Method and apparatus for depth modelling and providing depth information of moving objects
作者： Harald Aagaard Martens , Jan Otto Reberg
DOI:
关键词: Artificial intelligence 、 Depth dimension 、 Score vector 、 Computer vision 、 Principal component analysis 、 Observer (special relativity) 、 Column vector 、 Mathematics 、 Quantitative assessment 、 Image sequence
摘要: A method and apparatus for indirect quantitative assessment or determination modelling of the depth dimension moving objects in signal streams where information is not directly available, but occlusion can be derived. For this estimating an image sequence consisting at least two frames comprises steps (1) selecting characterizing recognizable points, (2) examining each point frame whether it visible occluded, collecting data list such that corresponds to one row a column list, elements corresponding points are given large values occluded small values, (3) performing Principal Component Analysis on resulting vectors called score loading vectors, collection vector with value being factor, (4) outputting numerical element first factor as point, indicates close camera observer farther away.
lens.org 参考文章(5)
Thomas D. Wason, Method and apparatus for producing three dimensional displays on a two dimensional surface ,(1995)
Emilio Bizzi, Ferdinando A. Mussa-Ivaldi, Reza Dr. Shadmehr, System for human trajectory learning in virtual environments ,(1997)
Carlo Tomasi, Takeo Kanade, Shape and motion from image streams under orthography: a factorization method International Journal of Computer Vision. ,vol. 9, pp. 137- 154 ,(1992) , 10.1007/BF00129684
Richard Szeliski, James Coughlan, Spline-Based Image Registration International Journal of Computer Vision. ,vol. 22, pp. 199- 218 ,(1997) , 10.1023/A:1007996332012
Sergei Valentinovich Fogel, Method and apparatus for constructing intermediate images for a depth image from stereo images using velocity vector fields ,(1993)