Single image depth estimation: An overview

Mertan, Alican; Duff, Damien Jade; Ünal, Gözde

doi:10.1016/j.dsp.2022.103441

Cited by 53 publications

(23 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, carrying out ground surveys is impractical since spots of interest could be hard or even dangerous to access and field studies would drastically reduce the automation potential of river camera images. A third solution that would consist in merging the camera images with digital elevation models can only be performed manually at this stage, as current literature suggests that deep learning methods are not accurate enough to perform such tasks (Mertan et al, 2021). An object detection approach has also been considered to evaluate flood situations in urban areas (Rizk et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

Calibrated river-level estimation from river cameras using convolutional neural networks

Vandaele

Dance

Ojha

2023

Environ. Data Science

View full text Add to dashboard Cite

Monitoring river water levels is essential for the study of floods and mitigating their risks. River gauges are a well-established method for river water-level monitoring but many flood-prone areas are ungauged and must be studied through gauges located several kilometers away. Taking advantage of river cameras to observe river water levels is an accessible and flexible solution but it requires automation. However, current automated methods are only able to extract uncalibrated river water-level indexes from the images, meaning that these indexes are relative to the field of view of the camera, which limits their application. With this work, we propose a new approach to automatically estimate calibrated river water-level indexes from images of rivers. This approach is based on the creation of a new dataset of 32,715 images coming from 95 river cameras in the UK and Ireland, cross-referenced with gauge data (river water-level information), which allowed us to train convolutional neural networks. These networks are able to accurately produce two types of calibrated river water-level indexes from images: one for continuous river water-level monitoring, and the other for flood event detection. This work is an important step toward the automated use of cameras for flood monitoring.

show abstract

Section: Introductionmentioning

confidence: 99%

Calibrated river-level estimation from river cameras using convolutional neural networks

Vandaele

Dance

Ojha

2023

Environ. Data Science

View full text Add to dashboard Cite

show abstract

“…Current data-driven methods predict depth by learning implicit structural and semantic information that provides enough monocular cues for depth estimation. This requires the network to look at bigger parts of the scene [2], which has been addressed by many works [3], [4] in the field of single-view depth estimation in recent years.…”

Section: Introductionmentioning

confidence: 99%

$\mathcal {S}^{2}$Net: Accurate Panorama Depth Estimation on Spherical Surface

Wang

Yuan

et al. 2023

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

“…D EPTH estimation is a crucial challenge that is used in a variety of computer vision applications, including 3D vision [1], 3D face recognition [2], and autonomous vehicles [3] due to the low cost of consumer depth cameras and real-time performances. Raw depth maps, on the other hand, continue to face significant acquisition distortion and detailed corruption.…”

Section: Introductionmentioning

confidence: 99%

A Robust Light-Weight Fused-Feature Encoder-Decoder Model for Monocular Facial Depth Estimation From Single Images Trained on Synthetic Data

et al. 2023

View full text Add to dashboard Cite

Due to the real-time acquisition and reasonable cost of consumer cameras, monocular depth maps have been employed in a variety of visual applications. Regarding ongoing research in depth estimation, they continue to suffer from low accuracy and enormous sensor noise. To improve the prediction of depth maps, this paper proposed a lightweight neural facial depth estimation model based on single image frames. Following a basic encoder-decoder network design, the features are extracted by initializing the encoder with a high-performance pre-trained network and reconstructing high-quality facial depth maps with a simple decoder. The model can employ pixel representations and recover full details in terms of facial features and boundaries by employing a feature fusion module. When tested and evaluated across four public facial depth datasets, the suggested network provides more reliable and state-of-the-art results, with significantly less computational complexity and a reduced number of parameters. The training procedure is primarily based on the use of synthetic human facial images, which provide a consistent ground truth depth map, and the employment of an appropriate loss function leads to higher performance. Numerous experiments have been performed to validate and demonstrate the usefulness of the proposed approach. Finally, the model performs better than existing comparative facial depth networks in terms of generalization ability and robustness across different test datasets, setting a new baseline method for facial depth maps.

show abstract

Single image depth estimation: An overview

Cited by 53 publications

References 66 publications

Calibrated river-level estimation from river cameras using convolutional neural networks

Calibrated river-level estimation from river cameras using convolutional neural networks

$\mathcal {S}^{2}$Net: Accurate Panorama Depth Estimation on Spherical Surface

A Robust Light-Weight Fused-Feature Encoder-Decoder Model for Monocular Facial Depth Estimation From Single Images Trained on Synthetic Data

Contact Info

Product

Resources

About