Graph-based Asynchronous Event Processing for Rapid Object Recognition
This work addresses the need for rapid object recognition in applications like robotics or autonomous systems by enabling efficient, event-by-event processing for event cameras, though it is incremental as it builds on existing graph-based methods.
The paper tackles the problem of low-latency object recognition from event cameras by introducing SlideGCN, a graph-based framework that processes events asynchronously, reducing computational complexity by up to 100 times while maintaining state-of-the-art performance.
Different from traditional video cameras, event cameras capture asynchronous events stream in which each event encodes pixel location, trigger time, and the polarity of the brightness changes. In this paper, we introduce a novel graph-based framework for event cameras, namely SlideGCN. Unlike some recent graph-based methods that use groups of events as input, our approach can efficiently process data event-by-event, unlock the low latency nature of events data while still maintaining the graph's structure internally. For fast graph construction, we develop a radius search algorithm, which better exploits the partial regular structure of event cloud against k-d tree based generic methods. Experiments show that our method reduces the computational complexity up to 100 times with respect to current graph-based methods while keeping state-of-the-art performance on object recognition. Moreover, we verify the superiority of event-wise processing with our method. When the state becomes stable, we can give a prediction with high confidence, thus making an early recognition. Project page: \url{https://zju3dv.github.io/slide_gcn/}.