Zebrafish tracking using YOLOv2 and Kalman filter

Barreiros, Marta de Oliveira; Dantas, Diego de Oliveira; Silva, Luis Claudio de Oliveira; Ribeiro, Sidarta Tollendal Gomes; Barros Filho, Allan Kardec Duailibe

Zebrafish tracking using YOLOv2 and Kalman filter

Página do item simplificado Estatísticas

dc.contributor.author	Barreiros, Marta de Oliveira
dc.contributor.author	Dantas, Diego de Oliveira
dc.contributor.author	Silva, Luis Claudio de Oliveira
dc.contributor.author	Ribeiro, Sidarta Tollendal Gomes
dc.contributor.author	Barros Filho, Allan Kardec Duailibe
dc.date.accessioned	2021-02-10T17:18:30Z
dc.date.available	2021-02-10T17:18:30Z
dc.date.issued	2021-02-05
dc.description.resumo	Fish show rapid movements in various behavioral activities or associated with the presence of food. However, in periods of rapid movement, the rate at which occlusion occurs among the fish is quite high, causing inconsistency in the detection and tracking of fish, hindering the fish's identity and behavioral trajectory over a long period of time. Although some algorithms have been proposed to solve these problems, most of their applications were made in groups of fish that swim in shallow water and calm behavior, with few sudden movements. To solve these problems, a convolutional network of object recognition, YOLOv2, was used to delimit the region of the fish heads to optimize individual fish detection. In the tracking phase, the Kalman filter was used to estimate the best state of the fish's head position in each frame and, subsequently, the trajectories of each fish were connected among the frames. The results of the algorithm show adequate performances in the trajectories of groups of zebrafish that exhibited rapid movements	pt_BR
dc.identifier.citation	BARREIROS, Marta de Oliveira; DANTAS, Diego de Oliveira; SILVA, Luís Claudio de Oliveira; RIBEIRO, Sidarta; BARROS, Allan Kardec. Zebrafish tracking using YOLOv2 and Kalman filter. Scientific Reports, [S.l.], v. 11, n. 1, p. 3219, fev. 2021. doi: http://dx.doi.org/10.1038/s41598-021-81997-9. Disponível em: https://www.nature.com/articles/s41598-021-81997-9. Acesso em: 10 fev. 2021.	pt_BR
dc.identifier.doi	10.1038/s41598-021-81997-9
dc.identifier.uri	https://repositorio.ufrn.br/handle/123456789/31459
dc.language	en	pt_BR
dc.publisher	Springer Science and Business Media LLC.	pt_BR
dc.rights	Attribution 3.0 Brazil	*
dc.rights.uri	http://creativecommons.org/licenses/by/3.0/br/	*
dc.subject	Zebrafish	pt_BR
dc.subject	YOLOv2 network	pt_BR
dc.subject	Kalman filter	pt_BR
dc.subject	Behavior, animal	pt_BR
dc.title	Zebrafish tracking using YOLOv2 and Kalman filter	pt_BR
dc.type	article	pt_BR