航空图像光流场的逆向金字塔计算方法

李佳田; 李显凯; 李应芸; 钱堂慧; 李果家; 林艳

doi:10.11947/j.AGCS.2016.20150367

测绘学报 >

2016 , Vol. 45 >Issue 9: 1059 - 1064

DOI: https://doi.org/10.11947/j.AGCS.2016.20150367

摄影测量学与遥感

航空图像光流场的逆向金字塔计算方法

李佳田 ,
李显凯 ,
李应芸 ,
钱堂慧 ,
李果家 ,
林艳

展开

1. 昆明理工大学国土资源工程学院, 云南昆明 650093;
2. 中国人民公安大学警务信息工程学院, 北京 100038

李佳田（1975-）,男，博士，副教授，研究方向为数值最优化方法与机器场景理解.E-mail:ljtwcx@163.com

收稿日期: 2015-07-13

修回日期: 2016-06-14

网络出版日期: 2016-09-29

基金资助

国家自然科学基金（41561082；41161061）

收起

A Backward Pyramid Oriented Optical Flow Field Computing Method for Aerial Image

LI Jiatian ,
LI Xiankai ,
LI Yingyun ,
QIAN Tanghui ,
LI Guojia ,
LIN Yan

Expand

1. Faculty of Land Resource Engineering, Kunming University of Science and Technology, Kunming 650093, China;
2. Policing Information Technology College, People's Public Security University of China, Beijing 100038, China

Received date: 2015-07-13

Revised date: 2016-06-14

Online published: 2016-09-29

Supported by

The National Natural Science Foundation of China (Nos.41561082;41161061)

Fold

摘要

航空图像光流场是低空运动目标检测与变化信息获取的基础，通常将图像金字塔结构引入数值过程以增强全局收敛性。然而，金字塔结构往往是由底层至顶层的递进方式构建，其忽略图像的几何成像过程，造成微小光流或不能得到光流的问题，导致难以支撑后续建模与分析。本文提出了一种以顶层图像为基准的逆向金字塔结构，首先依据中心投影定量地计算出顶层图像的降采样因子，使得顶层图像光流能够反映所设定的地面目标位移阈值；其次，结合顶层与原始图像，以等比方式确定中间层降采样因子；最后，利用高斯平滑与图像插值得到中间层图像，并形成金字塔。对比试验与分析表明，逆向金字塔可准确地计算航空图像光流场，在抑制地面微小位移方面具有优势。

关键词： 航空图像; 光流场; 逆向金字塔; 中心投影; 降采样

本文引用格式

李佳田 , 李显凯 , 李应芸 , 钱堂慧 , 李果家 , 林艳 . 航空图像光流场的逆向金字塔计算方法[J]. 测绘学报, 2016 , 45(9) : 1059 -1064 . DOI: 10.11947/j.AGCS.2016.20150367

Abstract

Aerial image optical flow field is the foundation for detecting moving objects at low altitude and obtaining change information. In general,the image pyramid structure is embedded in numerical procedure in order to enhance the convergence globally. However,more often than not,the pyramid structure is constructed using a bottom-up approach progressively,ignoring the geometry imaging process.In particular,when the ground objects moving it will lead to miss optical flow or the optical flow too small that could hardly sustain the subsequent modeling and analyzing issues. So a backward pyramid structure is proposed on the foundation of top-level standard image. Firstly,down sampled factors of top-level image are calculated quantitatively through central projection,which making the optical flow in top-level image represent the shifting threshold of the set ground target. Secondly,combining top-level image with its original,the down sampled factors in middle layer are confirmed in a constant proportion way. Finally,the image of middle layer is achieved by Gaussian smoothing and image interpolation,and meanwhile the pyramid is formed. The comparative experiments and analysis illustrate that the backward pyramid can calculate the optic flow field in aerial image accurately,and it has advantages in restraining small ground displacement.

Key words： aerial image; optical flow field; backward pyramid; central projection; down sample

参考文献

[1] 宋爽, 杨健, 王涌天. 全局光流场估计技术及展望[J]. 计算机辅助设计与图形学学报, 2014, 26(5): 841-850. SONG Shuang, YANG Jian, WANG Yongtian. Technology and Prospect of Global Optical Flow[J]. Journal of Computer-aided Design & Computer Graphics, 2014, 26(5): 841-850.
[2] 李秀智, 贾松敏, 尹晓琳, 等. 视觉光流矢量场估计算法综述[J]. 北京工业大学学报, 2013, 39(11): 1638-1643. LI Xiuzhi, JIA Songmin, YIN Xiaolin, et al. Review on Optical Flow Vector Fields Estimation Algorithm[J]. Journal of Beijing University of Technology, 2013, 39(11): 1638-1643.
[3] 涂志刚, 谢伟, 熊淑芬, 等. 一种高精度的TV-L¹光流算法[J]. 武汉大学学报(信息科学版), 2012, 37(4): 496-499. TU Zhigang, XIE Wei, XIONG Shufen, et al. An Efficient TV-L¹ Optical Flow Method[J]. Geomatics and Information Science of Wuhan University, 2012, 37(4): 496-499.
[4] 刘慧, 李清泉, 高春仙, 等. 利用C_SURF配准的空基视频运动目标检测[J]. 武汉大学学报(信息科学版), 2014, 39(8): 951-955. LIU Hui, LI Qingquan, GAO Chunxian, et al. Moving Target Detection Using C_SURF Registration[J]. Geomatics and Information Science of Wuhan University, 2014, 39(8): 951-955.
[5] 刘慧, 李清泉, 曾喆, 等. 利用低空视频检测道路车辆[J]. 武汉大学学报(信息科学版), 2011, 36(3): 316-320. LIU Hui, LI Qingquan, ZENG Zhe, et al. Vehicle Detection in Low-altitude Aircraft Video[J]. Geomatics and Information Science of Wuhan University, 2011, 36(3): 316-320.
[6] 闫利, 巩翼龙, 张毅, 等. 光流动态纹理在土地利用/覆盖变化检测研究中的应用[J]. 光谱学与光谱分析, 2014, 34(11): 3056-3061. YAN Li, GONG Yilong, ZHANG Yi, et al. Application of Optical Flow Dynamic Texture in Land Use/Cover Change Detection[J]. Spectroscopy and Spectral Analysis, 2014, 34(11): 3056-3061.
[7] 张正鹏, 江万寿, 张靖. 光流特征聚类的车载全景序列影像匹配方法[J]. 测绘学报, 2014, 43(12): 1266-1273. DOI: 10.13485/j.cnki.11-2089.2014.0172. ZHANG Zhengpeng, JIANG Wanshou, ZHANG Jing. An Image Match Method Based on Optical Flow Feature Clustering for Vehicle-borne Panoramic Image Sequence[J]. Acta Geodaetica et Cartographica Sinica, 2014, 43(12): 1266-1273. DOI: 10.13485/j.cnki.11-2089.2014.0172.
[8] ALVAREZ L, WEICKERT J, SNCHEZ J. Reliable Estimation of Dense Optical Flow Fields with Large Displacements[J]. International Journal of Computer Vision, 2000, 39(1): 41-56.
[9] BRUHN A, WEICKERT J, SCHNÖRR C. Lucas/Kanade Meets Horn/Schunck: Combining Local and Global Optic Flow Methods[J]. International Journal of Computer Vision, 2005, 61(3): 211-231.
[10] 李秀智, 尹晓琳, 贾松敏, 等. 改进的TV-L¹平滑光流估计[J]. 光学学报, 2013, 33(10): 1015002. LI Xiuzhi, YIN Xiaolin, JIA Songmin, et al. Improved TV-L¹ Algorithm for Smooth Optical Flow[J]. Acta Optica Sinica, 2013, 33(10): 1015002.
[11] 陈震, 张聪炫, 晏文敬, 等. 基于图像局部结构的区域匹配变分光流算法[J]. 电子学报, 2015, 43(11): 2200-2209. CHEN Zhen, ZHANG Congxuan, YAN Wenjing, et al. Region Matching Variational Optical Flow Algorithm Based on Image Local Structure[J]. Acta Electronica Sinica, 2015, 43(11): 2200-2209.
[12] 张聪炫, 陈震, 黎明. 金字塔光流三维运动估计与深度重建直接方法[J]. 仪器仪表学报, 2015, 36(5): 1093-1105. ZHANG Congxuan, CHEN Zhen, LI Ming. Direct Method for 3D Motion Estimation and Depth Reconstruction Based on Pyramid Optical Flow[J]. Chinese Journal of Scientific Instrument, 2015, 36(5): 1093-1105.
[13] 胡正华, 孟令奎, 张文. 面向关系数据库扩展的自适应影像金字塔模型[J]. 测绘学报, 2015, 44(6): 678-685. DOI: 10.11947/j.AGCS.2015.20140279. HU Zhenghua, MENG Lingkui, ZHANG Wen. Relational Database Extension Oriented, Self-adaptive Imagery Pyramid Model[J]. Acta Geodaetica et Cartographica Sinica, 2015, 44(6): 678-685. DOI: 10.11947/j.AGCS.2015.20140279.
[14] 谢剑斌, 王晖, 程江华, 等. 基于HS约束与轮廓条件的光流场计算[J]. 系统工程与电子技术, 2009, 31(4): 761-763. XIE Jianbin, WANG Hui, CHENG Jianghua, et al. Optical Flow Computation Method Based on HS Constraint and Outline Condition[J]. Systems Engineering and Electronics, 2009, 31(4): 761-763.
[15] 高银, 云利军, 石俊生, 等. 基于各向异性高斯滤波的暗原色理论雾天彩色图像增强算法[J]. 计算机辅助设计与图形学学报, 2015, 27(9): 1701-1706.GAO Yin, YUN Lijun, SHI Junsheng, et al. Enhancement Dark Channel Algorithm of Color Fog Image Based on the Anisotropic Gaussian Filtering[J]. Journal of Computer-aided Design & Computer Graphics, 2015, 27(9): 1701-1706.
[16] 肖进胜, 杜康华, 涂超平, 等. 基于多聚焦图像深度信息提取的背景虚化显示[J]. 自动化学报, 2015, 41(2): 304-311.XIAO Jinsheng, DU Kanghua, TU Chaoping, et al. Bokeh Display Based on Depth Information Extraction of Multi-focus Images[J]. Acta Automatica Sinica, 2015, 41(2): 304-311.
[17] 王昊京, 王建立, 王鸣浩, 等. 采用双线性插值收缩的图像修复方法[J]. 光学精密工程, 2010, 18(5): 1234-1241.WANG Haojing, WANG Jianli, WANG Minghao, et al. Efficient Image Inpainting Based on Bilinear Interpolation Downscaling[J]. Optics and Precision Engineering, 2010, 18(5): 1234-1241.
[18] 庞志勇, 谭洪舟, 陈弟虎. 一种改进的低成本自适应双三次插值算法及VLSI实现[J]. 自动化学报, 2013, 39(4): 407-417. PANG Zhiyong, TAN Hongzhou, CHEN Dihu. An Improved Low-cost Adaptive Bicubic Interpolation Arithmetic and VLSI Implementation[J]. Acta Automatica Sinica, 2013, 39(4): 407-417.
[19] BAKER S, SCHARSTEIN D, LEWIS J P, et al. A Database and Evaluation Methodology for Optical Flow[J]. International Journal of Computer Vision, 2011, 92(1): 1-31.
[20] SEVILLA-LARA L, SUN Deqing, LEARNED-MILLER E G, et al. Optical Flow Estimation with Channel Constancy[C]//Proceedings of the 13th European Conference on Computer Vision. Switzerland: Springer, 2014: 423-438.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献