Andrzej Ciarkowski

Multi-Stage Video Analysis Framework

The chapter is organized as follows. Section 2 presents the general structure of the proposed framework and a method of data exchange between system elements. Section 3 is describing the low-level analysis modules for detection and tracking of moving objects. In Section 4 we present the object classification module. Sections 5 and 6 describe specialized modules for detection and recognition of faces and license plates, respectively. In section 7 we discuss how video analysis results provided by other modules may be used for automatic detection of events related to possible security threats. The chapter ends with conclusions and discussion of future framework development.

Distributed Framework for Visual Event Detection in Parking Lot Area

The paper presents the framework for automatic detection of various events occurring in a parking lot basing on multiple camera video analysis. The framework is massively distributed, both in the logical and physical sense. It consists of several entities called node stations that use XMPP protocol for internal communication and SRTP protocol with Jingle extension for video streaming. Recognized events include detecting parking vehicles supplemented with parking place and vehicle identification. Event detection is based on low level image processing consisting of moving object detection, tracking and classification. Front-end of the framework is formed by the operator console that presents results of the framework accompanied with video streams from selected cameras in the real-time. Additionally, the operator console may be used to automatically aim any PTZ camera in the framework at the selected spot in video frames from fixed cameras and track moving objects as long as they move within the monitored area. The paper is concluded with the framework performance evaluation during real condition experiments.

Performance of Watermarking-Based DTD Algorithm under Time-Varying Echo Path Conditions

A novel double-talk detection (DTD) algorithm based on techniques similar to those used for audio signal watermarking was introduced by the authors. The application of the described DTD algorithm within acoustic echo cancellation system is presented. The problem of DTD robustness to time-varying conditions of acoustic echo path is discussed and explanation as to why such conditions occur in practical situations is provided. The environment and the procedure used for simulation of test conditions and evaluation of DTD algorithms are presented. Results of comparing performance of the introduced watermarking DTD with the well-established Geigel DTD algorithm are presented.

Massive surveillance data processing with supercomputing cluster

We propose a new model of online surveillance data streams processing on a supercomputer.Massive parallelization enables online object detection in high-resolution video streams.Crowding detection in multi-camera image sequences is performed in nearly real-time.Online privacy protection in surveillance systems is possible on cluster architecture. In recent years, increasingly complex algorithms for automated analysis of surveillance data are being developed. The rapid growth in the number of monitoring installations and higher expectations of the quality parameters of the captured data result in an enormous computational cost of analyzing the massive volume of data. In this paper a new model of online processing of surveillance data streams is proposed, which assumes the use of services running within a supercomputer platform. The study presents some of the highly parallelized algorithms for detecting safety-threatening events in high-resolution-video streams, which were developed during the research, and discusses their performance on the supercomputer platform.

Surveillance Camera Tracking of Geo positioned Objects

A system for tracking moving objects with a known GPS position using a set of PTZ cameras with limited areas of coverage is presented. The basic idea of the system and its possible applications are discussed. The proposed camera calibration technique is used to transform the GPS position to camera settings. The current position of the tracked object is predicted in order to compensate the transmission and processing delays. The distributed client-server system using mobile terminals and its application to tracking objects movement, with additional functionality such as showing the position of the objects on the map, is presented. The results of the tests performed in real-life conditions, as well as perspectives of a future development of the system, are discussed.

Double‐talk detector based on audio watermarking.

The double‐talk detection (DTD) algorithm is a vital part of an acoustic echo cancellation system commonly used in the telecommunication applications. The role of the DTD algorithm is to stop the adaptation process of the adaptive filter used for the estimation of echo path response in the presence of double‐talk condition. The typically used DTD solutions are often a compromise between high efficiency and affordable computational cost. The algorithm introduced by the authors is based on a novel principle related to the so‐called semi‐fragile watermarking, making it possible to achieve satisfactory performance with limited processing burden. A hidden signature is embedded into the arriving far‐end speaker signal just before it is replayed to the near‐end speaker. Consequently, the presence of that signature is detected in the signal recorded by the near‐end speaker microphone. The appropriate choice of the employed watermarking technique causes the signature to become undetectable during the near‐end spea...

Multimedia Mobile Services for the Semantic Web

This document describes the methodology of creating semantically-enriched multimedia mobile services using tools and service enablers provided by the DeSyME project. A brief introduction to the semantic Web is presented along with the explanation of its relation to the subject of Web services. Next, the description of the DeSyME framework is included. Finally, examples of multimedia mobile services developed at Gdansk University of Technology are presented to illustrate possible utilities of described technologies

Performance Measurements of Real Time Video Transmission from Car Patrol

The HSUPA technology application to video streaming from moving vehicle to the central server is presented in the paper. A dedicated software for transmission control in case of non public IP address is employed. Quality of video streaming in urban area was measured. Several car routes were investigated in the area of the Polish Tricity. Measurements pointed out that the real time streaming quality during vehicle movement is sufficient within the prevailing time period.