An approach to detect video transitions based on mathematical morphology

The video segmentation problem can be regarded as a problem of detecting the fundamental video units (shots). Due to different ways of linking two consecutive shots this task turns out to be difficult. In this work, we propose a method to detect both cuts and gradual transitions by image segmentation tools instead of using dissimilarity measures or mathematical models. Firstly, the video is transformed into a 2D image, called visual rhythm by sub-sampling. Afterwards, we apply image processing tools to detect all vertical aligned transitions in this image. The main operator applied here is the morphological multi-scale gradient. We also present some experimental results.

• Type: Conference
• Year: 2003
• Where: ICIP
• Authors: Arnaldo de Albuquerque Araújo, Michel Couprie, Neucimar Jerônimo Leite, Silvio Jamil Ferzoli Guimarães
• Keywords: ICIP 2003, Image Processing, Image Processing Tools, Image Segmentation Tools, Morphological Multi-scale Gradient, Vertical Aligned Transitions, Video Segmentation Problem