Current algorithms share one limitation: They rely on directly visible objects . This is a major drawback compared to human behavior, where indirect visual cues caused by the actual object (e.g.,shadows) are already used intuitively to retrieve information . Humans already process light artifacts caused by oncoming vehicles to assume their future appearance, whereas current objectdetection systems rely on the oncoming vehicle’s direct visibility . With this contribution, we want to put awareness on the unconventional sensing task ofprovident object detection and further close the performance gap between humanbehavior and computer vision algorithms in order to bring autonomous andautomated driving a step forward . We use the information of providently detected vehicles to control the glare-free high beam system proactively. Using thisexperimental setting, we quantify the time benefit that the provident vehicledetection system provides compared to an in-production computer vision system. We quantified the time advantage that the system provides to an In-production system provides with a real-time andreal-world visualization interface of the detection results. To demonstrate the system, we use the system in a test vehicle, we used the system to control it proactively, using the glare free beam system, and to provide the information to control its glare-

Author(s) : Lukas Ewecker, Ebubekir Asan, Lars Ohnemus, Sascha Saralajew

Links : PDF - Abstract

Code :
Coursera

Keywords : system - detection - time - vehicle - glare -

Leave a Reply

Your email address will not be published. Required fields are marked *