Detecting Anomalous Trajectories via Recurrent Neural Networks
| Autor: | Cong Ma, Zhenjiang Miao, Ming-Hsuan Yang, Shaoyue Song, Min Li |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
050210 logistics & transportation
Computer science business.industry Anomaly (natural sciences) 05 social sciences Pattern recognition 02 engineering and technology Autoencoder Measure (mathematics) Term (time) Recurrent neural network 0502 economics and business Metric (mathematics) 0202 electrical engineering electronic engineering information engineering Trajectory Benchmark (computing) 020201 artificial intelligence & image processing Artificial intelligence business |
| Zdroj: | Computer Vision – ACCV 2018 ISBN: 9783030208691 ACCV (4) |
| DOI: | 10.1007/978-3-030-20870-7_23 |
| Popis: | Detecting anomalies from trajectory data is an important task in video surveillance. However, it is difficult to give a precise definition of this term since trajectory data obtained from different camera views may vary in shape, direction, and spatial distribution. In this paper, we propose trajectory distance metrics based on a recurrent neural network to measure similarities and detect anomalies from trajectory data. First, we use an autoencoder to capture the dynamic features of a trajectory. The distance between two trajectories is defined by the reconstruction errors based on the learned models. We then detect anomalies based on the nearest neighbors using the proposed metric. As such, we can deal with various kinds of anomalies in different scenes and detect anomalous trajectories in either a supervised or unsupervised manner. Experiments show that the proposed algorithm performs favorably against the state-of-the-art anomaly detections on the benchmark datasets. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|