High-Performance Multi-Object Tracking for Autonomous Driving in Urban Scenarios With Heterogeneous Embedded Boards
Autonomous Driving is emerging as a paradigm shift in the way we conceive people and goods transportation. It promises to improve road safety, reduce traffic congestion, and increase overall transportation efficiency. It is made possible by a plethora of modern technologies, such as AI, low-power ha...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10723301/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592868730994688 |
|---|---|
| author | Alessio Medaglini Biagio Peccerillo Sandro Bartolini |
| author_facet | Alessio Medaglini Biagio Peccerillo Sandro Bartolini |
| author_sort | Alessio Medaglini |
| collection | DOAJ |
| description | Autonomous Driving is emerging as a paradigm shift in the way we conceive people and goods transportation. It promises to improve road safety, reduce traffic congestion, and increase overall transportation efficiency. It is made possible by a plethora of modern technologies, such as AI, low-power hardware, and complex computing. Common stages of Autonomous Driving systems are the identification of objects in the scene (Object Detection), and the ability to predict the evolution of the tracked objects’ states – usually, positions and velocities (Multi-Object Tracking). In this paper, we address the issues behind high-performance Multi-Object Tracking (MOT) algorithms for a real-world urban transportation scenario. The main objective is to exploit the high-performance capabilities of NVIDIA heterogeneous embedded platforms, which are not automatically compatible with the peculiar features of these algorithms. We propose and discuss some non-trivial software design choices and implementation strategies that are needed to match the specific computational and memory access needs of MOT strategies, and the architectural opportunities of NVIDIA embedded GPGPU systems. Our code is made available as open-source. We compare our solution against a highly optimized multi-core version and show that we are able to trigger significant performance speedups (up to <inline-formula> <tex-math notation="LaTeX">$7.19\times $ </tex-math></inline-formula>) in all power-modes, sometimes even surpassing the CPU reference with the GPU in a lower-power operating mode. |
| format | Article |
| id | doaj-art-7f0bd2bf343e41b4b513cea9a971511d |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-7f0bd2bf343e41b4b513cea9a971511d2025-01-21T00:02:18ZengIEEEIEEE Access2169-35362025-01-01138649866310.1109/ACCESS.2024.348412910723301High-Performance Multi-Object Tracking for Autonomous Driving in Urban Scenarios With Heterogeneous Embedded BoardsAlessio Medaglini0https://orcid.org/0000-0002-7572-6733Biagio Peccerillo1https://orcid.org/0000-0002-4998-0092Sandro Bartolini2https://orcid.org/0000-0002-7975-3632Department of Information Engineering and Mathematics, University of Siena, Siena, ItalyDepartment of Information Engineering and Mathematics, University of Siena, Siena, ItalyDepartment of Information Engineering and Mathematics, University of Siena, Siena, ItalyAutonomous Driving is emerging as a paradigm shift in the way we conceive people and goods transportation. It promises to improve road safety, reduce traffic congestion, and increase overall transportation efficiency. It is made possible by a plethora of modern technologies, such as AI, low-power hardware, and complex computing. Common stages of Autonomous Driving systems are the identification of objects in the scene (Object Detection), and the ability to predict the evolution of the tracked objects’ states – usually, positions and velocities (Multi-Object Tracking). In this paper, we address the issues behind high-performance Multi-Object Tracking (MOT) algorithms for a real-world urban transportation scenario. The main objective is to exploit the high-performance capabilities of NVIDIA heterogeneous embedded platforms, which are not automatically compatible with the peculiar features of these algorithms. We propose and discuss some non-trivial software design choices and implementation strategies that are needed to match the specific computational and memory access needs of MOT strategies, and the architectural opportunities of NVIDIA embedded GPGPU systems. Our code is made available as open-source. We compare our solution against a highly optimized multi-core version and show that we are able to trigger significant performance speedups (up to <inline-formula> <tex-math notation="LaTeX">$7.19\times $ </tex-math></inline-formula>) in all power-modes, sometimes even surpassing the CPU reference with the GPU in a lower-power operating mode.https://ieeexplore.ieee.org/document/10723301/Autonomous drivingcyber-physical systemCUDAheterogeneous boardKalman filtermulti-object tracking |
| spellingShingle | Alessio Medaglini Biagio Peccerillo Sandro Bartolini High-Performance Multi-Object Tracking for Autonomous Driving in Urban Scenarios With Heterogeneous Embedded Boards IEEE Access Autonomous driving cyber-physical system CUDA heterogeneous board Kalman filter multi-object tracking |
| title | High-Performance Multi-Object Tracking for Autonomous Driving in Urban Scenarios With Heterogeneous Embedded Boards |
| title_full | High-Performance Multi-Object Tracking for Autonomous Driving in Urban Scenarios With Heterogeneous Embedded Boards |
| title_fullStr | High-Performance Multi-Object Tracking for Autonomous Driving in Urban Scenarios With Heterogeneous Embedded Boards |
| title_full_unstemmed | High-Performance Multi-Object Tracking for Autonomous Driving in Urban Scenarios With Heterogeneous Embedded Boards |
| title_short | High-Performance Multi-Object Tracking for Autonomous Driving in Urban Scenarios With Heterogeneous Embedded Boards |
| title_sort | high performance multi object tracking for autonomous driving in urban scenarios with heterogeneous embedded boards |
| topic | Autonomous driving cyber-physical system CUDA heterogeneous board Kalman filter multi-object tracking |
| url | https://ieeexplore.ieee.org/document/10723301/ |
| work_keys_str_mv | AT alessiomedaglini highperformancemultiobjecttrackingforautonomousdrivinginurbanscenarioswithheterogeneousembeddedboards AT biagiopeccerillo highperformancemultiobjecttrackingforautonomousdrivinginurbanscenarioswithheterogeneousembeddedboards AT sandrobartolini highperformancemultiobjecttrackingforautonomousdrivinginurbanscenarioswithheterogeneousembeddedboards |