With the improvement of rail transportation automation level, obstacle detection technology gradually becomes a key technology for trains to realize unmanned driving in a complex environment. Traditional obstacle detection efficiency is low and labor-intensive; existing in-vehicle sensor obstacle detection limited by the work characteristics of different sensors have low detection rates and false alarms in the detection process. In this paper, we propose a target grid-based method for radar to sense the environment in the track area. We fuse millimeter wave radar and LIDAR two-source data and combine them with target grid algorithms to achieve environment sensing and obstacle detection in rail transit track areas. The relevant experiments show that the target grid-based environment sensing method for radar track area proposed in this paper effectively removes the flash-out noise, improves the accuracy of the information obtained by millimeter wave radar, and has a false alarm rate of 0.3% and a target detection rate of more than 99.2%, in a multi-noise target scenario, providing a reference for researchers in related fields.
Rail Track Area Environment Perception Based on Rader Target Gird
2022-12-01
1146762 byte
Conference paper
Electronic Resource
English
SLUB | 1967
|