Kingsley Sage

Security applications of computer vision

In an age which bears witness to a proliferation of Closed Circuit Television (CCTV) cameras for security and surveillance monitoring, the use of image processing and computer vision techniques which were provided as top end bespoke solutions can now be realised using desktop PC processing. Commercial Video Motion Detection (VMD) and Intelligent Scene Monitoring (ISM) systems are becoming increasingly sophisticated, aided, in no small way, by a technology transfer from previously exclusively military research sectors. Image processing is traditionally concerned with pre-processing operations such as Fourier filtering, edge detection and morphological operations. Computer vision extends the image processing paradigm to include understanding of scene content, tracking and object classification. Examples of computer vision applications include Automatic Number Plate Recognition (ANPR), people and vehicle tracking, crowd analysis and model based vision. Often image processing and computer vision techniques are developed with highly specific applications in mind and the goal of a more global understanding computer vision system remains, at least for now, outside the bounds of present technology. This paper will review some of the most recent developments in computer vision and image processing for challenging outdoor perimeter security applications. It also describes the efforts of development teams to integrate some of these advanced ideas into coherent prototype development systems.

Evaluating scene monitoring systems: a discussion paper

Scene monitoring systems are finding widespread application within the security market. The dominant share of the market is held by closed circuit TV (CCTV)-based systems. Techniques for evaluating CCTV-based systems are addressed. The systems, normally using imagery from CCTV cameras as their input, can range from simple movement detection equipment to very sophisticated intelligent scene analysis devices. Thought has been given to the issues which need to be addressed when evaluating such systems, as well as the various techniques which could be used. The authors review the thoughts of those involved. The view taken in evaluating scene monitoring systems has been to work closely with the potential end users of the systems to see how the systems perform in real life settings. Real-life scenes are seen as essential to the evaluation process as they contain such a wide range of changes. The implementation of a specific evaluation is described.<<ETX>>

AMETHYST: automatic alarm assessment: becoming a reality

The aim of the AMETHYST (AutoMatic Event auTHentication SYSTems) project is to encourage the development of a high performance perimeter detection system which combines Video Motion Detection (VMD) technology with another type of Perimeter Intrusion Detection System (PIDS). AMETHYST will automatically assess the cause of all PIDS alarms and pass to an operator only those alarms which are likely to be caused by an intruder. It will, therefore, filter out alarms that are not likely to have a human cause. A previous paper explaining and exploring the AMETHYST concept was presented at the 1995 Carnahan conference. Since then PSDB has produced a single channel AMETHYST demonstrator and placed a contract for the development of an 8 channel prototype AMETHYST system. This updated paper gives details of the hardware and software used with these two systems. Also described is PSDBs approach to the development of AMETHYSTs automatic assessment algorithms. These will combine current expertise from Video Motion Detection (VMD) and Intelligent Scene Monitoring (ISM) systems with the unique AMETHYST approach. AMETHYST analyses picture sequences from before and after an alarm instead of continuously analysing live video. Sequences are provided by a Loop Framestore, either connected to or part of the AMETHYST system. The algorithms will be assessed and developed using PSDBs growing collection of over 150 alarm sequences.

A methodology to evaluate the effect of video compression on the performance of analytics systems

The Image Library for Intelligent Detection Systems (i-LIDS) provides benchmark surveillance datasets for analytics systems. This paper proposes a methodology to investigate the effect of compression and frame-rate reduction, and to recommend an appropriate suite of degraded datasets for public release. The library consists of six scenarios, including Sterile Zone (SZ) and Parked Vehicle (PV), which are investigated using two different compression algorithms (H.264 and JPEG) and a number of detection systems. PV has higher spatio-temporal complexity than the SZ. Compression performance is dependent on scene content hence PV will require larger bit-streams in comparison with SZ, for any given distortion rate. The study includes both industry standard algorithms (for transmission) and CCTV recorders (for storage). CCTV recorders generally use proprietary formats, which may significantly affect the visual information. Encoding standards such as H.264 and JPEG use the Discrete Cosine Transform (DCT) technique, which introduces blocking artefacts. The H.264 compression algorithm follows a hybrid predictive coding approach to achieve high compression gains, exploiting both spatial and temporal redundancy. The highly predictive approach of H.264 may introduce more artefacts resulting in a greater effect on the performance of analytics systems than JPEG. The paper describes the two main components of the proposed methodology to measure the effect of degradation on analytics performance. Firstly, the standard tests, using the ‘f-measure’ to evaluate the performance on a range of degraded video sets. Secondly, the characterisation of the datasets, using quantification of scene features, defined using image processing techniques. This characterization permits an analysis of the points of failure introduced by the video degradation.

Latest developments in the iLids performance standard: New Imaging Modalities

The Imagery Library for Intelligent Detection Systems (iLids) is the UK Governments standard for Video Based Detection Systems (VBDS). The first four iLids scenarios were released in November 2006 and annual evaluations for these four scenarios began in 2007. The Home Office Scientific Development Branch (HOSDB), in partnership with the Centre for the Protection of National Infrastructure (CPNI), has also developed a fifth iLids Scenario; Multiple Camera Tracking (MCT). The fifth scenario data sets were made available in November 2008 to industry, academia, and commercial research organizations. The imagery contains various staged events of people walking through the camera views. Multiple Camera Tracking Systems (MCTS) are expected to initialise on a specific target and be able to track the target over some, or all, of the camera views. The Home Office Scientific Development Branch (HOSDB), in partnership with the Centre for the Protection of National Infrastructure (CPNI) are now working on a sixth iLids dataset series. These datasets will cover several technology areas: 1) Thermal imaging systems, and 2) Systems that rely on active IR illumination. The aim is to develop libraries that promote the development of systems that are able to demonstrate effective performance in the key application area of people and vehicular detection at a distance. This will: 1) Describe the evaluation process, infrastructure and tools that HOSDB will use to evaluate MCT systems. Building on the success of our previous automated tools for evaluation, HOSDB has developed the MCT evaluation tool CLAYMORE. CLAYMORE is a tool for the real-time evaluation of MCT systems, and 2) Provide an overview of the new sixth scenario aims and objectives, library specifications and timescales for release.

Computer vision for security applications

With the proliferation of Closed Circuit Television (CCTV) cameras for security and surveillance monitoring, the use of image processing and computer vision techniques can now be realised using desktop PC processing. Commercial Video Motion Detection (VMD) and Intelligent Scene Monitoring (ISM) systems are becoming increasingly sophisticated. Image processing is traditionally concerned with preprocessing operations such as Fourier filtering, edge detection and morphological operations. Computer vision extends the image processing paradigm to include understanding of scene content, tracking and object classification. Examples of computer vision applications include Automatic Number Plate Recognition (ANPR), people and vehicle tracking, crowd analysis and model based vision. Often image processing and computer vision techniques are developed with highly specific applications in mind and the goal of a more global understanding computer vision system remains outside the bounds of present technology. This paper reviews some of the most recent developments in computer vision and image processing for challenging outdoor perimeter security applications. It also describes the efforts of development teams to integrate some of these advanced ideas into coherent prototype development systems.

Optimising the performance of fence-mounted detection systems

The performance of fence-mounted perimeter intrusion detection systems (PIDSs) is examined. Performance specifications, the current performance of operational systems, fence and sensor types, and other factors affecting sensor performance are discussed, along with the implications of fence sensitivity variations and the measurement of these variations. The on-site optimization method (OSOM) is then introduced. Fence impact testers are a vital part of the OSOM. The OSOM addresses problems caused by different fence types, variations in sensitivity from zone to zone, and variability along each zone. The OSOM was developed for the optimization of a microphonic cable PIDS with digital signal processing. Adjusting the PIDS processing parameters to give a guaranteed level of detection, advantages over analog systems, and a comparison with off-site tuning are discussed.<<ETX>>

Latest developments in the iLids performance standard: from multiple standard camera views to new imaging modalities

The Imagery Library for Intelligent Detection Systems (iLids) is the UK Governments standard for Video Based Detection Systems (VBDS). The first four iLids scenarios were released in November 2006 and annual evaluations for these four scenarios began in 2007. The Home Office Scientific Development Branch (HOSDB), in partnership with the Centre for the Protection of National Infrastructure (CPNI), has also developed a fifth iLids Scenario; Multiple Camera Tracking (MCT). The fifth scenario data sets were made available in November 2008 to industry, academic and commercial research organizations The imagery contains various staged events of people walking through the camera views. Multiple Camera Tracking Systems (MCTS) are expected to initialise on a specific target and be able to track the target over some or all of the camera views. HOSDB and CPNI are now working on a sixth iLids dataset series. These datasets will cover several technology areas: • Thermal imaging systems • Systems that rely on active IR illumination The aim is to develop libraries that promote the development of systems that are able to demonstrate effective performance in the key application area of people and vehicular detection at a distance. This paper will: • Describe the evaluation process, infrastructure and tools that HOSDB will use to evaluate MCT systems. Building on the success of our previous automated tools for evaluation, HOSDB has developed the MCT evaluation tool CLAYMORE. CLAYMORE is a tool for the real-time evaluation of MCT systems. • Provide an overview of the new sixth scenario aims and objectives, library specifications and timescales for release.

Extending performance evaluation to near infrared and thermal imaging wavebands: the i-LIDS new technologies datasets

The Image Library for Intelligent Detection Systems (i-LIDS) is the United Kingdom governments benchmark for Video Analytics (VA) systems. There are currently 5 different scenario based datasets available. A new suite of datasets is under development, intended to assess VA performance working with imagery obtained under Near Infra Red (NIR) illumination conditions and from thermal imagers (infra red cameras). This paper describes the datasets that are under construction. The datasets should be publically available in late 2010.

Latest developments in the iLids performance standard: From multiple standard camera views to new imaging modalities

The Imagery Library for Intelligent Detection Systems (iLids) is the UK Governments standard for Video Based Detection Systems (VBDS). The first four iLids scenarios were released in November 2006 and annual evaluations for these four scenarios began in 2007.