基于坐标注意力脉冲神经网络的注视估计方法OA北大核心CSTPCD

The problems of dynamic blur and low temporal resolution in capturing eye movements with traditional cameras are addressed by employing an event camera for close-range capture and constructing a spiking-eye dataset.A spiking neural network model with a coordinate attention referred to as CA-SpikingRepVGG.The model reads encoded event data and performs feature extraction using the attention-based backbone network,followed by detection using the detection head.Experimental results demonstrate that CA-SpikingRepVGG achieves a mean average precision RP of 70.8%.Compared to SpikingVGG-16,the model shows a 15.9%improvement in RP and a 14.2%increase in Rr.With only one-third of the training time required by SpikingDensenet,the model achieves a 1.8%improvement in RP and a 0.9%improvement in Rr.These results indicate that the proposed model exhibits stronger eye detection and tracking capabilities in the context of eye movement,effectively accomplishing gaze estimation tasks.