Inceptive Event Time-Surfaces for Object Classification Using Neuromorphic Cameras
This addresses the problem of object classification for applications using neuromorphic cameras, representing an incremental improvement over existing methods.
The paper tackles object classification using neuromorphic camera data by introducing Inceptive Event Time-Surfaces (IETS), which enhance robustness to noise and temporal localization of edges, and combining it with transfer learning achieves state-of-the-art performance.
This paper presents a novel fusion of low-level approaches for dimensionality reduction into an effective approach for high-level objects in neuromorphic camera data called Inceptive Event Time-Surfaces (IETS). IETSs overcome several limitations of conventional time-surfaces by increasing robustness to noise, promoting spatial consistency, and improving the temporal localization of (moving) edges. Combining IETS with transfer learning improves state-of-the-art performance on the challenging problem of object classification utilizing event camera data.