arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2209.04362cs.CVcs.AIcs.LGcs.NE
收藏

EDeNN:用于低延迟视觉的事件衰减神经网络

EDeNN: Event Decay Neural Networks for low latency vision

University of Surrey(萨里大学)

Celyn Walters, Simon Hadfield

AI总结:

提出事件衰减神经网络(EDeNN),直接处理事件流以实现低延迟视觉,在角速度回归和光流估计上达到最先进性能,且延迟远低于现有方法。

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”只是对生物神经元的一种非常粗略的近似。当今的学习方法旨在数字设备上运行,并处理诸如图像帧之类的数字数据表示。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具能力且更高效。事件相机是一种新兴的传感器技术,它通过异步触发像素来模仿生物视觉,摒弃了图像帧的概念。为了利用现代学习技术,许多基于事件的算法被迫将事件累积回图像帧,这在一定程度上浪费了事件相机的优势。我们遵循相反的范式,开发了一种新型神经网络,其操作更接近原始事件数据流。我们展示了在角速度回归和竞争性光流估计方面的最先进性能,同时避免了训练SNN相关的困难。此外,我们提出的方法的处理延迟低于任何其他实现的1/10,而连续推理又将这一改进提升了一个数量级。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑