Automatic driving real-time positioning dynamic noise elimination method and system

• Main Author: SU WEIHUA
• Format: Patent
• Language: Chinese; English
• Published: 08.09.2023
• 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 discloses an automatic driving real-time positioning dynamic noise elimination method and system, and belongs to the technical field of automatic driving. The method comprises the following steps: realizing image semantic segmentation based on a pyramid neural network by using image data; meanwhile, in image data, dynamic object detection is completed by using a high-robustness SURF feature matching method; in combination with semantic segmentation and a dynamic object detection result, accurate detection of moving noisy points is realized, and then fusion of radar laser point cloud and image data is carried out to realize elimination of moving noisy points in fused data. According to the invention, the interference of a dynamic target on the precision and accuracy of real-time positioning in the prior art is solved. Through accurate marking and elimination of dynamic target noisy points, the positioning precision and accuracy of automatic driving under a multi-sensor fusion scheme are improved,