Object counting in a single surveillance image

Our objective is to count objects using a single frame from a surveillance camera. We focus on the area where individual object detectors fail, mostly due to clutter, occlusion, or variations in scene due to perspective change. For tackling the counting problem, first the object density is estimated by using ridge regression. Object counts are then estimated by integrating the density over the region of interest along with the use of one hot feature encoding and image perspective correction. Performance of the proposed method is shown in a typical counting applications such as people counting in a crowd and vehicle counting at the traffic signal.