Hierarchical affinity hybrid tree: A multidimensional index structure to organize videos and support content-based retrievals

Multimedia data, especially videos, have gained enormous popularity in the recent years. Data management techniques for traditional text-based data are inadequate to handle multimedia data efficiently due to their atypical characteristics. Thus, to have a robust data management framework for complex multimedia data like videos, comparable in efficiency and capability to the traditional data management approaches, components like multimedia data storage, index, and query engines need to be developed with dedicated abilities to handle the characteristics of multimedia data like multidimensional representation and semantic gap. In this paper, we investigate the design of the second component, i.e., a multimedia index, and propose a novel tree-based multidimensional hierarchical index structure called Hierarchical Affinity Hybrid-Tree (HAH-Tree) which addresses the critical issues of multidimensionality and semantic gap. The index structure accommodates different levels of video relationships during Content-Based Video Retrieval (CBVR) by utilizing a probabilistic approach called the Hierarchical Markov Model Mediator (HMMM), which is also responsible for managing the high-level semantic content of the video components. In addition, a computationally efficient k-Nearest Neighbor (k-NN) algorithm is proposed, which supports CBVR for different video units with a high precision level.