Analysis of Statistical and Artificial Intelligence Algorithms for Real-Time Speed Estimation Based on Vehicle Detection with YOLO
Source abstract
Abstract
Automobiles have increased urban mobility, but traffic accidents have also increased. Therefore, road safety is a significant concern involving academics and government. Transit studies are the main supply for studying road accidents, congestion, and flow traffic, allowing the understanding of traffic flow. They require special equipment (sensors) to measure the car’s speed. With technological advances, artificial intelligence, and videos, it is possible to estimate the speed in real-time without modifying the installed urban infrastructure. We need to employ public databases that provide reliable monocular videos to generate automated traffic studies. The problem of speed estimation with a monocular camera involves synchronizing data recording, tracking, and detecting the vehicles over the road considering the lanes and distance between cars. Usually, a set of constraints are considered, such as camera calibration, flat roads, including methods based on the homography and augmented intrusion lines, patterns or regions, or prior knowledge about the actual dimensions of some of the objects. In this paper, we present a system that generates a dataset from videos recorded from a highway—obtaining 532 samples; we separated the vehicle’s detection by lane, estimating its speed. We use this data set to compare five different statistical methods and three machine learning methods to evaluate their accuracy in estimating the cars’ speed in real-time. Our vehicle estimation requires a feature extraction process using YOLOv3 and Kalman filter to detect and track vehicles. The Linear Regression Model (LRM) yielded the best results obtaining a Mean Absolute Error (MAE) of 1.694 km/h for the center lane and 0.956 km/h for the last lane. The results were compared with several state-of-the-art works, having competitive performance. Hence, LRM is fast estimating speed in real time and does not require high computational resources allowing a future hardware implementation.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Autonomous Vehicle Technology and Safety · Advanced Neural Network Applications · Traffic Prediction and Management Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Technological Institute of Culiacan, Culiacan 80014, Sinaloa, Mexico
Faculty of Civil Engineering, Conacyt-Universidad Michoacana de San Nicolás de Hidalgo, Morelia 58004, Michoacán, Mexico
Higher Technological Institute of Libres, Libres 89930, Puebla, Mexico
Funding
Consejo Nacional de Ciencia y Tecnología · National Technological Institute of Mexico
References (55)
Show source-provided references
1. Zaki, P.S., William, M.M., Soliman, B.K., Alexsan, K.G., Khalil, K., and El-Moursy, M. (2020). Traffic signs detection and recognition system using deep learning. arXiv.10.1109/ICICIS46948.2019.9014763 ↗
2. Siniestralidad vial en la frontera norte de Tamaulipas. Enfoque en los procesos administrativos de control10.21670/ref.2017.36.a01 ↗
3. Conductas de riesgo al conducir un automóvil en zonas urbanas del sur de Tamaulipas y la Ciudad de México10.29059/cienciauat.v13i2.988 ↗
4. Impedovo, D., Balducci, F., Dentamaro, V., and Pirlo, G. (2019). Vehicular traffic congestion classification by visual features and deep learning approaches: A comparison. Sensors, 19.10.3390/s19235213 ↗
5. Improved speed estimation from singleloop detectors with high truck flow10.1080/15472450.2013.801708 ↗
6. Vehicle Classification Based on Seismic Signatures Using Convolutional Neural Network10.1109/LGRS.2018.2879687 ↗
7. Intelligent vehicle counting and classification sensor for real-time traffic surveillance10.1109/TITS.2017.2741507 ↗
8. Bautista, C.M., Dy, C.A., Mañalac, M.I., Orbe, R.A., and Cordel, M. (2016, January 9–11). Convolutional neural network for vehicle detection in low resolution traffic videos. Proceedings of the 2016 IEEE Region 10 Symposium (TENSYMP), Bali, Indonesia.10.1109/TENCONSpring.2016.7519418 ↗
9. Fast Multiclass Vehicle Detection on Aerial Images10.1109/LGRS.2015.2439517 ↗
10. Portable Roadside Sensors for Vehicle Counting, Classification, and Speed Measurement10.1109/TITS.2013.2273876 ↗
11. Using LIDAR to Validate the Performance of Vehicle Classification Stations10.1080/15472450.2014.941750 ↗
12. Won, M., Zhang, S., and Son, S.H. (August, January 31). WiTraffic: Low-Cost and Non-Intrusive Traffic Monitoring System Using WiFi. Proceedings of the 2017 26th International Conference on Computer Communication and Networks (ICCCN), Vancouver, BC, Canada.10.1109/ICCCN.2017.8038380 ↗
13. Vision-based vehicle speed estimation: A survey
14. Maduro, C., Batista, K., Peixoto, P., and Batista, J. (2008, January 22–25). Estimating Vehicle Velocity Using Rectified Images. Proceedings of the VISAPP (2), Funchal, Portugal.
15. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27–30). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.91 ↗
16. Huang, X., Wang, X., Lv, W., Bai, X., Long, X., Deng, K., Dang, Q., Han, S., Liu, Q., and Hu, X. (2021). PP-YOLOv2: A practical object detector. arXiv.
17. Redmon, J., and Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv.
18. A fast accurate fine-grain object detection model based on YOLOv4 deep neural network10.1007/s00521-021-06651-x ↗
19. Yu, J., and Zhang, W. (2021). Face mask wearing detection algorithm based on improved YOLO-v4. Sensors, 21.10.3390/s21093263 ↗
20. Kumar, K.K., Chandrakant, P., Kumar, S., and Kushal, K. (2014, January 8–10). Vehicle Speed Detection Using Corner Detection. Proceedings of the 2014 Fifth International Conference on Signal and Image Processing, Bangalore, India.10.1109/ICSIP.2014.46 ↗
21. Kamoji, S., Koshti, D., Dmonte, A., George, S.J., and Sohan Pereira, C. (2020, January 26–28). Image Processing based Vehicle Identification and Speed Measurement. Proceedings of the 2020 International Conference on Inventive Computation Technologies (ICICT), Coimbatore, India.10.1109/ICICT48043.2020.9112419 ↗
22. Accurate Vehicle Speed Estimation from Monocular Camera Footage10.5194/isprs-annals-V-2-2020-419-2020 ↗
23. Single-camera vehicle speed measurement using the geometry of the imaging system10.1007/s11042-020-08761-5 ↗
24. Dahl, M., and Javadi, S. (2020). Analytical modeling for a video-based vehicle speed measurement framework. Sensors, 20.10.3390/s20010160 ↗
25. A Vision-Based Pipeline for Vehicle Counting, Speed Estimation, and Classification10.1109/TITS.2020.3004066 ↗
26. Distance and velocity estimation using optical flow from a monocular camera10.1177/1756829317695566 ↗
27. Dynamic camera calibration of roadside traffic management cameras for vehicle speed estimation10.1109/TITS.2003.821213 ↗
28. Anil Rao, Y., Kumar, N.S., Amaresh, H., and Chirag, H. (2015, January 1–4). Real-time speed estimation of vehicles from uncalibrated view-independent traffic cameras. Proceedings of the TENCON 2015-2015 IEEE Region 10 Conference, Macao.10.1109/TENCON.2015.7373162 ↗
29. Lee, K.H. (2021). A Study on Distance Measurement Module for Driving Vehicle Velocity Estimation in Multi-Lanes Using Drones. Appl. Sci., 11.10.3390/app11093884 ↗
30. Video-Based Traffic Data Collection System for Multiple Vehicle Types10.1049/iet-its.2012.0099 ↗
31. Kurniawan, A., Ramadlan, A., and Yuniarno, E.M. (2017, January 26–27). Speed Monitoring for Multiple Vehicle Using Closed Circuit Television (CCTV) Camera. Proceedings of the 2018 International Conference on Computer Engineering, Network and Intelligent Multimedia (CENIM), Surabaya, Indonesia.10.1109/CENIM.2018.8710854 ↗
32. Jalalat, M., Nejati, M., and Majidi, A. (2016, January 14–15). Vehicle detection and speed estimation using cascade classifier and sub-pixel stereo matching. Proceedings of the 2016 2nd International Conference of Signal Processing and Intelligent Systems (ICSPIS), Tehran, Iran.10.1109/ICSPIS.2016.7869890 ↗
33. Dong, H., Wen, M., and Yang, Z. (2019). Vehicle Speed Estimation Based on 3D ConvNets and Non-Local Blocks. Future Internet, 11.10.3390/fi11060123 ↗
34. Burnett, K., Samavi, S., Waslander, S.L., Barfoot, T.D., and Schoellig, A.P. (2019). aUToTrack: A Lightweight Object Detection and Tracking System for the SAE AutoDrive Challenge, University of Toronto.10.1109/CRV.2019.00036 ↗
35. Moritz Kampelmuhler, M.G.M., and Feichtenhofer, C. (2018, January 5–7). Camera-Based Vehicle Velocity Estimation from Monocular Video. Proceedings of the 23rd Computer Vision Winter Workshop, Cesky Krumlov, Czech Republic.
36. Song, Z., Luand, J., Zhang, T., and Li, H. (2020). End-to-End Learning for Inter-Vehicle Distance and Relative Velocity Estimation in ADAS with a Monocular Camera, Cornell University.10.1109/ICRA40945.2020.9197557 ↗
37. Yaqi Zhang, B.W., and Liu, W. (2017). Vehicle Motion Detection Using CNN, Stanford.
38. Loor, C. (2017). Visual Speedometer: Learning Velocity from Two Images, University of Amsterdam.
39. Fernández-Llorca, D., Salinas, C., Jimenez, M., Morcillo, A., Izquierdo, R., Lorenzo Díaz, J., and Sotelo, M.A. (2016, January 1–4). Two-camera based accurate vehicle speed measurement using average speed at a fixed point. Proceedings of the 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC), Rio de Janeiro, Brazil.10.1109/ITSC.2016.7795963 ↗
40. Vehicle Speed Measurement Based on Binocular Stereovision System10.1109/ACCESS.2019.2932120 ↗
41. Yang, L., Luo, J., Song, X., Li, M., Wen, P., and Xiong, Z. (2021). Robust Vehicle Speed Measurement Based on Feature Information Fusion for Vehicle Multi-Characteristic Detection. Entropy, 23.10.3390/e23070910 ↗
42. Yang, L., Li, Q., Song, X., Cai, W., Hou, C., and Xiong, Z. (2021). An Improved Stereo Matching Algorithm for Vehicle Speed Measurement System Based on Spatial and Temporal Image Fusion. Entropy, 23.10.3390/e23070866 ↗
43. Luvizon, D., Nassu, B., and Minetto, R. (2014, January 4–9). Vehicle speed estimation by license plate detection and tracking. Proceedings of the ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing, Florence, Italy.10.1109/ICASSP.2014.6854869 ↗
44. Gutiérrez, E., and Vladimirovna, O. (2016). Estadística Inferencial 1 para Ingeniería y Ciencias, Grupo Editorial Patria.
45. Ridge regression10.1002/wics.14 ↗
46. Bayesian lasso regression10.1093/biomet/asp047 ↗
47. Discriminative Elastic-Net Regularized Linear Regression10.1109/TIP.2017.2651396 ↗
48. Minka, T. (2022, January 30). Bayesian Linear Regression. Technical Report, Citeseer. Available online: https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.39.4002&rep=rep1&type=pdf.
49. Machine learning predictive models for mineral prospectivity: An evaluation of neural networks, random forest, regression trees and support vector machines10.1016/j.oregeorev.2015.01.001 ↗
50. Olabe, X.B. (1998). Redes Neuronales Artificiales y sus Aplicaciones, Escuela Superior de Ingeniería de Bilbao. Publicaciones de la Escuela de Ingenieros.
51. Fu, C.Y., Liu, W., Ranga, A., Tyagi, A., and Berg, A.C. (2017). DSSD: Deconvolutional Single Shot Detector. arXiv.
52. Lin, T.Y., Goyal, P., Girshick, R., He, K., and Dollar, P. (2017, January 22–29). Focal Loss for Dense Object Detection. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.324 ↗
53. Welch, G., and Bishop, G. (2022, January 30). An Introduction to the Kalman Filter. Available online: https://perso.crans.org/club-krobot/doc/kalman.pdf.
54. Kramer, O. (2016). Scikit-Learn, Springer.10.1007/978-3-319-33383-0_5 ↗
55. Dillon, J.V., Langmore, I., Tran, D., Brevdo, E., Vasudevan, S., Moore, D., Patton, B., Alemi, A., Hoffman, M., and Saurous, R.A. (2017). Tensorflow distributions. arXiv.