SOO-CHANG PEILiou, Lin-GwoLin-GwoLiou2009-03-042018-07-062009-03-042018-07-06199800313203http://ntur.lib.ntu.edu.tw//handle/246246/142448https://www.scopus.com/inward/record.uri?eid=2-s2.0-0032021248&doi=10.1016%2fs0031-3203%2897%2900044-7&partnerID=40&md5=55715656786f9a36831cecd84a09d3a5Three-dimensional (3D) motion estimation is a very important topic in machine vision. However, reliability of the estimated 3D motion seems to be the most challenging problem, especially to the linear algorithms developed for solving a general 3D motion problem (six degrees of freedom). In real applications such as the traffic surveillance and auto-vehicle systems, the observed 3D motion has only three degrees of freedom because of the ground plane constraint (GPC). In this paper, a new iterative method is proposed for solving the above problem. Our method has several advantages: (1) It can handle both the point and line features as its input image data. (2) It is very suitable for parallel processing. (3) Its cost function is so well-conditioned that the final 3D motion estimation is robust and insensitive to noise, which is proved by experiments. (4) It can handle the case of missing data to a certain degree. The above benefits make our method suitable for a real application. Experiments including simulated and real-world images show satisfactory results. © 1997 Pattern Recognition Society. Published by Elsevier Science Ltd.application/pdf956187 bytesapplication/pdfen-USGround plane constraint; Image lines; Image points; Traffic surveillance systemAlgorithms; Computer vision; Constraint theory; Degrees of freedom (mechanics); Image analysis; Iterative methods; Parallel processing systems; Problem solving; Three dimensional; Ground plane constraint; Image point; Line features; Motion estimation; Traffic surveillance system; Feature extractionjournal article10.1016/s0031-3203(97)00044-72-s2.0-0032021248http://ntur.lib.ntu.edu.tw/bitstream/246246/142448/1/38.pdf