Stephan Herrmann

A video segmentation algorithm for hierarchical object representations and its implementation

This paper describes a segmentation algorithm for generating hierarchical object representations of images and image sequences. Starting from an object model, we describe the structure of the corresponding segmentation algorithm including all analysis methods applied. Besides the well-known color and motion analysis, we also show how to utilize shape information. Furthermore, we discuss the tradeoff between reducing the computational complexity and the quality of the segmentation results. Last, we present the implementation concept for our analysis model, which uses a special toolbox model. The toolbox provides a set of addressing schemes that are needed by low-level video processing tools. The low-level tools are functions that apply a single operation to all pixels in one frame. Using these addressing functions makes it easy to implement new video processing tools, which, when combined, form new analysis methods. The toolbox exists in C-code and is partially transferred into VHDL.

A Test-Bed for Region-Based Image Retrieval Using Multiple Segmentation Algorithms and the MPEG-7 eXperimentation Model: The Schema Reference System

The aim of the SCHEMA Network of Excellence is to bring together a critical mass of universities, research centers, industrial partners and end users, in order to design a reference system for content-based semantic scene analysis, interpretation and understanding. In this paper, recent advances in the development of the SCHEMA reference system are reported, focusing on the application of region-based image retrieval using automatic segmentation. More specifically, the first and the second version of the reference system are presented and the motivation behind the different approaches followed during the development of these two versions is discussed. Experimental results for both systems, using a common collection of images, are shown. Additionally, a comparative evaluation of the two versions both in terms of retrieval accuracy and in terms of time-efficiency is performed, allowing the evaluation of the system as a whole as well as the evaluation of the usability of different components integrated with the reference system, such as the MPEG-7 eXperimentation Model. This illustrates the suitability of the SCHEMA reference system in serving as a test-bed for evaluating and comparing different algorithms and approaches pertaining to the content-based and semantic manipulation of visual information, ranging from segmentation algorithms to indexing features and methodologies.

AN ENVIRONMENT FOR EFFICIENT HANDLING OF DIGITAL ASSETS

The proliferation of digital media assets, and particularly their easy accessibility over open networks such as the Internet, has raised challenging issues regarding management, delivery, search, retrieval and ownership protection of video content. The rapid expansion of E-commerce services and the increased distribution of digital assets over fixed and wireless networks have generated an urgent need for technologies able to deliver high quality services to content creators, providers and end users. While end-users expect easy access to digital content using query structures natural and close to human concepts, content creators and providers are looking for efficient distribution systems capable of protecting digital content and tracing illegal copies. The BUSMAN project is designing and implementing an efficient system for understanding, delivery and querying of video from large databases, fulfiling the needs of content creators, providers and end user linked by heterogeneous networks while employing and enhancing multimedia standards such as MPEG-7 and MPEG-21. This paper is organized as follows. Section 2 reviews related activities in the field of digital content, notably indexing, retrieval and copyright management. The BUSMAN approach to content management is then outlined in section 3, which is followed by an overview of the system architecture in section 4. The paper concludes in section 5 with the promise of a functional demonstrator in due course.

A Coprocessor for Accelerating Visual Information Processing

Visual information processing will play an increasingly important role in future electronics systems. In many applications, e.g. video surveillance cameras, data throughput of microprocessors is not sufficient and power consumption is too high. Instruction profiling on a typical test algorithm has shown that pixel address calculations are the dominant operations to be optimized. Therefore AddressLib, a structured scheme for pixel addressing was developed, that can be accelerated by AddressEngine, a coprocessor for visual information processing. In this paper, the architectural design of AddressEngine is described, which in the first step supports a subset of the AddressLib. Dataflow and memory organization are optimized during architectural design. AddressEngine was implemented in an FPGA and was tested with the MPEG-7 global motion estimation algorithm. Results on processing speed and circuit complexity are given and compared to a pure software implementation. The next step will be the support for the full AddressLib, including segment addressing. An outlook on further investigations on dynamic reconfiguration capabilities is given.

Combining multiple segmentation algorithms and the MPEG-7 eXperimentation model in the Schema reference system

The SCHEMA Network of Excellence aims to bring together a critical mass of universities, research centers, industrial partners and end users, in order to design a reference system for content-based semantic scene analysis, interpretation and understanding. In this paper, advances in the development of the SCHEMA reference system are reported, focusing on the application of region-based image retrieval using automatic segmentation. More specifically, the integration of four segmentation algorithms and the MPEG-7 eXperimentation Model with the reference system are discussed, along with the motivation behind these and various other choices that were made during the development of the reference system. Experimental results for this system, as well as results for an earlier version of it employing proprietary descriptors, are shown using a common collection of images. Comparative evaluation of these versions, both in terms of retrieval accuracy and in terms of time-efficiency, allows the evaluation of the reference system as a whole as well as the evaluation of the usability of different components integrated with it, such as the MPEG-7 eXperimentation Model. These results illustrate the efficiency of the proposed system, as well as its suitability in serving as a test-bed for evaluating and comparing different algorithms and approaches pertaining to the content-based and semantic manipulation of visual information.

Thermo-Economic Evaluation of Novel Flexible CAES/CCPP Concept

This paper presents the results of a thermodynamic and economic evaluation of a novel hybrid combination of a compressed air energy storage (CAES) and a combined cycle power plant (CCPP). The new cycle is modeled on the basis of a GE LM6000 gas turbine model, an adiabatic compressor model, an air expander, and a conventional dual-pressure heat recovery steam generator (HRSG) configuration. Furthermore, a detailed design of the recuperator is presented. With the simulated components, a storage efficiency of 60% is reached. In combined heat and power (CHP) configuration, the total efficiency of the plant reaches up to 86.2%. The thermodynamic and economic performance is compared to a conventional LM6000 combined cycle. For the economic evaluation, the German electricity day-ahead prices and average gas price of the year 2014 are used. Overall, it is found that the CAES/CCPP concept exhibits far more operation hours per year and a higher profit margin than the compared CCPP. Taking into account the investment and operational costs, especially with steam extraction, the net present value (NPV) of the novel cycle is higher than that of the combined cycle, despite the challenging market environment for storage technologies in Germany.

Supervised Learning via Optimal Control Labeling for Criticality Classification in Vehicle Active Safety

A core component of vehicle active safety algo-rithms is the estimation of criticality, which is a measure of the threat or danger of a traffic situation. Based on the criticality esti-mate, an active safety system can significantly increase passenger safety by triggering collision avoidance or mitigation maneuvers like emergency braking or steering. Interpreting criticality as the intensity of an evasion maneuver, we formulate a MinMax optimal control problem which incorporates moving obstacles and clothoidal lane constraints. We show how the solution of this optimal control problem can be used as a criticality labeling function to generate reference data sets for collision scenes. In order to achieve fast execution speeds, we present a supervised classification approach to criticality estimation. Using the Random Forest classifier with feature selection, we show that the criticality of combined braking and steering maneuvers can be predicted with high precision.

A User-Centred System for End-to-End Secure Multimedia Content Delivery: From Content Annotation to Consumer Consumption

The paper discusses the current status of progress of the on-going EU IST BUSMAN project (Bringing User Satisfaction to Media Access Networks), which now approaches the milestone of its 2nd year running. The issues explained include the motivation and approaches behind the design of its client-server system architecture for effective data flows handling, the progress in the implementation of the proposed server system functionalities, and the advanced video processing algorithms investigated and adopted. A fully functional client-server system for video content management, search and retrieval for both professional use scenarios and customers with either fixed or wireless network connections is expected to be demonstrable by year end of 2004.

Bringing user satisfaction to media access: the IST BUSMAN Project

Interactive and seamless access to video content is facilitated by technology that is able to annotate and retrieve media data efficiently and automatically with the minimal human interventions. Media should be accessible by intended users quickly and independent of the database size, regardless of the homogeneous or heterogeneous nature of the delivery channels or the user computing platform. These requirements are driving research and development efforts in the European project BUSMAN; in which a system for efficient annotation, seamless delivery of and access to video components across heterogeneous channels is being developed. The BUSMAN system architecture is based on the needs and expectations of two types of users: content providers and end users. In this paper an overview of the BUSMAN system is presented and its main functionalities are described.

Carrier Cooperation Can Reduce the Transmit Power in Parallel MIMO Broadcast Channels With Zero-Forcing

Even though parallel multiple-input multiple-output (MIMO) broadcast channels are known to be separable from an information theoretic point of view, performing separate encoding and decoding on each of the parallel channels has been shown to be potentially suboptimal in broadcast channels with linear transceivers. In this paper, we show that suboptimality of such a carrier-noncooperative transmission also occurs in broadcast channels with zero-forcing and quality of service constraints if time-sharing is not allowed. The proof is given by constructing a minimal example and identifying a rate tuple that is achievable using carrier-cooperative zero-forcing with a certain sum power but requires a higher sum power with carrier-noncooperative zero-forcing. This observation is of practical relevance since zero-forcing without time-sharing is a popular assumption in the design of low-complexity optimization algorithms.