Sky and Ground Segmentation in the Navigation Visions of the Planetary Rovers

Sky and ground are two essential semantic components in computer vision, robotics, and remote sensing. The sky and ground segmentation has become increasingly popular. This research proposes a sky and ground segmentation framework for the rover navigation visions by adopting weak supervision and tra...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Boyu Kuang, Zeeshan A. Rana, Yifan Zhao
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	semantic segmentation weak supervision transfer learning conservative annotation method visual navigation visual sensor Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/2f99883e9da1496c99f2e4db30fb5c74
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:2f99883e9da1496c99f2e4db30fb5c74
record_format	dspace
spelling	oai:doaj.org-article:2f99883e9da1496c99f2e4db30fb5c742021-11-11T19:02:19ZSky and Ground Segmentation in the Navigation Visions of the Planetary Rovers10.3390/s212169961424-8220https://doaj.org/article/2f99883e9da1496c99f2e4db30fb5c742021-10-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/6996https://doaj.org/toc/1424-8220Sky and ground are two essential semantic components in computer vision, robotics, and remote sensing. The sky and ground segmentation has become increasingly popular. This research proposes a sky and ground segmentation framework for the rover navigation visions by adopting weak supervision and transfer learning technologies. A new sky and ground segmentation neural network (network in U-shaped network (NI-U-Net)) and a conservative annotation method have been proposed. The pre-trained process achieves the best results on a popular open benchmark (the Skyfinder dataset) by evaluating seven metrics compared to the state-of-the-art. These seven metrics achieve 99.232%, 99.211%, 99.221%, 99.104%, 0.0077, 0.0427, and 98.223% on accuracy, precision, recall, dice score (F1), misclassification rate (MCR), root mean squared error (RMSE), and intersection over union (IoU), respectively. The conservative annotation method achieves superior performance with limited manual intervention. The NI-U-Net can operate with 40 frames per second (FPS) to maintain the real-time property. The proposed framework successfully fills the gap between the laboratory results (with rich idea data) and the practical application (in the wild). The achievement can provide essential semantic information (sky and ground) for the rover navigation vision.Boyu KuangZeeshan A. RanaYifan ZhaoMDPI AGarticlesemantic segmentationweak supervisiontransfer learningconservative annotation methodvisual navigationvisual sensorChemical technologyTP1-1185ENSensors, Vol 21, Iss 6996, p 6996 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	semantic segmentation weak supervision transfer learning conservative annotation method visual navigation visual sensor Chemical technology TP1-1185
spellingShingle	semantic segmentation weak supervision transfer learning conservative annotation method visual navigation visual sensor Chemical technology TP1-1185 Boyu Kuang Zeeshan A. Rana Yifan Zhao Sky and Ground Segmentation in the Navigation Visions of the Planetary Rovers
description	Sky and ground are two essential semantic components in computer vision, robotics, and remote sensing. The sky and ground segmentation has become increasingly popular. This research proposes a sky and ground segmentation framework for the rover navigation visions by adopting weak supervision and transfer learning technologies. A new sky and ground segmentation neural network (network in U-shaped network (NI-U-Net)) and a conservative annotation method have been proposed. The pre-trained process achieves the best results on a popular open benchmark (the Skyfinder dataset) by evaluating seven metrics compared to the state-of-the-art. These seven metrics achieve 99.232%, 99.211%, 99.221%, 99.104%, 0.0077, 0.0427, and 98.223% on accuracy, precision, recall, dice score (F1), misclassification rate (MCR), root mean squared error (RMSE), and intersection over union (IoU), respectively. The conservative annotation method achieves superior performance with limited manual intervention. The NI-U-Net can operate with 40 frames per second (FPS) to maintain the real-time property. The proposed framework successfully fills the gap between the laboratory results (with rich idea data) and the practical application (in the wild). The achievement can provide essential semantic information (sky and ground) for the rover navigation vision.
format	article
author	Boyu Kuang Zeeshan A. Rana Yifan Zhao
author_facet	Boyu Kuang Zeeshan A. Rana Yifan Zhao
author_sort	Boyu Kuang
title	Sky and Ground Segmentation in the Navigation Visions of the Planetary Rovers
title_short	Sky and Ground Segmentation in the Navigation Visions of the Planetary Rovers
title_full	Sky and Ground Segmentation in the Navigation Visions of the Planetary Rovers
title_fullStr	Sky and Ground Segmentation in the Navigation Visions of the Planetary Rovers
title_full_unstemmed	Sky and Ground Segmentation in the Navigation Visions of the Planetary Rovers
title_sort	sky and ground segmentation in the navigation visions of the planetary rovers
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/2f99883e9da1496c99f2e4db30fb5c74
work_keys_str_mv	AT boyukuang skyandgroundsegmentationinthenavigationvisionsoftheplanetaryrovers AT zeeshanarana skyandgroundsegmentationinthenavigationvisionsoftheplanetaryrovers AT yifanzhao skyandgroundsegmentationinthenavigationvisionsoftheplanetaryrovers
_version_	1718431633894277120

Sky and Ground Segmentation in the Navigation Visions of the Planetary Rovers

Ejemplares similares