Identification of adhesion coefficient ahead based on image feature and HMM
1. Automotive Engineering Research Institute, Jiangsu University, Zhenjiang， Jiangsu 212013, China； 2. Department of Computer and Information Science, University of MichiganDearborn, Dearborn， Michigan MI 48128, USA
Abstract：To identify the road adhesion coefficient ahead, the grayscale co-occurrence matrix and HSV color space were used to extract the seven texture feature parameters of typical road images. Based on the similarity characteristics, the Burckhardt μ-s model was improved, and a realtime estimation algorithm of the current road peak adhesion coefficient was proposed. The effectiveness and realtime performance were verified by Carsim and Simulink cosimulation. A roadtire adhesion characteristic model was established based on hidden Markov model(HMM), and the correctness of the model was verified. The HMM model algorithm was verified through real vehicle experiments. The results show that the recognition rate of HMM model is more than 90% for the roadtire adhesion coefficient ahead, and the proposed model can be used in the automatic emergency braking module of smart cars. The vehicle can brake in advance under the front harsh road environment, which effectively shortens the braking distance.
WANG Y, LIANG G Q, WEI Y T.Road identification algorithm of intelligent tire based on support vector[J]. Automotive Engineering,2020,42(12): 1671-1678，1717. (in Chinese)
[2]
MUKHERJEE A K, KULKARNI S G, CHAKRAVARTY S N. Evaluation of adhesion characteristics of nylon6 tire cord to natural rubber[J]. Journal of Applied Polymer Science, 1987, 34(3):913-918.
[3]
PATRA N, DATTA K. Observer based roadtire friction estimation for slip control of braking system[J]. Procedia Engineering, 2012, 38:1566-1574.
CHEN W W, LIU X Y, HUANG H, et al. An algorithm for estimating road adhesion coefficient in vehicle steering condition[J]. Automotive Engineering, 2011, 33(6):521-526. (in Chinese)
[5]
MINULLIN R G, MUSTAFIN R G, PISKOVATSKII Y V, et al. A detection technique for black ice and frost depositions on wires of a power transmission line by location sounding[J]. Russian Electrical Engineering, 2011, 82(10):541-543.
[6]
WANG C Q, ZHANG J, WANG W R, et al. The research on locating license plate of vehicle based on color conversion and projection[J]. Advanced Materials Research, 2013, 655:769-772.
ZHANG H X, LU Y J, ZHANG J N. Vehicle state and road surface adhesion coefficient estimation based on nonlinear model[J]. Journal of Shijiazhuang Tiedao University(Natural Science Edition),2020, 33(1):49-58. (in Chinese)
LIU Z Q, YANG P P, NI J，et al. Recognition method of driving intention for driving training with driving simulators[J]. Journal of Chongqing University of Technology (Natural Science), 2014,28(10):1-7. (in Chinese)
