Motion-based behaviour learning, profiling and classification in the presence of anomalies

Behaviour recognition using multivariate m-mediod based modelling of motion trajectories

“…These include synthetic SIM 1 and SIM 2 datasets and real-life LAB [40,30], ASL [13,14,40,23,30,44] and HJSL [14,23] datasets. The characteristics of these datasets are summarized in Table 2.…”

“…In our previous work [40], we have proposed m-mediodbased modelling and classification approach (MC) for motion-based behaviour recognition. m-mediod-based approach models a motion pattern by a set of cluster centres of mutually disjunctive sub-classes (referred to as mediods) within the pattern.…”

Behavior Recognition Using any Feature Space Representation of Motion Trajectories

“…In our previous work (Khalid, 2010b), we have proposed m-Medoids based activity Modeling and Classification approach using low dimensional feature vector representation of trajectories in Euclidean Space (MC-ES). m-Medoids based approach models a pattern by a set of cluster centres of mutually disjunctive sub-classes (referred to as medoids) within the pattern.…”

“…Experiments are conducted on synthetic SIM 2 and real life LAB (Khalid, 2010a;b;Khalid & Naftel, 2006), HIGHWAY (Khalid & Naftel, 2006) and ASL (Bashir et al, 2006;2005a;b;Khalid, 2010b;Khalid & Naftel, 2006) datasets. Details of these datasets can be found in Table 1.…”

“…Classified training data is obtained by randomly selecting half of the trajectories from each word class leaving the other half to be used as test data. Trajectories from ASL dataset are represented using DFT-MOD based coefficient feature vectors (Khalid, 2010b). Patterns are modeled using 20 medoids per pattern.…”