2015/08/25 by Bashar I. Ahmad, James K. Murphy, Ahmad, Bashar I. +5 · 2 citations
Computer Science · Engineering · #Applications (stat.AP) #FOS: Computer and information sciences #Maritime Navigation and Safety #Target Tracking and Data Fusion in Sensor Networks
paper · pdf · doi:10.48550/arxiv.1508.06115
openalex publication_date 2015/08/25 · openalex created_date 2022/10/03 · openalex updated_date 2026/07/28
In several application areas, such as human computer interaction,\nsurveillance and defence, determining the intent of a tracked object enables\nsystems to aid the user/operator and facilitate effective, possibly automated,\ndecision making. In this paper, we propose a probabilistic inference approach\nthat permits the prediction, well in advance, of the intended destination of a\ntracked object and its future trajectory. Within the framework introduced here,\nthe observed partial track of the object is modeled as being part of a Markov\nbridge terminating at its destination, since the target path, albeit random,\nmust end at the intended endpoint. This captures the underlying long term\ndependencies in the trajectory, as dictated by the object intent. By\ndetermining the likelihood of the partial track being drawn from a particular\nconstructed bridge, the probability of each of a number of possible\ndestinations is evaluated. These bridges can also be employed to produce\nrefined estimates of the latent system state (e.g. object position, velocity,\netc.), predict its future values (up until reaching the designated endpoint)\nand estimate the time of arrival. This is shown to lead to a low complexity\nKalman-filter-based implementation of the inference routine, where any linear\nGaussian motion model, including the destination reverting ones, can be\napplied. Free hand pointing gestures data collected in an instrumented vehicle\nand synthetic trajectories of a vessel heading towards multiple possible\nharbours are utilised to demonstrate the effectiveness of the proposed\napproach.\n