This paper focuses on road surface real-time detection by using tripod dolly equipped with Raspberry Pi 3 B+, MPU 9250, which is convenient to collect road surface data and realize real-time road surface detection. Firstly, six kinds of road surfaces data are collected by utilizing Raspberry Pi 3 B+ and MPU 9250. Secondly, the classifiers can be obtained by adopting several machine learning algorithms, recurrent neural networks (RNN) and long short-term memory (LSTM) neural networks. Among the machine learning classifiers, gradient boosting decision tree has the highest accuracy rate of 97.92%, which improves by 29.52% compared with KNN with the lowest accuracy rate of 75.60%. The accuracy rate of LSTM neural networks is 95.31%, which improves by 2.79% compared with RNN with the accuracy rate of 92.52%. Finally, the classifiers are embedded into the Raspberry Pi to detect the road surface in real time, and the detection time is about one second. This road surface detection system could be used in wheeled robot-car and guiding the robot-car to move smoothly.
AalizadehB (2019) Comparison of neural network and neurofuzzy identification of vehicle handling under uncertainties. Transactions of the Institute of Measurement and Control41(15): 4230–4239.
2.
AlqudahYASababhaBH (2017) On the analysis of road surface conditions using embedded smartphone sensors. In: The 8th International Conference on Information and Communication Systems (ICICS), Irbid, Jordan, 4–6 April, pp. 177–181.
3.
AlvarezJMLopezAMGeversT, et al. (2014) Combining priors, appearance, and context for road detection. IEEE Transactions on Intelligent Transportation Systems15(3): 1168–1178.
4.
AmbrožM (2017) Raspberry Pi as a low-cost data acquisition system for human powered vehicles. Measurement100(3): 7–18.
AnwaarWShahMA (2015) Energy efficient computing: A comparison of Raspberry Pi with modern devices. Energy4(2): 410–413.
7.
BrockJDBruceRFCameronME (2013) Changing the world with a Raspberry Pi. Journal of Computing Sciences in Colleges29(2): 151–153.
8.
BystrovAHoareETranTYClarkeN, et al. (2016) Road surface classification using automotive ultrasonic sensor. Procedia Engineering168: 19–22.
9.
CarrTAJenkinsMDIglesiasMI, et al. (2018) Road crack detection using a single stage detector based deep neural network. In: IEEE Workshop on Environmental, Energy, and Structural Monitoring Systems (EESMS), Salerno, Italy, 21–22 June, pp. 1–5.
10.
ChenFCJahanshahiMR (2018) Nb-cnn: deep learning-based crack detection using convolutional neural network and naive bayes data fusion. IEEE Transactions on Industrial Electronics65(5): 4392–4400.
11.
ElsheikhAYacoutSOualiMS (2019) Bidirectional handshaking lstm for remaining useful life prediction. Neurocomputing323(1): 148–156.
12.
El-SheimyNHouHNiuX (2008) Analysis and modeling of inertial sensors using Allan variance. IEEE Transactions on Instrumentation and Measurement57(1): 140–149.
13.
FanRAiXDahnounN (2018) Road surface 3d reconstruction based on dense subpixel disparity map estimation. IEEE Transactions on Image Processing27(6): 3025–3035.
14.
FischerTKraussC (2018) Deep learning with long shortterm memory networks for financial market predictions. European Journal of Operational Research270(2): 654–669.
15.
FletcherJMalalasekeraW (2016) Development of a userfriendly, low-cost home energy monitoring and recording system. Energy111(9): 32–46.
16.
GómezACuiñasDCatalaP, et al. (2015) Use of single board computers as smart sensors in the manufacturing industry. Procedia engineering132: 153–159.
17.
GravesAMohamedARHintonG (2013) Speech recognition with deep recurrent neural networks. In: International Conference on Acoustics, Speech and Signal Processing (ICASSP), Vancouver, BC, Canada, 26–31 May, pp. 6645–6649.
18.
HanTJiangDZhaoQ, et al. (2018) Comparison of random forest, artificial neural networks and support vector machine for intelligent diagnosis of rotating machinery. Transactions of the Institute of Measurement and Control40(8): 2681–2693.
19.
HochreiterSSchmidhuberJ (1997) Long short-term memory. Neural Computation9(8): 1735–1780.
20.
JiangXHPangYWLiXL, et al. (2018) Deep neural networks with elastic rectified linear units for object recognition. Neurocomputing275(1): 1132–1139.
21.
LecceseFCagnettiMTrincaD (2014) A smart city application: A fully controlled street lighting isle based on Raspberry-Pi card, a ZigBee sensor network and WiMAX. Sensors14(12): 24408–24424.
22.
LewisAJCampbellMStavroulakisP (2016) Performance evaluation of a cheap, open source, digital environmental monitor based on the Raspberry Pi. Measurement87(7): 228–235.
23.
LiuJShahroudyAXuD, et al. (2018) Skeleton-based action recognition using spatio-temporal LST)M network with trust gates. IEEE Transactions on Pattern Analysis and Machine Intelligence40(12): 3007–3021.
24.
MaXLTaoZMWangYH, et al. (2015) Long short-term memory neural network for traffic speed prediction using remote microwave sensor data. Transportation Research Part C: Emerging Technologies54: 187–197.
25.
MaoMDuanQDuanP, et al. (2018) Comprehensive improvement of artificial fish swarm algorithm for global MPPT in PV system under partial shading conditions. Transactions of the Institute of Measurement and Control40(7): 2178–2199.
26.
MilanARezatofighiSHDickAR, et al. (2017) Online multi-target tracking using recurrent neural networks. In: The 31st AAAI Conference on Artificial Intelligence (AAAI), San Francisco, California, USA, 4–9 February, pp. 4225–4232.
27.
NgJRWongJSGohVT, et al. (2018) Identification of road surface conditions using IoT sensors and machine learning. In: The 5th International Conference on Computational Science and Technology (ICCST), Kota Kinabalu, Malaysia, 29–30 August, pp. 259–268.
28.
NolteMKisterNMaurerM (2018) Assessment of deep convolutional neural networks for road surface classification. In: The 21st International Conference on Intelligent Transportation Systems (ITSC), Maui, HI, USA, 4–7 November, pp. 381–386.
29.
NomuraTShiraishiY (2015) A method for estimating road surface conditions with a smartphone. International Journal of Informatics Society7(1): 29–36.
30.
RajAKrishnaDPriyaRShantanuKDeviS (2012) Vision based road surface detection for automotive systems. In: 2012 International Conference on Applied Electronics, Pilsen, Czech Republic, 5–7 September, pp. 223–228.
31.
RatekeTJustenKWangenheimA (2019) Road surface classification with images captured from low-cost camera-road traversing knowledge (RTK) dataset. Revista De Informática Teórica E Aplicada26(3): 50–64.
32.
SuJCoombesMLiuC, et al. (2020) Machine learning based crop drought mapping system by UAV remote sensing RGB imagery. Unmanned Systems8(1): 71–83.
33.
SimonciniMTaccariLSamboF, et al. (2018) Vehicle classification from lowfrequency gps data with recurrent neural networks. Transportation Research Part C: Emerging Technologies91(7): 176–191.
34.
ShaoHYiZChenZ, et al (2020) Application of artificial neural networks for prediction of sinter quality based on process parameters control. Transactions of the Institute of Measurement and Control42(3): 422–429.
35.
VujovićVMaksimovićM (2015) Raspberry Pi as a Sensor Web node for home automation. Computers and Electrical Engineering44(5): 153–171.
36.
WangJYZhangHGWangZS, et al. (2017) Finite-time synchronization of coupled hierarchical hybrid neural networks with time-varying delays. IEEE Transactions on Cybernetics47(10): 2995–3004.
37.
XuCCJiJYLiuP (2018) The station-free sharing bike demand forecasting with a deep learning approach and large-scale datasets. Transportation Research Part C: Emerging Technologies95(10): 47–60.
38.
YiDSuJLiuC, et al. (2019) A machine learning based personalized system for driving state recognition. Transportation Research Part C: Emerging Technologies105(8): 241–261.
39.
ZhangLYangFZhangYD, et al. (2016) Road crack detection using deep convolutional neural network. In: International Conference on Image Processing (ICIP), Phoenix, AZ, USA, 25–28 September, pp. 3708–3712.
40.
ZhaoZChenWHWuXM, et al. (2017) LSTM network: A deep learning approach for short-term traffic forecast. IET Intelligent Transport Systems11(2): 68–75.
