Models of the classifier of prerequisites for the occurrence of road accidents to predict dangerous situations at intersections
DOI:
https://doi.org/10.30837/2522-9818.2025.2.177Keywords:
Object classification on an image; Computer vision; Machine Learning; Artificial Intelligence; Information Technologies; Nvidia Jetson; road traffic accidents prediction; YOLO; DetectNet_v2; Detectron2.Abstract
The subject matter: this study focuses on the preconditions for the occurrence of road traffic accidents at intersections and areas with limited visibility; the use of computer vision models for classifying the preconditions of road traffic accidents and evaluating the effectiveness of their use in real-time operation. The goal of the study is to compare computer vision models for the task of classifying the preconditions of traffic accidents for real-time operation. The study involves comparing models using the Jetson TX2 platform and determining the effectiveness of this approach for generating real-time warning signals for drivers. Tasks: explore computer vision models such as Detectron2 and YOLOv7 for the task of classifying traffic accident preconditions in terms of model performance, ease of dataset creation, model training, and deployment. Compare YOLOv8 and DetectNet_v2 on a single-board computer Jetson TX2 in terms of processing speed. The methods used include training and using machine learning models, as well as simulating hazardous situations using software such as BeamNG.tech and CARLA. A comparative analysis of the application results of the models was conducted using performance evaluation metrics. The main results of the study include identifying the most effective model for classification tasks on the Jetson TX2 single-board computer – DetectNet_v2; a positive evaluation of the effectiveness of this approach for real-time driver warning, although certain limitations were noted regarding the size of the training dataset and the complexity of its preparation. Conclusions. The following computer vision algorithms were examined: Detectron2, YOLOv7, and DetectNet_v2. It was found that YOLOv7 outperforms Detectron2 in detecting the preconditions of traffic accidents in images. However, DetectNet_v2 was found to be better suited for deployment on the Jetson TX2 single-board computer compared to YOLOv7. Additionally, based on experimental findings, it was concluded that the application of this approach to predicting accident preconditions is problematic due to difficulties in creating a training dataset – specifically, the variability of precondition scenarios.
References
Список літератури
Speed Bump and Pothole Detection Using Deep Neural Network with Images Captured through ZED Camera / J.-E. Peralta-López та ін. Applied Sciences. 2023. Vol. 13, № 14. 8349 р. DOI: https://doi.org/10.3390/app13148349
Speed Bump Detection Using Accelerometric Features: A Genetic Algorithm Approach / J. Celaya-Padill. Sensors. 2018. Vol. 18, № 2. 443 р. DOI: https://doi.org/10.3390/s18020443
Eslami Nezhad S. A., Delavar M. R. An integrated network-constrained spatial analysis for car accidents: a case study of tehran city, iran. ISPRS – International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2019. XLII-4/W18. Р. 335–342. DOI: https://doi.org/10.5194/isprs-archives-xlii-4-w18-335-2019
Contributors to Wikimedia projects. Kernel density estimation – Wikipedia. Wikipedia, the free encyclopedia. URL: https://en.wikipedia.org/wiki/Kernel_density_estimation (дата звернення: 19.04.2025).
Ravindran V., Viswanathan L., Rangaswamy S. A Novel Approach to Automatic Road-Accident Detection using Machine Vision Techniques. International Journal of Advanced Computer Science and Applications. 2016. Vol. 7, № 11. DOI: https://doi.org/10.14569/ijacsa.2016.071130
Robles-Serrano S., Sanchez-Torres G., Branch-Bedoya J. Automatic Detection of Traffic Accidents from Video Using Deep Learning Techniques. Computers. 2021. Vol. 10. № 11. 148 р. DOI: https://doi.org/10.3390/computers10110148
Amirfakhrian M., Parhizkar M. Integration of image segmentation and fuzzy theory to improve the accuracy of damage detection areas in traffic accidents. Journal of Big Data. 2021. Vol. 8, № 1. DOI: https://doi.org/10.1186/s40537-021-00539-2
Zimmermann H. J. Fuzzy set theory. Wiley Interdisciplinary Reviews: Computational Statistics. 2010. Vol. 2, № 3. Р. 317–332. DOI: https://doi.org/10.1002/wics.82
An Automatic Car Accident Detection Method Based on Cooperative Vehicle Infrastructure Systems / D. Tian та ін. IEEE Access. 2019. Vol.7. Р. 127453–127463. DOI: https://doi.org/10.1109/access.2019.2939532
Wang S. Traffic Accident Prediction based on CNN and Time of Commuting after Accident. Highlights in Science, Engineering and Technology. 2024. Vol. 118. Р. 65–71. DOI: https://doi.org/10.54097/5t9mba88
Suzen A. A., Duman B., Sen B. Benchmark Analysis of Jetson TX2, Jetson Nano and Raspberry PI using Deep-CNN. 2020 International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA), Ankara, Turkey, 2020 р. 2020. DOI: https://doi.org/10.1109/hora49412.2020.9152915
Detection, instance segmentation, and classification for astronomical surveys with deep learning (DeepDISC): Detectron2 implementation and demonstration with hyper suprime-cam data / G. Merz та ін. Monthly Notices of the Royal Astronomical Society. 2023. DOI: https://doi.org/10.1093/mnras/stad2785
Wang C.-Y., Bochkovskiy A., Mark Liao H.-Y. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. Computer Vision and Pattern Recognition. 2022. DOI: https://doi.org/10.48550/arxiv.2207.02696
BeamNG.tech Contributors. BeamNG.tech. BeamNG.tech. URL: https://beamng.tech/ (дата звернення: 25.02.2025).
Comparison of potential road accident detection algorithms for modern machine vision system / O. Byzkrovnyi та ін. Environment. technologies. resources. Proceedings of the International Scientific and Practical Conference. 2023. Vol. 3. Р. 50–55. DOI: https://doi.org/10.17770/etr2023vol3.7299
Comparison of Object Detection Algorithms for the Task of Person Detection on Jetson TX2 NX Platform / O. Byzkrovnyi та ін. 2024 IEEE Open Conference of Electrical, Electronic and Information Sciences (eStream), Vilnius, Lithuania, 2024 р. 2024. DOI: https://doi.org/10.1109/estream61684.2024.10542592
References
Peralta-López, J., Morales-Viscaya, J., Lázaro-Mata, D., Villaseñor-Aguilar, M., Prado-Olivarez, J., Pérez-Pinal, F., Gutiérrez, A. (2023), "Speed bump and pothole detection using deep neural network with images captured through zed camera". Applied Sciences, № 13(14), 8349 р. DOI: https://doi.org/10.3390/app13148349
Celaya-Padilla, J. M., Galván-Tejada, C. E., López-Monteagudo, F. E., Alonso-González, O., Moreno-Báez, A., Martínez‐Torteya, A., Gamboa-Rosales, H. (2018), "Speed bump detection using accelerometric features: a genetic algorithm approach". Sensors, № 18(2), 443 р. DOI: https://doi.org/10.3390/s18020443
Eslaminezhad, S. A. and Delavar, M. R. (2019), "An integrated network-constrained spatial analysis for car accidents: a case study of tehran city, iran". The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLII-4/W18, Р. 335–342. DOI: https://doi.org/10.5194/isprs-archives-xlii-4-w18-335-2019
Contributors to Wikimedia projects, (2005), "Kernel density estimation – Wikipedia. Wikipedia, the free encyclopedia", available at: https://en.wikipedia.org/wiki/Kernel_density_estimation (last accessed 25.02.2025)
Ravindran, V., Viswanathan, L., & Rangaswamy, S. (2016), "A novel approach to automatic road-accident detection using machine vision techniques". International Journal of Advanced Computer Science and Applications, №7(11). DOI: https://doi.org/10.14569/ijacsa.2016.071130
Robles-Serrano, S., Torres, G. S., & Branch, J. W. (2021), "Automatic detection of traffic accidents from video using deep learning techniques". Computers, №10(11), 148 р. DOI: https://doi.org/10.3390/computers10110148
Amirfakhrian, M. and Parhizkar, M. (2021), "Іntegration of image segmentation and fuzzy theory to improve the accuracy of damage detection areas in traffic accidents". Journal of Big Data, №8(1). DOI: https://doi.org/10.1186/s40537-021-00539-2
Zimmermann, H. (2010), "Fuzzy set theory". WIREs Computational Statistics, №2(3), Р. 317–332. DOI: https://doi.org/10.1002/wics.82
Tian, D., Zhang, C., Duan, X., & Wang, X. (2019), "An automatic car accident detection method based on cooperative vehicle infrastructure systems". IEEE Access, № 7, Р. 127453-127463. DOI: https://doi.org/10.1109/access.2019.2939532
Wang, S. (2024), "Traffic accident prediction based on cnn and time of commuting after accident". Highlights in Science, Engineering and Technology, №118, Р. 65–71. DOI: https://doi.org/10.54097/5t9mba88
Süzen, A. A., Duman, B., & Şen, B. (2020). "Benchmark analysis of jetson tx2, jetson nano and raspberry pi using deep-cnn". 2020 International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA), № 1-5. DOI: https://doi.org/10.1109/hora49412.2020.9152915
Merz, G., Liu, Y., Burke, C. J., Aleo, P., Liu, X., Kind, M. C., Liu, Y. (2023), "Detection, instance segmentation, and classification for astronomical surveys with deep learning (deepdisc): detectron2 implementation and demonstration with hyper suprime-cam data". Monthly Notices of the Royal Astronomical Society, № 526(1), Р. 1122–1137. DOI: https://doi.org/10.1093/mnras/stad2785
Wang, C., Bochkovskiy, A., & Liao, H. M. (2022), "Yolov7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors". Computer Vision and Pattern Recognition. DOI: https://doi.org/10.48550/arxiv.2207.02696
"BeamNG.tech Contributors, BeamNG.tech". 2023. available at: https://beamng.tech/ (last accessed: 25.02.2025)
Byzkrovnyi, O., Smelyakov, K., Chupryna, A., Savulionienė, L., & Sakalys, P. (2023), "Comparison of potential road accident detection algorithms for modern machine vision system". Environment. technologies. resources. Proceedings of the International Scientific and Practical Conference, №3, Р. 50–55. DOI: https://doi.org/10.17770/etr2023vol3.7299
Byzkrovnyi, O., Smelyakov, K., Chupryna, A., & Lanovyy, O. (2024), "Comparison of object detection algorithms for the task of person detection on jetson tx2 nx platform". IEEE Open Conference of Electrical, Electronic and Information Sciences (eStream). DOI: https://doi.org/10.1109/estream61684.2024.10542592
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Our journal abides by the Creative Commons copyright rights and permissions for open access journals.
Authors who publish with this journal agree to the following terms:
Authors hold the copyright without restrictions and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (CC BY-NC-SA 4.0) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-commercial and non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
Authors are permitted and encouraged to post their published work online (e.g., in institutional repositories or on their website) as it can lead to productive exchanges, as well as earlier and greater citation of published work.
