Sensor Generalization for Adaptive Sensing in Event-based Object Detection via Joint Distribution Training
Aheli Saha René Schuster Didier Stricker
作者信息
Abstract
Bio-inspired event cameras have recently attracted significant research due to their asynchronous and low-latency capabilities. These features provide a high dynamic range and significantly reduce motion blur. However, because of the novelty in the nature of their output signals, there is a gap in the variability of available data and a lack of extensive analysis of the parameters characterizing their signals. This paper addresses these issues by providing readers with an in-depth understanding of how intrinsic parameters affect the performance of a model trained on event data, specifically for object detection. We also use our findings to expand the capabilities of the downstream model towards sensor-agnostic robustness.引用本文复制引用
Aheli Saha,René Schuster,Didier Stricker.Sensor Generalization for Adaptive Sensing in Event-based Object Detection via Joint Distribution Training[EB/OL].(2026-02-26)[2026-02-28].https://arxiv.org/abs/2602.23357.学科分类
自动化技术、自动化技术设备
评论