An Application-Driven Survey on Event-based Neuromorphic Computer Vision

Traditional frame-based cameras, despite their effectiveness and usage in computer vision, exhibit limitations such as high latency, low dynamic range, power consumption and motion blur. For two decades researchers have started to explore neuromorphic cameras, which operate differently from traditional frame-based ones, mimicking biological vision systems for enhanced data acquisition and spatio-temporal resolution. Each pixel asynchronously captures intensity changes in the scene above some user-defined thresholds, and streams of events are captured. However, the distinct characteristics of these sensors mean that traditional computer vision methods are not directly applicable, necessitating investigating new approaches before being applied in real applications. This work aims to fill existing gaps in the literature by providing a survey and a discussion centered on the different application domains by differentiating between computer vision problems and whether solutions are better suited for or have been applied to a specific field. Moreover, an extensive discussion highlights major achievements and challenges in addition to the unique characteristics of each application field.

CAZZATO Dario;  BONO Flavio; 

2024-08-29

MDPI

JRC138371

2078-2489 (online),   

https://doi.org/10.3390/info15080472,    https://publications.jrc.ec.europa.eu/repository/handle/JRC138371,   

10.3390/info15080472 (online),