An effective single image depth estimating algorithm

机译：一种有效的单图像深度估计算法

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

Depth estimating from image is a essentially important work in many situations. However, traditional methods always extract depth information from binocular image pairs. Estimating depth information from a single image is much harder because single image lake the relationship between global and local coordinate. This paper proposes a single image depth estimating method by the segmentation convolutional neural network method. Our method aimed at getting the depth map from a single image with high revolution and high speed. The proposed method include three components: segmentation, coarse estimating and high revolution refine. Experiment results show the method can get high quality results. We compare our method with other methods on the accuracy and processing time to show the advantages.

机译：在许多情况下，从图像进行深度估计是一项重要的工作。然而，传统方法总是从双目图像对中提取深度信息。从单个图像估计深度信息要困难得多，因为单个图像影响了全局坐标和局部坐标之间的关系。本文提出了一种基于分段卷积神经网络的图像深度估计方法。我们的方法旨在以高转速和高速度从单个图像获取深度图。该方法包括三个部分：分割，粗略估计和高转细化。实验结果表明，该方法可以得到高质量的结果。我们将我们的方法与其他方法的准确性和处理时间进行比较，以显示其优势。

著录项

来源
《2017 International Conference on Security, Pattern Analysis, and Cybernetics》|2017年|242-246|共5页
会议地点 Shenzhen(CN)
作者
Baijiang Fan; Yunbo Rao; Wei Liu; Jiali Song;
展开▼
作者单位

School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China;

School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China;

School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China;

School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类
关键词
Image segmentation; Training; Convolution; Kernel; Convolutional neural networks; Security; Pattern analysis;

机译：图像分割;训练;卷积;核;卷积神经网络;安全性;模式分析;;

相似文献

外文文献
中文文献
专利

1. Effective Improvement for Depth Estimated Based on Defocus Images [J] . Hao Wang1, Fengyun Cao1, Shuai Fang1, Journal of Computers . 2013,第4期

机译：基于Defocus图像的深度估计有效改进
2. A two-streamed network for estimating fine-scaled depth maps from single RGB images [J] . Jun Li, Can Yuce, Reinhard Klein, Computer vision and image understanding . 2019,第Sepa期

机译：用于估计来自单个RGB图像的细微缩放深度映射的两流网络
3. Estimate Hand Poses Efficiently from Single Depth Images [J] . Xu Chi, Nanjappa Ashwin, Zhang Xiaowei, International Journal of Computer Vision . 2016,第1期

机译：从单深度图像有效估计手的姿势
4. An effective single image depth estimating algorithm [C] . Baijiang Fan, Yunbo Rao, Wei Liu, International Conference on Security, Pattern Analysis, and Cybernetics . 2017

机译：有效的单个图像深度估计算法
5. Convolutional neural network based age estimation from facial image and depth prediction from single image. [D] . Qiu, Jiayan. 2016

机译：基于卷积神经网络的基于面部图像的年龄估计和基于单个图像的深度预测。
6. Evaluation of algorithms for photon depth of interaction estimation for the TRIMAGE PET component [O] . Niccolo Camarlinghi, Nicola Belcari, Piergiorgio Cerello, 2015

机译：用于TRIMAGE PET组件的光子相互作用深度估计算法的评估
7. Fast Algorithms for Estimating Aerosol Optical Depth and Correcting Thematic Mapper Imagery [O] . Hassan Fallah-adl, Shunlin Liang 2007

机译：估算气溶胶光学深度和校正专题测绘仪图像的快速算法
8. Kalman Filter-Based Algorithms for Estimating Depth from Image Sequences [R] . Matthies, L., Szeliski, R., Kanade, T. 1988

机译：基于卡尔曼滤波的图像序列深度估计算法

An effective single image depth estimating algorithm

摘要

著录项

相似文献

相关主题

期刊订阅