Progressive match expansion via coherent subspace constraint

Information Sciences

Volumn 367-368, Issue , 2016, Pages 848-861

  Sun, Kun ^a,b   Liu, Liman ^a   Tao, Wenbing ^a,b  

^a SOUTH CENTRAL UNIVERSITY FOR NATIONALITIES   (China)

^b HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY   (China)

Author keywords

3D Reconstruction; Image matching; Quasi dense

Indexed keywords

ALGORITHMS; GEOMETRY; IMAGE PROCESSING; IMAGE RECONSTRUCTION; ITERATIVE METHODS; THREE DIMENSIONAL COMPUTER GRAPHICS;

3D RECONSTRUCTION; FEATURE SIMILARITIES; NON-RIGID TRANSFORMATION; NON-SMOOTH SURFACE; QUASI-DENSE; QUASI-DENSE MATCHING; SIFT DESCRIPTORS; SUBSPACE CONSTRAINT;

IMAGE MATCHING;

EID: 84978429673     PISSN: 00200255     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.ins.2016.07.020     Document Type: Article

References (58)

1. [1] Agarwal, S., Snavely, N., Simon, I., Seitz, S., Szeliski, R., Building rome in a day. Computer Vision, 2009 IEEE 12th International Conference on, 2009, 72–79, 10.1109/ICCV.2009.5459148.
2. [2] Ali, M.N., Abdullah-Al-Wadud, M., Lee, S.-L., Multiple object tracking with partial occlusion handling using salient feature points. Inf. Sci. 278 (2014), 448–465 http://dx.doi.org/10.1016/j.ins.2014.03.064.
3. [3] Barnes, C., Shechtman, E., Finkelstein, A., Goldman, D.B., Patchmatch: A randomized correspondence algorithm for structural image editing. ACM Trans. Graph. 28:3 (2009), 24:1–24:11, 10.1145/1531326.1531330.
4. [4] Belkin, M., Niyogi, P., Laplacian eigenmaps for dimensionality reduction and data representation. Neural Comput. 15:6 (2003), 1373–1396.
5. [5] Chen, L., Gao, Y., Xing, Z., Jensen, C.S., Chen, G., I2rs: A distributed geo-textual image retrieval and recommendation system. Proc. VLDB Endow. 8:12 (2015), 1884–1887, 10.14778/2824032.2824092.
6. [6] Cho, M., Shin, Y., Lee, K., Co-recognition of image pairs by data-driven monte carlo image exploration. Forsyth, D., Torr, P., Zisserman, A., (eds.) ECCV 2008 Lecture Notes in Computer Science, volume 5305, 2008, Springer Berlin Heidelberg, 144–157, 10.1007/978-3-540-88693-8_11.
7. [7] Cho, M., Shin, Y.M., Lee, K.-M., Unsupervised detection and segmentation of identical objects. Computer Vision and Pattern Recognition, IEEE Conference on, 2010, 1617–1624.
8. [8] Crandall, D., Owens, A., Snavely, N., Huttenlocher, D., Sfm with mrfs: Discrete-continuous optimization for large-scale structure from motion. Pattern Anal. Mach. Intell. IEEE Trans. 35:12 (2013), 2841–2853, 10.1109/TPAMI.2012.218.
9. [9] Cui, C., Ngan, K.N., Global propagation of affine invariant features for robust matching. Image Process. IEEE Trans. 22:7 (2013), 2876–2888, 10.1109/TIP.2013.2246521.
10. [10] Furukawa, Y., Curless, B., Seitz, S., Szeliski, R., Towards internet-scale multi-view stereo. Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on, 2010, 1434–1441, 10.1109/CVPR.2010.5539802.
11. [11] Furukawa, Y., Ponce, J., Accurate, dense, and robust multiview stereopsis. Pattern Anal. Mach. Intell. IEEE Trans. 32:8 (2010), 1362–1376, 10.1109/TPAMI.2009.161.
12. [12] Gherardi, R., Farenzena, M., Fusiello, A., Improving the efficiency of hierarchical structure-and-motion. Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on, 2010, 1594–1600, 10.1109/CVPR.2010.5539782.
13. [13] Gong, M., Wu, Y., Cai, Q., Ma, W., Qin, A., Wang, Z., Jiao, L., Discrete particle swarm optimization for high-order graph matching. Inf. Sci. 328 (2016), 158–171 http://dx.doi.org/10.1016/j.ins.2015.08.038.
14. [14] Hamid, R., Decoste, D., Lin, C.J., Dense non-rigid point-matching using random projections. Computer Vision and Pattern Recognition, IEEE Conference on, 2013, 2914–2921, 10.1109/CVPR.2013.375.
15. [15] Han, Y., Yang, Y., Wu, F., Hong, R., Compact and discriminative descriptor inference using multi-cues. Image Process. IEEE Trans. 24:12 (2015), 5114–5126, 10.1109/TIP.2015.2479917.
16. [16] Han, Y., Yang, Y., Yan, Y., Ma, Z., Sebe, N., Zhou, X., Semisupervised feature selection via spline regression for video semantic recognition. Neural Netw. Learn. Syst. IEEE Trans. 26:2 (2015), 252–264, 10.1109/TNNLS.2014.2314123.
17. [17] He, J., Gu, H., Wang, Z., Multi-instance multi-label learning based on gaussian process with application to visual mobile robot navigation. Inf. Sci. 190 (2012), 162–177 http://dx.doi.org/10.1016/j.ins.2011.12.015.
18. [18] Heinly, J., Dunn, E., Frahm, J.M., Comparative evaluation of binary features. Proc. European Conf. Computer Vision, 2012, 759–773.
19. [19] Hong, C., Zhu, J., Song, M., Wang, Y., Realtime object matching with robust dominant orientation templates. Pattern Recognition (ICPR), 2012 21st International Conference on, 2012, 1152–1155.
20. [20] Hu, Y.-T., Lin, Y.-Y., Chen, H.-Y., Hsu, K.-J., Chen, B.-Y., Matching images with multiple descriptors: An unsupervised approach for locally adaptive descriptor selection. Image Process. IEEE Trans. 24:12 (2015), 5995–6010, 10.1109/TIP.2015.2496305.
21. [21] Jiang, Y., Sun, C., Tan, X., Yang, L., Orientation-guided geodesic weighting for patchmatch-based stereo matching. Inf. Sci. 334–335 (2016), 293–306 http://dx.doi.org/10.1016/j.ins.2015.11.041.
22. [22] Kang, U., Hebert, M., Park, S., Fast and scalable approximate spectral graph matching for correspondence problems. Inf. Sci. 220 (2013), 306–318 Online Fuzzy Machine Learning and Data Mining. http://dx.doi.org/10.1016/j.ins.2012.07.008.
23. [23] Kannala, J., Brandt, S., Quasi-dense wide baseline matching using match propagation. Computer Vision and Pattern Recognition, IEEE Conference on, 2007, 1–8.
24. [24] Kannala, J., Rahtu, E., Brandt, S., Heikkila, J., Object recognition and segmentation by non-rigid quasi-dense matching. Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on, 2008, 1–8, 10.1109/CVPR.2008.4587472.
25. [25] Kim, B., Yoo, H., Sohn, K., Exact order based feature descriptor for illumination robust image matching. Pattern Recognit. 46:12 (2013), 3268–3278 http://dx.doi.org/10.1016/j.patcog.2013.04.015.
26. [26] Kim, D.Y., Jeon, M., Data fusion of radar and image measurements for multi-object tracking via kalman filtering. Inf. Sci. 278 (2014), 641–652 http://dx.doi.org/10.1016/j.ins.2014.03.080.
27. [27] Kim, J., Liu, C., Sha, F., Grauman, K., Deformable spatial pyramid matching for fast dense correspondences. Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on, 2013, 2307–2314, 10.1109/CVPR.2013.299.
28. [28] Lhuillier, M., Quan, L., Match propagation for image-based modeling and rendering. Pattern Anal. Mach. Intell. IEEE Trans. 24:8 (2002), 1140–1146, 10.1109/TPAMI.2002.1023810.
29. [29] Lhuillier, M., Quan, L., A quasi-dense approach to surface reconstruction from uncalibrated images. Pattern Anal. Mach. Intell. IEEE Trans. 27:3 (2005), 418–433, 10.1109/TPAMI.2005.44.
30. [30] Li, X., Hu, Z., Rejecting mismatches by correspondence function. Int. J. Comput. Vis. 89:1 (2010), 1–17, 10.1007/s11263-010-0318-x.
31. [31] Li, Y., Liu, W., Li, X., Huang, Q., Li, X., Ga-sift: A new scale invariant feature transform for multispectral image using geometric algebra. Inf. Sci. 281 (2014), 559–572 Multimedia Modeling. http://dx.doi.org/10.1016/j.ins.2013.12.022.
32. [32] Liu, C., Yuen, J., Torralba, A., Sift flow: Dense correspondence across scenes and its applications. Pattern Anal. Mach. Intell. IEEE Trans. 33:5 (2011), 978–994, 10.1109/TPAMI.2010.147.
33. [33] Liu, H., Sun, F., Efficient visual tracking using particle filter with incremental likelihood calculation. Inf. Sci. 195 (2012), 141–153 http://dx.doi.org/10.1016/j.ins.2012.01.033.
34. [34] Lowe, D., Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60:2 (2004), 91–110.
35. [35] Mikolajczyk, K., Schmid, C., A performance evaluation of local descriptors. Pattern Anal. Mach. Intell. IEEE Trans. 27:10 (2005), 1615–1630, 10.1109/TPAMI.2005.188.
36. [36] Mozerov, M.G., van de Weijer, J., Accurate stereo matching by two-step energy minimization. IEEE Trans. Image Process. 24:3 (2015), 1153–1163.
37. [37] Myronenko, A., Song, X., Point set registration: Coherent point drift. Pattern Anal. Mach. Intell. IEEE Trans. 32:12 (2010), 2262–2275, 10.1109/TPAMI.2010.46.
38. [38] Pizarro, D., Bartoli, A., Feature-based deformable surface detection with self-occlusion reasoning. Int. J. Comput. Vis. 97:1 (2012), 54–70.
39. [39] Shi, C., Wang, G., Yin, X., Pei, X., He, B., Lin, X., High-accuracy stereo matching based on adaptive ground control points. IEEE Trans. Image Process. 24:4 (2015), 1412–1423.
40. [40] Sinha, S., Scharstein, D., Szeliski, R., Efficient high-resolution stereo matching using local plane sweeps. Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on, 2014, 1582–1589, 10.1109/CVPR.2014.205.
41. [41] Snavely, N., Seitz, S., Szeliski, R., Modeling the world from internet photo collections. Int. J. Comput. Vis. 80:2 (2008), 189–210, 10.1007/s11263-007-0107-3.
42. [42] Steele, K., Egbert, P., Correspondence expansion for wide baseline stereo. Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, volume 1, 2005, 1055–1062 vol.1, 10.1109/CVPR.2005.113.
43. [43] Strecha, C., von Hansen, W., Van Gool, L., Fua, P., Thoennessen, U., On benchmarking camera calibration and multi-view stereo for high resolution imagery. Computer Vision and Pattern Recognition, 2008, IEEE Conference on., 2008, 1–8, 10.1109/CVPR.2008.4587706.
44. [44] Sun, K., Li, P., Tao, W., Tang, Y., Feature guided biased gaussian mixture model for image matching. Inf. Sci. 295 (2015), 323–336 http://dx.doi.org/10.1016/j.ins.2014.10.029.
45. [45] Tang, J., Shao, L., Zhen, X., Robust point pattern matching based on spectral context. Pattern Recognit. 47:3 (2014), 1469–1484 Handwriting Recognition and other {PR} Applications. http://dx.doi.org/10.1016/j.patcog.2013.09.017.
46. [46] Taniai, T., Matsushita, Y., Naemura, T., Graph cut based continuous stereo matching using locally shared labels. Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on, 2014, 1613–1620, 10.1109/CVPR.2014.209.
47. [47] Torki, M., Elgammal, A., One-shot multi-set non-rigid feature-spatial matching. Computer Vision and Pattern Recognition, IEEE Conference on, 2010, 3058–3065, 10.1109/CVPR.2010.5540059.
48. [48] Torki, M., Elgammal, A., Putting local features on a manifold. Computer Vision and Pattern Recognition, IEEE Conference on, 2010, 1743–1750, 10.1109/CVPR.2010.5539843.
49. [49] Tran, Q.H., Chin, T.J., Carneiro, G., Brown, M., Suter, D., In defence of ransac for outlier rejection in deformable registration. Proceeding of the European Conference on Computer Vision, 2012, 274–287.
50. [50] Tuytelaars, T., Van Gool, L., Matching widely separated views based on affine invariant regions. Int. J. Comput. Vis. 59:1 (2004), 61–85, 10.1023/B:VISI.0000020671.28016.e8.
51. [51] Valiente, D., Gil, A., Fernández, L., Reinoso, Ó., A modified stochastic gradient descent algorithm for view-based {SLAM} using omnidirectional images. Inf. Sci. 279 (2014), 326–337 http://dx.doi.org/10.1016/j.ins.2014.03.122.
52. [52] A. Vedaldi, B. Fulkerson, VLFeat: An open and portable library of computer vision algorithms, 2008, (http://www.vlfeat.org/).
53. [53] Viejo, D., Garcia-Rodriguez, J., Cazorla, M., Combining visual features and growing neural gas networks for robotic 3D {SLAM}. Inf. Sci. 276 (2014), 174–185 http://dx.doi.org/10.1016/j.ins.2014.02.053.
54. [54] Yang, D., Liu, Z., Sun, F., Zhang, J., Liu, H., Wang, S., Recursive depth parametrization of monocular visual navigation: Observability analysis and performance evaluation. Inf. Sci. 287 (2014), 38–49 http://dx.doi.org/10.1016/j.ins.2014.07.025.
55. [55] Yang, Q., Stereo matching using tree filtering. IEEE Trans. Pattern Anal. Mach. Intell. 37:4 (2015), 834–846.
56. [56] Yu, J., Bian, W., Song, M., Cheng, J., Tao, D., Graph based transductive learning for cartoon correspondence construction. Neurocomputing 79 (2012), 105–114 http://dx.doi.org/10.1016/j.neucom.2011.10.003.
57. [57] Yu, W., Yang, K., Bai, Y., Yao, H., Rui, Y., Dnn flow: Dnn feature pyramid based image matching. Proceedings of the British Machine Vision Conference, 2014, BMVA Press.
58. [58] Zhao, J., Ma, J., Tian, J., Ma, J., Zhang, D., A robust method for vector field learning with application to mismatch removing. Computer Vision and Pattern Recognition, IEEE Conference on, 2011, 2977–2984.