Lightweight Pedestrian Detection Based on Feature Multiplexed Residual Network

As an important part of autonomous driving intelligence perception, pedestrian detection has high requirements for parameter size, real-time, and model performance. Firstly, a novel multiplexed connection residual block is proposed to construct the lightweight network improving ability extract features. Secondly, scalable attention module investigated expand local perceptual field based on dilated convolution that can maintain most feature channels. Finally, we verify Caltech dataset BDD 100 K datasets. The results show method superior existing methods in terms size