Data safety prediction using YOLOv7+G3HN for traffic roads

Lek Ming Lim; Lu Yang; Ahmad Sufril Azlan  Mohamed; Majid Khan Majahar Ali

doi:10.46481/jnsps.2024.2198

Authors

Lek Ming Lim
School of Mathematical Sciences, Universiti Sains Malaysia, 11800 USM Pulau Pinang, Malaysia
Yang Lu
School of Computer Sciences, Universiti Sains Malaysia, 11800 USM Pulau Pinang, Malaysia.
Ahmad Sufril Azlan Mohamed
School of Computer Sciences, Universiti Sains Malaysia, 11800 USM Pulau Pinang, Malaysia.
Majid Khan Majahar Ali
[email protected]

School of Mathematical Sciences, Universiti Sains Malaysia, 11800 USM Pulau Pinang, Malaysia.

Keywords:

Vehicle detection, Near miss detection, YOLOv7+G3HN, Machine Learning

Abstract

Pulau Pinang has introduced several measures to enhance traffic safety and promote sustainability, including the installation of CCTV systems and the implementation of smart solutions and green technology as part of the Penang 2030 vision, aligning with the Sustainable Development Goals (SDGs). However, despite these efforts, road accidents persist due to non-optimised detection models, incomplete data from manual reporting, and technological constraints in real-time video analysis and predictive modelling. This study evaluates the effectiveness of the YOLOv7+G3HN framework for vehicle detection and near-miss analysis, with a focus on the influence of video quality on detection performance. The research aims to understand how high- and low-quality video inputs affect the accuracy and computational efficiency of detection algorithms. High[1]quality videos resulted in significantly faster computation times for vehicle detection than low-quality videos, highlighting the importance of video resolution in optimising detection processes. Despite the robustness of the algorithm, with no errors detected in both video qualities, higher miss detection rates in low-quality videos suggest that lower resolution may compromise detection accuracy and the effectiveness of monitoring systems. Near-miss analysis revealed that high-quality videos had a lower probability of near-miss occurrences than low-quality videos, highlighting the importance of video resolution for detection efficacy. These findings emphasise the critical role of high-resolution video inputs in enhancing detection accuracy and reliability, advocating for their implementation to optimise vehicle detection and improve road safety. Additionally, YOLOv7+G3HN outperforms YOLOv7 in both accuracy and speed. The study concludes that the YOLOv7+G3HN framework is effective for vehicle detection and near-miss analysis, provided that video quality is considered in system design and implementation.

Dimensions

REFERENCES

A. Ajmal & I. M. Hussain, Vehicle detection using morphological image processing technique, proceedings of the 2010 International Conference on Multimedia Computing and Information Technology (MCIT), 2010 pp. 65–68. https://doi.org/10.1109/MCIT.2010.5444851.

R. A. Hadi, G. Sulong & L. E. George, “Vehicle detection and tracking techniques: a concise review”, Signal & Image Processing 5 (2014) 1. https://doi.org/10.48550/arXiv.1410.5894.

M. A. Rouf, Q. Wu, X. Yu, Y. Iwahori, H. Wu & A.Wang, “Real-time vehicle detection, tracking and counting system based on YOLOv7”, Embedded Selforganising Systems 10 (2023) 4. https://doi.org/10.14464/ess.v10i7.598.

Y. Zeng, T. Zhang, W. He & Z. Zhang, “Yolov7-uav: an unmanned aerial vehicle image object detection algorithm based on improved yolov7”, Electronics 12 (2023) 3141. https://doi.org/10.3390/electronics12143141.

H. Makizako, H. Shimada, R. Hotta, T. Doi, K. Tsutsumimoto, S. Nakakubo & K. Makino, “Associations of near-miss traffic incidents with attention and executive function among older Japanese driver”, Gerontology 64 (2018) 495. https://doi.org/10.1159/000486547.

J. A. Terum & F. Svartdal, “Lessons learned from accident and near accident experiences in traffic”, Safety Science 120 (2019) 672. https://doi.org/10.1016/j.ssci.2019.07.040.

L. M. Lim, S. Sathasivam, M. Ismail, A. Mohamed, A. Sufril, O. J. Ibidoja & M. K. M. Ali, “Comparison using intelligent systems for data prediction and near miss detection techniques”, Pertanika Journal of Science & Technology 32 (2023). https://doi.org/10.47836/pjst.32.1.20.

L. M. Lim, M. K. M. Ali, M. T. Ismail & A. S. A. Mohamed, “Data safety prediction using bird’s eye view and social distancing monitoring for penang roads”, Pertanika Journal of Science & Technology 30 (2022) 2563. http://dx.doi.org/10.47836/pjst.30.4.15.

C. Y. Wang, A. Bochkovskiy & H. Y. M. Liao, YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors, In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2023, pp. 7464–7475. https://doi.org/10.48550/arXiv.2207.02696.

G. Yasmine, G. Maha & M. Hicham, “Overview of single-stage object detection models: from Yolov1 to Yolov7”, In 2023 International Wireless Communications and Mobile Computing (IWCMC), IEEE, 2023, pp. 1579–1584. https://doi.org/10.1109/IWCMC58020.2023.10182423.

L. Yang, A. S. A. Mohamed & M. K. M. Ali, “An improved object detection and trajectory prediction method for traffic conflicts analysis”, Promet – Traffic & Transportation 35 (2023) 462. https://doi.org/10.7307/ptt.v35i4.173.

L. M. Wilcox, R. S. Allison, J. Helliker, B. Dunk & R. C. Anthony, “Evidence that viewers prefer higher frame-rate film”, ACM Transactions on Applied Perception (TAP) 12 (2015) 1. https://doi.org/10.1145/2810039.

L. M. Lim, A. F. M. Sadullah, M. Ismail, N. Awang & M. K. M. Ali, “Penang data safety prediction using database development and alternative road identification using Dijkstra approach”, In AIP Conference Proceedings 2465 (2022) 040007. https://doi.org/10.1063/5.0078252.

H. Kataoka, T. Suzuki, S. Oikawa, Y. Matsui & Y. Satoh, Drive video analysis for the detection of traffic near-miss incidents, 2018 IEEE International Conference on Robotics and Automation (ICRA), 2018, pp. 3421–3428. https://doi.org/10.1109/ICRA.2018.8460812.

P. M. Salmon, M. G. Lenne, N. A. Stanton, D. P. Jenkins & G. H. Walker, “Managing error on the open road: The contribution of human error models and methods”, Safety science 48 (2010) 1225. https://doi.org/10.1016/j.ssci.2010.04.004.

A. S. Karakaya, J. Hasenburg & D. Bermbach, “SimRa: using crowd sourcing to identify near miss hotspots in bicycle traffic”, Pervasive and Mobile Computing 67 (2020) 1. https://doi.org/10.1016/j.pmcj.2020.101197.

M. L. Siregar, H. R. Agah & F. Hidayatullah, “Near-miss accident analysis for traffic safety improvement at a ‘channelized’ junction with U-turn”, International Journal of Safety and Security Engineering 8 (2018) 31. https://doi.org/10.2495/SAFE-V8-N1-31-38.

D. Hu, S. Li & M. Wang, “Object detection in hospital facilities: a comprehensive dataset and performance evaluation”, Engineering Applications of Artificial Intelligence 123 (2023) 106223. https://doi.org/10.1016/j.engappai.2023.106223.

L. D. Quach, K. N. Quoc, A. N. Quynh & H. T. Ngoc, “Evaluating the effectiveness of YOLO models in different sized object detection and feature-based classification of small objects”, Journal of Advances in Information Technology 14 (2023) 907. https://doi.org/10.12720/jait.14.5.907-917.

K. Zhao, L. Zhao, Y. Zhao & H. Deng, “Study on lightweight model of maize seedling object detection based on YOLOv7”, Applied Sciences 13 (2023) 7731. https://doi.org/10.3390/app13137731.

Y. Rao, W. Zhao, Y. Tang, J. Zhou, S. N. Lim & J. Lu, “Hornet: Efficient high-order spatial interactions with recursive gated convolutions”, Advances in Neural Information Processing Systems 35 (2022) 10353. http://arxiv.org/abs/2207.14284.

Y. Fang, W. Wang, B. Xie, Q. Sun, L. Wu, X. Wang, T. Huang, X. Wang & Y. Cao, Eva: Exploring the limits of masked visual representation learning at scale, In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 19358–19369. https://doi.org/10.48550/arXiv.2211.07636.

Z. Chen, Y. Duan, W. Wang, J. He, T. Lu, J. Dai & Y. Qiao, Vision transformer adapter for dense predictions, In The Eleventh International Conference on Learning Representations, 2022. https://doi.org/10.48550/arXiv.2205.08534.

J. Zheng, H. Wu, H. Zhang, Z. Wang & W. Xu, “Insulator-defect detection algorithm based on improved YOLOv7”, Sensors 22 (2022) 8801. https://doi.org/10.3390/s22228801.

W. Wang, H. Bao, L. Dong, J. Bjorck, Z. Peng, Q. Liu, K. Aggarwal, O. K. Mohammed, S. Singhal, S. Som & F. Wei, Image as a foreign language: BEIT pretraining for vision and vision-language tasks, In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, pp. 19175-19186. https://doi.ieeecomputersociety.org/10.1109/CVPR52729.2023.01838.

W. Yu, C. Si, P. Zhou, M. Luo, Y. Zhou, J. Feng, S. Yan & X. Wang, “Metaformer baselines for vision”, IEEE Transactions on Pattern Analysis and Machine Intelligence 1 (2023) 1. https://doi.org/10.1109/TPAMI.2023.3329173.

Q. Hou, C. Z. Lu, M. M. Cheng & J. Feng, “Conv2former: a simple transformer-style convnet for visual recognition”, IEEE Transactions on Pattern Analysis & Machine Intelligence 01 (2022) 1. https://doi.org/10.48550/arXiv.2211.11943.

J. Chen, S. Bai, G. Wan, & Y. Li, “Research on YOLOv7-based defect detection method for automotive running lights”, Systems Science & Control Engineering 11 (2023) 2185916. https://doi.org/10.1080/21642583.2023.2185916.

B. Tu, Q. Ren, Q. Li & W. He, “Hyperspectral image classification using a superpixel-pixel-subpixel multilevel network”, IEEE Transactions on Instrumentation and Measurement 72 (2023) 3271713. https://doi.org/10.1109/TIM.2023.3271713.

X. Gong, Q. Liu, R. Fu, R. Zhou, T. Xie & X. Chen, “GAM-YOLOv7-tiny and Soft-NMS-AlexNet: improved lightweight sheep body object detection and pose estimation network”, Research Square (2024). https://doi.org/10.21203/rs.3.rs-4008441/v1.

Q. Zhu, K. Ma, Z. Wang & P. Shi, “YOLOv7-CSAW for maritime target detection”, Frontiers in neurorobotics 17 (2023) 1210470. https://doi.org/10.3389%2Ffnbot.2023.1210470.

K. Liu, Q. Sun, D. Sun, L. Peng, M. Yang & N. Wang, “Underwater target detection based on improved YOLOv7”, Journal of Marine Science and Engineering 11 (2023) 677. https://doi.org/10.3390/jmse11030677.

L. Yang, A. S. A. Mohamed & M. K. M. Ali, “Traffic conflicts analysis in penang based on improved object detection with transformer model”, IEEE Access 11 (2023) 84061. https://doi.org/10.1109/ACCESS.2023.3299316.

R. Chang, S. Zhou, Y. Zhang, N. Zhang, C. Zhou & M. Li, “Research on insulator defect detection based on improved YOLOv7 and multi-UAV cooperative system”, Coatings 13 (2023) 880. https://doi.org/10.3390/coatings13050880.

Z. Pan, J. Cai & B. Zhuang, “Fast vision transformers with hilo attention”, Advances in Neural Information Processing Systems 35 (2022) 14541. https://dl.acm.org/doi/abs/10.5555/3600270.3601327.

Z. Yang, & L. S. Pun-Cheng, “Vehicle detection in intelligent transportation systems and its applications under varying environments: a review”, Image and Vision Computing 69 (2018) 143. https://doi.org/10.1016/j.imavis.2017.09.008.

Z. Luo, F. Branchaud-Charron, C. Lemaire, J. Konrad, S. Li, A. Mishra, A. Achkar, J. Eichel & P. M. Jodoin, “MIO-TCD: A new benchmark dataset for vehicle classification and localization”, IEEE Transactions on Image Processing 27 (2018) 5129. https://doi.org/10.1109/TIP.2018.2848705.

A. Jazayeri, H. Cai, J. Y. Zheng & M. Tuceryan, “Vehicle detection and tracking in car video based on motion model”, IEEE transactions on intelligent transportation systems 12 (2011) 583. https://doi.org/10.1109/TITS.2011.2113340.

M. Ahmed, N. El-Sheimy, H. Leung, & A. Moussa, “Enhancing object detection in remote sensing: a hybrid yolov7 and transformer approach with automatic model selection”, Remote Sensing 16 (2023) 51. https://doi.org/10.3390/rs16010051.

N. F. Alhussainan, B. Ben Youssef & M. M. Ben Ismail, “A deep learning approach for brain tumor firmness detection based on five different YOLO Versions: YOLOv3–YOLOv7”, Computation 12 (2024) 44. https://doi.org/10.3390/computation12030044.

M. Ljung, Y. H. Huang, N. Åberg & E. Johansson, Close calls on the road: a study of drivers’ near-misses. Proceedings of the 3rd International Conference on Traffic and Transportation Psychology, University of Nottingham, UK, 2004. https://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-14258.

R. Suwanda, Z. Syahputra & E. M. Zamzami, “Analysis of Euclidean distance and manhattan distance in the K-means algorithm for variations number of centroid K”, Journal of Physics: Conference Series IOP Publishing 1566 (2020) 012058. https://iopscience.iop.org/article/10.1088/1742-6596/1566/1/012058/meta.

C. Ricotta & S. Pavoine, “A new parametric measure of functional dis similarity: bridging the gap between the Bray-Curtis dissimilarity and the Euclidean distance”, Ecological Modelling 466 (2022) 109880. https://doi.org/10.1016/j.ecolmodel.2022.109880.

S. S. Mahmud, L. Ferreira, M. S. Hoque & A. Tavassoli, “Application of proximal surrogate indicators for safety evaluation: A review of recent developments and research needs”, IATSS research 41 (2017) 153. https://doi.org/10.1016/j.iatssr.2017.02.001.

Q. Chen, H. Huang, Y. Li, J. Lee, K. Long, R. Gu & X. Zhai, “Modeling accident risks in different lane-changing behavioral patterns”, Analytic methods in accident research 30 (2021) 100159. https://doi.org/10.1016/j.amar.2021.100159.

T. Tang, K. Anupam, C. Kasbergenn & A. Scarpas, “Study of influence of operating parameters on braking distance”, Transportation research record 2641 (2017) 139. https://doi.org/10.3141/2641-16.

M. A. Bin Zuraimi & F. H. Kamaru Zaman, Vehicle detection and track ing using YOLO and DeepSORT, 2021 IEEE 11th IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE), 2021, pp. 23–29. https://doi.org/10.1109/iscaie51753.2021.9431784.

P. Jagannathan, S. Rajkumar, J. Frnda, B. Divakarachari & P. Subramani, “Moving vehicle detection and classification using gaussian mix ture model and ensemble deep learning technique”, Wireless Communications and Mobile Computing 2021 (2021) 5590894. https://doi.org/10.1155/2021/5590894.

A. Taheri Tajar, A. Ramazani & M. Mansoorizadeh, “A lightweight TinyYOLOv3 vehicle detection approach”, Journal of Real-Time Image Processing 18 (2021) 2389. https://doi.org/10.1007/s11554-021-01131-w.

M. Aqqa, P. Mantini & S. K. Shah, “Understanding how video quality affects object detection algorithms”, Science and Technology Publications 5 (2019) 96. https://doi.org/10.5220/0007401600960104.

K. D. Johnson, S. R. Patel, D. M. Baur, E. Edens, P. Sherry, A. Malhotra & S. N. Kales, “Association of sleep habits with accidents and Near Misses in United States Transportation Operators”, Journal of Occupational & Environmental Medicine 56 (2014) 510. https://doi.org/10.1097/JOM.0000000000000132.

S. Chikkerur, V. Sundaram, M. Reisslein, & L. J. Karam, “Objective video quality assessment methods: a classification, review, and performance comparison”, IEEE transactions on broadcasting 57 (2011) 165. https://doi.org/10.1109/TBC.2011.2104671.

V. A. Adewopo & N. Elsayed, “Smart city transportation: Deep learning ensemble approach for traffic accident detection”, IEEE Access 12 (2024) 59134. https://doi.org/10.1109/ACCESS.2024.3387972.

A. Rothblum, D. Wheal, S. Withington, S. A. Shappell, D. A. Wiegmann, W. Boehm & M. Chaderjian, Improving incident investigation through inclusion of human factors, Proceedings of the 2nd International Workshop On Human Factors In Offshore Operations ’02, Huston, Texas, 2002. https://digitalcommons.unl.edu/usdot/32/.

Y. Xu, L. Zhu, Y. Yang & F. Wu, “Training robust object detectors from noisy category labels and imprecise bounding boxes”, IEEE Transactions on Image Processing 30 (2021) 5782. https://doi.org/10.1109/TIP.2021.3085208.

P. Wang, H. Liu, X. Zhou, Z. Xue, L. Ni, Q. Han & J. Li, “Multidimensional evaluation methods for deep learning models in target detection for sar images”, Remote Sens. 16 (2024) 1097. https://doi.org/10.3390/rs16061097.

T. Diwan, G. Anirudh & J. V. Tembhurne, “Object detection using YOLO: Challenges, architectural successors, datasets and applications”, Multimedia Tools and Applications 82 (2023) 9243. https://doi.org/10.1007/s11042-022-13644-y.

G. S. Patel, A. A. Desai, Y. Y. Kamble, G. V. Pujari, P. A. Chougule & V. A. Jujare, Identification and separation of medicine through Robot using YOLO and CNN algorithms for healthcare, In International Conference on Artificial Intelligence for Innovations in Healthcare Industries (ICAIIHI), IEEE, 2023, pp. 1–5. https://doi.org/10.1109/ICAIIHI57871.2023.10489407.