Tunnel pedestrian target detection method based on cascade super-resolution network and improved Faster R-CNN

Abstract

The invention discloses a tunnel pedestrian target detection method based on a cascaded super-resolution network and an improved Faster R-CNN, and the method comprises the following steps of S1, training the super-resolution network, and obtaining an SRCNN super-resolution network model; S2, acquiring a tunnel pedestrian training sample and marking the pedestrians; S3, clustering the dimension proportion of a label box, and selecting a proper anchor frame dimension in the RPN network; S4, training the Faster R-CNN network, and obtaining a trained model; and S5, detecting the tunnel pedestriantarget by adopting the trained model to obtain a detection result. Compared with an original Faster R-CNN network, the method has the higher detection precision and can be effectively applied to low-resolution pedestrian target detection in a tunnel environment.

Description

technical field [0001] The invention relates to the field of traffic data analysis and processing, in particular to a tunnel pedestrian target detection method based on cascaded super-resolution networks and improved Faster R-CNN. Background technique [0002] With the rapid development and progress of artificial intelligence, pedestrian detection has become one of the main research directions in the field of computer vision, and it also occupies an important position in intelligent video surveillance. Relevant scholars around the world have conducted extensive research on pedestrian detection. According to traffic rules, expressway tunnels can only allow vehicles to pass through, and pedestrians are not allowed to enter, but there are still pedestrians who do not obey the traffic rules and pass through the expressway tunnel. In the tunnel, the ambient light is insufficient, the driver's vision is limited, and when the vehicle enters and exits the tunnel, the driver will be ...

AI Technical Summary

Problems solved by technology

Starting from the actual environment of expressway tunnels, the present invention conducts research on the problem of poor pedestrian feature extraction by Faster R-CNN in the tunnel environment, and designs a pedestrian target detection network cascaded with a super-resolution network and Faster R-CNN

And to solve the problem that the size ratio of the candidate frame in the RPN network in the original Faster R-CNN network is not suitable for the task of tunnel pedestrian target detection, the K-Means algorithm is used to perform clustering statistics on the real marked frame of pedestrians to generate higher quality candidate windows

Images