基于局部投影的视差图像拼接平滑优化

doi:10.12263/DZXB.20200664

电子学报 ›› 2022, Vol. 50 ›› Issue (6): 1451-1456.DOI: 10.12263/DZXB.20200664

基于局部投影的视差图像拼接平滑优化

刘杰¹, 游品鸿¹, 田明², 刘金凤¹

^1.哈尔滨理工大学测控技术与通信工程学院，黑龙江哈尔滨 150080
^2.中国电信黑龙江省分公司，黑龙江哈尔滨 150080

收稿日期:2020-07-08 修回日期:2021-01-04 出版日期:2022-06-25
- 作者简介:
- 刘杰女，1980年出生，黑龙江齐齐哈尔人.副教授.2005年于哈尔滨工业大学获得硕士学位，2013年于哈尔滨理工大学获得博士学位.主要研究方向为光纤光栅传感及解调技术、数字图像处理及计算机视觉技术.E-mail: liujie@hrbust.edu.cn
  游品鸿男，1995年出生，福建福州人.哈尔滨理工大学测控技术与通信工程学院硕士研究生.主要研究方向为计算机视觉以及图像处理.E-mail: 1091453221@qq.com
- 基金资助:
- 国家自然科学基金 (51607049); 黑龙江省自然科学基金 (LH2019E067)

Smooth Optimization of Parallax Images Mosaic Based on Local Projection

LIU Jie¹, YOU Pin-hong¹, TIAN Ming², LIU Jin-feng¹

^1.School of Measurement and Control Technology and Communication Engineering, Harbin University of Science and Technology, Harbin, Heilongjiang 150080, China
^2.Heilongjiang Branch of China Telecom, Harbin, Heilongjiang 150080, China

Received:2020-07-08 Revised:2021-01-04 Online:2022-06-25 Published:2022-06-25
- Supported by:
- National Natural Science Foundation of China (51607049); Natural Science Foundation of Heilongjiang Province, China (LH2019E067)

摘要/Abstract

摘要：

针对视差图像拼接之后存在对齐不准和扭曲的问题，提出一种基于局部投影的视差图像拼接的平滑优化方法.将输入图像进行特征点检测，通过局部保留结构进行图像匹配并计算投影矩阵，利用重合边界投影模型与投影矩阵进行归一化距离判定，距离小于阈值则保留，大于阈值则舍弃并继续矩阵计算.在图像非重合部分，利用图像的变形函数得到最小弯曲能量函数，使非重合区域向全局变换上过渡.实验结果表明：所提算法提高了图像匹配精度，对图像的扭曲具有优化作用，增强了图像的整体性并获得了更好的视觉体验.

关键词: 视差图像拼接, 投影矩阵, 全局变换, 阈值

Abstract:

Aiming at the problems of misalignment and distortion after parallax image stitching, a smooth optimization method for parallax image stitching based on local projection is proposed. The input image is performed feature point detection, matched by locality preserving structure, and calculated the projection matrix. The normalized distance is determined by the projection model of the coincident area and the projection matrix. If it is less than the threshold, it will be retained, otherwise it will be discarded and continue matrix calculation. In the non-coincident part of the image, the minimum bending energy function is obtained by calculating the deformation function of the image, so that the non-coincident region transits to the global transformation. The experimental results show that the proposed algorithm can not only improve the matching accuracy of the image, but also optimize the distortion of the image, enhance the integrity of the image and obtain a better visual experience.

Key words: parallax images stitching, projection matrix, global transformation, threshold

中图分类号:

TP311

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.

LIU Jie, YOU Pin-hong, TIAN Ming, LIU Jin-feng. Smooth Optimization of Parallax Images Mosaic Based on Local Projection[J]. Acta Electronica Sinica, 2022, 50(6): 1451-1456.

图/表 6

参考文献 18

1	CHENJ, WANQ, LUOL B, et al. Drone image stitching based on compactly supported radial basis function[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2019, 12(11): 4634-4643.
2	韩敏, 闫阔, 秦国帅. 基于改进KAZE的无人机航拍图像拼接算法[J]. 自动化学报, 2019, 45(2): 305-314.
	HANM, YANK, QING S. A mosaic algorithm for UAV aerial image with improved KAZE[J]. Acta Automatica Sinica, 2019, 45(2): 305-314. (in Chinese)
3	TAPETED, CIGNAF. Detection of archaeological looting from space: Methods, achievements and challenges[J]. Remote Sensing, 2019, 11(20): 2389.
4	ALMADHOUNR, ABDULDAYEMA, TAHAT, et al. Guided next best view for 3D reconstruction of large complex structures[J]. Remote Sensing, 2019, 11(20): 2440.
5	丁颖, 刘延伟, 刘金霞, 等. 虚拟现实全景图像显著性检测研究进展综述[J]. 电子学报, 2019, 47(7): 1575-1583.
	DINGY, LIUY W, LIUJ X, et al. An overview of research progress on saliency detection of panoramic VR images[J]. Acta Electronica Sinica, 2019, 47(7): 1575-1583. (in Chinese)
6	LOWED G. Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision, 2004, 60(2): 91-110.
7	BROWNM, LOWED G. Automatic panoramic image stitching using invariant features[J].International Journal of Computer Vision, 2007, 74(1): 59-73.
8	徐弘祯, 李世超, 季宇寒, 等. 基于特征点匹配的全景相机图像拼接方法研究[J]. 农业机械学报, 2019, 50(S1): 150-158.
	XUH Z, LIS C, JIY H, et al. Panoramic camera image mosaic method based on feature points[J]. Transactions of the Chinese Society for Agricultural Machinery, 2019, 50(S1): 150-158. (in Chinese)
9	ZARAGOZAJ, CHINT J, BROWNM S, et al. As-projective-as-possible image stitching with moving DLT[C]//2013 IEEE Conference on Computer Vision and Pattern Recognition. Portland: IEEE, 2013: 2339-2346.
10	赵春晖, 樊斌, 胡劲文, 等. 基于网格的统计优化特征匹配算法[J]. 西北工业大学学报, 2019, 37(2): 249-257.
	ZHAOC H, FANB, HUJ W, et al. Matching algorithm of statistical optimization feature based on grid method[J]. Journal of Northwestern Polytechnical University, 2019, 37(2): 249-257. (in Chinese)
11	MAJ Y, JIANGJ J, ZHOUH B, et al. Guided locality preserving feature matching for remote sensing image registration[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(8): 4435-4447.
12	WUZ M. Compactly supported positive definite radial functions[J].Advances in Computational Mathematics, 1995, 4(1): 283-292.
13	FORNEFETTM, ROHRK, STIEHLH S. Radial basis functions with compact support for elastic registration of medical images[J]. Image and Vision Computing, 2001, 19(1/2): 87-96.
14	唐逸之, 罗闪, 冉清, 等. 基于多薄板样条的多视角非刚性配准算法[J]. 计算机辅助设计与图形学学报, 2017, 29(12): 2153-2161.
	TANGY Z, LUOS, RANQ, et al. Multi-view non-rigid registration based on multiple thin-plate splines[J]. Journal of Computer-Aided Design & Computer Graphics, 2017, 29(12): 2153-2161. (in Chinese)
15	ZHANGZ R, YANGX, LIY R, et al. Sparse constrained transformation model based on radial basis function expansion: Application to cardiac and brain image registration[J]. IEEE Access, 2018, 6: 42631-42646.
16	SPRENGELR, ROHRK, STIEHLH S. Thin-plate spline approximation for image registration[C]//Proceedings of 18th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Amsterdam: IEEE, 1996: 1190-1191.
17	LINC C, PANKANTIS U, RAMAMURTHYK N, et al. Adaptive as-natural-as-possible image stitching[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston: IEEE, 2015: 1155-1163.
18	WANGZ, BOVIKA C, SHEIKHH R, et al. Image quality assessment: From error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004, 13(4): 600-612.

图像	文献[7]	APAP	AANAP	本文算法
a组	0.881 1	0.918 6	0.948 7	0.973 4
b组	0.872 5	0.865 4	0.887 4	0.898 3
公园	0.769 4	0.884 8	0.895 2	0.935 8
人行道	0.876 4	0.896 4	0.896 2	0.901 5
desk	0.861 5	0.876 9	0.902 3	0.901 4
park	0.871 4	0.876 4	0.879 2	0.887 1
campus	0.925 6	0.915 4	0.928 1	0.942 9

图像	文献[7]	APAP	AANAP	本文算法
a组	0.881 1	0.918 6	0.948 7	0.973 4
b组	0.872 5	0.865 4	0.887 4	0.898 3
公园	0.769 4	0.884 8	0.895 2	0.935 8
人行道	0.876 4	0.896 4	0.896 2	0.901 5
desk	0.861 5	0.876 9	0.902 3	0.901 4
park	0.871 4	0.876 4	0.879 2	0.887 1
campus	0.925 6	0.915 4	0.928 1	0.942 9

[1]	赵夫群, 耿国华. 基于特征区域划分的文物碎片自动匹配算法[J]. 电子学报, 2022, 50(6): 1436-1443.
[2]	张清华, 黄志康, 高满, 艾志华. 基于不确定性与错误分类率博弈的序贯三支决策模型[J]. 电子学报, 2022, 50(5): 1033-1041.
[3]	吴龙文, 聂雨亭, 张宇鹏, 何胜阳, 赵雅琴. 基于变分模态分解的自适应滤波降噪方法[J]. 电子学报, 2021, 49(8): 1457-1465.
[4]	邢远秀, 李军贤, 王文波, 王松. 基于非局部自相似序列集的一类视频图像盲去噪算法[J]. 电子学报, 2021, 49(8): 1498-1506.
[5]	侯志强, 刘晓义, 余旺盛, 蒲磊, 马素刚, 范九伦. 使用GIoU改进非极大值抑制的目标检测算法[J]. 电子学报, 2021, 49(4): 696-705.
[6]	窦家维, 王颖囡, 葛雪. 区间关系保密计算若干问题研究[J]. 电子学报, 2021, 49(1): 50-57.
[7]	代振, 王平波, 卫红凯. 非高斯背景下的自适应限幅检测研究[J]. 电子学报, 2020, 48(3): 426-430.
[8]	黄俊君, 关杰. 基于元胞自动机的S盒的性质与神经网络实现研究[J]. 电子学报, 2020, 48(12): 2462-2468.
[9]	邹耀斌, 乔焰, 孙水发, 臧兆祥, 夏平, 王俊英, 董方敏, 龚国强. 边缘引导和轮廓约束下的跨域香农熵最大化导向的自动阈值选取方法[J]. 电子学报, 2019, 47(12): 2495-2504.
[10]	王文波, 晋云雨, 王斌, 李维刚, 汪祥莉. 混沌信号的自适应阈值同步挤压小波变换消噪[J]. 电子学报, 2018, 46(7): 1652-1657.
[11]	辛艳辉, 袁合才, 辛洋. 对称三材料双栅应变硅MOSFET亚阈值电流与亚阈值斜率解析模型[J]. 电子学报, 2018, 46(11): 2768-2772.
[12]	马塾亮, 王俊平, 邓晟, 冯玉颖. 图空间上自适应形态学算子[J]. 电子学报, 2018, 46(1): 118-126.
[13]	梁常建, 李永明. 具有模糊时态的广义可能性线性时序逻辑的模型检测[J]. 电子学报, 2017, 45(12): 2971-2977.
[14]	陈海强, 梁奇, 黎相成, 孙友明, 覃团发, 李道丰. 瑞利信道下基于广义阈值函数的LDPC译码算法[J]. 电子学报, 2017, 45(1): 16-21.
[15]	王凯, 肖亮, 黄丽丽, 韦志辉. 优化重加权L1范数的图像盲复原算法[J]. 电子学报, 2016, 44(9): 2175-2180.

基于局部投影的视差图像拼接平滑优化

Smooth Optimization of Parallax Images Mosaic Based on Local Projection

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 6

参考文献 18

相关文章 15

编辑推荐

Metrics