基于生物突触可塑性的仿生分层脉冲神经网络事件相机对象识别系统  

A bio-inspired hierarchical spiking neural network with biological synaptic plasticity for event camera object recognition

作　　者：周茜[1,2,3] 郑鹏 李小虎 ZHOU Qian;ZHENG Peng;LI Xiaohu(State Key Laboratory of Reliability and Intelligence of Electrical Equipment,Hebei University of Technology,Tianjin 300130,P.R.China;Hebei Key Laboratory of Bioelectromagnetics and Neural Engineering,School of Health Sciences and Biomedical Engineering,Hebei University of Technology,Tianjin 300130,P.R.China;Tianjin Key Laboratory of Bioelectricity and Intelligent Health,School of Health Sciences and Biomedical Engineering,Hebei University of Technology,Tianjin 300130,P.R.China)

机构地区：[1]河北工业大学省部共建电工装备可靠性与智能化国家重点实验室,天津300130 [2]河北工业大学生命科学与健康工程学院河北省生物电磁与神经工程重点实验室,天津300130 [3]河北工业大学生命科学与健康工程学院天津市生物电工与智能健康重点实验室,天津300130

出　　处：《生物医学工程学杂志》2023年第4期692-699,共8页Journal of Biomedical Engineering

基　　金：国家自然科学基金面上项目(52077056)。

摘　　要：脉冲神经网络(SNNs)以稀疏脉冲时间编码、异步事件驱动的方式天然地适合处理事件相机输出的事件流数据。为了提高现有的仿生分层脉冲神经网络对事件相机对象的特征提取和分类性能,本文提出一种基于生物突触可塑性的仿生分层脉冲神经网络事件相机对象识别系统。该系统首先基于脉冲神经元电位对原始事件流进行自适应分割以提高系统计算效率,然后使用基于生物突触可塑性的仿生分层脉冲神经网络对事件流数据进行多层的时空特征提取并分类。在基于Gabor滤波器的事件驱动卷积层提取初级视觉特征之后,网络使用基于无监督脉冲时间依赖突触可塑性(STDP)规则的特征层提取频繁出现的显著特征,以及基于奖励调节STDP规则的特征层学习诊断性特征。本文提出的网络在四个基准事件流数据集上的分类精度均优于现有的仿生分层脉冲神经网络,并且本文方法对于较短的事件流输入数据也有很好的分类能力,对输入事件流噪声也具有较强的鲁棒性。综上,本文提出的网络能够提高该类网络对事件相机对象的特征提取和分类性能。With inherent sparse spike-based coding and asynchronous event-driven computation,spiking neural network(SNN)is naturally suitable for processing event stream data of event cameras.In order to improve the feature extraction and classification performance of bio-inspired hierarchical SNNs,in this paper an event camera object recognition system based on biological synaptic plasticity is proposed.In our system input event streams were firstly segmented adaptively using spiking neuron potential to improve computational efficiency of the system.Multi-layer feature learning and classification are implemented by our bio-inspired hierarchical SNN with synaptic plasticity.After Gabor filter-based event-driven convolution layer which extracted primary visual features of event streams,we used a feature learning layer with unsupervised spiking timing dependent plasticity(STDP)rule to help the network extract frequent salient features,and a feature learning layer with reward-modulated STDP rule to help the network learn diagnostic features.The classification accuracies of the network proposed in this paper on the four benchmark event stream datasets were better than the existing bio-inspired hierarchical SNNs.Moreover,our method showed good classification ability for short event stream input data,and was robust to input event stream noise.The results show that our method can improve the feature extraction and classification performance of this kind of SNNs for event camera object recognition.

关 键 词：事件相机 对象识别 脉冲时间依赖突触可塑性(STDP) 奖励调节STDP 脉冲神经网络 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP212[自动化与计算机技术—计算机科学与技术]