Traffic flow parameter estimation for complex environments based on improved YOLOv8

Abstract

Estimation of traffic flow parameters based on computer vision is still a very popular challenge. In particular, the detection problems such as occlusion, small targets, luminance variations, and lighting jitter, etc., are caused by dense traffic scenes and complex weather conditions. Previous studies about detecting and tracking methods focused on daytime and nighttime or single weather condition, but the performance of this model will decline dramatically due to complex conditions. In this paper, a framework for estimating traffic flow parameters in complex environments is presented, in which Ghost-YOLOv8 vehicle detection model is proposed. GhostConv is used to replace part of Conv and a new C2fGhost module is designed to replace part of C2f, reducing the number of parameters and improving the detection performance of the model; The global attention mechanism module is added to the neck network, which strengthens the semantic and location information in the features and improves the model’s ability of feature fusion; In view of the loss of semantic information caused by different scales in detecting small targets, a small target detection layer is added to enhance a combination of deep and shallow semantic information; The GIoU bounding loss function is used instead of the original loss function, which improves the performance of the network’s bounding box regression. Then, combining DeepSORT tracking algorithm and virtual line counting method, the proposed framework estimates traffic flow parameters, including volume, speed, and density in complex environments. The experimental results show that compared with the original model in the UA-DETRAC dataset, the improved YOLOv8 model’s the accuracy is increased by 1.4%, and the parameter number and model size are reduced by 0.229G and 0.2MB respectively. In addition, the framework has good robustness, reaching 97.56% accuracy when estimating average traffic flow parameters. It is sufficient to overcome complex weather conditions and effectively help control traffic for intelligent transportation systems and traffic management to provide good data support. In conclusion, it shows that the model can reduce the number and size of model parameters and improve the detection precision as well as meeting the requirements of edge computing devices and having better real-time performance, so it has practical application value.

Keywords

Traffic flow parameter estimation YOLOv8 traffic image analysis complex weather vehicle detection

Get full access to this article

View all access options for this article.

References

Zeng

Qian

, et al. Congestion and energy consumption of heterogeneous traffic flow mixed with intelligent connected vehicles and platoons. Phys A Stat Mech Appl 2023; 609: 128331.

Zhu

Chen

, et al. Parallel transportation systems: toward IoT-enabled smart urban traffic control and management. IEEE Trans Intell Transp Syst 2020; 21(10): 4063–4071.

Zhang

Qian

Zeng

, et al. Hybrid characteristics of heterogeneous traffic flow mixed with electric vehicles considering the amplitude of acceleration and deceleration. Phys A Stat Mech Appl 2023; 614: 128556.

Huang

Autonomous detection for traffic flow parameters of a vehicle-mounted sensing device based on symmetrical difference. Symmetry 2020; 12(1): 72.

Tang

, et al. Real-time traffic flow parameter estimation from UAV video based on ensemble classifier and optical flow. IEEE Trans Intell Transp Syst 2019; 20(1): 54–64.

Brkić

Miler

Sevrović

, et al. An analytical framework for accurate traffic flow parameter calculation from UAV aerial videos. Remote Sens (Basel) 2020; 12(22): 3844.

Liu

Chang

Hybrid cascade structure for license plate detection in large visual surveillance scenes. IEEE Trans Intell Transp Syst 2019; 20(6): 2122–2135.

Jiang

Liu

Zhu

, et al. Improved YOLO v5 with balanced feature pyramid and attention module for traffic sign detection. MATEC Web Conf 2022; 355: 03023.

Alhuthali

SAH

Zia

MYI

Rashid

. A simplified traffic flow monitoring system using computer vision techniques. In: 2nd international conference on computing and information technology (ICCIT), Tabuk, Saudi Arabia, 25–27 January 2022, pp.167–170. New York: IEEE.

10.

Thomas

Gopi

, et al. Fast approach for moving vehicle localization and bounding box estimation in highway traffic videos. Signal Image Video Process 2021; 15: 1041–1048.

11.

Bui

KHN

Cho

. A vehicle counts by class framework using distinguished regions tracking at multiple intersections. In: IEEE/CVF conference on computer vision and pattern recognition workshops (CVPRW), 2020, pp.2466–2474. New York: IEEE.

12.

, et al. Domain adaptation from daytime to nighttime: a situation-sensitive vehicle detection and traffic flow parameter estimation framework. Transp Res C Emerg Technol 2021; 124: 102946.

13.

Khazukov

Shepelev

Karpeta

, et al. Real-time monitoring of traffic parameters. J Big Data 2020; 7: 84.

14.

Zhuang

Wang

Edge-based traffic flow data collection method using onboard monocular camera. J Transp Eng A Syst 2020; 146(9): 04020096.

15.

Liu

Shao

Hoffmann

Global attention mechanism: retain information to enhance channel-spatial interactions. ArXiv 2021; abs/2112.05561, 2021.

16.

Rezatofighi

Tsoi

Gwak

, et al. Generalized intersection over union: a metric and a loss for bounding box regression. In: IEEE/CVF conference on computer vision and pattern recognition (CVPR), 2019, pp.658–666. New York: IEEE.

17.

Wen

Cai

, et al. UA-DETRAC: a new benchmark and protocol for multi-object detection and tracking. Comput Vis Image Underst 2020; 193: 102907.

18.

Agrawal

Girshick

Malik

. Analyzing the performance of multilayer neural networks for object recognition. In: European conference on computer vision, Zurich, Switzerland, 6–12 September 2014.

19.

Girshick

. Fast R-CNN. CoRR 2015; abs/1504.08083, 2015.

20.

Liu

Anguelov

Erhan

, et al. SSD: single shot multibox detector. In: Leibe

Matas

Sebe

, et al. (eds) Computer vision – ECCV 2016. Cham: Springer International Publishing, 2016, pp.21–37.

21.

Sermanet

Eigen

Zhang

, et al. Overfeat: integrated recognition, localization and detection using convolutional networks. CoRR 2013; abs/1312.6229, 2013.

22.

, et al. Improved YOLOv3 model for vehicle detection in high-resolution remote sensing images. J Appl Remote Sens 2021; 15: 026505.

23.

Tian

Lin

Zhou

, et al. SA-YOLOv3: an efficient and accurate object detector using self-attention mechanism for autonomous driving. IEEE Trans Intell Transp Syst 2022; 23(5): 4099–4110.

24.

Shen

Zhou

Liu

, et al. An anchor-free lightweight deep convolutional network for vehicle detection in aerial images. IEEE trans Intell Transp Syst 2022; 23(12): 24330–24342.

25.

Hamzenejadi

Mohseni

Fine-tuned yolov5 for real-time vehicle detection in UAV imagery: architectural improvements and performance boost. Expert Syst Appl 2023; 231: 120845.

26.

Qian

Zeng

Wang

, et al. A traffic flow model considering influence of car-following and its echo characteristics. Nonlinear Dyn 2017; 89(2): 1099–1109.

27.

Sochor

Juránek

Herout

Traffic surveillance camera calibration by 3d model bounding box alignment for accurate vehicle speed measurement. Comput Vis Image Underst 2017; 161: 87–98.

28.

Sochor

Juránek

Špaňhel

, et al. Comprehensive data set for automatic single camera visual speed measurement. IEEE trans Intell Transp Syst 2019; 20(5): 1633–1643.

29.

Biswas

Wang

, et al. An automatic traffic density estimation using single shot detection (SSD) and mobilenet-SSD. Phys Chem Earth A/B/C 2019; 110: 176–184.

30.

Zeroual

Harrou

Sun

Road traffic density estimation and congestion detection with a hybrid observer-based strategy. Sustain Cities Soc 2019; 46: 101411.

31.

Zeng

Qian

Yin

, et al. A multi-value cellular automata model for multi-lane traffic flow under Lagrange coordinate. Comput Math Organ Theory 2022; 28(2): 178–192.

32.

Nugroho

Taha

Claudel

CG.

A control-theoretic approach for scalable and robust traffic density estimation using convex optimization. IEEE Trans Intell Transp Syst 2021; 22(1): 64–78.

33.

Fedorov

Nikolskaia

Ivanov

, et al. Traffic flow estimation with data from a video surveillance camera. J Big Data 2019; 6: 73.

34.

Woo

Park

Lee

, et al. Cbam: convolutional block attention module. In: Computer vision – ECCV 2018: 15th European conference, proceedings, part VII, Munich, Germany, 8–14 September 2018, pp.3–19. Berlin, Heidelberg: Springer-Verlag.

35.

Kenk

Hassaballah

Dawn: vehicle detection in adverse weather nature dataset. ArXiv 2020; abs/2008.05402, 2020.

36.

Liu

Wang

, et al. Yolox: exceeding yolo series in 2021. ArXiv 2021; abs/2107.08430, 2021.

37.

Wang

Yang

. Multi-target pedestrian tracking based on yolov5 and deepsort. In: IEEE Asia-Pacific conference on image processing, electronics and computers (IPEC), Dalian, China, 2022, pp.508–514. New York: IEEE.

38.

Wang

Bochkovskiy

Liao

HYM

. YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada, 2023, pp. 7464–7475.

39.

Noor

Algrafi

Alharbi

, et al. A cloud-based ambulance detection system using YOLOv8 for minimizing ambulance response time. Appl Sci 2024; 14(6): 2555.