Event-driven video adaptation: A powerful tool for industrial video supervision

Efficient video content adaptation requires techniques for content analysis and understanding as well as the development of appropriate mechanisms for content scaling in terms of the network properties, terminal devices characteristics and users’ preferences. This is particularly evident in industrial surveillance applications, due to the huge amount of data needed to be stored, delivered and handled. In this paper, we address both issues by incorporating (a) computer vision tools that allows efficient tracking of salient visual objects for long time regardless of the dynamics of the visual environment –via a self initialized tracking algorithm—and (b) an adaptive optimal rate distortion scheme able to allocate different priorities for each detected video object with respect to users’ needs, network platforms capabilities and terminal characteristics. The self initialized tracker firstly appropriately describes visual content, secondly incorporates adaptive mechanisms for automatically update the tracker to adjust to the current conditions and thirdly includes an efficient decision mechanism that estimates the time instances in which adaptation should be activated. For the rate distortion algorithm, an optimal adaptive framework is adopted which is capable of allocating the desired quality to objects of users’ interest without violating the target bit rate of the sequence. The Wavelet Packet Transform (WPT) is adopted towards this purpose. The advantage of the WPT is that it localizes the frequency components of each video object and therefore it offers additionally content adaptability according to video object texture coding. The WPT tree is transmitted only at the first frame of each shot and thus dew bits are required for its encoding. Experimental results and comparisons with other approaches are presented to illustrate the good performance of the proposed architecture. The results cover real-world and complex industrial environments.