Semantic Segmentation of Underwater Environments Using DeepLabv3+ and Transfer Learning

Miguel Chicchon, Hector Bedon

Resultado de la investigación: Capítulo del libro/informe/acta de congresoArticulo (Contribución a conferencia)revisión exhaustiva

1 Cita (Scopus)

Resumen

The semantic segmentation approach is essential in automated scene analysis, but its application in underwater environments is still limited. Datasets generally have insufficient labeled data, unbalanced data classes, and different lighting conditions, making it difficult to obtain optimal results. Currently, deep convolutional neural networks allow very good results in machine vision tasks, and one of the network architectures with good performance in semantic segmentation is DeepLabv3 +. This paper evaluates the performance of DeepLabv3 + and transfer learning based on pre-trained backend networks in ImageNet to study underwater scenes. The experimentation is carried out on a dataset available on the Internet with labels of eight classes. Experimental results show that DeepLabv3 + and transfer learning are effective for semantic segmentation of multiple underwater scene objects with insufficient tagged data and unbalanced classes.

Idioma originalInglés
Título de la publicación alojadaSmart Trends in Computing and Communications - Proceedings of SmartCom 2021
EditoresYu-Dong Zhang, Tomonobu Senjyu, Chakchai So-In, Amit Joshi
EditorialSpringer Nature
Páginas301-309
Número de páginas9
Volumen286
ISBN (versión impresa)9789811640155
DOI
EstadoPublicada - 26 oct. 2021
Evento5th International Conference on Smart Trends in Computing and Communications, SmartCom 2021 - Virtual, Online
Duración: 15 abr. 202116 abr. 2021

Serie de la publicación

NombreLecture Notes in Networks and Systems
Volumen286

Conferencia

Conferencia5th International Conference on Smart Trends in Computing and Communications, SmartCom 2021
CiudadVirtual, Online
Período15/04/2116/04/21

COAR

  • Artículo de conferencia

Huella

Profundice en los temas de investigación de 'Semantic Segmentation of Underwater Environments Using DeepLabv3+ and Transfer Learning'. En conjunto forman una huella única.

Citar esto