电子学报 ›› 2019, Vol. 47 ›› Issue (3): 707-713.DOI: 10.3969/j.issn.0372-2112.2019.03.027

• 学术论文 • 上一篇    下一篇

相互结构引导滤波TV-L1变分光流估计

葛利跃1, 张聪炫1,2, 陈震1,2, 黎明2, 陈昊2   

  1. 1. 南昌航空大学测试与光电工程学院, 江西南昌 330063;
    2. 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
  • 收稿日期:2018-03-12 修回日期:2018-07-09 出版日期:2019-03-25 发布日期:2019-03-25
  • 通讯作者: 张聪炫
  • 作者简介:葛利跃 男,1992年10月出生于安徽省蚌埠市.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:lygeah@163.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.20152BCB24004,No.20165BCB19007)、航空科学基金(No.2016ZC56005);江西省青年科学基金(No.20171BAB212012);江西省重点研发计划(No.20161BBE50080);江西省研究生创新专项资金项目资助(No.YC2017-S339)

Mutual-Structure Guided Filtering Based TV-L1 Optical Flow Estimation

GE Li-yue1, ZHANG Cong-xuan1,2, CHEN Zhen1,2, LI Ming2, CHEN Hao2   

  1. 1. School of Measuring and Optical Engineering, Nanchang Hangkong University, Nanchang, Jiangxi 330063, China;
    2. Key Laboratory of Nondestructive Testing, Ministry of Education, Nanchang Hangkong University, Nanchang, Jiangxi 330063, China
  • Received:2018-03-12 Revised:2018-07-09 Online:2019-03-25 Published:2019-03-25

摘要: 由于光流场既包含物体的运动信息,又包含场景的三维结构信息,因此光流计算技术是计算机视觉和机器视觉领域研究的重要任务之一.针对现有光流计算方法在图像边缘保护方面存在过度平滑问题,提出一种基于相互结构引导滤波的TV-L1(Total Variational with L1 norm,TV-L1)变分光流估计方法.通过提取置信度较高的图像相互结构区域,构造基于相互结构引导滤波的全局目标函数,并采用金字塔分层细化与交替迭代方案结合的策略进行优化,该方法可以较好的保护图像边缘信息.最后采用标准测试图像集对本文方法与现有代表性变分方法LDOF(Large Displacement Optical Flow,LDOF),CLG-TV(Combined Local-Global Total Variation,CLG-TV),Classic++,NNF(Nearest Neighbor Fields,NNF)以及深度学习方法FlowNet2.0进行对比,实验结果表明本文方法具有较高的光流估计精度与鲁棒性,尤其对图像边缘保护具有显著的效果,并且在运动目标检测,机器人避障等方面具有一定应用前景.

关键词: 光流计算, 计算机视觉, 机器视觉, 图像边缘保护, 图像相互结构, 深度学习, 运动目标检测, 机器人避障

Abstract: Because the optical flow field contains both the motion information of the object and the three-dimensional structure information of the scene,optical flow calculation technology is one of the important tasks in the field of computer vision and machine vision.But,for the existing optical flow methods,there is over-smoothing problem in image boundary preserving.This paper proposes a global TV-L1(Total Variational with L1 norm,TV-L1) variational optical flow computation method based on the mutual-structure guided filtering.By extracting the mutual-structural regions of the image with higher confidence,we construct the global mutual-structure guided filtering objective function,and optimize the algorithm via combining the pyramid layering strategy with the alternating iteration scheme.This method can better preserve the image boundary information.Finally,we compare the proposed method with the existing representative variational methods LDOF(Large Displacement Optical Flow,LDOF),CLG-TV(Combined Local-Global Total Variation,CLG-TV),Classic++,NNF(Nearest Neighbor Fields,NNF) and deep learning method FlowNet2.0 by using standard test image datasets.The experimental results demonstrate that the presented method has more accuracy and better robustness than the other evaluated methods,especially has the significant effect of boundary preserving in the areas,and it has application prospects in moving target detection,robot obstacle avoidance,and so on.

Key words: optical flow calculation, computer vision, machine vision, image boundary preserving, image mutual-structure, deep learning, moving target detection, robot obstacle avoidance

中图分类号: