A Comparison of Deep Neural Networks for Monocular Depth Map Estimation in Natural Environments Flying at Low Altitude
Currently, the use of Unmanned Aerial Vehicles (UAVs) in natural and complex environments has been increasing, because they are appropriate and affordable solutions to support different tasks such as rescue, forestry, and agriculture by collecting and analyzing high-resolution monocular images. Auto...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/24/9830 |
| _version_ | 1797455314809782272 |
|---|---|
| author | Alexandra Romero-Lugo Andrea Magadan-Salazar Jorge Fuentes-Pacheco Raúl Pinto-Elías |
| author_facet | Alexandra Romero-Lugo Andrea Magadan-Salazar Jorge Fuentes-Pacheco Raúl Pinto-Elías |
| author_sort | Alexandra Romero-Lugo |
| collection | DOAJ |
| description | Currently, the use of Unmanned Aerial Vehicles (UAVs) in natural and complex environments has been increasing, because they are appropriate and affordable solutions to support different tasks such as rescue, forestry, and agriculture by collecting and analyzing high-resolution monocular images. Autonomous navigation at low altitudes is an important area of research, as it would allow monitoring parts of the crop that are occluded by their foliage or by other plants. This task is difficult due to the large number of obstacles that might be encountered in the drone’s path. The generation of high-quality depth maps is an alternative for providing real-time obstacle detection and collision avoidance for autonomous UAVs. In this paper, we present a comparative analysis of four supervised learning deep neural networks and a combination of two for monocular depth map estimation considering images captured at low altitudes in simulated natural environments. Our results show that the Boosting Monocular network is the best performing in terms of depth map accuracy because of its capability to process the same image at different scales to avoid loss of fine details. |
| first_indexed | 2024-03-09T15:52:39Z |
| format | Article |
| id | doaj.art-7fa968f5c38f4da98ec84b5a0bbc2f83 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T15:52:39Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-7fa968f5c38f4da98ec84b5a0bbc2f832023-11-24T17:55:59ZengMDPI AGSensors1424-82202022-12-012224983010.3390/s22249830A Comparison of Deep Neural Networks for Monocular Depth Map Estimation in Natural Environments Flying at Low AltitudeAlexandra Romero-Lugo0Andrea Magadan-Salazar1Jorge Fuentes-Pacheco2Raúl Pinto-Elías3Tecnológico Nacional de México, CENIDET, Cuernavaca 62490, Morelos, MexicoTecnológico Nacional de México, CENIDET, Cuernavaca 62490, Morelos, MexicoCONACyT-Centro de Investigación en Ciencias, Instituto de Investigación en Ciencias Básicas y Aplicadas, Universidad Autónoma del Estado de Morelos, Cuernavaca 62209, Morelos, MexicoTecnológico Nacional de México, CENIDET, Cuernavaca 62490, Morelos, MexicoCurrently, the use of Unmanned Aerial Vehicles (UAVs) in natural and complex environments has been increasing, because they are appropriate and affordable solutions to support different tasks such as rescue, forestry, and agriculture by collecting and analyzing high-resolution monocular images. Autonomous navigation at low altitudes is an important area of research, as it would allow monitoring parts of the crop that are occluded by their foliage or by other plants. This task is difficult due to the large number of obstacles that might be encountered in the drone’s path. The generation of high-quality depth maps is an alternative for providing real-time obstacle detection and collision avoidance for autonomous UAVs. In this paper, we present a comparative analysis of four supervised learning deep neural networks and a combination of two for monocular depth map estimation considering images captured at low altitudes in simulated natural environments. Our results show that the Boosting Monocular network is the best performing in terms of depth map accuracy because of its capability to process the same image at different scales to avoid loss of fine details.https://www.mdpi.com/1424-8220/22/24/9830deep learningmonocular depth estimationunmanned aerial vehicles |
| spellingShingle | Alexandra Romero-Lugo Andrea Magadan-Salazar Jorge Fuentes-Pacheco Raúl Pinto-Elías A Comparison of Deep Neural Networks for Monocular Depth Map Estimation in Natural Environments Flying at Low Altitude Sensors deep learning monocular depth estimation unmanned aerial vehicles |
| title | A Comparison of Deep Neural Networks for Monocular Depth Map Estimation in Natural Environments Flying at Low Altitude |
| title_full | A Comparison of Deep Neural Networks for Monocular Depth Map Estimation in Natural Environments Flying at Low Altitude |
| title_fullStr | A Comparison of Deep Neural Networks for Monocular Depth Map Estimation in Natural Environments Flying at Low Altitude |
| title_full_unstemmed | A Comparison of Deep Neural Networks for Monocular Depth Map Estimation in Natural Environments Flying at Low Altitude |
| title_short | A Comparison of Deep Neural Networks for Monocular Depth Map Estimation in Natural Environments Flying at Low Altitude |
| title_sort | comparison of deep neural networks for monocular depth map estimation in natural environments flying at low altitude |
| topic | deep learning monocular depth estimation unmanned aerial vehicles |
| url | https://www.mdpi.com/1424-8220/22/24/9830 |
| work_keys_str_mv | AT alexandraromerolugo acomparisonofdeepneuralnetworksformonoculardepthmapestimationinnaturalenvironmentsflyingatlowaltitude AT andreamagadansalazar acomparisonofdeepneuralnetworksformonoculardepthmapestimationinnaturalenvironmentsflyingatlowaltitude AT jorgefuentespacheco acomparisonofdeepneuralnetworksformonoculardepthmapestimationinnaturalenvironmentsflyingatlowaltitude AT raulpintoelias acomparisonofdeepneuralnetworksformonoculardepthmapestimationinnaturalenvironmentsflyingatlowaltitude AT alexandraromerolugo comparisonofdeepneuralnetworksformonoculardepthmapestimationinnaturalenvironmentsflyingatlowaltitude AT andreamagadansalazar comparisonofdeepneuralnetworksformonoculardepthmapestimationinnaturalenvironmentsflyingatlowaltitude AT jorgefuentespacheco comparisonofdeepneuralnetworksformonoculardepthmapestimationinnaturalenvironmentsflyingatlowaltitude AT raulpintoelias comparisonofdeepneuralnetworksformonoculardepthmapestimationinnaturalenvironmentsflyingatlowaltitude |