Abstract: The present invention relates to a method and apparatus for processing video image data, so as to apply different types of processing to different aspects of video image data. A detection process is arranged to detect a item, object or event appearing or occurring in a scene being viewed by an image device. An image data process is responsive to the detection of the object or event and to control information to process the image data for a portion of the scene where the object or event appears or occurs, differently from the processing of the image data associated with the rest of scene. For example, the object may be a person's face, and the face image data may be processed to produce high resolution data, the rest of the scene being provided in low resolution. This saves on processing, transmission and storage.

Abstract: A system and method for surveillance of a scene comprising the steps of: capturing a scene via at least two image streams; processing the first of the two image streams to detect an act, event or object; and, wherein when an act, event or object is detected, storing portions of the second image stream corresponding to the act, event or object independently of the first image stream.

Abstract: There is provided a surveillance management process comprising a management system maintaining a plurality of client accounts that regulate access to image data via a data network, each of the client accounts having an authorization parameter that defines an access level for a corresponding client system, the management system receiving image streams from a surveillance network comprising a plurality of imaging nodes and autonomously producing metadata descriptors from the image streams, the metadata descriptors identifying sub-frame features of an image stream, the management system using the metadata descriptors to classify image data derived from the corresponding sub-frame features in predefined access categories, and the management system using the authorization parameter of the client accounts to regulate access to classified image data, the access level for a client account defining the access categories that a corresponding client system can access.

Abstract: A method of verifying an input biometric identifier against a reference biometric identifier is disclosed in this specification. The method comprises evaluating the input biometric identifier relative to a group (the ‘cohort’) to improve verification accuracy. Up to three matching scores are used to determine a verification probability for the input biometric identifier. The three matching scores measure the similarity of the input biometric identifier to the biometric identifiers of the cohort, the similarity of the reference biometric identifier to the biometric identifiers of the cohort and the similarity of the input biometric identifier to the reference biometric identifier.

Abstract: There is included a method of surveillance comprising the steps of obtaining image data of a scene, the image data including depth data providing depth information, processing the depth data to identify potential head object(s), that may represent head(s) of persons in the scene, and processing the image data to discount objects within a predetermined lateral distance of potential head objects.

Abstract: Biometric computer systems are systems which use one or biometric identifiers to enroll, verify or identify a person. This disclosure concerns the automatic enrolment of people into biometric systems. Aspects include methods, computer systems, software and biometric systems. A first biometric identifier (i.e. face) and a second biometric identifier (e.g. iris) is captured (201). The first biometric identifier (e.g. face) is compared (206) to the biometric identifiers associated with records in the datastore (i.e. employment records 121) to identify a candidate matching record. An association of the second biometric identifier with the candidate record to be stored (209) in memory.

Abstract: The present invention relates to systems and processes for the management of image data captured by a network covering a plurality of imaging nodes. The systems and processes may include a surveillance network arranged to receive surveillance streams from a plurality of checkpoints that are spatially separated along a route, extracting image data containing facial image content from the surveillance streams, and identifying individual people and determining an elapsed time between distinct checkpoints along the route, to track progress of people along the route.

Abstract: An automated surveillance system is disclosed in this specification. The system comprises a computing system arranged to receive a plurality of surveillance feeds from a surveillance network and detect characteristics of the surveillance feeds that are indicative of categorized events. Each of the surveillance feeds has a geospatial reference tag that identifies the origin of content contained within the feed. The surveillance system determines a response reaction to detected events and identifies potential response units in the vicinity of the surveillance location using the geospatial reference tag.

Abstract: This disclosure concerns image quality assessment. In particular, there is described a computer implemented method, software, and computer for assessing the quality of an image. For example but not limited to, quality of the image of a face indicates the suitability of the image for use in face recognition. The invention comprises determining (112) a similarity of features of two or more sub-images of the image (608) to a model (412) of the object which is based on multiple training images (612) of multiple different objects of that type. The model (412) is comprised of sub-models (406) and each sub-model (406) corresponds to a sub-image of the image (608). Determining similarity is based on the similarity of features of each sub-image to features modelled by the corresponding sub-model. It is an advantage that no input parameters are required for quality assessment since the quality of the image can be determined from only the similarity between the image and the same, therefore single generic, model.

Abstract: The disclosure concerns face recognition systems. The aim is to identify candidate matching images to a probe image. There is provided methods, software and computer system to select (22, 24) a method of matching images from two or more methods of matching images based on an underlying resolution (20) of the probe image (8). Comparing two images of differing resolutions is common in surveillance environments. To alleviate this degradation, the method advantageously dynamically selects the most appropriate matching method for a probe image. The disclosure also provided methods to determine the underlying resolution of a probe (8) or gallery image (14).

Abstract: An image sequence derived from area surveillance is considered as a collection of independent time series, each of which describes an image feature that summarizes a small neighborhood of the image. These time series are regarded as samples from some underlying distribution, and statistical techniques are used to identify the density function of this distribution. The background can then be identified as a feature of this distribution, moreover the distribution of features in subsequent image frames can be monitored to see if it deviates sufficiently from the current distributions to indicate a change in the background.