Aiming at the problems of low model detection speed and low detection accuracy caused by pedestrian occlusion and changing pedestrian poses in dense pedestrian detection, a dense pedestrian detection algorithm with Hierarchical Vision Transformer Prediction Head (STPH)-YOLOv5 is proposed. Based on YOLOv5, the original YOLOv5 prediction head is replaced with a Hierarchical Vision Transformer Prediction Head (STPH) to explore the prediction potential with selfattention mechanism. In addition, a coordinate attention mechanism is integrated to accurately capture the location and orientation information of pedestrians in the image. In order to avoid the loss of feature information caused by the deepening of the network, the fused multi-scale feature network (BiFPN) is used in the neck part of the improved algorithm to replace the PANet in the original YOLOv5, which makes the prediction network more sensitive to targets of different sizes and improves the overall model. The detection ability reduces the missed detection rate and false detection rate of the model.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.