OrchardDepth: Precise Metric Depth Estimation of Orchard Scene from Monocular Camera Images

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zheng, Zhichao, Williams, Henry, MacDonald, Bruce A
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916622511374336
author Zheng, Zhichao
Williams, Henry
MacDonald, Bruce A
author_facet Zheng, Zhichao
Williams, Henry
MacDonald, Bruce A
contents Monocular depth estimation is a rudimentary task in robotic perception. Recently, with the development of more accurate and robust neural network models and different types of datasets, monocular depth estimation has significantly improved performance and efficiency. However, most of the research in this area focuses on very concentrated domains. In particular, most of the benchmarks in outdoor scenarios belong to urban environments for the improvement of autonomous driving devices, and these benchmarks have a massive disparity with the orchard/vineyard environment, which is hardly helpful for research in the primary industry. Therefore, we propose OrchardDepth, which fills the gap in the estimation of the metric depth of the monocular camera in the orchard/vineyard environment. In addition, we present a new retraining method to improve the training result by monitoring the consistent regularization between dense depth maps and sparse points. Our method improves the RMSE of depth estimation in the orchard environment from 1.5337 to 0.6738, proving our method's validation.
format Preprint
id arxiv_https___arxiv_org_abs_2502_14279
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle OrchardDepth: Precise Metric Depth Estimation of Orchard Scene from Monocular Camera Images
Zheng, Zhichao
Williams, Henry
MacDonald, Bruce A
Computer Vision and Pattern Recognition
Monocular depth estimation is a rudimentary task in robotic perception. Recently, with the development of more accurate and robust neural network models and different types of datasets, monocular depth estimation has significantly improved performance and efficiency. However, most of the research in this area focuses on very concentrated domains. In particular, most of the benchmarks in outdoor scenarios belong to urban environments for the improvement of autonomous driving devices, and these benchmarks have a massive disparity with the orchard/vineyard environment, which is hardly helpful for research in the primary industry. Therefore, we propose OrchardDepth, which fills the gap in the estimation of the metric depth of the monocular camera in the orchard/vineyard environment. In addition, we present a new retraining method to improve the training result by monitoring the consistent regularization between dense depth maps and sparse points. Our method improves the RMSE of depth estimation in the orchard environment from 1.5337 to 0.6738, proving our method's validation.
title OrchardDepth: Precise Metric Depth Estimation of Orchard Scene from Monocular Camera Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.14279