All Title Author
Keywords Abstract


像素聚类改进二进制描述子鲁棒性

DOI: 10.11834/jig.20140411

Keywords: 关键点,图像补丁,局部特征,二进制描述子,鲁棒性

Full-Text   Cite this paper   Add to My Lib

Abstract:

目的通过挖掘图像局部区域特征信息,提出了一种鲁棒性更高的二进制描述子。针对BRIEF(binaryrobustindependentelementaryfeatures)关于旋转和视角变化鲁棒性差的问题,通过图像补丁分层处理、增加关键点图像补丁个数来捕获更多的局部特征信息,对BRIEF描述子改进。方法首先,根据灰度序列对补丁内所有像素点分类,像素的一个聚类形成了一个亚补丁,然后在每个亚补丁上进行类似BRIEF的随机测试。其次,由于原图像补丁大小、尺度大小影响补丁的像素点成分,从而影响像素聚类的效果,所以在原图像关键点周围分割出多个不同大小的图像补丁,或是将原图像补丁根据尺度金字塔确定几个尺度大小不同的补丁,然后再对图像补丁进行分层、测试。所构建的描述子不仅包含了补丁像素的灰度比较信息,而且包含了灰度排序信息和像素群聚信息,提高了描述子的鲁棒性。结果通过性能对比实验,发现所提的描述子的性能提高了,而且好于对比的浮点描述子。结论挖掘图像补丁的特征信息能提高二进制描述子的鲁棒性。

References

[1]  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]
[2]  Bay H, Ess A, Tuytelaars T, et al. SURF: speeded up robust features[J]. Computer Vision and Image Understanding, 2008, 110(3): 346-359.[DOI: 10.1016/j.cviu.2007.09.014]
[3]  Ke Y, Sukthankar R. PCA-SIFT: a more distinctive representation for local image descriptors[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Washington DC, USA: IEEE, 2004: 506-513.[DOI: 10.1109/CVPR.2004.1315206]
[4]  Mikolajczyk K, Schmid C. A performance evaluation of local descriptors[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1615-1630.[DOI: 10.1109/TPAMI.2005.188]
[5]  Tola E, Lepetit V, Fua P. DAISY: an efficient dense descriptor applied to wide baseline stereo[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(5): 815-830.[DOI: 10.1109/TPAMI.2009.77]
[6]  Zhang J, Youssef B, Thomas S. A new biologically inspired color image descriptor[C]//Proceedings of the European Conference on Computer Vision. Florence, Italy: IEEE, 2012: 312-324.[DOI: 10.1007/978-3-642-33715-4_23]
[7]  Fan B, Wu F C, Hu Z Y. Aggregating gradient distributions into intensity orders: a novel local image descriptor[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Providence, RI: IEEE, 2011: 2377-2384.[DOI: 10.1109/CVPR.2011.5995385]
[8]  Wang Z H, Fan B, Wu F C. Local intensity order pattern for feature description[C]//Proceedings of the International Conference on Computer Vision. Barcelona, Spain: IEEE, 2011: 603-610.[DOI: 10.1109/ICCV.2011.6126294]
[9]  Liu P P, Zhao H W, Zang X B, et al. A fast local feature description algorithm[J]. Acta Automatica Sinica, 2010, 36(1): 40-45.[刘萍萍, 赵宏伟, 臧雪柏, 等. 一种快速局部特征描述算法[J].自动化学报, 2010, 36(1): 40-45.][DOI: 10.3724/SP.J.1004.2010.00040]
[10]  Tang Y H, Lu H Z, Hu M F. Local feature description algorithm based on laplacian[J]. Optics and Precision Engineering, 2011, 19(12): 2999-3006.[唐永鹤, 卢焕章, 胡谋法. 基于Laplacian的局部特征描述算法[J]. 光学精密工程, 2011, 19(12): 2999-3006.][DOI: 10.3788/OPE.20111912.2999]
[11]  Ge J, Cao W G, Zhou W, et al. A local feature descriptor under color affine transformation[J]. Jounal of Computer-Aided Design & Computer Graphics, 2013, 25(1): 26-33.[葛娟, 曹伟国, 周炜, 等. 一种颜色仿射变换下的局部特征描述子[J].计算机辅助设计与图形学学报, 2013, 25(1): 26-33.]
[12]  Calonder M, Lepetit V, Ozuysal M, et al. BRIEF: computing a local binary descriptor very fast[J]. IEEE Transactions on Patt-ern Analysis and Machine Intelligence, 2012, 34(7):1281-1298.[DOI: 10.1109/TPAMI.2011.222]
[13]  Lepetit V, Fua P. Keypoint recognition using randomized trees[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28 (9): 1465-1479.[DOI: 10.1109/TPAMI.2006.188]
[14]  Ozuysal M, Calonder M, Lepetit V, et al. Fast keypoint recognition using random ferns[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(3): 448-461.[DOI: 10.1109/TPAMI.2009.23]
[15]  Trzcinski T, Lepetit V. Efficient discriminative projections for compact binary descriptors[C]//Proceedings of the European Conference on Computer Vision. Florence, Italy: IEEE, 2012: 228-242.[DOI: 10.1007/978-3-642-33718-5_17]
[16]  Rublee E, Rabaud V, Konolidge K, et al. ORB: an efficient alternative to SIFT or SURF[C]//Proceedings of the International Conference on Computer Vision. Barcelona, Spain: IEEE, 2011: 2564-2571.[DOI: 10.1109/ICCV.2011.6126544]
[17]  Leutenegger S, Chli M, Siegwart R Y. BRISK: binary robust invariant scalable keypoints[C]//Proceedings of the International Conference on Computer Vision. Barcelona, Spain: IEEE, 2011: 2548-2555.[DOI: 10.1109/ICCV.2011.6126542]
[18]  Mair E, Hager G D, Burschka D, et al. Adaptive and generic corner detection based on the accelerated segment test[C]//Proceedings of the European Conference on Computer Vision. Heraklion, Crete, Greec: IEEE, 2010: 183-196.[DOI: 10.1007/978-3-642-15552-9_14]
[19]  Alahi A, Ortiz R, Vandergheynst P. FREAK: fast retina keypoint[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Rhode Island, Providence, USA: IEEE, 2012: 2069-2076.[DOI: 10.1109/CVPR.2012.6247715]
[20]  Trzcinski T, Christoudias M, Fua P, et al. boosting binary keypoint descriptors[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Portland, Oregon, USA: IEEE, 2013: 2874-2881.[DOI: 10.1109/CVPR.2013.370]

Full-Text

comments powered by Disqus

Contact Us

service@oalib.com

QQ:3279437679

微信:OALib Journal