迭代二次规划遮挡点恢复

doi:10.3969/j.issn.0372-2112.2018.11.021

电子学报 ›› 2018, Vol. 46 ›› Issue (11): 2733-2737.DOI: 10.3969/j.issn.0372-2112.2018.11.021

迭代二次规划遮挡点恢复

彭亚丽^1,2,3, 刘侍刚^1,2, 孙增国^2,3, 洪灵^1,3, 曹菡^1,2,3

1. 现代教学技术教育部重点实验室, 陕西西安 710062;
2. 陕西省教学信息技术工程实验室, 陕西西安 710119;
3. 陕西师范大学计算机科学学院, 陕西西安 710119

收稿日期:2017-08-30 修回日期:2018-07-18 出版日期:2018-11-25
- 通讯作者:
- 刘侍刚
- 作者简介:
- 彭亚丽 女,1979年3月出生,陕西石泉人.2005年在哈尔滨工程大学获得硕士学位,2013年在西安电子科技大学获得博士学位.现为陕西师范大学副教授,从事计算机视觉、模式识别等方面的有关研究;孙增国 男,1980年10月出生,陕西西安人,2003年和2010年在西安交通大学分别获得学士和博士学位,2011年至2015年在华侨大学从事教学科研工作,现为陕西师范大学副教授.从事遥感图像处理、计算机视觉、模式识别等方面的有关研究;洪灵女,1986年3月出生,浙江台州人,2008年和2015年在西安电子科技大学分别获得学士学位和博士学位,现为陕西师范大学副研究员.从事机器学习、模式识别等方面的有关研究;曹菡女,1963年出生,四川荣县人,1986年和1989年在西北大学计算机系分别获得学士学位和硕士学位,2002年武汉大学测绘遥感信息工程国家重点实验室获得博士学位,现为陕西师范大学教授.从事图像处理、空间数据挖掘、智慧旅游等方面的有关研究.
- 基金资助:
- 国家自然科学基金 (No.61672333，No.61873155，No.61701290）; 陕西省工业科技攻关项目 (No.2016GY-081）; 陕西省自然科学基础研究计划 (No.2018JM6050）; 陕西省重点科技创新团队 (No.2014KTS-18）; 现代教学技术教育部重点实验室学习科学交叉学科培育计划资助; 陕西师范大学中央高校基本科研业务费项目 (No.GK201803088，No.GK201803059）

Iterative Quadratic Programming Method for Occlusion Recovery

PENG Ya-li^1,2,3, LIU Shi-gang^1,2, SUN Zeng-guo^2,3, HONG Ling^1,3, CAO Han^1,2,3

1.Key Laboratory of Modern Teaching Technology, Ministry of Education, Xi'an, Shaanxi 710062;
2.Engineering Laboratory of Teaching Information Technology of Shaanxi Province, Xi'an, Shaanxi 710119;
3.School of Computer Science, Shaanxi Normal University, Xi'an, Shaanxi 710119

Received:2017-08-30 Revised:2018-07-18 Online:2018-11-25 Published:2018-11-25
- Corresponding author:
- LIU Shi-gang
- Supported by:
- National Natural Science Foundation of China (No.61672333, No.61873155, No.61701290); Industrial Science and Technology Research and Development Project of Shaanxi Province (No.2016GY-081); Natural Science Basic Research Program of Shaanxi Province (No.2018JM6050); Key Science and Technology Innovation Team of Shaanxi Province (No.2014KTS-18); Supported by the Learning Science Interdisciplinary Program for Key Laboratory of Modern Teaching Technology of Ministry of Education of China; Program of Fundamental Research Funds for the Central Universities of Shaanxi Normal University (No.GK201803088, No.GK201803059)

摘要/Abstract

摘要： 为了有效地的恢复遮挡点，本文提出一种迭代二次规划遮挡点恢复方法，该方法首先分别利用图像矩阵的行向量和列向量在图像矩阵生成的正交补空间上的投影为0的特性，构造行和列余差函数，同时，对遮挡点分别按行为主序和列为主序进行排列，利用排列后这两者之间存在一个变换关系，将行和列余差函数统一表示为一个二次优化目标函数.该方法同时考虑了遮挡点在行和列两个方向的约束，而且将遮挡点求解转化为迭代求解一个二次规划问题.实验结果表明，本文方法具有收敛速度快，恢复精度高等优点.

关键词: 遮挡点恢复, 二次规划, 投影

Abstract: In order to effectively recover the occlusion, this paper presents an iterative quadratic programming method for occlusion recovery. Based on the characteristic that the projections of the row vector and the column vector of image matrix to the orthogonal complementary subspace spanned by image matrix are zero vectors, the row and the column residual objective functions are respectively defined. At the same time, the occlusion positions are respectively sorted according to the row and the column order, whichcan be denoted by a transformation matrix. Based on the transformation matrix, a united residual objective function which is quadratic is obtained from the row and the column ones. The method has the advantages that both the row and the column constraints are simultaneously considered and the solution of occlusion is transformed to iterative solution a quadratic programming. The experimental results show that the method has fast convergence speed and high precision.

Key words: occlusion recovery, quadratic programming, projection

中图分类号:

彭亚丽, 刘侍刚, 孙增国, 等. 迭代二次规划遮挡点恢复[J]. 电子学报, 2018, 46(11): 2733-2737.

PENG Ya-li, LIU Shi-gang, SUN Zeng-guo, et al. Iterative Quadratic Programming Method for Occlusion Recovery[J]. Acta Electronica Sinica, 2018, 46(11): 2733-2737.

参考文献

[1] 彭亚丽,等.基于非刚体轨迹基的线性自标定方法[J].电子学报,2017,45(1):135-139. Peng Yali,et al.Linear camera self-calibration method based on non-rigid trajectory basis[J].Acta Electronica Sinica,2017,45(1):135-139.(in Chinese)
[2] Peng Y L,et al.Space-frequency domain based joint dictionary learning and collaborative representation for face recognition[J].Signal Processing,2018,147:101-109.
[3] Liu T,et al.On the performance of Manhattan nonnegative matrix factorization[J].IEEE Transactions on Neural Networks and Learning Systems,2016,27(9):1851-1863.
[4] Chen G,et al.Multi-modal curriculum learning for semi-supervised image classification[J].IEEE Transactions on Image Processing,2016,25(7):3249-3260.
[5] Peng Y L,et al.Negative ε dragging technique for pattern classification[J].IEEE Access,2018,6(1):488-494.
[6] Liu T,et al.A large-cone nonnegative matrix factorization[J].IEEE Transactions on Neural Networks and Learning Systems,2017,28(9):2129-2142.
[7] Jacobs D.Linear fitting with missing data for structure-from-motion[J].Computer Vision and Image Understanding,2008,82(1):57-81.
[8] Chen P.Optimization algorithms on subspaces:revisiting missing data problem in low-rank matrix[J].International Journal of Computer Vision,2008,80(1):125-142.
[9] Okatani T,et al.On the Wiberg algorithm for matrix factorization in the presence of missing components[J].International Journal of Computer Vision,2007,72(3):329-337
[10] Zheng Y,et al.Generalizing Wiberg algorithm for rigid and nonrigid factorizations with missing components and metric constraints[A].IEEE Conference on Computer Vision and Pattern Recognition[C].Rhode Island,2012.2010-2017.
[11] Strelow D,et al.Eriksson.General,nested,and constrained Wiberg minimization[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,38(9):1803-1815.
[12] Jiang X,et al.Robust matrix completion via alternating projection[J].IEEE Signal Processing Letters,2017,24(5):579-583.
[13] Kennedy R,et al.Online algorithms for factorization-based structure from motion[J].Computer Vision and Image Understanding,2016,150:139-152.
[14] Agudo A,et al.Sequential non-rigid structure from motion using physical priors[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,38(5):979-994.
[15] 刘侍刚,等.基于正交补空间的遮挡点恢复方法[J].电子学报,2015,43(5):911-915. Liu Shigang,et al.An occlusion recovery method based on orthogonal complement subspace[J].Acta Electronica Sinica,2015,43(5):911-915.(in Chinese)
[16] Kumar S,et al.Spatio-temporal union of subspaces for multi-body non-rigid structure-from-motion[J].Pattern Recognition,2017,71(2):428-443.
[17] 刘侍刚,等.投影约束的遮挡点恢复方法[J].电子学报,2017,45(11):2611-2616. Liu Shigang,et al.Occlusion recovery method based on projective constraints[J].Acta Electronica Sinica,2017,45(11):2611-2616.(in Chinese)

迭代二次规划遮挡点恢复

Iterative Quadratic Programming Method for Occlusion Recovery

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	刘少鹏, 赵慧民, 洪佳明, 吴晓航, 许发宝, 欧阳佳, 梁鹏, 熊建斌. 面向医学图像生成的鲁棒条件生成对抗网络[J]. 电子学报, 2023, 51(2): 427-437.
[2]	杨柳, 利强, 邵怀宗. Open-MUSIC：基于度量学习与特征子空间投影的电磁目标开集识别算法[J]. 电子学报, 2022, 50(6): 1310-1318.
[3]	刘杰, 游品鸿, 田明, 刘金凤. 基于局部投影的视差图像拼接平滑优化[J]. 电子学报, 2022, 50(6): 1451-1456.
[4]	刘秋红, 许漫坤, 李天昀. 基于ML的多径信道下直扩信号PN码和信道的联合盲估计[J]. 电子学报, 2021, 49(8): 1480-1488.
[5]	邓翔宇, 杨雅涵. 纸质简谱图像的分割、倾斜校正及音符歌词提取[J]. 电子学报, 2021, 49(4): 716-728.
[6]	李燕, 严永财. 基于同心圆阵列的结构光主动视觉系统标定算法[J]. 电子学报, 2021, 49(3): 536-541.
[7]	李东瑾, 杨瑞娟, 李晓柏, 董睿杰. 基于核协同表示与鉴别投影的辐射源调制识别[J]. 电子学报, 2020, 48(9): 1695-1702.
[8]	张彩霞, 王子涵, 文成林, 刘国文, 余伟. 样本空间基于多级高维特征表示的微小故障诊断[J]. 电子学报, 2020, 48(8): 1647-1654.
[9]	蔺想红, 郑鉴洋, 王向文, 马慧芳. 基于深度学习网络的神经元自适应投影分类方法[J]. 电子学报, 2020, 48(7): 1321-1329.
[10]	赖锦祥, 雷亮, 阮杨, 邓凯元, 徐初东, 周金运. 基于等积环投影与Zernike矩的快速模板匹配[J]. 电子学报, 2019, 47(6): 1324-1330.
[11]	杨亮, 付根平, 陈勇. 考虑关节角加速度约束的仿人机器人偏摆力矩控制方法[J]. 电子学报, 2019, 47(2): 475-482.
[12]	李玉, 王亚琼, 赵雪梅, 赵泉华. 基于随机投影深度函数的停车场车辆提取方法[J]. 电子学报, 2019, 47(2): 322-330.
[13]	张素玲, 陈胜垚, 席峰, 刘中. 亚奈奎斯特采样雷达的运动目标回波信号的快速重构[J]. 电子学报, 2019, 47(10): 2098-2107.
[14]	罗婷, 李孟飞, 赵云松. 基于二次有理分式拟合多能投影曲线的X射线能谱估计方法[J]. 电子学报, 2018, 46(11): 2580-2587.
[15]	唐波, 张玉, 张浩. 基于交替投影的MIMO雷达信号盲分离算法研究[J]. 电子学报, 2017, 45(9): 2092-2097.