Key Frame Extraction and Foreground Modelling Using K-Means Clustering

In this paper, we have proposed and implemented a novel robust key frame extraction and foreground isolation method using k-means clustering and mean squared error method for variable frame rate videos. We also isolated foreground objects in the video whilst eliminating the noise generated in the recording. The flickering of the frames caused as a result of variable frame rate in a recorded video is reduced by a considerable degree using this method. Also, the k-means clustering is performed on Apache's hadoop infrastructure to make the results of the computation faster. We have implemented this method and obtained results to be clear enough to extract meaningful detail from the frames. The results of the method have been compared to similar results obtained using well-known techniques such as the Gaussian Mixture Model and have been shown to be better.