Joint geometric and photometric direct image registration based on Lie algebra parameterization

Chenxi Li, Zelin Shi, Yunpeng Liu
2016 Infrared Technology and Applications, and Robot Sensing and Advanced Control  
In this paper, we consider direct image registration problem which estimate the geometric and photometric transformations between two images. The efficient second-order minimization method (ESM) is based on a second-order Taylor series of image differences without computing the Hessian under brightness constancy assumption. This can be done due to the fact that the considered geometric transformations is Lie group and can be parameterized by its Lie algebra. In order to deal with lighting
more » ... s, we extend ESM to the compositional dual efficient second-order minimization method (CDESM). In our approach, the photometric transformations is parameterized by its Lie algebra with compositional operation, which is similar to that of geometric transformations. Our algorithm can give a second-order approximation of image differences with respect to geometric and photometric parameters. The geometric and photometric parameters are simultaneously obtained by non-linear least-square optimization. Our algorithm preserves the advantages of the original ESM method which has high convergence rate and large capture radius. Experimental results show that our algorithm is more robust to lighting changes and has higher registration accuracy compared to previous algorithms. Downloaded From: http://proceedings.spiedigitallibrary.org/ on 12/06/2016 Terms of Use: http://spiedigitallibrary.org/ss/termsofuse.aspx    zH z0 J 0 d z J J J 0 , and * ( ) ( ) ( ) w zH zx J x d z J J J x     . J is the image gradient of , w J is the Jacobian due to a pixel warping function, () w      H J 0 J x x J J J J 0 x . Let * ( ) ( ) esm w    H J J J J J 0 , then the problem (5) can be approximated as () min esm x d 0 0 J J J 0 J J J
doi:10.1117/12.2246720 fatcat:wpmojq3rqncwvnucht6i2byope