In:
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Copernicus GmbH, Vol. XLIII-B2-2022 ( 2022-05-30), p. 1017-1023
Abstract:
Abstract. Depth estimation from a single image is a challenging task, especially inside the highly structured forest environment. In this paper, we propose a supervised deep learning model for monocular depth estimation based on forest imagery. We train our model on a new data set of forest RGB-D images that we collected using a terrestrial laser scanner. Alongside the input RGB image, our model uses a sparse depth channel as input to recover the dense depth information. The prediction accuracy of our model is significantly higher than that of state-of-the-art methods when applied in the context of forest depth estimation. Our model brings the RMSE down to 2.1 m, compared to 4 m and above for reference methods.
Type of Medium:
Online Resource
ISSN:
2194-9034
DOI:
10.5194/isprs-archives-XLIII-B2-2022-1017-2022
Language:
English
Publisher:
Copernicus GmbH
Publication Date:
2022
detail.hit.zdb_id:
2874092-0
Permalink
