Train forward obstacle detection method based on 4D millimeter wave radar

• Main Authors: WANG DAJING, WANG WEI, LIU QUANLI
• Format: Patent
• Language: Chinese; English
• Published: 10.05.2024
• Subjects: ANALOGOUS ARRANGEMENTS USING OTHER WAVES; CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION ORRERADIATION OF RADIO WAVES; MEASURING; PHYSICS; RADIO DIRECTION-FINDING; RADIO NAVIGATION; TESTING

The invention relates to a train forward obstacle detection method based on a 4D millimeter wave radar, and relates to the technical field of intelligent train auxiliary driving, and the method comprises the steps: carrying out the preprocessing of collected 4D millimeter wave radar point cloud data through statistical filtering and straight-through filtering, removing the interference of outliers, noise points and high-altitude obstacles, and carrying out the detection of a forward obstacle of a train; then, the point cloud segmentation range of the left side and the right side of the train track is adjusted based on a DBSCAN clustering algorithm, the point cloud information of an obstacle is reserved as far as possible while the model calculation consumption is reduced, and finally, through multi-scale and multi-dimensional feature extraction and a deep learning network model with spatial dimension and channel dimension attention enhancement, the method can be used for realizing the multi-scale and multi-di