-
摘要: 非剛性圖像配準一直是計算機視覺領域的研究重點. 為解決上述問題, 提出一種改進的光流場模型算法, 以提高光流估計的準確度. 算法首先對原始變分光流模型進行了改進, 提出利用新的各向異性正則項來代替原來的同向擴散函數, 以避免圖像模糊, 保留圖像的邊緣特征與細節特征; 此外, 通過引入包含鄰域信息的非局部平滑項來去除光流噪點, 同時增加了一個結合圖像結構與光流運動信息的權函數, 以減少過平滑所造成的細節丟失, 提高算法的魯棒性. 最后, 利用交替最小化與金字塔分層迭代策略相結合的方法求解位移場, 實現非剛性圖像的自動配準. 仿真實驗結果表明, 與傳統方法相比, 本文算法對不同類型的非剛性圖像均具有較高的魯棒性, 取得了理想的圖像配準效果.Abstract: With the rapid development of image registration technology, it is being widely used in the fields of medical image processing, remote sensing image analysis, computer vision, and others. Image registration involves two or more images that contain the same object that are obtained under different conditions. Geometric mapping between images is realized by spatial geometric transformation, so that the points in one image can be related to their corresponding points in the other. Compared with rigid transformations, non-rigid transformations usually have severe local distortions and obvious nonlinear characteristics. So, it is difficult to describe non-rigid transformations using a unified transformation model. For this reason, non-rigid image registration has always been an issue and a source of difficulty in the field of computer vision. To solve this problem, an improved optical-flow-model algorithm was proposed to more accurately estimate the optical flow field. First, the original variational optical flow model was improved. To prevent blurring and preserve the edge and detail features of images, a new anisotropic regular term was proposed to replace the original homologous diffusion term. Then, to remove optical flow outliers, a non-local smoothness term was introduced that contained neighborhood information. Moreover, a weight function that combines image-structure and optical-flow information was added to reduce the loss of detail caused by over-smoothing and to improve robustness. Finally, to solve the displacement field and realize the automatic registration of non-rigid images, an alternating minimization method and pyramid hierarchical iteration strategy were utilized. To verify the effectiveness of the proposed algorithm, subjective and objective evaluation values such as the peak signal-to-noise ratio (PSNR) and normalized mutual information (NMI) were adopted to analyze the registration results. Compared with state-of-the-art methods, experimental results reveal the robustness and ideal registration effects of the proposed method on different types of non-rigid images.
-
圖 1 采用各向同性與各向異性正則項的光流場對比. (a)真實光流；(b)各向同性正則項；(c)各向異性正則項
Figure 1. Comparison of optical flow fields with isotropic and anisotropic regularization terms: (a) ground truth; (b) isotropic regularization term; (c) anisotropic regularization term
圖 2 增加非局部平滑項前后的光流場結果對比. (a)真實光流; (b)未加局部平滑項; (c)加局部平滑項
Figure 2. Comparison of optical flow fields before and after adding non-local smoothing term: (a) ground truth; (b) without non-local smoothing term; (c) with non-local smoothing term
圖 3 原始參考圖像和浮動圖像. (a)參考圖像；(b)浮動圖像
Figure 3. Original reference and floating images: (a) reference images; (b) floating images
圖 4 核磁共振圖像糾正結果對比. (a)H-S算法；(b)Brox算法；(c)SIFT Flow算法；(d)本文算法
Figure 4. Comparison of aligned results on MRI images: (a) H-S method; (b) Brox method; (c) SIFT flow method; (d) proposed method
圖 5 柔性圖像糾正結果對比. (a)H-S算法；(b)Brox算法；(c)SIFT Flow算法；(d)本文算法
Figure 5. Comparison of aligned results on flexible images: (a) H-S method; (b)Brox method; (c)SIFT flow method; (d) proposed method
圖 6 人臉圖像糾正結果對比. (a)H-S算法；(b)Brox算法；(c)SIFT Flow算法；(d)本文算法
Figure 6. Comparison of aligned results on human face images: (a) H-S method; (b) Brox method; (c) SIFT flow method; (d) proposed method
表 1 不同算法的峰值信噪比對比結果
Table 1. Comparison of PSNR values of different methods?
dB 圖像 不同算法 H-S Brox SIFT Flow 本文算法 核磁共振 13.30 16.99 16.89 18.09 柔性 18.69 21.57 25.23 25.24 人臉 20.27 20.35 22.08 22.82 
下載: 導出CSV
表 2 不同算法的歸一化互信息對比結果
Table 2. Comparison of NMI values of different methods
圖像 不同算法 H-S Brox SIFT Flow 本文算法 核磁共振 1.0279 1.1031 1.1255 1.1545 柔性 1.5076 1.5027 1.1790 1.5216 人臉 1.4180 1.4324 1.4060 1.4554
下載: 導出CSV
259luxu-164<th id="5nh9l"></th> <strike id="5nh9l"></strike> <th id="5nh9l"><noframes id="5nh9l"><th id="5nh9l"></th> <strike id="5nh9l"></strike> <th id="5nh9l"><noframes id="5nh9l"> <th id="5nh9l"></th> <strike id="5nh9l"><noframes id="5nh9l"><span id="5nh9l"></span> <span id="5nh9l"><noframes id="5nh9l"><span id="5nh9l"></span> <strike id="5nh9l"><noframes id="5nh9l"><strike id="5nh9l"></strike> <span id="5nh9l"><noframes id="5nh9l"> <span id="5nh9l"><noframes id="5nh9l"> <span id="5nh9l"></span> <span id="5nh9l"><video id="5nh9l"></video></span> <th id="5nh9l"><noframes id="5nh9l"><th id="5nh9l"></th> -
參考文獻
[1] Chen S W, Zhang S X, Yang X G, et al. Registration of visual-infrared images based on ellipse symmetrical orientation moment. Chin J Eng, 2017, 39(7): 1107 https://www.cnki.com.cn/Article/CJFDTOTAL-BJKD201707018.htm陳世偉, 張勝修, 楊小岡, 等. 基于橢圓對稱方向矩的可見光與紅外圖像配準算法. 工程科學學報, 2017, 39(7): 1107 https://www.cnki.com.cn/Article/CJFDTOTAL-BJKD201707018.htm [2] Pan B, Ben J, Yan J W, et al. Method to extract micro device profile in ultrasound image under global constraints. J Harbin Inst Technol, 2018, 50(1): 24 https://www.cnki.com.cn/Article/CJFDTOTAL-HEBX201801005.htm潘博, 賁進, 閆佳雯, 等. 全局約束下超聲圖像微器械輪廓提取方法. 哈爾濱工業大學學報, 2018, 50(1): 24 https://www.cnki.com.cn/Article/CJFDTOTAL-HEBX201801005.htm [3] Dellinger F, Delon J, Gousseau Y, et al. SAR-SIFT: a SIFT-like algorithm for SAR images. IEEE Trans Geosci Remote Sens, 2015, 53(1): 453 doi: 10.1109/TGRS.2014.2323552 [4] Sariyanidi E, Gunes H, Cavallaro A. Automatic analysis of facial affect: a survey of registration, representation, and recognition. IEEE Trans Pattern Anal Mach Intell, 2015, 37(6): 1113 doi: 10.1109/TPAMI.2014.2366127 [5] Thirion J P. Image matching as a diffusion process: an analogy with Maxwell's demons. Med Image Anal, 1998, 2(3): 243 doi: 10.1016/S1361-8415(98)80022-4 [6] Horn B K P, Schunck B G. Determining optical flow. Artif Intell, 1981, 17(1-3): 185 doi: 10.1016/0004-3702(81)90024-2 [7] Nagel H H, Enkelmann W. An investigation of smoothness constraints for the estimation of displacement vector fields from image sequences. IEEE Trans Pattern Anal Mach Intell, 1986, 8(5): 565 doi: 10.1109/TPAMI.1986.4767833 [8] Brox T, Malik J. Large displacement optical flow: descriptor matching in variational motion estimation. IEEE Trans Pattern Anal Mach Intell, 2011, 33(3): 500 doi: 10.1109/TPAMI.2010.143 [9] Amiaz T, Lubetzky E, Kiryati N. Coarse to over-fine optical flow estimation. Pattern Recognit, 2007, 40(9): 2496 doi: 10.1016/j.patcog.2006.09.011 [10] Bao L C, Yang Q X, Jin H L. Fast edge-preserving patch match for large displacement optical flow//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Columbus, 2014: 3534 doi: 10.1109/CVPR.2014.452 [11] Liu C, Yuen J, Torralba A. SIFT flow: dense correspondence across scenes and its applications. IEEE Trans Pattern Anal Mach Intell, 2011, 33(5): 978 doi: 10.1109/TPAMI.2010.147 [12] Sun D Q, Roth S, Black M J. A quantitative analysis of current practices in optical flow estimation and the principles behind them. Int J Comput Vision, 2014, 106(2): 115 doi: 10.1007/s11263-013-0644-x [13] Liu H B, Chang F L. Moving object detection by optical flow method based on adaptive weight coefficient. Opt Precis Eng, 2016, 24(2): 460 https://www.cnki.com.cn/Article/CJFDTOTAL-GXJM201602027.htm劉紅彬, 常發亮. 權重系數自適應光流法運動目標檢測. 光學精密工程, 2016, 24(2): 460 https://www.cnki.com.cn/Article/CJFDTOTAL-GXJM201602027.htm [14] Revaud J, Weinzaepfel P, Harchaoui Z, et al. EpicFlow: edge-preserving interpolation of correspondences for optical flow//Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition. Boston, 2015: 1164 doi: 10.1109/CVPR.2015.7298720 [15] Li S, Fan X G, Xu Y L, et al. Bio-inspired motion-adaptive estimation algorithm of sequence image. Chin J Eng, 2017, 39(8): 1238 https://www.cnki.com.cn/Article/CJFDTOTAL-BJKD201708014.htm李帥, 樊曉光, 許悅雷, 等. 序列圖像運動自適應V1-MT光流估計算法. 工程科學學報, 2017, 39(8): 1238 https://www.cnki.com.cn/Article/CJFDTOTAL-BJKD201708014.htm [16] Dosovitskiy A, Fischer P, Ilg E, et al. FlowNet: learning optical flow with convolutional networks//Proceedings of the IEEE International Conference on Computer Vision. Santiago, 2015: 2758 https://www.researchgate.net/publication/304409658_FlowNet_Learning_Optical_Flow_with_Convolutional_Networks [17] He K, Yan J X, Wei Y, et al. Non-rigid image registration using improved optical flow field. J Tianjin Univ Sci Technol, 2018, 51(5): 491 https://www.cnki.com.cn/Article/CJFDTOTAL-TJDX201805008.htm何凱, 閆佳星, 魏穎, 等. 基于改進光流場模型的非剛性圖像配準. 天津大學學報: 自然科學與工程技術版, 2018, 51(5): 491 https://www.cnki.com.cn/Article/CJFDTOTAL-TJDX201805008.htm -
點擊查看大圖
計量
- 文章訪問數: 1196
- HTML全文瀏覽量: 424
- PDF下載量: 36
- 被引次數: 0
