Smart City Gnosys

Smart city article details

Title	Vehicle Detection And Classification Using An Ensemble Of Efficientdet And Yolov8
ID_Doc	60903
Authors	Lv C.; Mittal U.; Madaan V.; Agrawal P.
Year	2024
Published	PeerJ Computer Science, 10
DOI	http://dx.doi.org/10.7717/PEERJ-CS.2233
Abstract	With the rapid increase in vehicle numbers, efficient traffic management has become a critical challenge for society. Traditional methods of vehicle detection and classification often struggle with the diverse characteristics of vehicles, such as varying shapes, colors, edges, shadows, and textures. To address this, we proposed an innovative ensemble method that combines two state-of-the-art deep learning models i.e., EfficientDet and YOLOv8. The proposed work leverages data from the Forward-Looking Infrared (FLIR) dataset, which provides both thermal and RGB images. To enhance the model performance and to address the class imbalances, we applied several data augmentation techniques. Experimental results demonstrate that the proposed ensemble model achieves a mean average precision (mAP) of 95.5% on thermal images, outperforming the individual performances of EfficientDet and YOLOv8, which achieved mAPs of 92.6% and 89.4% respectively. Additionally, the ensemble model attained an average recall (AR) of 0.93 and an optimal localization recall precision (oLRP) of 0.08 on thermal images. For RGB images, the ensemble model achieved mAP of 93.1%, AR of 0.91, and oLRP of 0.10, consistently surpassing the performance of its constituent models. These findings highlight the effectiveness of proposed ensemble approach in improving vehicle detection and classification. The integration of thermal imaging further enhances detection capabilities under various lighting conditions, making the system robust for real-world applications in intelligent traffic management. Copyright 2024 Lv et al.
Author Keywords	Computer vision; Deep learning; Intelligent traffic management; Intelligent transport; Object detection; Smart city; Sustainable infrastructure; Sustainable transport; Thermal imaging; Vehicle detection

Similar Articles

Id	Similarity	Authors	Title	Published
23693	0.875	Agrawal A.; Shukla C.; Shukla P.	Enhanced Vehicle Detection And Counting Using Yolov8 With Augmented Data And Optimized Object Grouping	Lecture Notes in Networks and Systems, 1278 (2025)
62129	0.872	Deepthi shree A.M.; Brindha M.	Yolov8 For Robust Traffic Object Instance Segmentation Using Image Quality Assessment	Procedia Computer Science, 260 (2025)
23647	0.867	Bhonde T.; Temare H.; Dadwhal Y.S.	Enhanced Object Detection Using Yolov8: Identifying Vehicles And Pedestrians In Urban Environments	2024 IEEE Pune Section International Conference, PuneCon 2024 (2024)
50560	0.861	Baiat Z.E.; Baydere S.	Smart City Traffic Monitoring:Yolov7 Transfer Learning Approach For Real-Time Vehicle Detection	2023 International Conference on Smart Applications, Communications and Networking, SmartNets 2023 (2023)
43780	0.856	Tahir N.U.A.; Zhang Z.; Asim M.; Iftikhar S.; A. Abd El-Latif A.	Pvdm-Yolov8L: A Solution For Reliable Pedestrian And Vehicle Detection In Autonomous Vehicles Under Adverse Weather Conditions	Multimedia Tools and Applications, 84, 23 (2025)
60904	0.853	Shihabudeen H.; Rajeesh J.	Vehicle Detection And Classification Using Yolov5 On Fused Infrared And Visible Images	6th International Conference on Inventive Computation Technologies, ICICT 2023 - Proceedings (2023)
17940	0.853	Amir M.; Haque A.; Zaheeruddin	Deep Learning-Based Autonomous Vehicle To Vehicle Detection For Smart Traffic Monitoring In Smart Cities	Smart Cities: Power Electronics, Renewable Energy, and Internet of Things (2024)
6033	0.852	Islam J.; Islam M.T.; Golam Rashed M.; Das D.	Accurate Vehicles Detection And Speed Estimation Using Homography Based Background Subtraction And Deep Learning Approaches	2023 26th International Conference on Computer and Information Technology, ICCIT 2023 (2023)