Open Access iconOpen Access

ARTICLE

crossmark

Perpendicular-Cutdepth: Perpendicular Direction Depth Cutting Data Augmentation Method

Le Zou1, Linsong Hu1, Yifan Wang1, Zhize Wu2, Xiaofeng Wang1,*

1 Anhui Provincial Engineering Laboratory of Big Data Technology Application for Urban Infrastructure, School of Artificial Intelligence and Big Data, Hefei University, Hefei, 230601, China
2 Institute of Applied Optimization, School of Artificial Intelligence and Big Data, Hefei University, Hefei, 230601, China

* Corresponding Author: Xiaofeng Wang. Email: email

Computers, Materials & Continua 2024, 79(1), 927-941. https://doi.org/10.32604/cmc.2024.048889

Abstract

Depth estimation is an important task in computer vision. Collecting data at scale for monocular depth estimation is challenging, as this task requires simultaneously capturing RGB images and depth information. Therefore, data augmentation is crucial for this task. Existing data augmentation methods often employ pixel-wise transformations, which may inadvertently disrupt edge features. In this paper, we propose a data augmentation method for monocular depth estimation, which we refer to as the Perpendicular-Cutdepth method. This method involves cutting real-world depth maps along perpendicular directions and pasting them onto input images, thereby diversifying the data without compromising edge features. To validate the effectiveness of the algorithm, we compared it with existing convolutional neural network (CNN) against the current mainstream data augmentation algorithms. Additionally, to verify the algorithm’s applicability to Transformer networks, we designed an encoder-decoder network structure based on Transformer to assess the generalization of our proposed algorithm. Experimental results demonstrate that, in the field of monocular depth estimation, our proposed method, Perpendicular-Cutdepth, outperforms traditional data augmentation methods. On the indoor dataset NYU, our method increases accuracy from 0.900 to 0.907 and reduces the error rate from 0.357 to 0.351. On the outdoor dataset KITTI, our method improves accuracy from 0.9638 to 0.9642 and decreases the error rate from 0.060 to 0.0598.

Keywords


Cite This Article

APA Style
Zou, L., Hu, L., Wang, Y., Wu, Z., Wang, X. (2024). Perpendicular-cutdepth: perpendicular direction depth cutting data augmentation method. Computers, Materials & Continua, 79(1), 927-941. https://doi.org/10.32604/cmc.2024.048889
Vancouver Style
Zou L, Hu L, Wang Y, Wu Z, Wang X. Perpendicular-cutdepth: perpendicular direction depth cutting data augmentation method. Comput Mater Contin. 2024;79(1):927-941 https://doi.org/10.32604/cmc.2024.048889
IEEE Style
L. Zou, L. Hu, Y. Wang, Z. Wu, and X. Wang "Perpendicular-Cutdepth: Perpendicular Direction Depth Cutting Data Augmentation Method," Comput. Mater. Contin., vol. 79, no. 1, pp. 927-941. 2024. https://doi.org/10.32604/cmc.2024.048889



cc This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 188

    View

  • 146

    Download

  • 0

    Like

Share Link