HOTS: A Hierarchy of Event-Based Time-Surfaces for Pattern Recognition
HOTS: A Hierarchy of Event-Based Time-Surfaces for Pattern Recognition
复制标题
DOI：
10.1109/tpami.2016.2574707
复制
发表时间：
2017-07-01
影响因子：
23.6
通讯作者：
Benosman, Ryad B.
中科院分区：
文献类型：
--
作者：
Lagorce, Xavier;Orchard, Garrick;Benosman, Ryad B.
本文介绍了新的事件为基础的时空功能称为时间表面，以及如何使用它们来创建一个分层的基于事件的模式识别架构。与现有的模式识别的层次结构，所提出的模型依赖于一个面向时间的方法来提取时空特征的异步获取动态的视觉场景。这些动态是使用生物启发的无框架异步事件驱动的视觉传感器。与皮层结构类似，我们层次结构中的后续层使用越来越大的时空窗口提取越来越抽象的特征。其核心概念是使用事件提供的丰富的时间信息来创建上下文的时间表面的形式表示最近的时间活动在一个本地的空间邻域。我们证明，这个概念可以鲁棒地用于基于事件的层次模型的所有阶段。第一层特征单元对像素组进行操作，而后续层特征单元对较低级别特征单元的输出进行操作。我们报告的结果在以前发表的36类字符识别任务和4类典型的动态卡pip任务，实现近100%的准确率。我们引入了一个新的七类移动人脸识别任务，达到79%的准确率。
This paper describes novel event-based spatio-temporal features called time-surfaces and how they can be used to create a hierarchical event-based pattern recognition architecture. Unlike existing hierarchical architectures for pattern recognition, the presented model relies on a time oriented approach to extract spatio-temporal features from the asynchronously acquired dynamics of a visual scene. These dynamics are acquired using biologically inspired frameless asynchronous event-driven vision sensors. Similarly to cortical structures, subsequent layers in our hierarchy extract increasingly abstract features using increasingly large spatio-temporal windows. The central concept is to use the rich temporal information provided by events to create contexts in the form of time-surfaces which represent the recent temporal activity within a local spatial neighborhood. We demonstrate that this concept can robustly be used at all stages of an event-based hierarchical model. First layer feature units operate on groups of pixels, while subsequent layer feature units operate on the output of lower level feature units. We report results on a previously published 36 class character recognition task and a four class canonical dynamic card pip task, achieving near 100 percent accuracy on each. We introduce a new seven class moving face recognition task, achieving 79 percent accuracy.