Research on vision measurement error's compensation of spatial target system by double-theodolites

Double-Theodolites measuring equipments are widely employed on the studies of geometric variable measurement in the fields of binocular stereo vision. On the basis of geometrical relationship between three-dimension spatial target system and double-theodolites, the measurement models of observing angle and spatial coordinates together with distance are established according to the principles of the space rendezvous and docking technology. In fact, due to the trigonometric function's nonlinearities, observing angle readings of double-theodolites produce errors at certain position, the results of which leads to distance and coordinates' measuring system errors. The reasons of such errors are analyzed, and the idea is provided of taking errors as nonlinear components, building the Neural Network(NN) to simulate the mapping between observing angle and distance errors, and regarding the outputs of NN as the compensation term. Simulation curves imply the weights of NN intermediate layer influence the final compensation precision. In experiment, NN with optimized weights is applied in the processing of measured data, the results of which certificate that such idea and method may adaptively compensate system errors' influences.