The current research direction of active suspension is primarily focused on the design of feedback control based on pavement information, whilst research effort in actively detecting driving pavement information is rarely put in. Good pavement information recognition system is especially important for the development of suspension technology. This text adopts the binocular vision system to obtain the road two-dimensional image. Firstly, the Semi-Global Block Matching(SGBM)is used for stereo matching and three-dimensional reconstruction. Secondly, the “cleansing” algorithm is then used to remove the erroneous data points in the road vertical contour model. Finally, Multi-class support vector machines (SVM) are trained by using road feature data sets. Vector machine. The research results show that the road two-bit image acquired by the binocular vision system can provide the road surface feature basis for the control of the active suspension system and classification model of road feature data set training can also extract useful information from road images and classify them correctly.
Research on Classification of Vehicle Driving
Pavement Characteristics Based on Intelligent Perception
Lect. Notes Electrical Eng.
2020-11-05
18 pages
Article/Chapter (Book)
Electronic Resource
English
Research on Classification of Vehicle Driving
TIBKAT | 2021
|Research on Classification of Vehicle Driving
British Library Conference Proceedings | 2021
|MODEL HYPERPARAMETER ADJUSTMENT USING VEHICLE DRIVING CONTEXT CLASSIFICATION
European Patent Office | 2023
|