An attentive vision system is proposed that estimates traffic motion parameters from MPEG-2 compressed video recorded using an un-calibrated camera mounted on a pantilt unit. Compressed domain information from a stream of MPEG-2 video is used to estimate a traffic motion field and infer the 2D frame location of the traffic lanes. With these visual cues attentive visual servoing automatically adjusts camera pose so as to improve the motion parameter estimation process. An existing technique to acquire motion parameters from an un-calibrated camera is used after obtaining an optimal camera pose. This system provides a computationally inexpensive alternative to existing Intelligent Transport Systems for surveillance.