EC-IoU: Orienting Safety for Object Detectors via Ego-Centric Intersection-over-Union

arXiv:2403.15474v1 Announce Type: cross
Abstract: This paper presents safety-oriented object detection via a novel Ego-Centric Intersection-over-Union (EC-IoU) measure, addressing practical concerns when applying state-of-the-art learning-based perception models in safety-critical domains such as autonomous driving. Concretely, we propose a weighting mechanism to refine the widely used IoU measure, allowing it to assign a higher score to a prediction that covers closer points of a ground-truth object from the ego agent's perspective. The proposed EC-IoU measure can be used in typical evaluation …

abstract art arxiv autonomous autonomous driving concerns cs.ai cs.cv cs.lg cs.ro detection domains driving intersection intersection-over-union iou novel object paper perception practical refine safety safety-critical state type union via