融合特征点密度与边缘信息的场景深度估计

通过分析特征点密度与物点聚焦程度的关系，建立基于特征点密度的聚焦测度。将融合特征点密度与边缘信息建立新的聚焦测度，利用聚焦堆栈数据实现场景深度的估计与全聚焦成像。对于由边缘信息建立的聚焦测度在图像纹理区域存在不准确性，该方法可以有效地弥补这一缺点。将刻画边缘信息的Sum-Modified-Laplacian(SML)方法与特征点密度函数相融合建立新的聚焦测度，用于三维场景重构，实现了场景深度估计和全聚焦成像算法。实验结果表明，新方法有效地剔除了SML在纹理区域估计错误的深度值，保留了SML在边缘区域的优势，得到了高精度的场景深度图及其全聚焦图像。

Abstract

The relationship between the feature point density and the object degree of focus is analyzed, and a focus measure based on the feature point density is proposed. A novel focus measure fusing the feature point density and the edge information is proposed. The focus measure for scene depth estimation and all-in-focus imaging from focus stack is utilized. The proposed method can effectively compensate for the focus measure based on the edge information which is inaccurate in the image texture regions. The focus measure fusing the feature point density function and the sum-modified-Laplacian (SML) is used for the three-dimensional scene reconstruction, and the scene depth estimation and all-in-focus imaging algorithm are achieved. The experimental results show that the proposed method can effectively eliminate the error depth value which the SML estimates in the image texture region, retain the advantages of SML in the edge region and the high precision scene depth maps and all-in-focus images are obtained.

参考文献

[1] Levin A, Fergus R, Durand F, et al. Image and depth from a conventional camera with a coded aperture［J］. Acm Transactions on Graphics, 2007, 26(3): 70-79.

[2] Subbarao M. Parallel depth recovery by changing camera parameters［C］. IEEE International Conference on Computer Vision, 1988: 149-155.

[3] Soatto S, Favaro P. A geometric approach to blind deconvolution with application to shape from defocus［C］. IEEE Conference on Computer Vision and Pattern Recognition, 2000: 2010.

[4] Geusebroek J M, Cornelissen F, Smeulders A W M, et al. Robust autofocusing in microscopy［J］. Cytometry Part A, 2000, 39(1): 1-9.

[5] Xie H, Rong W, Sun L. Wavelet-based focus measure and 3D surface reconstruction method for microscopy images［C］. IEEE International Conference on Intelligent Robots and Systems, 2006: 229-234.

[6] Pertuz S, Puig D, Garcia M A. Reliability measure for shape-from-focus［J］. Image and Vision Computing, 2013, 31(10): 725-734.

[7] Pertuz S, Puig D, Garcia M A. Analysis of focus measure operators for shape-from-focus［J］. Pattern Recognition, 2013, 46(5): 1415-1432.

[8] Huang W, Jing Z. Evaluation of focus measures in multi-focus image fusion［J］. Pattern Recognition Letters, 2007, 28(4): 493-500.

[9] Subbarao M, Choi T S, Nikzad A. Focusing techniques［J］. Optical Engineering, 1993, 32(11): 2824-2836.

[10] Nomnob N, Kitjaidure Y. Adaptive window size multi-focus images fused based on sum of modified Laplacian［C］. Joint International Conference on Information and Communication Technology, Electronic and Electrical Engineering, 2014: 1-4.

[11] Nayar S K, Nakagawa Y. Shape from focus［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1994, 16(8): 824-831.

[12] An Y, Kang G, Kim I J, et al. Shape from focus through Laplacian using 3D window［C］. Second International Conference on Future Generation Communication and Networking, 2008: 46-50.

[13] Firestone L, Cook K, Culp K, et al. Comparison of autofocus methods for automated microscopy［J］. Cytometry Part A, 1991, 12(3): 195-206.

[14] Sun Y, Duthaler S, Nelson B J. Autofocusing in computer microscopy: selecting the optimal focus algorithm［J］. Microscopy Research & Technique, 2004, 65(3): 139-149.

[15] 孟繁浩, 丁亚林, 王德江, 等. 像移对长焦距高分辨率航空相机检调焦精度影响的分析［J］. 光学学报, 2015, 35(6): 0611001.

Meng Fanhao, Ding Yalin, Wang Dejiang, et al. Analysis of influence of image motion on auto-focus precision for high resolution aerial camera［J］. Acta Optica Sinica, 2015, 35(6): 0611001.

[16] 张振久, 胡泓, 李天利. 透镜检测中复合自动对焦技术的研究及应用［J］. 光学学报, 2011, 31(3): 0312005.

Zhang Zhenjiu, Hu Hong, Li Tianli. Application and research of composite autofocusing technique in optical-lens measurement［J］. Acta Optica Sinica, 2011, 31(3): 0312005.

[17] 吴迪, 冯华君, 徐之海, 等. 基于简化对焦模型的自动对焦窗口调整方法［J］. 光子学报, 2016, 45(7): 0710002.

Wu Di, Feng Huajun, Xu Zhihai, et al. Autofocus window adjustment based on simplified focus model［J］. Acta Photonica Sinica, 2016, 45(7): 0710002.

[18] 陈国波. 基于散焦显微图像的三维重构方法研究［D］. 杭州: 浙江工业大学, 2007.

Chen Guobo. Research of defocus microscopy image 3D surface reconstruction［D］. Hangzhou: Zhejiang University of Technology, 2007.

[19] Muhammad M, Choi T S. Sampling for shape from focus in optical microscopy［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(3): 564-573.

[20] Liu Y, Xu Q. Design of a flexure-based auto-focusing device for a microscope［J］. International Journal of Precision Engineering and Manufacturing, 2015, 16(11): 2271-2279.

[21] Lee S Y, Yoo J T, Kumar Y, et al. Reduced energy-ratio measure for robust autofocusing in digital camera［J］. IEEE Signal Processing Letters, 2009, 16(2): 133-136.

[22] Shen C H, Chen H. Robust focus measure for low-contrast images［C］. Digest of Technical Papers, IEEE International Conference on Consumer Electronics, 2006: 69-70.

[23] Baina J, Dublet J. Automatic focus and iris control for video cameras［C］. Fifth International Conference on Image Processing and its Applications, 1995: 232-235.

[24] Lee S Y, Kumar Y, Cho J M, et al. Enhanced autofocus algorithm using robust focus measure and fuzzy reasoning［J］. IEEE Transactions on Circuits and Systems for Video Technology, 2008, 18(9): 1237-1246.

[25] Lowe D G. Distinctive image features from scale-invariant keypoints［J］. International Journal of Computer Vision, 2004, 60(2): 91-110.

何建梅, 邱钧, 刘畅. 融合特征点密度与边缘信息的场景深度估计[J]. 激光与光电子学进展, 2017, 54(7): 071101. He Jianmei, Qiu Jun, Liu Chang. Fusing Feature Point Density and Edge Information for Scene Depth Estimation[J]. Laser & Optoelectronics Progress, 2017, 54(7): 071101.

融合特征点密度与边缘信息的场景深度估计

关于本站 Cookie 的使用提示

全站搜索

融合特征点密度与边缘信息的场景深度估计

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索