基于神经网络的编码光场深度值估计  

Depth Estimation for Phase-Coding Light Field Based on Neural Network

作　　者：杨成卓 向森 邓慧萍[1,2] 吴谨 Yang Chengzhuo;Xiang Sen;Deng Huiping;Wu Jing(School of Information Science and Engineering,Wuhan University of Science and Technology,Wuhan 430081,Hubei,China;Engineering Research Center for Metallurgical Automation and Measurement Technology,Ministry of Education,Wuhan University of Science and Technology,Wuhan 430081,Hubei,China)

机构地区：[1]武汉科技大学信息科学与工程学院,湖北武汉430081 [2]武汉科技大学冶金自动化与检测技术教育部工程研究中心,湖北武汉430081

出　　处：《激光与光电子学进展》2023年第12期262-272,共11页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(61702384,62001180,61871437)。

摘　　要：针对传统光场深度值估计中的测量对象纹理不足导致深度值精度低的问题和光场高维数据带来的高计算负荷的问题,提出一个基于轻量级卷积神经网络对相位编码的光场进行深度值估计的方法,并提出相应的相位编码光场数据集。所提方法利用水平和垂直视点流的多角度信息,利用全卷积网络和逐级深化的平均池化充分提取特征,并由中心视图引导,将两个方向的特征流融合,最终得到中心视点的深度图。实验结果表明,所提方法可生成高精度深度图,而且网络参数量和推理时间仅为典型光场深度值估计网络的27.4%和41.2%,具有更高的效率和实时性能。In this study,we propose a depth estimation method for phase-coding light field based on a lightweight convolutional neural network.This method aims to solve the problems of low accuracy for depth values caused by the insufficient texture of a measured object in traditional light field depth value estimation and high computational loads caused by high-dimensional light field data.In addition,a new phase-coding light field dataset is proposed.This novel method exploits the information of horizontal and vertical perspectives in phase-coding light field to extract the features using full convolutional networks and deepening average pooling.Furthermore,the central view is used as a guide to fuse the horizontal and vertical features and acquire the depth map.The experimental results demonstrate that the proposed method can generate high-accuracy depth maps,while number of parameters and computation time in generating such maps are,respectively,27.4%and 41.2%of those of a typical light field depth estimation network.Thus,the proposed method has a higher efficiency and real-time performance than the traditional approach.

关 键 词：深度估计 光场 卷积神经网络 相位编码 结构光 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]