We present a new compressed representation of free trajectories of moving
objects. It combines a partial-sums-based structure that retrieves in constant
time the position of the object at any instant, with a hierarchical
minimum-bounding-boxes representation that allows determining if the object is
seen in a certain rectangular area during a time period. Combined with spatial
snapshots at regular intervals, the representation is shown to outperform
classical ones by orders of magnitude in space, and also to outperform previous
compressed representations in time performance, when using the same amount of
space.