| 单目深度估计研究综述 |
| 投稿时间：2024-12-05 修订日期：2025-01-06 点此下载全文 |
| 引用本文：王诚,李梦媛,李春领.单目深度估计研究综述[J].红外,2025,46(5):1~10 |
| 摘要点击次数: 64 |
| 全文下载次数: 45 |
|
|
| 中文摘要:单目深度估计在三维重建、目标跟踪、场景理解等众多应用中起到非常重要的作用。由于单目摄像头具有成本低、设备较为普及、图像获取方便等特点，从单目图像中获取深度信息成为热门研究。首先概述了用于单目深度估计的常见深度学习模型，主要包括卷积神经网络(Convolutional Neural Network, CNN)、循环神经网络(Recurrent Neural Network, RNN)和生成对抗网络(Generative Adversarial Network, GAN)。然后从训练方法的角度归纳了用于单目深度估计的深度学习方法，并对单目深度估计的发展趋势进行了总结。 |
| 中文关键词:单目深度估计 计算机视觉 深度学习 |
| |
| A Review of Monocular Depth Estimation Research |
|
|
| Abstract:Monocular depth estimation plays a very important role in many applications such as 3D reconstruction, target tracking, and scene understanding. Since monocular cameras have the characteristics of low cost, widespread equipment, and convenient image acquisition, obtaining depth information from monocular images has become a hot research topic. First, the common deep learning models used for monocular depth estimation are summarized, mainly including convolutional neural network (CNN), recurrent neural network (RNN), and generative adversarial network (GAN). Then, the deep learning methods for monocular depth estimation are summarized from the perspective of training methods, and the development trend of monocular depth estimation is summarized. |
| keywords:monocular depth estimation computer vision deep learning |
| 查看全文 HTML 查看/发表评论 下载PDF阅读器 |
|
|
|
|
|