- Full text PDF available (44)
- This year (0)
- Last 5 years (13)
- Last 10 years (33)
Journals and Conferences
The paper investigates the unsupervised learning of a model of activity for a multi-camera surveillance network that can be created from a large set of observations. This enables the learning algorithm to establish links between camera views associated with an activity. The learning algorithm operates in a correspondence-free manner, exploiting the… (More)
This paper considers the problem of automatically learning an activity-based semantic scene model from a stream of video data. A scene model is proposed that labels regions according to an identifiable activity in each region, such as entry/exit zones, junctions, paths, and stop zones. We present several unsupervised methods that learn these scene elements… (More)
The paper considers two problems associated with the detection and classification of motion in image sequences obtained from a static camera. Motion is detected by differencing a reference and the “current” image frame, and therefore requires a suitable reference image and the selection of an appropriate detection threshold. Several threshold selection… (More)
This paper proposes an activity-based semantic model for a scene under visual surveillance. It illustrates methods that allow unsupervised learning of the model, from trajectory data derived from automatic visual surveillance cameras. Results are shown for each method. Finally, the benefits of such a model in a visual surveillance system are discussed.
This paper addresses the problem of automatically extracting frequently used pedestrian pathways from video sequences of natural outdoor scenes. Path models are learnt from the accumulation of trajectory data over long time periods, and can be used to augment the classification of subsequent track data. In particular, labelled paths provide an efficient… (More)
This paper investigates the combination of spatial and probabilistic models for reasoning about pedestrian behaviour in visual surveillance systems. Models are learnt by a multi-step unsupervised method and they are used for trajectory labelling and atypical behaviour detection.
We introduce a large body of virtual human action silhouette (ViHASi) data generated recently for the purpose of evaluating a family of action recognition methods. These are the silhouette-based human action recognition methods. This synthetic multi-camera video data-set consists of 20 action classes, 9 actors and up to 40 synchronized perspective cameras.… (More)
This paper presents a method for multi camera image tracking in the context of image surveillance. The approach differs from most methods in that we exploit multiple camera views to resolve object occlusion. Moving objects are detected by using background subtraction. Viewpoint correspondence between the detected objects is then established by using the… (More)
Peat bogs have historically represented exceptional carbon (C) sinks because of their extremely low decomposition rates and consequent accumulation of plant remnants as peat. Among the factors favoring that peat accumulation, a major role is played by the chemical quality of plant litter itself, which is poor in nutrients and characterized by polyphenols… (More)
This paper describes a novel application of Fourier Descriptor techniques for the recognition of hand gesture trajectories. Appearance based coordinates of hand centroids and time steps are normalized to a fixed length by multirate techniques. Fourier techniques are applied to the data to produce frequency domain data that is scale and translation… (More)