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.
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi. 2023 Aug 25;40(4):692-699. doi: 10.7507/1001-5515.202207040.
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.
基于固有的基于稀疏脉冲的编码和异步事件驱动计算，脉冲神经网络（SNN）自然适用于处理事件相机的事件流数据。为了提高受生物启发的分层SNN的特征提取和分类性能，本文提出了一种基于生物突触可塑性的事件相机目标识别系统。在我们的系统中，首先使用脉冲神经元电位对输入事件流进行自适应分割，以提高系统的计算效率。多层特征学习和分类由具有突触可塑性的受生物启发的分层SNN实现。在基于Gabor滤波器的事件驱动卷积层提取事件流的初级视觉特征之后，我们使用具有无监督脉冲时间依赖可塑性（STDP）规则的特征学习层来帮助网络提取频繁的显著特征，以及具有奖励调制STDP规则的特征学习层来帮助网络学习诊断特征。本文提出的网络在四个基准事件流数据集上的分类准确率优于现有的受生物启发的分层SNN。此外，我们的方法对短事件流输入数据显示出良好的分类能力，并且对输入事件流噪声具有鲁棒性。结果表明，我们的方法可以提高这种SNN用于事件相机目标识别的特征提取和分类性能。
