Normally surveillance involves the monitoring of behavior and activities of humans. Biometric systems are technologies which measure and analyze human physical and/or behavioral characteristics for authentication, identification or screening purposes. Some physical characteristics which can be measured are fingerprints, iris, DNA and facial patterns. The two most common behavioral characteristics are voice and human gait (which refers to the manner of walking). Recent biometric technologies have moved towards distance-based, real-time non-cooperative surveillance. For example both facial and iris recognition systems are commercially available which operate within two-meters of the human and are soon to be released operating within ten-metres. However gait identification may prove to be one of the most promising emerging biometrics for surveillance such as screening of individuals in high-security civilian or military facilities and monitoring potential targets of theft or terrorism.
IdentiGait is a new individual gait recognition technology for surveillance video (e.g. CCTV) developed at UU’s ISRC through a PhD project. It is based on feature extraction from image sequences which collectively capture gait. The technology has been demonstrated using the CASIA-B gait database and associated journal and conference papers are available if required. Preliminary findings have shown that our IdentiGait system performs remote gait biometric person identification in video CCTV surveillance even while humans are wearing different clothing or are carrying unknown objects. There is no known CCTV product available on the market for person identification in video surveillance using gait biometrics.
The gait of individuals checking in at an airport could be compared to an existing database, perhaps even before they enter the airport concourse or during initial security checks. Such data compared with existing CCTV footage could be used to track suspect terrorists or criminals who may be disguising their features or carrying forged documents. A key advantage of gait identification is that identification at a distance is possible where the face and/or iris are not visible . The ability to identify a possible threat from a distance provides a longer time frame in which to react before a possible suspect becomes a real threat without the knowledge of the suspect. An ideal gait identification biometric example is that of CCTV surveillance technology where there is a need to capture biometric data without human contact or cooperation at a distance.
This technology has the potential to solve a specific market problem as outlined above where there is unmet customer need. A most obvious market for Biometric Surveillance is the intelligence and defence community. Based on an Acuity Market Intelligence report , core biometrics technology is poised for sustained growth with global revenues reaching nearly $11 billion annually by 2017 (see Figure 2). Market researchers Homeland Security Research Corporation (HSRC) released a report in 2011  in which they predict that the global installed base of more than 45 million CCTV surveillance systems will drive a fusion of CCTV with biometrics and human behavioural signatures, which will create a new multi-billion dollar premium security market of CCTV-based remote biometric and behavioural suspect detection, growing from a value of $0.593b in 2010 to $3.2b in 2016 (Figure 3) . This new fusion of technologies results from the need to remove the bottlenecks of current CCTV and people screening systems which include very high costs of security officer hire for 24/7 CCTV workstation operation and also the inability to provide reliable and real-time alarms when suspects are viewed by CCTV cameras. This fusion of technologies brings significant growth opportunities for CCTV, biometric and IT systems manufacturers, security systems integrators and entrepreneurs.
There are biometric video surveillance solutions available on the market to identify and track humans using information such as colour or cue. There are also products available which distinguish suspicious human action from normal human action. The main focus of IdentiGait is that of individual human identification based on gait recognition. For example Gait-R developed by ’Defencesoftware’  uses video capture and a motion capture database to recognise and identify how people walk. Gait-R uses Reflective Marker Technology and Video Feed Analysis and so is unsuitable for CCTV based person identification in an uncontrolled environment. Also there are a number of iris and face recognition solutions. For example ‘Neurotechnology’ have released new product VeriLook Surveillance , a software development kit (SDK), for biometric face identification. In addition ‘Cognitec Systems’ provide face recognition technology  within the security market. ‘IrisGuard’  specialise in the deployment of Iris Recognition systems where a high number of people need to be processed in real-time. ‘L-1 Identity Solutions’  deliver solutions (finger, palm, iris and facial and multimodal) for solving issues associated with managing human identity. These face and iris identification systems are not suitable for the identification of humans at a distance. IdentiGait can facilitate this unmet need.
School of Computing and Intelligent Systems
University of Ulster