Contextual Content Analysis

Stream Leader: Professor Noel O’Connor

Sensed data in its raw unprocessed state is often worse than useless in any real application scenario. In fact, gathering such sensed data constitutes further polluting a virtual world already suffering from overwhelming information overload. Thus, it is necessary to process and extract only relevant content as carried by the raw sensed data. That is, to process the sensed data in order to extract and even discover semantic information, whilst doing this in an application-centric manner (i.e. taking cognisance of the manner in which the semantic information will eventually be used). As the sensing modality becomes more sophisticated, it becomes increasingly difficult to extract useful semantics. For instance, while it is relatively straightforward to map the signal from a simple point temperature sensor to useful content-rich characterisations (such as “hot” and “cold” and graduations thereof), such an extraction task becomes much more challenging when we consider any of the spectrum of sensing modalities, from text, to multi-media to ‘virtual’ sensors of higher-level user intent, that we address in CLARITY.

Sensor networks composed of combinations of sensing modalities of various levels of sophistication only exacerbates the problem of extracting meaning from data. The objective of this Research Stream is to extend current capabilities for mining context information from sensed data with a view to leveraging this to assist in identifying semantic information. Context mining will be enabled by considering capture mechanisms augmented with multiple sensing modalities that provide either useful analysis constraints or reinforcement of uni-modal analysis. Key ancillary objectives include developing fusion frameworks that handle multiple potentially conflicting data sources and extending the use of pattern recognition techniques to model the desired semantics using non-traditional sensor input in a manner that can be easily configured to different application scenarios.

Case Studies


The InSPeCT (Integrated Surveillance for Port Container Traffic) project is a collaboration between researchers in CLARITY and Irish company Fairview Analytics, a leading supplier of advanced software solutions that monitor vehicle and container traffic. The work analyses video from CCTV and Vehicle Monitoring cameras and brings a new dimension of intelligence to recordings and analysis of vehicle traffic that passes through border crossings and seaports. InSPeCT automatically reads and records the container number and vehicle number plate and uses advanced query and search techniques for efficient retrieval of relevant contextual information. This project was awarded an Enterprise Ireland Commercialisation award at the Big Ideas Showcase 2010.


Multimodal Sensing for Anti-Social Behaviour

CLARITY researchers are developing multimodal sensing of public and domestic places using various spectrum CCTV, as well as audio. By analysing each sensor modality independently and then in combination, a sophisticated model of the usual behaviour in a sensed area can be built, and when deviations from that model are detected, such as caused by anti-social behavior in a public place or falls in a home, these can be used to raise alerts.


Contact Us

It would be great to hear from you!