A parallel computing framework for real-time moving object detection on high resolution videos

Graphic Processing Units (GPUs) are becoming very important in the present day. Their high computational capabilities with high speed and accuracy are making them a very strong force in communication engineering. In recent times, their need has increased tremendously due to the increasing range of applications. Video surveillance is an important field where very heavy computations are needed to be done on videos to perfectly detect the motion of an object in suspicious situations. The various analyses on video can be used to extract information and process data to generate actionable intelligent conclusions. However, CPUs fail to deliver real time results when it comes to high-resolution videos from a large number of cameras simultaneously. Thankfully, there is a lot of graphic hardware available nowadays, which comprises powerful hardware processors often intended to process data in parallel and so greatly accelerates the processes being done on them. An accelerated algorithm is required for processing petabytes of data from security cameras and video surveillance satellites and that in real time. In this paper, we propose a method of using GPUs in detecting the motion of an object at different junctions in video surveillance. The results show a great gain in performance when the proposed method runs on GPUs and CPUs in terms of speed as well as accuracy. The new parallel processing approaches are developed on each phase of the algorithm to enhance the efficiency of the system. Proposed algorithm achieved an average speed up of 50.094x for lower resolution video frames (320 × 240,720 × 480,1024 × 768) and 38.012x for higher resolution video frames (1360 × 768,1920 × 1080) on GPU, which is superior to CPU processing.