面向空间遮挡的复合代价光场快速三维成像方法  

Composite-Cost-Based Fast Light-Field 3D Imaging Method for Handling Spatial Occlusions

作　　者：李安虎[1,2,3] 龚祯昱 赵鑫 LI Anhu;GONG Zhenyu;ZHAO Xin(School of Mechanical Engineering,Tongji University,Shanghai 201804,China;Shanghai Key Laboratory of Wearable Robotics and Human‑Machine Interaction,Shanghai 201804,China;Jiangxi Provincial Key Laboratory of Modern Agricultural Equipment,Ji’an 343009,China)

机构地区：[1]同济大学机械与能源工程学院,上海201804 [2]上海市穿戴机器人与人机交互技术重点实验室,上海201804 [3]现代农业装备江西省重点实验室,吉安343009

出　　处：《数据采集与处理》2025年第2期365-373,共9页Journal of Data Acquisition and Processing

基　　金：上海市2022年度“科技创新行动计划”国际科技合作项目(22550711200);同济大学开放场景验证项目(kh0100020242361)。

摘　　要：光场相机凭借其多维多尺度的成像能力和极简的资源配置,显著拓展了空地海探索等非结构化环境中的成像应用边界。光场成像过程中容易受到遮挡和噪声影响而产生不可靠的深度估计,传统的深度细化方法计算成本高且效果差。提出了一种面向空间遮挡的复合代价光场快速三维成像方法,深入分析影响深度估计准确性的主要因素,针对不同空间遮挡模式,建立最优的光场快速滤波构架。使用像素点的单比特特征构造高度集成的复合代价,实现深度图像的细化和遮挡优化。实验表明,该方法的运算效率显著优于基于马尔可夫随机场等为代表的后期细化手段,且使三维成像的均方根误差提高51.3%,以较低的运算成本显著提高深度估计算法的可靠性,有望为光场成像技术在复杂场景应用提供有力支持。Light field cameras,with their multi-dimensional imaging capabilities and minimal resource allocation,expand the exploration boundaries of imaging applications in unstructured air-ground-sea environments.The process of light field imaging is susceptible to occlusion and noise,and may produce unreliable depth estimation.This paper proposes a fast light fields depth estimation method for spatial occlusion-oriented,analyzes the main factors affecting the accuracy of depth estimation in depth,and establishes the optimal light field fast filtering architecture for different spatial occlusion modes.Then a highly integrated composite cost is constructed using single-bit features of pixel points to achieve depth image refinement and occlusion optimization.The experiments demonstrate that the computational efficiency of this method is significantly better than those of Markov random fields,and can reduce the MSE by 51.3%,the reliability of the depth estimation algorithm is improved at a lower operational cost,and this method is expected to provide strong support for the application of light-field imaging technology in complex scenes.

关 键 词：复杂环境 三维成像 光场相机 复合代价 快速滤波 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]