Hierarchical Video Indexing Based On Changes Of Camera And Object Motions


Video content analysis; Video indexing; Video retrieval; Video similarity model


Since an entire video stream is too coarse as a level of abstraction, it is decomposed into a number of shots in general. A shot, which is defined as a collection of frames recorded from a single camera operation, is a basic unit for indexing video data. The existing video indexing models try to index these shots using either low-level (i.e., color, motion), or high-level (i.e., human interpretations) features. Recently, hybrid approach to combine these low-level and high-level features for indexing purpose has been proposed to take advantages from both of them. In this paper, we extend our previous works for shot boundary detecting and indexing, and propose a new shot indexing technique to be fit into the hybrid environment. It supports in-depth classification of various kinds of shots according to camera motions and object movements. The results from preliminary experiments can confirm the effectiveness of the proposed techniques.

Publication Date


Publication Title

Proceedings of the ACM Symposium on Applied Computing

Number of Pages


Document Type

Article; Proceedings Paper

Personal Identifier


DOI Link


Socpus ID

0038336694 (Scopus)

Source API URL


This document is currently not available here.