Non-intrusively estimating the live body biomass of Pintado Real® fingerlings: A feature selection approach

Pache, Marcio Carneiro Brito; Sant’Ana, Diego André; Rezende, Fábio Prestes Cesar; Porto, João Vitor de Andrade; Rozales, João Victor Araújo; Weber, Vanessa; Oliveira, Adair da Silva; Garcia, Vanir; Naka, Marco Hiroshi; Pistori, Hemerson

doi:10.1016/j.ecoinf.2021.101509

Cited by 7 publications

(1 citation statement)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In more recent work, a machine learning approach for estimating the biomass of Pintado Real fingerlings was developed by Pache et al [23], comparing an environment with lighting and without lighting. The approach showed better results for the illuminated dataset, and the Linear Regression algorithm obtained 76% R2.…”

Section: Related Workmentioning

confidence: 99%

The influence of lighting on fingerlings counting

Garcia,

Sant’Ana,

Zanoni

et al. 2023

Anais Do XVIII Workshop De Visão Computacional (WVC 2023)

View full text Add to dashboard Cite

The search for the automation of processes within fish farms has encouraged the research of new methods for counting fingerlings. The purpose of these devices is to reduce manual labor, increase counting precision and reduce fish stress. The automatic counting system consists of software that uses computer vision techniques to process captured images and a mechanical structure to manipulate fingerlings. A difficulty encountered in image processing is the influence of lighting, which may vary according to the environment, position, and time of day that the device is used. In this paper, we vary the illumination intensity, measured by luxmeter, to identify if this variation interferes in the counting precision. We analyzed five video blocks recorded in the Pacu Project environment in Terenos-MS. A MSE of 9.85 was achieved. The conclusion was that the illumination interferes in the recognition of fingerlings in the video and, consequently, in the counting.

show abstract

Section: Related Workmentioning

confidence: 99%

The influence of lighting on fingerlings counting

Garcia,

Sant’Ana,

Zanoni

et al. 2023

Anais Do XVIII Workshop De Visão Computacional (WVC 2023)

View full text Add to dashboard Cite

show abstract

A review of deep learning-based stereo vision techniques for phenotype feature and behavioral analysis of fish in aquaculture

Zhao,

Qin,

et al. 2024

Artif Intell Rev

View full text Add to dashboard Cite

The industrialization, high-density, and greener aquaculture requires a more precise and intelligent aquaculture management. Phenotypic and behavioral information of fish, which can reflect fish growth and welfare status, play a crucial role in aquaculture management. Stereo vision technology, which simulates parallax perception of the human eye, can obtain the three-dimensional phenotypic characteristics and movement trajectories of fish through different types of sensors. It can overcome the limitations in dealing with fish deformation, frequent occlusions and understanding three-dimension scenes compared to the traditional two-dimensional computer vision techniques. With the deep learning development and application in aquaculture, stereo vision has become a super computer vision technology that can provide more precise and interpretable information for intelligent aquaculture management, such as size estimation, counting and behavioral analysis of fish. Hence, it is very beneficial for researchers, managers, and entrepreneurs to possess a thorough comprehension about the fast-developing stereo vision technology for modern aquaculture. This study provides a critical review of relevant topics, including the four-layer application structure of stereo vision technology in aquaculture, various deep learning-based technologies used, and specific application scenarios. The review contributes to research development by identifying the current challenges and provide valuable suggestions for future research directions. This review can serve as a useful resource for developing future studies and applications of stereo vision technology in smart aquaculture, focusing on phenotype feature extraction and behavioral analysis of fish.

show abstract