Extracting Key Frames for Surveillance Video Based on Color Spatial Distribution Histograms

This paper proposes a new key frame extraction method by using color spatial distribution histograms. Pixels in the same color are contiguous or non-contiguous to each other in an image, which is a noticeable spatial character. With this property, the pixels are classified as contiguous and non-contiguous ones. Therefore, refined histograms distinguish the small changes better than the original histograms between frames, and it allows fine distinctions that are similar to original histograms. With the evaluation of our experiments, this approach extract key frames more efficiently and accurately.