Hyperspectral Trajectory Image for Multi-Month Trajectory Anomaly Detection
Md Awsafur Rahman, Chandrakanth Gudavalli, Hardik Prajapati, B. S. Manjunath

TL;DR
This paper introduces TITAnD, a novel vision-based approach using hyperspectral trajectory images and a cyclic transformer to detect anomalies in multi-month dense GPS trajectories efficiently.
Contribution
It reformulates trajectory anomaly detection as a vision problem, introducing the Hyperspectral Trajectory Image and Cyclic Factorized Transformer for scalable, accurate multi-month analysis.
Findings
Achieves state-of-the-art AUC-PR on benchmarks.
Enables dense multi-month anomaly detection.
Runs 11-75x faster than comparable transformers.
Abstract
Trajectory anomaly detection underpins applications from fraud detection to urban mobility analysis. Dense GPS methods preserve fine-grained evidence such as abnormal speeds and short-duration events, but their quadratic cost makes multi-month analysis intractable; consequently, no existing approach detects anomalies over multi-month dense GPS trajectories. The field instead relies on scalable sparse stay-point methods that discard this evidence, forcing separate architectures for each regime and preventing knowledge transfer. We argue this bottleneck is unnecessary: human trajectories, dense or sparse, share a natural two-dimensional cyclic structure along within-day and across-day axes. We therefore propose TITAnD (Trajectory Image Transformer for Anomaly Detection), which reformulates trajectory anomaly detection as a vision problem by representing trajectories as a Hyperspectral…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAnomaly Detection Techniques and Applications · Automated Road and Building Extraction · Human Mobility and Location-Based Analysis
