Real-Time Semantic Segmentation of Aerial Images Using an Embedded U-Net: A Comparison of CPU, GPU, and FPGA Workflows
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910870382051328 |
|---|---|
| author | Posso, Julien Kieffer, Hugo Menga, Nicolas Hlimi, Omar Tarris, Sébastien Guerard, Hubert Bois, Guy Couderc, Matthieu Jenn, Eric |
| author_facet | Posso, Julien Kieffer, Hugo Menga, Nicolas Hlimi, Omar Tarris, Sébastien Guerard, Hubert Bois, Guy Couderc, Matthieu Jenn, Eric |
| contents | This study introduces a lightweight U-Net model optimized for real-time semantic segmentation of aerial images, targeting the efficient utilization of Commercial Off-The-Shelf (COTS) embedded computing platforms. We maintain the accuracy of the U-Net on a real-world dataset while significantly reducing the model's parameters and Multiply-Accumulate (MAC) operations by a factor of 16. Our comprehensive analysis covers three hardware platforms (CPU, GPU, and FPGA) and five different toolchains (TVM, FINN, Vitis AI, TensorFlow GPU, and cuDNN), assessing each on metrics such as latency, power consumption, memory footprint, energy efficiency, and FPGA resource usage. The results highlight the trade-offs between these platforms and toolchains, with a particular focus on the practical deployment challenges in real-world applications. Our findings demonstrate that while the FPGA with Vitis AI emerges as the superior choice due to its performance, energy efficiency, and maturity, it requires specialized hardware knowledge, emphasizing the need for a balanced approach in selecting embedded computing solutions for semantic segmentation tasks |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_08700 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Real-Time Semantic Segmentation of Aerial Images Using an Embedded U-Net: A Comparison of CPU, GPU, and FPGA Workflows Posso, Julien Kieffer, Hugo Menga, Nicolas Hlimi, Omar Tarris, Sébastien Guerard, Hubert Bois, Guy Couderc, Matthieu Jenn, Eric Computer Vision and Pattern Recognition Artificial Intelligence Hardware Architecture Machine Learning This study introduces a lightweight U-Net model optimized for real-time semantic segmentation of aerial images, targeting the efficient utilization of Commercial Off-The-Shelf (COTS) embedded computing platforms. We maintain the accuracy of the U-Net on a real-world dataset while significantly reducing the model's parameters and Multiply-Accumulate (MAC) operations by a factor of 16. Our comprehensive analysis covers three hardware platforms (CPU, GPU, and FPGA) and five different toolchains (TVM, FINN, Vitis AI, TensorFlow GPU, and cuDNN), assessing each on metrics such as latency, power consumption, memory footprint, energy efficiency, and FPGA resource usage. The results highlight the trade-offs between these platforms and toolchains, with a particular focus on the practical deployment challenges in real-world applications. Our findings demonstrate that while the FPGA with Vitis AI emerges as the superior choice due to its performance, energy efficiency, and maturity, it requires specialized hardware knowledge, emphasizing the need for a balanced approach in selecting embedded computing solutions for semantic segmentation tasks |
| title | Real-Time Semantic Segmentation of Aerial Images Using an Embedded U-Net: A Comparison of CPU, GPU, and FPGA Workflows |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Hardware Architecture Machine Learning |
| url | https://arxiv.org/abs/2503.08700 |