Intelligent identification method and system for detecting underground hidden danger of road by geological radar

• Main Authors: WANG JIHAO, ZHENG LEI, LIU XIANCUI, ZHOU YUNJIAN, LIU YU, HUANG JUNGE, LU NINGQI
• Format: Patent
• Language: Chinese; English
• Published: 08.07.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; HANDLING RECORD CARRIERS; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

The invention discloses an intelligent identification method and system for detecting underground hidden dangers of a road by a geological radar, and relates to the field of automatic detection, and the method comprises the steps: constructing a geological radar image database, screening a two-dimensional geological radar map sample containing an underground hidden danger target, carrying out the marking and data enhancement of a target sample picture, and carrying out the detection of the underground hidden dangers. Constructing a PASCA-VOC data set, dividing the data set, obtaining a Mask-RCNN network model, and detecting a geological radar road underground hidden danger target; the geological radar database is constructed, data information is rich, and the requirement for a large amount of data in network training is met; target detection precision is effectively improved through technologies such as data enhancement and a network structure according to engineering application requirements, complex road un