hoku | repository holds research toward analysis of lost-in-space | Machine Learning library

hoku is a C++ library typically used in Artificial Intelligence, Machine Learning, Deep Learning, Example Codes applications. hoku has no bugs, it has no vulnerabilities and it has low support. You can download it from GitHub.

Ancient mariners could look up the night sky, point out what stars they were looking at, and navigate across the globe with precision. Star identification algorithm refers to a computational approach to pointing out which stars are in the sky. Given an image of the sky, star identification is matching the bright spots in an image, to stars in an astronomical catalog. The device that performs these computations is the star tracker, much like the navigators on the ship. Lost-in-space refers to an additional constraint on the problem: the absence of knowing where we took the picture and how we pointed the camera. This repository holds research toward the analysis of various lost-in-space star identification procedures for spacecraft. This includes a study of feature uniqueness, permutation order, candidate reduction, and identification under the introduction of various noise. The process of identifying blobs in an image, constructing the image coordinate system, and efficiently querying static databases is not addressed here, but there does exist some rudimentary programs to execute the attitude determination process end-to-end.