Smart City Gnosys
Smart city article details
| Title | Performance Evaluation Of Deep Learning Models On Embedded Platform For Edge Ai-Based Real Time Traffic Tracking And Detecting Applications |
|---|---|
| ID_Doc | 41750 |
| Authors | Minh H.T.; Mai L.; Minh T.V. |
| Year | 2021 |
| Published | Proceedings - 2021 15th International Conference on Advanced Computing and Applications, ACOMP 2021 |
| DOI | http://dx.doi.org/10.1109/ACOMP53746.2021.00024 |
| Abstract | Edge Artificial Intelligence based traffic tracking and detecting sensors are very essential for smart cities, especially for smart transportation applications. These sensors are not only used to collect large amount of traffic data, but also reduce the bandwidth of the communication network to transfer and reduce the workload to process huge data on the cloud or server side. It is very necessary to process, store, and extract useful data at the edge of the Internet before transferring the data to central server which can be called Artificial Intelligence on The Edge. This research aims at studying, implementing and evaluating machine learning models which are suitable for running on limited computing embedded computers. Computer vision and real-time object detection techniques are applied on Nvidia Jetson Nano Embedded Computer to build an Edge-AI based traffic tracking and detecting sensor, two popular models (MobileNet-SSD and YOLOv4) have been studied and implemented to compare the performance on vehicle counting and license plate detection applications. There has been a new propose method to apply TensorRT engine for these two models to increase the processing speed. The data source used in this project is manually collected at actual traffic routes and parking lots in Vietnam with more than 11700 images of Vietnamese vehicles and license plates then trained on Google Colab. The performance evaluation results show that both models have high accuracy in real-time license plate detection and vehicle counting application when implemented on the Edge computer Jetson Nano with the mAPs of both model are higher than 90 percent during training session. The MobileNet-SSD model has good speed (40 FPS) which is very much faster than some previous works (25 FPS), this model is suitable for real-time applications. The YOLOv4 model, after being optimized by TensorRT engine, has a better speed (7.2 FPS) than the original version (1.7 FPS), although the YOLOv4 model has low speed than MobileNet-SSD model but can detect smaller size, this model is suitable for some applications that need to detect complicated objects with small sizes. © 2021 IEEE. |
| Author Keywords | Edge-AI; Jetson Nano; License Plate; MobileNet-SSD; Real-time Object Detection; TensorRT; YOLOv4 |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
41774  | 0.912 | Bulut A.; Ozdemir F.; Bostanci Y.S.; Soyturk M. | Performance Evaluation Of Recent Object Detection Models For Traffic Safety Applications On Edge | ACM International Conference Proceeding Series (2023) |
| 50560 | 0.878 | 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) |
| 24693 | 0.865 | Kocejko T.; Neumann T.; Mazur-Milecka M.; Kowalczyk N.; Ruminski J.; Jo K.-H.; Kaszynski M.; Ludwisiak T. | Evaluating The Use Of Edge Devices For Detection And Tracking Of Vehicles In Smart City Environment | 2024 International Workshop on Intelligent Systems, IWIS 2024 (2024) |
| 21807 | 0.865 | Skadins A.; Ivanovs M.; Rava R.; Nesenbergs K. | Edge Pre-Processing Of Traffic Surveillance Video For Bandwidth And Privacy Optimization In Smart Cities | Proceedings of the Biennial Baltic Electronics Conference, BEC, 2020-October (2020) |
| 6033 | 0.865 | 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) |
| 5789 | 0.864 | Ranka S.; Rangarajan A.; Elefteriadou L.; Srinivasan S.; Poasadas E.; Hoffman D.; Ponnulari R.; Dilmore J.; Byron T. | A Vision Of Smart Traffic Infrastructure For Traditional, Connected, And Autonomous Vehicles | Proceedings - 2020 International Conference on Connected and Autonomous Driving, MetroCAD 2020 (2020) |
| 44470 | 0.861 | Saklani S.; Manchanda M.; Sharma R.; Singh D. | Real-Time Traffic Management System Using Yolov8 And Cnn: A Deep Learning Approach With Iot Integration | 1st International Conference on Advances in Computer Science, Electrical, Electronics, and Communication Technologies, CE2CT 2025 (2025) |
| 16287 | 0.861 | Yang S.; Bailey E.; Yang Z.; Ostrometzky J.; Zussman G.; Seskar I.; Kostic Z. | Cosmos Smart Intersection: Edge Compute And Communications For Bird'S Eye Object Tracking | 2020 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2020 (2020) |
| 21836 | 0.86 | Barthélemy, J; Verstaevel, N; Forehead, H; Perez, P | Edge-Computing Video Analytics For Real-Time Traffic Monitoring In A Smart City | SENSORS, 19, 9 (2019) |
| 604 | 0.86 | Azmi N.; Kamarudin L.M.; Ali Yeon A.S.; Zakaria A.; Syed Zakaria S.M.M.; Visvanathan R.; Elham Alhim M.F.; Mao X.; Abdurrahman Zuhair M.S.; Chung W.-Y. | A Case Study: Deployment Of Real-Time Smart City Monitoring Using Yolov7 In Selangor Cyber Valley | Journal of Ambient Intelligence and Humanized Computing, 15, 12 (2024) |