Abstract
A method based on 3D videos is proposed for multi-target segmentation and tracking with a moving viewing system. A spatiotemporal energy functional is built up to perform motion segmentation and estimation simultaneously. To overcome the limitation of the local minimum problem with the level set method, a convex relaxation method is applied to the 3D spatiotemporal segmentation model. The relaxed convex model is independent of the initial condition. A primal-dual algorithm is used to improve computational efficiency. Several indoor experiments show the validity of the proposed method.
Similar content being viewed by others
References
Alvarez, L., Castano, C.A., Garcia, M., Krissian, K., Mazorra, L., Salgado, A., Sanchez, J., 2009. A new energy-based method for 3D motion estimation of incompressible PIV flows. Comput. Vis. Image Understand., 113(7):802–810. [doi:10.1016/j.cviu.2009.01.005]
Boykov, Y., Funka-Lea, G., 2006. Graph cuts and efficient N-D image segmentation. Int. J. Comput. Vis., 70(2):109–131. [doi:10.1007/s11263-006-7934-5]
Boykov, Y., Kolmogorov, V., 2004. An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. IEEE Trans. Pattern Anal. Mach. Intell., 26(9):1124–1137. [doi:10.1109/TPAMI.2004.60]
Bresson, X., Esedoglu, S., Vandergheynst, P., Thiran, J., Osher, S., 2007. Fast global minimization of the active contour/snake model. J. Math. Imag. Vis., 28(2):151–167. [doi:10.1007/s10851-007-0002-0]
Caselles, V., Kimmell, R., Sapiro, G., 1997. Geodesic active contours. Int. J. Comput. Vis., 22(1):61–79. [doi:10.1023/A:1007979827043]
Chambolle, A., 2004. An algorithm for total variation minimization and applications. J. Math. Imag. Vis., 20(1–2): 89–97. [doi:10.1023/B:JMIV.0000011325.36760.1e]
Chan, T.F., Vese, L.A., 2001. Active contours without edges. IEEE Trans. Image Process., 10(2):266–277. [doi:10.1109/83.902291]
Chan, T.F., Golub, G.H., Mulet, P., 1999. A nonlinear primal-dual method for total variation-based image restoration. SIAM J. Sci. Comput., 20(6):1964–1977. [doi:10.1137/S1064827596299767]
Chan, T.F., Esedoglu, S., Nikolova, M., 2004. Algorithms for finding global minimizers of image segmentation and denoising models. SIAM J. Appl. Math., 66:1632–1648. [doi:10.1137/040615286]
Dufaux, F., Moccagatta, I., Moscheni, F., Nicolas, H., 1994. Vector quantization-based motion field segmentation under the entropy criterion. J. Vis. Commun. Image Represent., 5:356–369. [doi:10.1006/jvci.1994.1034]
Feghali, R., Mitiche, A., 2004. Spatiotemporal motion boundary detection and motion boundary velocity estimation for tracking moving objects with a moving camera: a level sets PDEs approach with concurrent camera motion compensation. IEEE Trans. Image Process., 13(11): 1473–1490. [doi:10.1109/TIP.2004.836158]
Goldstein, T., Bresson, X., Osher, S., 2009. Geometric applications of the split Bregman method: segmentation and surface reconstruction. J. Sci. Comput., 45(1–3):272–293. [doi:10.1007/s10915-009-9331-z]
Heeger, D.J., Jepson, A.D., 1992. Subspace methods for recovering rigid motion I: algorithm and implementation. Int. J. Comput. Vis., 7(2):95–117. [doi:10.1007/BF00128130]
Horn, B.K.P., Schunck, B.G., 1981. Determining optical flow. Artif. Intell., 17(1–3):185–203. [doi:10.1016/0004-3702(81)90024-2]
Jonasson, L., Bresson, X., Hagmann, P., Cuisenaire, O., Meuli, R., Thiran, J.P., 2005. White matter fiber tract segmentation in DT-MRI using geometric flows. Med. Image Anal., 9(3):223–236. [doi:10.1016/j.media.2004.07.004]
Kass, M., Witkin, A., Terzopoulos, D., 1988. Snakes: active contour models. Int. J. Comput. Vis., 1(4):321–331. [doi:10.1007/BF00133570]
Leventon, M.E., Grimson, W.E.L., Faugeras, O., 2000. Statistical Shape Influence in Geodesic Active Contours. IEEE Conf. on Computer Vision and Pattern Recognition, 1:316–323. [doi:10.1109/CVPR.2000.855835]
Longuet-Higgins, H.C., Prazdny, K., 1980. The interpretation of a moving retinal image. Proc. R. Soc. Lond. B, 208(1173):385–397. [doi:10.1098/rspb.1980.0057]
Malladi, R., Kimmel, R., Adalsteinsson, D., Sapiro, G., Caselles, V., Sethian, J.A., 1996. A Geometric Approach to Segmentation and Analysis of 3D Medical Images. Proc. Workshop on Mathematical Methods in Biomedical Image Analysis, p.244–252. [doi:10.1109/MMBIA.1996.534076]
Merriman, B., Bence, J.K., Osher, S.J., 1994. Motion of multiple junctions: a level set approach. J. Comput. Phys., 112(2):334–363. [doi:10.1006/jcph.1994.1105]
Mémin, E., Pérez, P., 2002. Hierarchical estimation and segmentation of dense motion fields. Int. J. Comput. Vis., 46(2):129–155. [doi:10.1023/A:1013539930159]
Mumford, D., Shah, J., 1989. Optimal approximations of piecewise smooth functions and associated variational problems. Commun. Pure Appl. Math., 42(5):577–685. [doi:10.1002/cpa.3160420503]
Ohno, K., Nomura, T., Tadokoro, S., 2006. Real-Time Robot Trajectory Estimation and 3D Map Construction Using 3D Camera. IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, p.5279–5285. [doi:10.1109/IROS.2006.282027]
Osher, S., Sethian, J., 1988. Fronts propagating with curvature dependent speed: algorithms based on the Hamilton-Jacobi formulation. J. Comput. Phys., 79(1):12–49. [doi:10.1016/0021-9991(88)90002-2]
Paragios, N., Deriche, R., 2005. Geodesic active regions and level set methods for motion estimation and tracking. Comput. Vis. Image Understand., 97(3):259–282. [doi:10.1016/j.cviu.2003.04.001]
Rudin, L.I., Osher, S., Fatemi, E., 1992. Nonlinear total variation based noise removal algorithms. Phys. D, 60(1–4): 259–268. [doi:10.1016/0167-2789(92)90242-F]
Schnorr, C., 1991. Determining optical flow for irregular domains by minimizing quadratic functionals of a certain class. Int. J. Comput. Vis., 6(1):25–38. [doi:10.1007/BF00127124]
Wang, S., Yu, H., 2011. A Variational Approach for Ego-motion Estimation and Segmentation Based on 3D TOF Camera. 4th Int. Congress on Image and Signal Processing, p.1160–1164. [doi:10.1109/CISP.2011.6100402]
Ye, C., Hegde, G.P.M., 2009. Robust Edge Extraction for SwissRange SR-3000 Range Image. Proc. IEEE Int. Conf. on Robotics and Automation, p.2437–2442. [doi:10.1109/ROBOT.2009.5152559]
Author information
Authors and Affiliations
Corresponding author
Additional information
Project supported by the National Natural Science Foundation of China (No. 60872069) and the National Basic Research Program (973) of China (No. 2012CB316400)
Rights and permissions
About this article
Cite this article
Wang, Sy., Yu, Hm. Convex relaxation for a 3D spatiotemporal segmentation model using the primal-dual method. J. Zhejiang Univ. - Sci. C 13, 428–439 (2012). https://doi.org/10.1631/jzus.C1100331
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1631/jzus.C1100331