Road disease detection method and system using information fusion and cloud-edge deployment

• Main Authors: ZHAO RUNJING, LI ZHAOJIA, SHI ZHIPING, BAI YINGDUO, JIANG NA, QIU YUXUAN
• Format: Patent
• Language: Chinese; English
• Published: 22.03.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The invention relates to a road disease detection method and system using information fusion and cloud-edge deployment, and the method comprises the steps: S1, constructing an enhanced image data set SA and a road edge information data set E based on an original road image data set S, and carrying out the training through combining SA and E, and obtaining a trained full-precision road disease detection model; s2, quantifying the trained full-precision road disease detection model to obtain a quantified road disease detection model; inputting the fact image into a quantized road disease detection model for coarse filtering detection to obtain a road disease coarse filtering detection result, and uploading the road disease coarse filtering detection result to a cloud; s3, deploying a trained full-precision road disease detection model at a cloud end, and processing a coarse filtering detection result to obtain a fine particle detection result; analyzing, converging and displaying the sample, and selecting a sam