计算机科学 ›› 2020, Vol. 47 ›› Issue (3): 130-136.doi: 10.11896/jsjkx.190100239
庞荣来,林静,张磊
PANG Rong,LAI Lin-jing,ZHANG Lei
摘要: 图像拼接是将不同视角下的多幅图像合并成一幅宽视角图像的技术。该技术不仅要求拼接后的重叠区域重影尽可能少,而且要求非重叠区域的扭曲尽可能小。在Moving DLT(Moving Direct Linear Transformation)的基础上,文中提出了网格驱动的双向图像拼接算法。对于重叠区域,利用双向Moving DLT做特征点对齐,并通过定量评估的方式来判断图像叠加的方式,进而得到拼接准确、重影少的结果;对于非重叠区域,利用网格在单应变换和相似变换后的顶点插值进行矫正,进而减小非重叠区域的扭曲。实验结果显示,提出的双向拼接算法比单向拼接算法更准确,对应点的MAE(Mean Absolute Error)会下降0.2个点,而且得到的拼接结果更加自然平滑。
中图分类号:
[1]WANG J J,LIU J M,HU Y F,et al.Research and Development of Image Mosaics[J].Computer Science,2003,30(6):141-144. [2]BROWN M,LOWE D G.Automatic panoramic image stitching using invariant features[J].International Journal of Computer Vision,2007,74(1):59-73. [3]GAO J,KIM S J,BROWN M S.Constructing image panoramas using dual-homography warping[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Colorado Springs:IEEE Press,2011:49-56. [4]LIN W Y,LIU S,MATSUSHITA Y,et al.Smoothly varying affine stitching[C]∥Proceedings of IEEE Conference on Compu-ter Vision and Pattern Recognition.Colorado Springs:IEEE Press,2011:345-352. [5]ZARAGOZA J,CHIN T J,BROWN M S,et al.As-projective-as-possible image stitching with moving DLT[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Portland:IEEE Press,2013:2339-2346. [6]CHANG C H,SATO Y,CHUANG Y Y.Shape-preserving half-projective warps for image stitching[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Columbus:IEEE Press,2014:3254-3261. [7]LIN C C,PANKANTI S U,NATESAN RAMAMURTHY K,et al.Adaptive as-natural-as-possible image stitching[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Boston:IEEE Press,2015:1155-1163. [8]GUPTA R,AWASTHI D.WAVE—packet image fusion tech- nique based ongenetic algorithm[J].IEEE International Confe-rence on Confluence The Next Generation InformationTechno-logy Summit,2014,3(2):280-285. [9]ZHU Z,LU J,WANG M,et al.A Comparative Study of Algorithms for Realtime Panoramic Video Blending[J].IEEE Tran-sactions on Image Processing,2018,27(6):2952-2965. [10]WANG M,ZHU Z,ZHANG S,et al.Avoiding bleeding in image blending[C]∥2017 IEEE International Conference on Image Processing.Beijng:IEEE Press,2017:2139-2143. [11]CHEN R,WANG J,HUANG H J,et a1.Multi-focus image fusion based on block DCT Transform[J].Journal of Chinese Computer Systems,2016,37(2):321-326. [12]ZHANG X Q,TANG Z J,LUN J T.Image Stitching Based on Line Matching[J].Computer Science,2005,32(1):221-223. [13]ZHANG F,LIU F.Parallax-tolerant image stitching[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Columbus:IEEE Press,2014:3262-3269. [14]LIN K,JIANG N,CHEONG L F,et al.Seagull:seam-guided local alignment for parallax-tolerant image stitching[C]∥Euro-pean Conference on Computer Vision.Amsterdam:IEEE Press,2016:370-385. [15]SONG B S,FU Y Q,SONG H L.New Efficient Image Fusion Algorithm for Image Mosaic[J].Computer Science,2011,38(2):260-263. [16]HARTLEY R,ZISSERMAN A.Multiple view geometry in computer vision[M].London:Cambridge university press,2003:75-89. [17]FISCHLER M A,BOLLES R C.Random sample consensus:a paradigm for model fitting with applications to image analysis and automated cartography[J].Communications of the ACM,1981,24(6):381-395. [18]GAO J,LI Y,CHIN T J,et al.Seam-Driven Image Stitching [C]∥Eurographics (Short Papers).Girona,2013:45-48. [19]KWATRA V,SCHÖDL A,ESSA I,et al.Graphcut textures:image and video synthesis using graph cuts[J].ACM Transactions on Graphics (ToG),2003,22(3):277-286. [20]PÉREZ P,GANGNET M,BLAKE A.Poisson image editing [J].ACM Transactions on graphics (TOG),2003,22(3):313-318. [21]VEDALDI A,FULKERSON B.VLFeat:An open and portable library of computer vision algorithms[C]∥Proceedings of the 18th ACM International Conference on Multimedia.Firenze:ACM Press,2010:1469-1472. [22]LOWE D G.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110. |
[1] | 张美玉, 王洋洋, 侯向辉, 秦绪佳. 基于ORB和改进的RANSAC图像拼接算法 Image Stitching Algorithm Based on ORB and Improved RANSAC 计算机科学, 2019, 46(11A): 294-298. |
[2] | 卢嘉铭,朱哲. 基于GPU加速的实时4K全景视频拼接 Real-time 4K Panoramic Video Stitching Based on GPU Acceleration 计算机科学, 2017, 44(8): 18-21. https://doi.org/10.11896/j.issn.1002-137X.2017.08.003 |
[3] | 苏慧嘉,郑继明. 结合游程长度与共生矩阵的图像拼接篡改检测方法 Image Splicing Blind Detection Method Combined RLRN with GLCM 计算机科学, 2017, 44(6): 150-154. https://doi.org/10.11896/j.issn.1002-137X.2017.06.025 |
[4] | 杨程,徐晓刚,王建国. 图像配准技术研究 Research on Importance of Image Mosaic Technology 计算机科学, 2016, 43(Z11): 133-135. https://doi.org/10.11896/j.issn.1002-137X.2016.11A.028 |
[5] | 瞿中,林嗣鹏,鞠芳蓉. 一种改进的降低扭曲误差的快速图像拼接算法 Improved Algorithm of Fast Image Stitching by Reducing Panoramic Distortion 计算机科学, 2016, 43(5): 279-282. https://doi.org/10.11896/j.issn.1002-137X.2016.05.053 |
[6] | 陈志昂,徐晓刚,徐冠雷. 图像拼接技术研究 Research on Image Mosaic Technology 计算机科学, 2015, 42(Z11): 160-161. |
[7] | 瞿 中,乔高元,林嗣鹏. 一种消除图像拼接缝和鬼影的快速拼接算法 Fast Image Stitching Algorithm Eliminates Seam Line and Ghosting 计算机科学, 2015, 42(3): 280-283. https://doi.org/10.11896/j.issn.1002-137X.2015.03.058 |
[8] | 秦绪佳,王 琪,王慧玲,郑红波,陈胜男. 基于最佳缝合线的序列遥感图像拼接融合方法 Image Fusion Method Based on Best Seam-line for Serial Remote Sensing Images Mosaic 计算机科学, 2015, 42(10): 306-310. |
[9] | 常嘉义,秦瑞,李庆,陈大鹏. 全景鸟瞰拼接图像的质量评价方法 Image Quality Assessment of Panoramic Image 计算机科学, 2014, 41(6): 278-281. https://doi.org/10.11896/j.issn.1002-137X.2014.06.055 |
[10] | 路晓静,黄向生. 一种快速的空间变换模型计算方法 Fast Calculation Method of Space Transform Model 计算机科学, 2014, 41(3): 279-281. |
[11] | 郭一汉,史美萍,吴涛. 基于GPU的实时图像拼接 Real Time Image Mosaic Based on GPU 计算机科学, 2012, 39(7): 257-261. |
[12] | 仇国庆,冯汉青,蒋天跃,涂乐飞. 一种改进的Harris角点图像拼接算法 Improved Image Mosaic Algorithm Based on Harris Corner 计算机科学, 2012, 39(11): 264-266. |
[13] | 宋宝森,付永庆,宋海亮. 一种消除图像拼接痕迹的新方法 New Efficient Image Fusion Algorithm for Image Mosaic 计算机科学, 2011, 38(2): 260-263. |
[14] | 冯宇平,戴明,张威,王美娇. 一种用于图像序列拼接的角点检测算法 Corner Detection Algorithm for Image Mosaic 计算机科学, 2009, 36(12): 270-271. |
[15] | 张显全 唐振军 卢江涛. 基于线匹配的图像拼接 计算机科学, 2005, 32(1): 221-223. |
|