How Machine Perception Relates to Human Perception: Visual Saliency and Distance in a Frame-by-Frame Semantic Segmentation Task for Highly/Fully Automated Driving

Nico Herbig, Frederik Wiehr, Atanas Poibrenski, Janis Sprenger, Christian Müller

In: ACM/IEEE 1st International Workshop on Software Engineering for AI in Autonomous Systems. International Workshop on Software Engineering for AI in Autonomous Systems (SEFAIAS-2018) located at ICSE May 27-June 3 Gothenburg Sweden ISBN 978-1-4503-5739-5/18/05 ACM/IEEE 2018.


In this paper, we investigate the link between machine perception and human perception for highly/fully automated driving. We compare the classification results of a camera-based frame-by-frame semantic segmentation model (Machine) with a well-established visual saliency model (Human) on the Cityscapes dataset. The results show that Machine classifies foreground objects better if they are more salient, indicating a similarity with the human visual system. For background objects, the accuracy drops when the saliency increases, giving evidence for the assumption that Machine has an implicit concept of saliency.


Weitere Links

machine-perception-relates_SEFAIAS.pdf (pdf, 825 KB)

German Research Center for Artificial Intelligence
Deutsches Forschungszentrum für Künstliche Intelligenz