A BodyMap matrix for a pose includes elements representing Euclidean distances between markers on the object. The BodyMap matrix can be normalized and visualized using a grayscale or mesh image, enabling a user to easily interpret the pose. The pose is characterized in a low-dimensional space by determining the singular values of the BodyMap matrix for the pose and using a small set of dominant singular values to characterize and visually represent the pose. A candidate pose is classified in a low-dimensional space by comparing the characterization of the candidate pose to characterizations of known poses and determining which known pose is most similar to the candidate pose. Determining the similarity of the candidate pose to the known poses is accomplished through distance calculations, including the calculation of Mahalanobis distances from the characterization of the candidate pose to characterizations of known poses and their noisy variations.