Unsupervised AER Object Recognition Based on Multiscale Spatio-Temporal Features and Spiking Neurons
This work addresses object recognition for neuromorphic vision systems, offering an unsupervised method that is incremental in combining existing techniques like SNNs and STDP with a novel feature representation.
The paper tackles unsupervised object recognition from address event representation (AER) data by introducing a multiscale spatio-temporal feature representation and a spiking neural network with STDP, achieving effective recognition across five datasets including a new one called GESTURE-DVS.
This paper proposes an unsupervised address event representation (AER) object recognition approach. The proposed approach consists of a novel multiscale spatio-temporal feature (MuST) representation of input AER events and a spiking neural network (SNN) using spike-timing-dependent plasticity (STDP) for object recognition with MuST. MuST extracts the features contained in both the spatial and temporal information of AER event flow, and meanwhile forms an informative and compact feature spike representation. We show not only how MuST exploits spikes to convey information more effectively, but also how it benefits the recognition using SNN. The recognition process is performed in an unsupervised manner, which does not need to specify the desired status of every single neuron of SNN, and thus can be flexibly applied in real-world recognition tasks. The experiments are performed on five AER datasets including a new one named GESTURE-DVS. Extensive experimental results show the effectiveness and advantages of this proposed approach.