Efficient Search and Localization of Human Actions in Video Databases

As digital video databases grow, so grows the problem of effectively navigating through them. In this paper we propose a novel content-based video retrieval approach to searching such video databases, specifically those involving human actions, incorporating spatio-temporal localization. We outline a novel, highly efficient localization model that first performs temporal localization based on histograms of evenly spaced time-slices, then spatial localization based on histograms of a 2-D spatial grid. We further argue that our retrieval model, based on the aforementioned localization, followed by relevance ranking, results in a highly discriminative system, while remaining an order of magnitude faster than the current stateof-the-art method. We also show how relevance feedback can be applied to our localization and ranking algorithms. As a result, the presented system is more directly applicable to real world problems than any prior content-based video retrieval system.