In this paper, an automated methodology that builds a profile for each pedestrian tracked based on its appearance, its occlusion status and the semantic information related to its position, is presented. The extracted profiles are utilized to perform context-aware tracking in multi-target tracking scenarios. A novel fusion scheme that combines the output of multiple trackers, exploiting context-related information cues is proposed. A set of decision rules is created that implicitly integrates occlusion reasoning capabilities in multi-target scenarios. Key aspects of the fusion process presented are (a) a common, context-aware methodology to assess the confidence of each tracker’s output and (b) a correlation scheme that evaluates the consistency of the trackers’ output. The confidence and consistency metrics extracted are used to produce weights for the fusion of the available trackers.