Multidimensional transcoding for adaptive video streaming

Abstract

In this thesis we present a complete image retrieval system based on topic models and evaluate the suitability of different types of topic models for the task of large-scale retrieval on realworld databases. Different similarity measure are evaluated in a retrieval-by-example task.Next, we focus on the incorporation of different types of local image features in the topic models. For this, we first evaluate which types of feature detectors and descriptors are appropriate to model the images, then we propose and explore models that fuse multiple types of local features. All basic topic models require the quantization of the otherwise high-dimensional continuous local feature vectors into a finite, discrete vocabulary to enable the bag-of-words image representation the topic models are built on. As it is not clear how to optimally quantize the high-dimensional features, we introduce different extensions to a basic topic model which model the visual vocabulary continuously, making the quantization step obsolete.On-line image repositories of the Web 2.0 often store additional information about the images besides their pixel values, called metadata, such as associated tags, date of creation, ownership and camera parameters. In this work we also investigate how to include such cues in our retrieval system. We present work in progress on (hierarchical) models which fuse features from multiple modalities.Finally, we present an approach to find the most relevant images, i.e., very representative images, in a large web-scale collection given a query term. Our unsupervised approach ranks highest the image whose image content and its various metadata types gives us the highest probability according to a the model we automatically build for this tag.

Fast Frame-Based Scene Change Detection in the Compressed Domain for MPEG-4 Video

“…In [5] we presented a transcoding architecture which can be used for such video adaptation. Based on this architecture we implemented our presented methods as one transcoding module for our multidimensional transcoder.…”

“…For instance, in case of a scene cut none of the frames immediately before or after the cut should be skipped. In our previous work we presented a transcoding architecture which can be used in such an environment [5]. The implementation of our scene change detection mechanism, which we used for the evaluation of the algorithm is based on this architecture.…”

Adaptive video streaming for mobile clients

“…For the video adaptation itself we use our multidimensional transcoding architecture which we presented in [2]. Currently we have implemented a transcoding module which can adapt an MPEG-4 ASP video stream in the following three dimensions: temporal, spatial and detail resolution.…”

Distributed Cluster Multidimensional Transcoding for Stereoscopic Video Stream

“…According to [5], we propose an optimized framework for multidimensional transcoding. In this framework, we make a concatenation of bit-rate reduction, spatial resolution reduction, temporal resolution reduction and detail resolution reduction to constitute a transcoder.…”