An efficient star acquisition method based on SVM with mixtures of kernels

Star acquisition and star pattern recognition are the most time-consuming routines in star tracker operation. To speed up the star acquisition procedure, the innovative efficient star cluster grouping method is based on the mapped least squares support vector machine (LS-SVM) with mixtures of radial basis function and polynomial kernels. By convolving star image with the second order directional derivative operators deduced from the mapped LS-SVM, the maximum extremum points (the possible center of stars) on the two-dimensional star image intensity surface are reliably determined, and then the star cluster grouping process in star acquisition procedure is significantly speeded up. The mixtures of kernels provide more optimal performance than any single kernel. Computer experiments for the simulated star images are carried out. The results demonstrate that the proposed algorithm is efficient and robust over a wide range of sensor noise.