Human behaviour recognition in data-scarce domains

This paper presents the novel theory for performing multi-agent activity recognition without requiring large training corpora. The reduced need for data means that robust probabilistic recognition can be performed within domains where annotated datasets are traditionally unavailable. Complex human activities are composed from sequences of underlying primitive activities. We do not assume that the exact temporal ordering of primitives is necessary, so can represent complex activity using an unordered bag. Our three-tier architecture comprises low-level video tracking, event analysis and high-level inference. High-level inference is performed using a new, cascading extension of the Rao–Blackwellised Particle Filter. Simulated annealing is used to identify pairs of agents involved in multi-agent activity. We validate our framework using the benchmarked PETS 2006 video surveillance dataset and our own sequences, and achieve a mean recognition F-Score of 0.82. Our approach achieves a mean improvement of 17% over a Hidden Markov Model baseline.

Contextual anomaly detection in crowded surveillance scenes

This work addresses the problem of detecting human behavioural anomalies in crowded surveillance environments. We focus in particular on the problem of detecting subtle anomalies in a behaviourally heterogeneous surveillance scene. To reach this goal we implement a novel unsupervised context-aware process. We propose and evaluate a method of utilising social context and scene context to improve behaviour analysis. We find that in a crowded scene the application of Mutual Information based social context permits the ability to prevent self-justifying groups and propagate anomalies in a social network, granting a greater anomaly detection capability. Scene context uniformly improves the detection of anomalies in both datasets. The strength of our contextual features is demonstrated by the detection of subtly abnormal behaviours, which otherwise remain indistinguishable from normal behaviour.

Steps towards fully nonlinear simulations of arrays of OWSC

Abandonment of farming systems on upland areas in southwest Britain during the Late Bronze Age – some 3000 years ago – is widely considered a ‘classic’ demonstration of the impact of deteriorating climate on the vulnerability of populations in such marginal environments. Here we test the hypothesis that climate change drove the abandonment of upland areas by developing new chronologies for human activity on upland areas during the Bronze Age across southwest Britain (Dartmoor, Exmoor and Bodmin Moor). We find Bronze Age activity in these areas spanned 3900–2950 calendar years ago with abandonment by 2900 calendar years ago. Holocene Irish bog and lake oak tree populations provide evidence of major shifts in hydroclimate across western Britain and Ireland, coincident with ice rafted debris layers recognized in North Atlantic marine sediments, indicating significant changes in the latitude and intensity of zonal atmospheric circulation across the region. We observe abandonment of upland areas in southwest Britain coinciding with a sustained period of extreme wet conditions that commenced 3100 calendar years ago. Our results are consistent with the view that climate change increased the vulnerability of these early farming communities and led to a less intensive use of such marginal environments across Britain.

Robust indoor speaker recognition in a network of audio and video sensors

Situational awareness is achieved naturally by the human senses of sight and hearing in combination. Automatic scene understanding aims at replicating this human ability using microphones and cameras in cooperation. In this paper, audio and video signals are fused and integrated at different levels of semantic abstractions. We detect and track a speaker who is relatively unconstrained, i.e., free to move indoors within an area larger than the comparable reported work, which is usually limited to round table meetings. The system is relatively simple: consisting of just 4 microphone pairs and a single camera. Results show that the overall multimodal tracker is more reliable than single modality systems, tolerating large occlusions and cross-talk. System evaluation is performed on both single and multi-modality tracking. The performance improvement given by the audio–video integration and fusion is quantified in terms of tracking precision and accuracy as well as speaker diarisation error rate and precision–recall (recognition). Improvements vs. the closest works are evaluated: 56% sound source localisation computational cost over an audio only system, 8% speaker diarisation error rate over an audio only speaker recognition unit and 36% on the precision–recall metric over an audio–video dominant speaker recognition method.

Deep Head Pose: Gaze-Direction Estimation in Multimodal Video

In this paper we present a convolutional neuralnetwork (CNN)-based model for human head pose estimation inlow-resolution multi-modal RGB-D data. We pose the problemas one of classification of human gazing direction. We furtherfine-tune a regressor based on the learned deep classifier. Next wecombine the two models (classification and regression) to estimateapproximate regression confidence. We present state-of-the-artresults in datasets that span the range of high-resolution humanrobot interaction (close up faces plus depth information) data tochallenging low resolution outdoor surveillance data. We buildupon our robust head-pose estimation and further introduce anew visual attention model to recover interaction with theenvironment. Using this probabilistic model, we show thatmany higher level scene understanding like human-human/sceneinteraction detection can be achieved. Our solution runs inreal-time on commercial hardware