referring to Four Common Diseases Based on Improved YOLOv4 Model

Zhang

Chen

et al. 2023

Fishes

View full text Add to dashboard Cite

A primary problem affecting the sustainable development of aquaculture is fish skin diseases. In order to prevent the outbreak of fish diseases and to provide prompt treatment to avoid mass mortality of fish, it is essential to detect and identify skin diseases immediately. Based on the YOLOv4 model, coupled with lightweight depthwise separable convolution and optimized feature extraction network and activation function, the detection and identification model of fish skin disease is constructed in this study. The developed model is tested for the diseases hemorrhagic septicemia, saprolegniasis, benedeniasis, and scuticociliatosis, and applied to monitor the health condition of fish skin in deep-sea cage culture. Results show that the MobileNet3-GELU-YOLOv4 model proposed in this study has an improved learning ability, and the number of model parameters is reduced. Compared to the original YOLOv4 model, its mAP and detection speed increased by 12.39% and 19.31 FPS, respectively. The advantages of the model are its intra-species classification capability, lightweight deployment, detection accuracy, and speed, making the model more applicable to the real-time monitoring of fish skin health in a deep-sea aquaculture environment.

show abstract

Drones Computer Vision using Deep Learning to Support Fishing Management in Indonesia

Cited by 2 publications

References 9 publications

Nano‐scale applications in aquaculture: Opportunities for improved production and disease control

Nano‐scale applications in aquaculture: Opportunities for improved production and disease control

Detection and Identification of Fish Skin Health Status Referring to Four Common Diseases Based on Improved YOLOv4 Model

Contact Info

Product

Resources

About