论文标题

Edenn:低潜伏期视觉的事件衰减神经网络

EDeNN: Event Decay Neural Networks for low latency vision

论文作者

Walters, Celyn, Hadfield, Simon

论文摘要

尽管神经网络在计算机视觉任务中取得了成功,但数字“神经元”还是生物神经元的非常松散的近似。当今的学习方法旨在在具有数字数据表示(例如图像框架)的数字设备上运行。相比之下,生物视觉系统通常比最先进的数字计算机视觉算法更有能力和高效。事件摄像机是一种新兴的传感器技术,它以异步射击像素模仿生物学视觉,避免了图像框架的概念。为了利用现代学习技术,许多基于事件的算法被迫将事件积累回图像帧,在某种程度上浪费了事件摄像机的优势。 我们遵循相反的范式,并开发一种新型的神经网络,该网络更接近原始事件数据流。我们证明了角速度回归和竞争性光流估计的最新性能,同时避免了与训练SNN相关的困难。此外,我们提出的方法的处理延迟小于1/10其他任何实施,而持续推断将这种改进增加了另一个数量级。

Despite the success of neural networks in computer vision tasks, digital 'neurons' are a very loose approximation of biological neurons. Today's learning approaches are designed to function on digital devices with digital data representations such as image frames. In contrast, biological vision systems are generally much more capable and efficient than state-of-the-art digital computer vision algorithms. Event cameras are an emerging sensor technology which imitates biological vision with asynchronously firing pixels, eschewing the concept of the image frame. To leverage modern learning techniques, many event-based algorithms are forced to accumulate events back to image frames, somewhat squandering the advantages of event cameras. We follow the opposite paradigm and develop a new type of neural network which operates closer to the original event data stream. We demonstrate state-of-the-art performance in angular velocity regression and competitive optical flow estimation, while avoiding difficulties related to training SNN. Furthermore, the processing latency of our proposed approach is less than 1/10 any other implementation, while continuous inference increases this improvement by another order of magnitude.

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源