Bina-Rep Event Frames: a Simple and Effective Representation for Event-based cameras
This addresses the challenge of processing event-based camera data for computer vision applications, offering an incremental improvement over existing representation methods.
The paper tackles the problem of converting asynchronous event streams from event cameras into a more effective representation, resulting in state-of-the-art performance with sparser and more expressive event frames.
This paper presents "Bina-Rep", a simple representation method that converts asynchronous streams of events from event cameras to a sequence of sparse and expressive event frames. By representing multiple binary event images as a single frame of $N$-bit numbers, our method is able to obtain sparser and more expressive event frames thanks to the retained information about event orders in the original stream. Coupled with our proposed model based on a convolutional neural network, the reported results achieve state-of-the-art performance and repeatedly outperforms other common event representation methods. Our approach also shows competitive robustness against common image corruptions, compared to other representation techniques.