Urban sweeper road condition sensing system and method based on Internet of Things

• Main Authors: CHEN JINFU, LIU QINGXIU, CUI FEIYI
• Format: Patent
• Language: Chinese; English
• Published: 21.06.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; PHYSICS

The invention discloses an urban road sweeper road condition sensing system and method based on the Internet of Things, relates to the field of vehicle traffic control, and provides a basis for subsequent acquisition of image samples of obstacles by setting a total obstacle category set and an obstacle sub-category matrix, so as to obtain an accurate ConvNeXt convolutional neural network model, and improve the road condition sensing accuracy of the urban road sweeper. The method provides an accurate calculation model for the subsequent classification operation of the image data of the obstacles collected in the surrounding during the advancing process of the urban road sweeper on the urban road, and then carries out the feature extraction of the obstacles according to the classification result obtained through the classification of the image data collected in real time through the ConvNeXt convolutional neural network model. The mass and the volume of the obstacle are calculated according to the extracted fea