Airborne behaviour monitoring using Gaussian processes with map information

Behavior Monitoring Using Learning Techniques and Regular-Expressions-Based Pattern Matching

“…The proposed approach to curvature analysis is based on a moving-window-based trajectory approximation ( [7]) and exploits a third-order polynomial function generating a trajectory with a virtually increased sampling frequency ( [7], [24]). Given a window composed of N T original samples taken at time instants 1 [0,…”

“…In this approach, any pattern that stands out with respect to other data-points is considered as anomaly, paying however the necessary attention in discriminating anomalies from novelties in the observed behaviours (referred as problem of 'novelty detection', [12], [13], [14]). Various approaches involving different techniques, usually based on learning processes, have been used for discriminating anomalies from regular data points: classification of patterns by means of neural networks ( [15], [16]), Bayesian networks ( [17], [18]), SVM ( [19]) or rule-based systems ( [20]), clustering of data for outliers identification ( [21], [22]), distance or density analysis respect to nearest neighbour ( [23]), statistical approaches leveraging parametric models (Gaussian regression models, [24], [25]) or Kernel Functions ( [26]), information-theoretic techniques based on entropy ( [27]) or Kologomorov complexity ( [28]), spectral analysis performed, e.g., by means of Principal Components Analysis (PCA, [29] ) or wavelet transform ( [15]). There have been also interesting studies exploiting the recent developments in Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) for the anomaly detection, directly based on the images [30], [31], [32], [33].…”

“…Clearly, this approach requires domain experts to analyse and define prior knowledge of behaviours of interest, which is expensive and unsustainable under deluge of data and information. To reduce the workload of human operators, Learning-Based (LB) approaches, e.g., Gaussian regression models [24], [39], unsupervised clustering [22], multi-feature clustering [21], nonparametric bayesian learning [18], were widely utilised in traffic monitoring in recent years. The issue with the LB approaches is that it is hard to identify any behaviour of interest, which is not exhibited in the data.…”

IMM Fifth-Degree Spherical Simplex-Radial Cubature Filter for Maneuvering Target Tracking

“…Maneuvering target tracking has been widely used in many applications, such as aircraft surveillance [1,2], road vehicle navigation [3,4] and radar tracking [5][6][7]. Because of the complexity of maneuvering target motion, the single model structure is not appropriate in tracking maneuvering targets.…”

New Environmental Dependent Modelling with Gaussian Particle Filtering Based Implementation for Ground Vehicle Tracking

“…The most apparent domain knowledge is the road constraint information such as the constrained region imposed by a road map. Studies on road network-aided ground vehicle tracking have been reported in different works such as [2], [3] and [4]. In these works, different state estimation algorithms (such as the Gaussian (s) approximation filtering method in [2] and [4], and particle filtering method [3]) have been applied together with the road constraint information for the state estimation.…”