Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Recurso digital |
| Lingua: | |
| Pubblicazione: |
Zenodo
2025
|
| Accesso online: | https://doi.org/10.5281/zenodo.17830310 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866901413880135680 |
|---|---|
| author | Palacios, Fernando Redondo Rodríguez, Ana Rodríguez, Hélder Domínguez-Durante, Salvador Sanz-Merodio, Daniel López, Miguel |
| author_facet | Palacios, Fernando Redondo Rodríguez, Ana Rodríguez, Hélder Domínguez-Durante, Salvador Sanz-Merodio, Daniel López, Miguel |
| contents | <p>Test split from the dataset presented in the paper "A Holistic Comparison of Performance and Efficiency between Von Neumann and Neuromorphic Computing in a Real-World Application"</p> <p>This split is part of an aerial beach dataset that captured the dynamic activity of surfers, swimmers, and beach users from drone-mounted vision sensors. It offers synchronized data obtained through conventional frame-based and event-based cameras for multi-modal analysis of real-world coastal environments. </p> <p><strong>Dataset structure</strong></p> <ul> <li> <p>The split is organized into <strong>four top-level folders</strong>, one per beach.</p> </li> <li> <p>Inside each beach folder there are <strong>three modality subfolders</strong>:</p> <ul> <li> <p><code>classic/</code> — frame images in <strong>PNG</strong> format</p> </li> <li> <p><code>events/</code> — event-based images in <strong>PNG</strong> format</p> </li> <li> <p><code>tensors/</code> — event-based tensors in <strong>PyTorch <code>.pt</code></strong> format</p> </li> </ul> </li> </ul> <p><strong>Annotations</strong></p> <ul> <li> <p>Each modality folder contains a <code>labels_detection/</code> subfolder.</p> </li> <li> <p>Within <code>labels_detection/</code>, <strong>ZIP files</strong> are provided; <strong>each ZIP</strong> contains an <code>annotations.xml</code> file (CVAT format) with the <strong>bounding boxes and class labels</strong> corresponding to its paired data file (<code>.png</code> or <code>.pt</code>).</p> </li> </ul> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_17830310 |
| institution | Zenodo |
| language | |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | ARC-DVS Coastal Benchmark - Test split Palacios, Fernando Redondo Rodríguez, Ana Rodríguez, Hélder Domínguez-Durante, Salvador Sanz-Merodio, Daniel López, Miguel <p>Test split from the dataset presented in the paper "A Holistic Comparison of Performance and Efficiency between Von Neumann and Neuromorphic Computing in a Real-World Application"</p> <p>This split is part of an aerial beach dataset that captured the dynamic activity of surfers, swimmers, and beach users from drone-mounted vision sensors. It offers synchronized data obtained through conventional frame-based and event-based cameras for multi-modal analysis of real-world coastal environments. </p> <p><strong>Dataset structure</strong></p> <ul> <li> <p>The split is organized into <strong>four top-level folders</strong>, one per beach.</p> </li> <li> <p>Inside each beach folder there are <strong>three modality subfolders</strong>:</p> <ul> <li> <p><code>classic/</code> — frame images in <strong>PNG</strong> format</p> </li> <li> <p><code>events/</code> — event-based images in <strong>PNG</strong> format</p> </li> <li> <p><code>tensors/</code> — event-based tensors in <strong>PyTorch <code>.pt</code></strong> format</p> </li> </ul> </li> </ul> <p><strong>Annotations</strong></p> <ul> <li> <p>Each modality folder contains a <code>labels_detection/</code> subfolder.</p> </li> <li> <p>Within <code>labels_detection/</code>, <strong>ZIP files</strong> are provided; <strong>each ZIP</strong> contains an <code>annotations.xml</code> file (CVAT format) with the <strong>bounding boxes and class labels</strong> corresponding to its paired data file (<code>.png</code> or <code>.pt</code>).</p> </li> </ul> |
| title | ARC-DVS Coastal Benchmark - Test split |
| url | https://doi.org/10.5281/zenodo.17830310 |