Automated Real-time Anomaly Detection in Human Trajectories using Sequence to Sequence Networks

Abstract

Detection of anomalous trajectories is an important problem with potential applications to various domains, such as video surveillance, risk assessment, vessel monitoring and high-energy physics. Modeling the distribution of trajectories with statistical approaches has been a challenging task due to the fact that such time series are usually non stationary and highly dimensional. However, modern machine learning techniques provide robust approaches for data-driven modeling and critical information extraction. In this paper, we propose a Sequence to Sequence architecture for real-time detection of anomalies in human trajectories, in the context of risk-based security. Our detection scheme is tested on a synthetic dataset of diverse and realistic trajectories generated by the ISL iCrowd simulator [11,12]. The experimental results indicate that our scheme accurately detects motions that deviate from normal behaviors and is promising for future real-world applications.

GeoTrackNet—A Maritime Anomaly Detector Using Probabilistic Neural Network Representation of AIS Tracks and A Contrario Detection

“…The latter group uses historical data to learn the implicit detection rules. Since no representative groundtruth data are available for maritime anomaly detection, learningbased anomaly detection schemes cannot apply supervised methods like in [5]- [7]. Unsupervised learning methods are then preferred [9]- [11], [16], [22], [23], [27].…”

“…For these reasons, anomaly detection methods used in other domains such as network traffic analysis or cybersecurity [3], [4] do not apply. We may also emphasise there are no representative groundtruth datasets for this task, hence, supervised learning strategies for anomaly detection as in [5]- [7] do not apply either.…”

Risk Assessment and Automated Anomaly Detection Using a Deep Learning Architecture

“…In the work presented in [9,10], those two issues were addressed as follows. To develop a privacy and GDPR compliant tracking method, we assumed that passengers are tracked using overhead cameras that identify passengers as point targets from their top-down footprints (silhouettes); the footprints are reduced to a point for each passenger and are tracked across the entire airport area or BCP.…”

“…To develop a privacy and GDPR compliant tracking method, we assumed that passengers are tracked using overhead cameras that identify passengers as point targets from their top-down footprints (silhouettes); the footprints are reduced to a point for each passenger and are tracked across the entire airport area or BCP. In the initial phase of the study in [9,10], it was assumed that passengers tracking was perfect, i.e. that all passengers' traces as they moved around the airport or BCP area are (anonymously) identifiable and traceable.…”

“…The difficulty in risk assessment based on trajectories stems from the difficulty in defining what constitutes an abnormal behavior and how it can analytically be described. In the approach in [9,10] this has been overcome by defining what constitutes a normal (expected) behavior, training the AI (Artificial Intelligence) system to recognize normal behavior and test it with abnormal behaviors to reflect loitering, jittering, and other deviations from expected "normal" behaviors. As discussed above, we assumed that travelers can be tracked anonymously using topdown view cameras in compliance with GDPR and ethics regulations.…”