浏览全部资源
扫码关注微信
Received：19 June 2018，
Revised：2018-8-21，
Published：16 February 2019
移动端阅览
目的
2
色彩纠正和图像融合是生成高质量全景场景图像的关键技术。色彩纠正中参考图像的选择以及图像融合算法，决定着所生成全景图像的质量和速度。现有方法在确定一幅图像是否适合作为参考图像时，需要遍历所有其他图像，计算其作为参考图像进行色彩纠正的效果，复杂度高，速度慢；在图像融合时存在融合质量与融合速度之间的矛盾。因此，如何快速生成高质量的全景图像就成为全景场景再现的主要诉求。为此本文提出优化的参考图像自动选择的色彩纠正方法和基于重叠区域划分的分区融合方法。
方法
2
针对参考图像选择算法复杂度高的问题，根据图像质量与稳定性通常呈反比关系的事实，采用贪婪策略，选择质量最差的图像在色彩纠正前后的相似度，作为是否选择当前图像作为参考图像的评价指标，在保证参考图像满足色彩纠正需求的前提下，大幅降低计算复杂度。针对融合质量与融合速度之间的矛盾，提出分区融合：将重叠区域划分为接缝区域和非接缝区域，利用泊松融合的接缝不可见性和线性融合实现速度快的特性分别对接缝区域和非接缝区域进行融合，既保证融合的质量，又加快融合速度。在此基础上，加入简单点光源，解决上述过程产生的光线一致性问题，进一步提高图像质量。
结果
2
采用主观和客观相结合的方法对结果进行评估。主观方面，本文算法生成的全景图像色彩基本实现平滑过渡且图像原始信息保留完整。客观方面，色彩纠正前后图像的结构相似度（SSIM）控制在0.85~0.99之间，时间复杂度由原来的O（
$${n^2}$$
）降低到O（
$$n$$
）；分区融合后图像信息熵接近于泊松融合，但时间消耗降低72%。采用基于PC端的问卷调查法和OG-IQA算法将本文算法与PTGui、OpenCV、Xiong方法生成的全景图质量进行对比，在大多数情况下本文算法均优于上述算法。
结论
2
实验表明，本文算法适用于多种场景，在保证目视效果良好的前提下，时间消耗降低，可广泛应用于医学、数字旅游、遥感等领域。
Objective
2
Panorama scene reproduction
which is widely used in medicine
tourism
remote sensing
and photography
is a technique utilized to produce a large or wide-angle scene with multiple overlapping images. Color correction and image blending are the key issues in the generation of high-quality panoramas. The generation efficiency and quality are primarily determined by selecting a reference image for color correction and an image blending algorithm. To determine a reference image
state-of-the-art methods compare the similarity of all target images
which is computationally complex with poor real-time responsiveness. In addition
a contradiction exists between the quality and speed in image blending. Therefore
a high-quality panoramic image should be rapidly generated to reproduce panoramic scenes.
Method
2
A key task for a panorama stitching technique is finding the optimal seams in the overlap region of the source image
merging them along the seam
and minimizing the seam artifact. This study presents an efficient method in selecting a reference image for color correction and a partition blending method that differentiates the overlapping area. The color and illumination of images are inconsistent due to the difference in camera equipment
shooting angle
and shooting time
which affect the visual quality of the panorama. Color correction is applied to reduce the color difference between images and accelerate the optimal seam search and image blending processes. Color correction uses a reference image to adjust the color style of other images. In other words
the reference image determines the quality of the final panorama. The panoramic image may suffer from blurriness
inappropriate brightness
and low contrast when the quality of the selected reference image is poor. The quality of an image is usually inversely proportional to the stability of an image; thus
a greedy strategy is adopted to determine the best reference image and reduce the computational complexity. The worst quality image is selected as the baseline
which is determined based on the relative standard deviation of the image pixels of adjacent images. The similarity between the original and corrected baselines is used to determine whether an input image is appropriate to be used as the reference image
such that the complexity for selecting a reference image is remarkably reduced while guaranteeing the need for color correction. An effective color correction method can achieve a smooth transition of the panoramic image. However
an unnatural transition along the seam is observed. Image blending is required to conceal the artifacts
in which Poisson and linear blending are usually used. Linear blending is simple and fast. However
the weakness of linear blending is that stitching artifacts may be visible after the blending. In comparison with linear blending
Poisson blending is more effective although it is more time-consuming than the former. Partition blending is proposed to solve the following problems. The overlapping region is divided into seam and non-seam regions
Poisson blending is performed in the seam region
and linear correction is conducted in the non-seam region to obtain a high-quality image. A simple point-light source is added to solve the light inconsistency generated by the aforementioned processes and improve the quality of the panorama.
Result
2
Subjective and objective evaluations show interesting results for the proposed method. For the subjective evaluation
the methods can produce a panoramic scene with consistent color styles and can maintain the original details. For the objective evaluation
the structural similarity of the image after color correction is controlled between 0.85 and 0.99
the time complexity is reduced to O(
$$n$$
) from the original O(
$${n^2}$$
)
the image information entropy is close to Poisson blending after the partition blending
and the time consumption is 72% lower than that of its original. In addition
we use a PC-based questionnaire method and an OG-IQA algorithm to compare the quality of the panorama generated by PTGui
OpenCV
Xiong's method
and our proposed method. Results show that our proposed method performs best in most cases.
Conclusion
2
Experiments demonstrate that our proposed method works well in various scenarios. The time consumption is reduced and good visual effect is ensured
and the method can be widely used in medicine
digital tourism
remote sensing
and other fields.
Chen K. Research and implementation of panorama technology based on mobile terminal[D]. Wuhan: Huazhong University of Science and Technology, 2016. http://cdmd.cnki.com.cn/Article/CDMD-10487-1016920496.htm .
陈康.基于移动终端的全景图技术研究与实现[D].武汉: 华中科技大学, 2016.
Yan W X, Liu C C, Luo W. Fast and low complexity image stitching method on mobile phones[C]//Proceedings of 2015 International Conference on Control, Automation and Information Sciences. Changshu, China: IEEE, 2015: 245-250.[ DOI:10.1109/ICCAIS.2015.7338670 http://dx.doi.org/10.1109/ICCAIS.2015.7338670 ]
Li L, Yao J, Xie R P, et al. A unified framework for street-view panorama stitching[J]. Sensors, 2017, 17(1):#1.[DOI:10.3390/s17010001]
Xu W, Mulligan J. Performance evaluation of color correction approaches for automatic multi-view image and video stitching[C]//Proceedings of 2015 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.San Francisco, CA, USA: IEEE, 2010: 263-270.[ DOI:10.1109/CVPR.2010.5540202 http://dx.doi.org/10.1109/CVPR.2010.5540202 ]
Ibrahim M T, Hafiz R, Khan M M, et al. Automatic selection of color reference image for panoramic stitching[J]. Multimedia Systems, 2016, 22(3):379-392.[DOI:10.1007/s00530-015-0467-4]
Brown M, Lowe D G. Automatic panoramic image stitching using invariant features[J]. International Journal of Computer Vision, 2007, 74(1):59-73.[DOI:10.1007/s11263-006-0002-3]
Gui Y T, Gledhill D, Taylor D, et al. Colour correction for panoramic imaging[C]//Proceedings of the 6th International Conference on Information Visualisation. London, UK: IEEE, 2002: 483-488.[ DOI:10.1109/IV.2002.1028817 http://dx.doi.org/10.1109/IV.2002.1028817 ]
Xiong Y G, Pulli K. Fast panorama stitching for high-quality panoramic images on mobile phones[J]. IEEE Transactions on Consumer Electronics, 2010, 56(2):298-306.[DOI:10.1109/TCE.2010.5505931]
Tian Q C, Cohen L D. Color correction in image stitching using histogram specification and global mapping[C]//Proceedings of the 6th International Conference on Image Processing Theory, Tools and Applications. Oulu, Finland: IEEE, 2016: 1-6.[ DOI:10.1109/IPTA.2016.7821034 http://dx.doi.org/10.1109/IPTA.2016.7821034 ]
Xiong Y G, Pulli K. Color matching for high-quality panoramic images on mobile phones[J]. IEEE Transactions on Consumer Electronics, 2011, 56(4):2592-2600.[DOI:10.1109/TCE.2010.5681145]
Dai H Y, Ran F P. Fast panorama stitching algorithm for mobile devices[J]. Journal of Computer Applications, 2014, 34(9):2673-2677.
戴华阳, 冉飞鹏.一种适于移动设备的全景图快速拼接方法[J].计算机应用, 2014, 34(9):2673-2677. [DOI:10.11772/j.issn.1001-9081.2014.09.2673]
Ibrahim M T, Hafiz R, Khan M M, et al. Automatic reference selection for parametric color correction schemes for panoramic video stitching[C]//The 8th International Symposium on Advances in Visual Computing. Rethymnon, Crete, Greece: Springer, 2012: 492-501.[ DOI:10.1007/978-3-642-33179-4_47 http://dx.doi.org/10.1007/978-3-642-33179-4_47 ]
Xiong Y G, Pulli K. Fast and high-quality image blending on mobile phones[C]//Proceedings of the 7th Consumer Communications and Networking Conference. Las Vegas, NV, USA: IEEE, 2010: 1-5.[ DOI:10.1109/CCNC.2010.5421736 http://dx.doi.org/10.1109/CCNC.2010.5421736 ]
Yan W Q, Hou C P, Lei J J, et al. Stereoscopic image stitching based on a hybrid warping model[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2017, 27(9):1934-1946.[DOI:10.1109/TCSVT.2016.2564838]
Sadeghi M A, Hejrati S M M, Gheissari N. Poisson local color correction for image stitching[C]//Proceedings of the 3rd International Conference on Computer Vision Theory and Applications. Funchal, Madeira, Portugal: VISAPP, 2008: 275-282.
Reinhard E, Adhikhmin M, Gooch B, et al. Color transfer between images[J]. IEEE Computer Graphics and Applications, 2002, 21(5):34-41.[DOI:10.1109/38.946629]
Lowe D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110.[DOI:10.1023/B:VISI.0000029664.99615.94]
Wang J X, Wang Y W. Modified SURF applied in remote sensing image stitching[J]. International Journal of Signal Processing, Image Processing and Pattern Recognition, 2015, 8(8):1-10.[DOI:10.14257/ijsip.2015.8.8.01]
Xiong Y G, Pulli K. Fast image labeling for creating high-resolution panoramic images on mobile devices[C]//The 11th IEEE International Symposium on Multimedia. San Diego, CA, USA: IEEE, 2009: 369-376.[ DOI:10.1109/ISM.2009.122 http://dx.doi.org/10.1109/ISM.2009.122 ]
Gao Z Y, Yang X M, Gong J M, et al. Research on image complexity description methods[J]. Journal of Image and Graphics, 2010, 15(1):129-135.
高振宇, 杨晓梅, 龚剑明, 等.图像复杂度描述方法研究[J].中国图象图形学报, 2010, 15(1):129-135. [DOI:10.11834/jig.20100121]
Liu L X, Hua Y, Zhao Q J, et al. Blind image quality assessment by relative gradient statistics and adaboosting neural network[J]. Signal Processing:Image Communication, 2016, 40:1-15.[DOI:10.1016/j.image.2015.10.005]
相关作者
相关机构
京公网安备11010802024621
