Fast Vision Through Frameless Event-Based Sensing and Convolutional Processing: Application to Texture Recognition
Fast Vision Through Frameless Event-Based Sensing and Convolutional Processing: Application to Texture Recognition
复制标题
DOI：
10.1109/tnn.2009.2039943
复制
发表时间：
2010-04-01
影响因子：
--
通讯作者：
Linares-Barranco, Bernabe
中科院分区：
文献类型：
--
作者：
Antonio Perez-Carrasco, Jose;Acha, Begona;Linares-Barranco, Bernabe
地址事件表示（AER）是一种新兴的硬件技术，它在不久的将来为模拟类脑处理结构提供坚实的技术基础方面显示出巨大潜力。当用于视觉时，AER传感器和处理器不像商业的基于帧的视频技术那样局限于捕捉和处理静止图像帧，而是以基于像素级事件的无帧方式感知和处理视觉信息。因此，视觉处理实际上与视觉感知同时进行，因为不需要等待感知完整的帧。而且，只有有意义的信息被感知、传递和处理。对于类脑视觉处理特别有意义的是一些已经报道的AER卷积芯片，它们显示出非常高的计算吞吐量以及以模块化方式组装大型卷积神经网络的可能性。预计在不久的将来，我们可能会看到具有数百或数千个单独模块的大规模卷积神经网络的出现。同时，需要一些研究来探讨如何为特定应用组装和配置这种大规模卷积网络。在本文中，我们分析了用于纹理识别硬件应用的AER脉冲卷积神经网络。基于已经可用的单个AER卷积芯片的性能数据，我们使用定制的基于事件的行为模拟器来模拟大规模网络。我们开发了一种新的基于事件的处理架构，它使用AER硬件模拟Manjunath的基于帧的特征识别软件算法，并使用我们的行为模拟器分析了其性能。识别率性能没有下降。然而，在速度方面，我们表明在等效帧被完全感知和传输之前就可以实现识别。
Address-event representation (AER) is an emergent hardware technology which shows a high potential for providing in the near future a solid technological substrate for emulating brain-like processing structures. When used for vision, AER sensors and processors are not restricted to capturing and processing still image frames, as in commercial frame-based video technology, but sense and process visual information in a pixel-level event-based frameless manner. As a result, vision processing is practically simultaneous to vision sensing, since there is no need to wait for sensing full frames. Also, only meaningful information is sensed, communicated, and processed. Of special interest for brain-like vision processing are some already reported AER convolutional chips, which have revealed a very high computational throughput as well as the possibility of assembling large convolutional neural networks in a modular fashion. It is expected that in a near future we may witness the appearance of large scale convolutional neural networks with hundreds or thousands of individual modules. In the meantime, some research is needed to investigate how to assemble and configure such large scale convolutional networks for specific applications. In this paper, we analyze AER spiking convolutional neural networks for texture recognition hardware applications. Based on the performance figures of already available individual AER convolution chips, we emulate large scale networks using a custom made event-based behavioral simulator. We have developed a new event-based processing architecture that emulates with AER hardware Manjunath's frame-based feature recognition software algorithm, and have analyzed its performance using our behavioral simulator. Recognition rate performance is not degraded. However, regarding speed, we show that recognition can be achieved before an equivalent frame is fully sensed and transmitted.