Optimized Deployment of Deep Neural Networks for Visual Pose Estimation on Nano-drones
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913241327730688 |
|---|---|
| author | Risso, Matteo Daghero, Francesco Motetti, Beatrice Alessandra Pagliari, Daniele Jahier Macii, Enrico Poncino, Massimo Burrello, Alessio |
| author_facet | Risso, Matteo Daghero, Francesco Motetti, Beatrice Alessandra Pagliari, Daniele Jahier Macii, Enrico Poncino, Massimo Burrello, Alessio |
| contents | Miniaturized autonomous unmanned aerial vehicles (UAVs) are gaining popularity due to their small size, enabling new tasks such as indoor navigation or people monitoring. Nonetheless, their size and simple electronics pose severe challenges in implementing advanced onboard intelligence. This work proposes a new automatic optimization pipeline for visual pose estimation tasks using Deep Neural Networks (DNNs). The pipeline leverages two different Neural Architecture Search (NAS) algorithms to pursue a vast complexity-driven exploration in the DNNs' architectural space. The obtained networks are then deployed on an off-the-shelf nano-drone equipped with a parallel ultra-low power System-on-Chip leveraging a set of novel software kernels for the efficient fused execution of critical DNN layer sequences. Our results improve the state-of-the-art reducing inference latency by up to 3.22x at iso-error. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_15273 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Optimized Deployment of Deep Neural Networks for Visual Pose Estimation on Nano-drones Risso, Matteo Daghero, Francesco Motetti, Beatrice Alessandra Pagliari, Daniele Jahier Macii, Enrico Poncino, Massimo Burrello, Alessio Computer Vision and Pattern Recognition Machine Learning Miniaturized autonomous unmanned aerial vehicles (UAVs) are gaining popularity due to their small size, enabling new tasks such as indoor navigation or people monitoring. Nonetheless, their size and simple electronics pose severe challenges in implementing advanced onboard intelligence. This work proposes a new automatic optimization pipeline for visual pose estimation tasks using Deep Neural Networks (DNNs). The pipeline leverages two different Neural Architecture Search (NAS) algorithms to pursue a vast complexity-driven exploration in the DNNs' architectural space. The obtained networks are then deployed on an off-the-shelf nano-drone equipped with a parallel ultra-low power System-on-Chip leveraging a set of novel software kernels for the efficient fused execution of critical DNN layer sequences. Our results improve the state-of-the-art reducing inference latency by up to 3.22x at iso-error. |
| title | Optimized Deployment of Deep Neural Networks for Visual Pose Estimation on Nano-drones |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2402.15273 |