Interpreting Camera Operations in the Context of Content-based Video Indexing and Retrieval

In this work, we intend to go one step further to overcome the difficulty that lies in the gap between low-level media features (e.g. colors, texture, motion, etc.) and high-level concepts to perform a reliable content-based indexing and retrieval. More especially, our work proposes a new way to establish a connection between both geometric and radiometric deformations and the characterization of them in terms of camera operations. Based on both the apparent motion and the defocus blur (low-level features), we estimate extrinsic and intrinsic camera parameter changes, and then deduce 3D camera operations (i.e. mid-level features), such as panning/tracking, tilting/booming, zooming/ dollying and rolling, as well as focus changes. Finally, camera operations are recorded into an index which is then used for video retrieval. Experiments confirm that the proposed mid-level features can be accurately deduced from low-level features and that they can be used for indexing and retrieval purpose.