The determination of orientation information of a 3D object is a crucial step in hypothesis-verification approach to object recognition. In this paper. two approaches are presented to estimate the orientation parameters of a 3D object from a single image. The first one is based on camera model estimation and analysis. The second one is a hierarchical search method. Simulation experiments are conducted to evaluate the performance of the estimations.
Lin, W. C., Fu, K. S., & Sederberg, T. (1984). Estimation of Three-Dimensional Object Orientation for Computer Vision Systems with Feedback. Journal of Robotic Systems, 1, 59-82. https://doi.org/10.1002/rob.4620010105