E-Acj: Accurate Junction Extraction For Event Cameras

Junctions reflect the important geometrical structure information of images, and are of primary significance to applications such as image matching and motion analysis. Previous event-based feature extraction methods are mainly fo-cused on corners, which only find the locations, however, ignoring the geometrical structure information like orientationsand scales of edges. This paper adapts the frame-based a-contrario junction detector(ACJ) to event cameras, proposing the event-based a-contrario junction detector(e-ACJ) which yields junctionsƒ?? locations while giving the scales and orientations of their branches. The proposed method relies on an a-contrario model and can operate on asynchronous events directly without generating synthesized event frames. We evaluate our method on public event datasets. The result shows our method successfully finds the orientations and scales of branches, while maintaining high accuracy in junctionsƒ?? locations.