Ocularone-Bench: Benchmarking DNN Models on GPUs to Assist the Visually Impaired
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909566626693120 |
|---|---|
| author | Raj, Suman Madhabhavi, Bhavani A Astu, Kautuk Rajesh, Arnav A M, Pratham Simmhan, Yogesh |
| author_facet | Raj, Suman Madhabhavi, Bhavani A Astu, Kautuk Rajesh, Arnav A M, Pratham Simmhan, Yogesh |
| contents | VIP navigation requires multiple DNN models for identification, posture analysis, and depth estimation to ensure safe mobility. Using a hazard vest as a unique identifier enhances visibility while selecting the right DNN model and computing device balances accuracy and real-time performance. We present Ocularone-Bench, which is a benchmark suite designed to address the lack of curated datasets for uniquely identifying individuals in crowded environments and the need for benchmarking DNN inference times on resource-constrained edge devices. The suite evaluates the accuracy-latency trade-offs of YOLO models retrained on this dataset and benchmarks inference times of situation awareness models across edge accelerators and high-end GPU workstations. Our study on NVIDIA Jetson devices and RTX 4090 workstation demonstrates significant improvements in detection accuracy, achieving up to 99.4% precision, while also providing insights into real-time feasibility for mobile deployment. Beyond VIP navigation, Ocularone-Bench is applicable to senior citizens, children and worker safety monitoring, and other vision-based applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_03709 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Ocularone-Bench: Benchmarking DNN Models on GPUs to Assist the Visually Impaired Raj, Suman Madhabhavi, Bhavani A Astu, Kautuk Rajesh, Arnav A M, Pratham Simmhan, Yogesh Distributed, Parallel, and Cluster Computing VIP navigation requires multiple DNN models for identification, posture analysis, and depth estimation to ensure safe mobility. Using a hazard vest as a unique identifier enhances visibility while selecting the right DNN model and computing device balances accuracy and real-time performance. We present Ocularone-Bench, which is a benchmark suite designed to address the lack of curated datasets for uniquely identifying individuals in crowded environments and the need for benchmarking DNN inference times on resource-constrained edge devices. The suite evaluates the accuracy-latency trade-offs of YOLO models retrained on this dataset and benchmarks inference times of situation awareness models across edge accelerators and high-end GPU workstations. Our study on NVIDIA Jetson devices and RTX 4090 workstation demonstrates significant improvements in detection accuracy, achieving up to 99.4% precision, while also providing insights into real-time feasibility for mobile deployment. Beyond VIP navigation, Ocularone-Bench is applicable to senior citizens, children and worker safety monitoring, and other vision-based applications. |
| title | Ocularone-Bench: Benchmarking DNN Models on GPUs to Assist the Visually Impaired |
| topic | Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2504.03709 |