Human activity detection using spiking neural networks regulated by a gene regulatory network

Detecting human activities automatically in a video stream in various scenes is a challenging task. The major difficulty of this task lies in how to extract the spatial and temporal features of video sequences so that the human activities can be recognized. To tackle this problem, we propose a new classifier model using a BCM-based spiking neural network, where the auto-regulated plasticity and meta-plasticity of the BCM network will help to extract the temporal features for the classifier. In the proposed model, the weight, weight plasticity, and meta-plasticity of the BCM network are regulated by a gene regulatory network (GRN), which plays a key role in neural development and neuromodulation. Meanwhile, the GRN will also be influenced by the activity of the neurons it resides in, resulting in a closed loop between the neural network and GRN. By using this new classifier model, only the spatial features need to be extracted from image frames in the preprocessing. Extensive experimental results have demonstrated the efficiency of the proposed model for online human activity detection.