FRFCM聚类与深度优化的RGBD场景流计算

doi:10.3969/j.issn.0372-2112.2020.07.018

电子学报 ›› 2020, Vol. 48 ›› Issue (7): 1380-1386.DOI: 10.3969/j.issn.0372-2112.2020.07.018

FRFCM聚类与深度优化的RGBD场景流计算

张聪炫^1,2, 裴刘继¹, 陈震¹, 黎明¹, 江少锋¹

1. 南昌航空大学无损检测技术教育部重点实验室, 江西南昌 330063;
2. 中国科学院自动化研究所, 北京 100190

收稿日期:2019-07-01 修回日期:2020-04-17 出版日期:2020-07-25 发布日期:2020-07-25
作者简介:张聪炫 男,1984年7月出生于河南焦作.分别于2007和2014年在南昌航空大学和南京航空航天大学获得学士和博士学位.现为南昌航空大学副教授,硕士生导师,中国科学院自动化研究所博士后.主要研究方向为图像检测与智能识别.E-mail:zcxdsg@163.com;裴刘继 男,1993年7月出生于安徽宣城.现为南昌航空大学测试与光电工程学院硕士研究生.主要研究方向为图像检测与智能识别.E-mail:492888191@qq.com
基金资助:
国家自然科学基金（No.61866026，No.61772255，No.61866025）；江西省优势科技创新团队计划（No.20165BCB19007）；江西省科技创新杰出青年人才计划（No.20192BCB23011）；航空科学基金（No.2018ZC56008）；中国博士后科学基金（No.2019M650894）

RGBD Scene Flow Estimation Based on FRFCM Clustering and Depth Optimization

ZHANG Cong-xuan^1,2, PEI Liu-ji¹, CHEN Zhen¹, LI Ming¹, JIANG Shao-feng¹

1. Key Laboratory of Nondestructive Testing(Ministry of Education), Nanchang Hangkong University, Nanchang, Jiangxi 330063, China;
2. Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China

Received:2019-07-01 Revised:2020-04-17 Online:2020-07-25 Published:2020-07-25

摘要/Abstract

摘要： 针对现有RGBD场景流计算模型在复杂场景、非刚性运动和运动遮挡等情况下易产生场景过度平滑和运动边缘模糊的问题，提出一种基于FRFCM（Fast and Robust Fuzzy C-Means）聚类与深度优化的RGBD场景流计算方法.首先以图像序列连续帧间光流信息为基准，利用FRFCM聚类算法对输入图像进行初始分割，然后根据深度图像的运动边缘信息优化初始分割结果，提取高置信度的运动分层信息.最后设计基于图像分割的RGBD场景流能量函数，采用金字塔变形策略计算精确的场景流结果.分别采用Middlebury和MPI-Sintel数据库所提供的测试图像集对本文方法和现有的RGBD场景流算法进行综合对比分析，实验结果表明本文方法相对于其他方法具有更好的场景流估计精度和鲁棒性，有效改善了场景过度平滑和运动边缘模糊问题.

关键词: RGBD场景流, FRFCM聚类, 深度信息, 过度平滑, 边缘模糊

Abstract: In order to address the issues of scene over-smoothing and motion edge-blurring caused by the existing RGBD scene flow methods under complex scenes,non-rigid movement and motion occlusions,this paper proposes a RGBD scene flow method based on FRFCM (Fast and Robust Fuzzy C-Means) clustering and depth optimization.First,the optical flow information from the consecutive frames is marked as the benchmark and the FRFCM clustering approach is utilized to obtain the initial segmentation of the input image sequences.Second,according to the motion edge information of the depth image,we further optimize the initial segmentation to extract the high-confidence hierarchical motion information.Finally,an energy function of RGBD scene flow based on image segmentation is designed,and the pyramid warping strategy is adopted to compute the scene flow field.We employ the test sets of Middlebury and MPI-Sintel databases to conduct a comparison experiment between the proposed method and the existing RGBD scene flow methods.The experimental results indicate that the proposed method has better accuracy and robustness of scene flow estimation,especially when dealing with the issues of scene over-smoothing and motion edge-blurring.

Key words: RGBD scene flow, FRFCM clustering, depth information, over-smoothing, edge-blurring

中图分类号:

TP391

张聪炫, 裴刘继, 陈震, 黎明, 江少锋. FRFCM聚类与深度优化的RGBD场景流计算[J]. 电子学报, 2020, 48(7): 1380-1386.

ZHANG Cong-xuan, PEI Liu-ji, CHEN Zhen, LI Ming, JIANG Shao-feng. RGBD Scene Flow Estimation Based on FRFCM Clustering and Depth Optimization[J]. Acta Electronica Sinica, 2020, 48(7): 1380-1386.

参考文献

[1] Ke R,Li Z,Tang J,et al.Real-time traffic flow parameter estimation from UAV video based on ensemble classifier and optical flow[J].IEEE Transactions on Intelligent Transportation Systems,2018,20(1):54-64.
[2] 张聪炫,陈震,汪明润,等.基于光流与Delaunay三角网格的图像序列运动遮挡检测[J].电子学报,2018,46(2):479-485. ZHANG Cong-xuan,CHEN Zhen,WANG Ming-run,et al.Motion occlusion detecting from image sequence based on optical flow and Delaunay triangulation[J].Acta Electronica Sinica,2018,46(2):479-485.(in Chinese)
[3] Vedula S,Rander P,Collins R,et al.Three-dimensional scene flow[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(3):475-480.
[4] Gottfried J M,Fehr J,Garbe C S,et al.Computing range flow from multi-modal Kinect data[A].Advances in Visual Computing[C].Berlin:Springer,2011.758-767.
[5] Yamaguchi K,McAllester D,Urtasun R.Efficient joint segmentation,occlusion labeling,stereo and flow estimation[A].European Conference on Computer Vision[C].Cham:Springer,2014.756-771.
[6] Sun D,Sudderth E B,Pfister H.Layered RGBD scene flow estimation[A].IEEE Conference on Computer Vision and Pattern Recognition[C].Boston:IEEE,2015.548-556.
[7] Golyanik V,Kim K,Maier R,et al.Multiframe scene flow with piecewise rigid motion[A].IEEE International Conference on 3D Vision[C].Qingdao:IEEE,2017.273-281.
[8] Brox T,Malik J.Large displacement optical flow:Descriptor matching in variational motion estimation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(3):500-513.
[9] Sun D,Roth S,Black M J.A quantitative analysis of current practices in optical flow estimation and the principles behind them[J].International Journal of Computer Vision,2014,106(2):115-137.
[10] Menze M,Heipke C,Geiger A.Object scene flow[J].ISPRS Journal of Photogrammetry and Remote Sensing,2018,140:60-76.
[11] Vogel C,Schindler K,Roth S.3D scene flow estimation with a piecewise rigid scene model[J].International Journal of Computer Vision,2015,115(1):1-28.
[12] Schuster R,Wasenmuller O,Kuschk G,et al.SceneFlowFields:Dense interpolation of sparse scene flow correspondences[A].IEEE Winter Conference on Applications of Computer Vision[C].Lake Tahoe:IEEE,2018.1056-1065.

FRFCM聚类与深度优化的RGBD场景流计算

RGBD Scene Flow Estimation Based on FRFCM Clustering and Depth Optimization

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics