In order to safely navigate traffic, automated vehicles need to face a variety of challenges such as the uncertainty of typical road environments. A key component of road traffic, that both illustrates such uncertainty and highly influences traffic participants behavior, is parked cars. For instance, mistakenly considering a car as parked directly increases the collision risk and, on the other hand, expecting parked cars to move leads to over-precautions, inefficient, and potentially confusing planned trajectories. Despite being a major component of traffic prediction, little work addresses the parked car detection, and to our knowledge none in the context of autonomous driving. This paper introduces the problem of parked car classification and illustrates some of its challenges and corner cases. For generality, we focus on sensor-set independent classification and in particular we ignore vehicle light information which further increases the difficulty of the problem. Our contribution includes introducing, discussing, and comparing a list of features as candidate predictors of parked car classification. More precisely, we collect and annotate 180,469 vehicle occurrences over a duration of approximately 21 minutes; we then compare the classification accuracy of a list of features over a few classification methods. Based on sensor set independent detections and map information, we achieve an accuracy of 92.9% on our test-set and discuss how this can likely be improved.