Eite-Mono: An Extreme Lightweight Architecture for Self-Supervised Monocular Depth Estimation
IEEE Access · 2024 · 12 · 167010-167021
DOI: 10.1109/access.2024.3432181 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2024. Verfasst von Chaopeng Ren. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Progress of Ecological Restoration and Governance of Open-Pit Coal Mines in Jinsha East Mining Area, Guizhou Province in 2024.
Abstract (Originalsprache)
In intelligent mine construction, depth prediction via machine vision plays a pivotal role in enhancing visual perception. This need, coupled with the scarcity of high-quality monocular depth estimation datasets, has led to the development of self-supervised learning approaches for depth prediction in complex scenarios. To address the balance between model complexity and feature extraction capability, we introduce Eite-Mono, a lightweight Monocular Depth Estimation (MDE) framework. Eite-Mono features a dual-component architecture, incorporating PoseNet for camera motion estimation and EiteDepth for dense depth prediction, which utilizes a U-shaped encoder-decoder to extract multiscale features. Central to our approach is the Local-Global Feature Aggregation (LGFA) module, which captures both local and global image features efficiently, using lightweight CNN and Vision Transformer structures to minimize model size and computational load. Evaluated on the KITTI and Make3D datasets, Eite-Mono outperforms existing self-supervised MDE models in both accuracy and complexity, surpassing Lite-Mono in accuracy with 60% fewer trainable parameters. Furthermore, we have assessed the performance of our method in mining scenarios, demonstrating its remarkable superiority over the comparative approaches.
Förderung
- Progress of Ecological Restoration and Governance of Open-Pit Coal Mines in Jinsha East Mining Area, Guizhou Province in 2024
Zitieren
APA
Ren, C. (2024). Eite-Mono: An Extreme Lightweight Architecture for Self-Supervised Monocular Depth Estimation. IEEE Access, 12, 167010-167021. https://doi.org/10.1109/access.2024.3432181
Vancouver
Ren C. Eite-Mono: An Extreme Lightweight Architecture for Self-Supervised Monocular Depth Estimation. IEEE Access. 2024;12:167010-167021. doi:10.1109/access.2024.3432181
BibTeX
@article{Ren2024,
author = {Ren, Chaopeng},
title = {Eite-Mono: An Extreme Lightweight Architecture for Self-Supervised Monocular Depth Estimation},
journal = {IEEE Access},
year = {2024},
volume = {12},
pages = {167010--167021},
doi = {10.1109/access.2024.3432181}
}
EUVIMED