An SNN-Based and Neuromorphic-Hardware-Implementable Noise Filter with Self-adaptive Time Window for Event-Based Vision Sensor

Event-based dynamic vision sensors (DVS), inspired by biological vision systems, lead to new sensing and computing paradigms. The novel sensors output the sensed signal alone with many noise events asynchronously. Data-preprocessing for filtering these noises is significant before utilizing the data in applications such as classification, tracking and motion-data extraction. This paper describes a fully spike-based and neuromorphic-hardware-implementable neural network with a signal-oriented self-adaptive filtering time window for filtering the noise events robustly in the data captured by DVS. In particular, the simple leaky integrate-and-fire (LIF) neuron model is adopted as the basic elements of the network out of the purpose of hardware-friendly. Experiments based on both synthesized data and authentically-captured data are designed for quantitative comparison with traditional DVS noise filters to verify the outperformance of the proposed filter. The main contribution of this work is that the proposed spiking neural network (SNN) based filter achieves higher signal-noise-ratio (SNR) compared to traditional noise filters and performances more robust in the tolerance for changing signals.

I. Introduction

Bio-inspired address event representation change detection image sensors, such as Silicon Retina [1], Dynamic Vision Sensor (DVS) [2], Asynchronous Time-based Image Sensor (ATIS) [3], and the Dynamic and Active pixel Vision Sensor (DAVIS) [4], leads to a new paradigm for information sensing, representation and computation. These sensors are considered to be an alternative to fixed frequency image sensors and nowadays have matured to the transition where they can be commercially and availably used in industry [5] [6]. Compared to conventional frame-based image sensors, DVS has a lot of advantages, such as larger dynamic range, higher sensitivity, lower power consumption and lower redundant data. Applications of these sensors have been investigated widely, including spiking optical flow [7] [8], simultaneous localization and mapping (SLAM) [9], attention tracking [10], pattern recognition [11]–[13], and stereovision system [14]. A more detailed survey on such kinds of sensors including the working principle and varied application field as well as the challenges and opportunities is presented in [15].