SAEN-BGS: Energy-efficient spiking autoencoder network for background subtraction

Zhixuan Zhang, Xiao Peng Li, Qi Liu

Abstract: Highlights•To address the background noise, a spiking autoencoder network is developed using the noise resilience and time-sequence sensitivity of SNNs.•This is the first instance of solving background subtraction from a spike-based perspective, where a continuous spiking convolutional and deconvolutional block is employed to enhance foreground features and diminish background noise within the decoder.•To achieve energy efficiency, a novel self-distillation spiking supervised learning method is proposed within ANN-to-SNN framework.•The empirical evaluations on CDnet-2014 and DAVIS-2016 demonstrate the superiority of the proposed method.