Benchmarking neuromorphic vision: lessons learnt from computer vision.
Benchmarking neuromorphic vision: lessons learnt from computer vision.
复制标题
DOI：
10.3389/fnins.2015.00374
复制
发表时间：
2015
影响因子：
4.3
通讯作者：
Orchard G
中科院分区：
文献类型：
--
作者：
Tan C;Lallee S;Orchard G
自近三十年前第一个硅视网膜问世以来，视觉传感器已经有了很大的改进。它们最近已经成熟到可以在商业上获得并且可以由外行人操作的程度。然而，尽管传感器的可用性有所提高，但仍然缺乏良好的数据集，而处理基于尖峰的视觉数据的算法仍处于起步阶段。另一方面，基于帧的计算机视觉算法要成熟得多，这在一定程度上要归功于广泛接受的数据集，这些数据集允许算法之间的直接比较并鼓励竞争。我们有一个独特的机会，通过利用在基于帧的计算机视觉中使用数据集所学到的知识，来塑造神经形态视觉基准和挑战的发展。利用这个机会，在本文中，我们回顾了基准和挑战在基于框架的计算机视觉的发展中所发挥的作用，并提出了创建神经形态视觉基准和挑战的指导方针。我们还讨论了在基准神经形态视觉算法时所面临的独特挑战，特别是在试图与基于帧的计算机视觉进行直接比较时。
Neuromorphic Vision sensors have improved greatly since the first silicon retina was presented almost three decades ago. They have recently matured to the point where they are commercially available and can be operated by laymen. However, despite improved availability of sensors, there remains a lack of good datasets, while algorithms for processing spike-based visual data are still in their infancy. On the other hand, frame-based computer vision algorithms are far more mature, thanks in part to widely accepted datasets which allow direct comparison between algorithms and encourage competition. We are presented with a unique opportunity to shape the development of Neuromorphic Vision benchmarks and challenges by leveraging what has been learnt from the use of datasets in frame-based computer vision. Taking advantage of this opportunity, in this paper we review the role that benchmarks and challenges have played in the advancement of frame-based computer vision, and suggest guidelines for the creation of Neuromorphic Vision benchmarks and challenges. We also discuss the unique challenges faced when benchmarking Neuromorphic Vision algorithms, particularly when attempting to provide direct comparison with frame-based computer vision.