Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

What goes around comes around: Cycle-Consistency-based Short-Term Motion Prediction for Anomaly Detection using Generative Adversarial Networks

: Golda, Thomas; Murzyn, Nils A.; Qu, Chengchao; Kroschel, Kristian

Postprint urn:nbn:de:0011-n-5828998 (2.0 MByte PDF)
MD5 Fingerprint: 57a479ed2c7d0f97d54504e098c528ba
© IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Created on: 6.6.2020

Institute of Electrical and Electronics Engineers -IEEE-:
16th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2019 : 18-21 September 2019, Taipei, Taiwan
Piscataway, NJ: IEEE, 2019
ISBN: 978-1-7281-0990-9
ISBN: 978-1-7281-0989-3
ISBN: 978-1-7281-0991-6
International Conference on Advanced Video and Signal-Based Surveillance (AVSS) <16, 2019, Taipei>
Conference Paper, Electronic Publication
Fraunhofer IOSB ()

Anomaly detection plays in many fields of research, along with the strongly related task of outlier detection, a very important role. Especially within the context of the automated analysis of video material recorded by surveillance cameras, abnormal situations can be of very different nature. For this purpose this work investigates Generative-Adversarial-Network-based methods (GAN) for anomaly detection related to surveillance applications. The focus is on the usage of static camera setups, since this kind of camera is one of the most often used and belongs to the lower price segment. In order to address this task, multiple subtasks are evaluated, including the influence of existing optical flow methods for the incorporation of short-term temporal information, different forms of network setups and losses for GANs, and the use of morphological operations for further performance improvement. With these extension we achieved up to 2.4% better results. Furthermore, the final method reduced the anomaly detection error for GAN based methods by about 42.8%.