Please wait a minute...
Front. Inform. Technol. Electron. Eng.  2012, Vol. 13 Issue (6): 428-439    DOI: 10.1631/jzus.C1100331
    
Convex relaxation for a 3D spatiotemporal segmentation model using the primal-dual method
Shi-yan Wang, Hui-min Yu
Department of Information Science & Electronic Engineering, Zhejiang University, Hangzhou 310027, China
Download:   PDF(0KB)
Export: BibTeX | EndNote (RIS)      

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.

Key words3D spatiotemporal segmentation      Motion estimation      Total variation      Primal-dual     
Received: 15 November 2011      Published: 05 June 2012
CLC:  TP391.7  
  TP317.4  
Cite this article:

Shi-yan Wang, Hui-min Yu. Convex relaxation for a 3D spatiotemporal segmentation model using the primal-dual method. Front. Inform. Technol. Electron. Eng., 2012, 13(6): 428-439.

URL:

http://www.zjujournals.com/xueshu/fitee/10.1631/jzus.C1100331     OR     http://www.zjujournals.com/xueshu/fitee/Y2012/V13/I6/428


Convex relaxation for a 3D spatiotemporal segmentation model using the primal-dual method

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.

关键词: 3D spatiotemporal segmentation,  Motion estimation,  Total variation,  Primal-dual 
[1] Yan-hong Liu, Juan Cao, Zhong-gui Chen, Xiao-ming Zeng. Ray-triangular Bézier patch intersection using hybrid clipping algorith[J]. Front. Inform. Technol. Electron. Eng., 2016, 17(10): 1018-1030.
[2] Hao XIE,Ruo-feng TONG. Image meshing via hierarchical optimization[J]. Front. Inform. Technol. Electron. Eng., 2016, 17(1): 32-40.
[3] Xiao Liu, Jia-min Liu, An-xi Cao, Zhuang-le Yao. HAPE3D—a new constructive algorithm for the 3D irregular packing problem[J]. Front. Inform. Technol. Electron. Eng., 2015, 16(5): 380-390.
[4] Divya Udayan J, HyungSeok Kim, Jee-In Kim. An image-based approach to the reconstruction of ancient architectures by extracting and arranging 3D spatial components[J]. Front. Inform. Technol. Electron. Eng., 2015, 16(1): 12-27.
[5] Xiao-juan Duan, Guo-zhao Wang. Degree elevation of unified and extended spline curves[J]. Front. Inform. Technol. Electron. Eng., 2014, 15(12): 1098-1105.
[6] Yong-wei Miao, Fei-xia Hu, Min-yan Chen, Zhen Liu, Hua-hao Shou. Visual salience guided feature-aware shape simplification[J]. Front. Inform. Technol. Electron. Eng., 2014, 15(9): 744-753.
[7] Fei-wei Qin, Lu-ye Li, Shu-ming Gao, Xiao-ling Yang, Xiang Chen. A deep learning approach to the classification of 3D CAD models[J]. Front. Inform. Technol. Electron. Eng., 2014, 15(2): 91-106.
[8] Lie-fu Ai, Jun-qing Yu, Yun-feng He, Tao Guan. High-dimensional indexing technologies for large scale content-based image retrieval: a review[J]. Front. Inform. Technol. Electron. Eng., 2013, 14(7): 505-520.
[9] Xiao-hong Tan, Rui-min Shen, Yan Wang. Personalized course generation and evolution based on genetic algorithms[J]. Front. Inform. Technol. Electron. Eng., 2012, 13(12): 909-917.
[10] Juan Cao, Guo-zhao Wang. Non-uniform B-spline curves with multiple shape parameters[J]. Front. Inform. Technol. Electron. Eng., 2011, 12(10): 800-808.
[11] Yu-lei Geng, Jin Wang, Guo-dong Lu, Zheng Liu, Gang Chen. Sketch based garment modeling on an arbitrary view of a 3D virtual human model[J]. Front. Inform. Technol. Electron. Eng., 2011, 12(3): 195-203.
[12] Chun-luan Zhou, Jun Xiao. Cartoon capture by key-frame based contour tracking[J]. Front. Inform. Technol. Electron. Eng., 2011, 12(1): 36-43.
[13] Jia Li, Han-nan Yu, Yong-hong Tian, Tie-jun Huang, Wen Gao. Salient object extraction for user-targeted video content association[J]. Front. Inform. Technol. Electron. Eng., 2010, 11(11): 850-859.
[14] Wan-qiang Shen, Guo-zhao Wang. Triangular domain extension of linear Bernstein-like trigonometric polynomial basis[J]. Front. Inform. Technol. Electron. Eng., 2010, 11(5): 356-364.
[15] Qian-qian Hu, Guo-jin Wang. Representing conics by low degree rational DP curves[J]. Front. Inform. Technol. Electron. Eng., 2010, 11(4): 278-289.