VGRAPH: An Effective Approach for Generating Static Video Summaries

A video summary is a sequence of still pictures that represent the content of a video in such a way that the respective target group is rapidly provided with concise information about the content, while the essential message of the original video is preserved. In this paper, we present VGRAPH, a simple yet effective video summarization approach that utilizes both color and texture features. This approach is based on partitioning the video into shots by utilizing the color features, and extracting video key frames using a nearest neighbor graph built from the texture features of the shots representative frames. Also, this paper introduces and illustrates an enhanced evaluation method based on color and texture matching. Video summaries generated by VGRAPH are compared with summaries generated by others found in the literature and the ground truth summaries. Experimental results indicate that the video summaries generated by VGRAPH have a higher quality than others.

[1]  Radomir S. Stankovic,et al.  The Haar wavelet transform: its status and achievements , 2003, Comput. Electr. Eng..

[2]  Peter L. Stanchev,et al.  Multimedia Retrieval , 2007, Data-Centric Systems and Applications.

[3]  Robert E. Tarjan,et al.  Depth-First Search and Linear Graph Algorithms , 1972, SIAM J. Comput..

[4]  T. Kailath.  The Divergence and Bhattacharyya Distance Measures in Signal Selection , 1967 .

[5]  Arnaldo de Albuquerque Araújo,et al.  VSUMM: A mechanism designed to produce static video summaries and a novel evaluation method , 2011, Pattern Recognit. Lett..

[6]  David S. Doermann,et al.  Video summarization by curve simplification , 1998, MULTIMEDIA '98.

[7]  Gary Marchionini,et al.  Open video: A framework for a test collection , 2000, J. Netw. Comput. Appl..

[8]  Wolfgang Effelsberg,et al.  Abstracting Digital Movies Automatically , 1996, J. Vis. Commun. Image Represent..

[9]  Yelena Yesha,et al.  Keyframe-based video summarization using Delaunay clustering , 2006, International Journal on Digital Libraries.

[10]  Ba Tu Truong,et al.  Video abstraction: A systematic review and classification , 2007, TOMCCAP.

[11]  Neil A. Thacker,et al.  The Bhattacharyya metric as an absolute similarity measure for frequency coded data , 1998, Kybernetika.

[12]  Marco Pellegrini,et al.  STIMO: STIll and MOving video storyboard for the web scenario , 2009, Multimedia Tools and Applications.

[13]  Nagia M. Ghanem,et al.  VSCAN: An Enhanced Video Summarization Using Density-Based Spatial Clustering , 2013, ICIAP.

[14]  Arnaldo de Albuquerque Araújo,et al.  Video segmentation based on 2D image analysis , 2003, Pattern Recognit. Lett..