KIT | KIT-Bibliothek | Impressum | Datenschutz

Anomaly Detection in 3D Space for Autonomous Driving

Schilling, Marcus 1
1 Karlsruher Institut für Technologie (KIT)


Current state-of-the-art perception models do not always detect all objects in an image. Therefore, they cannot currently be relied upon in safety critical applications such as autonomous driving. Objects that cannot be detected are called anomalies. Current work on anomaly detection is primarily based on camera data. This work evaluates to what extent it is possible today to do anomaly detection in 3D on pseudo-lidar data. A pseudo-lidar is a model that estimates 3D depth for each pixel of an image. Currently, there is no approach available that performs anomaly detection on pseudo-lidar data.

Research Question 1 (RQ1) considers whether dissimilarities between lidar and pseudo-lidar are an indicator of anomalies. For this purpose, it is evaluated whether there are larger deviations between pseudo-lidar and lidar point clouds for anomalies compared to non-anomalies. There is no multi-modal dataset for anomaly detection available which could be directly used. Therefore, in the multi-modal KITTI-360 dataset each instance that was not correctly segmented by a panoptic segmentation model, was labeled as anomaly. It is shown how the anomaly definition depends on the used segmentation criterion. ... mehr

Volltext §
DOI: 10.5445/IR/1000148848
Veröffentlicht am 25.07.2022
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Angewandte Informatik und Formale Beschreibungsverfahren (AIFB)
Institut für Anthropomatik und Robotik (IAR)
Institut für Informationssicherheit und Verlässlichkeit (KASTEL)
Publikationstyp Hochschulschrift
Publikationsdatum 15.06.2022
Sprache Englisch
Identifikator KITopen-ID: 1000148848
Verlag Karlsruher Institut für Technologie (KIT)
Umfang VIII, 70 S.
Art der Arbeit Abschlussarbeit - Master
Referent/Betreuer Zöllner, J. M.
Reussner, R.
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page