A Dataset of Annotated Omnidirectional Videos for Distancing Applications
Omnidirectional (or 360°) cameras are acquisition devices that, in the next few years, could have a big impact on video surveillance applications, research, and industry, as they can record a spherical view of a whole environment from every perspective. This paper presents two new contributions to t...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-08-01
|
| Series: | Journal of Imaging |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-433X/7/8/158 |
| _version_ | 1827685001752215552 |
|---|---|
| author | Giuseppe Mazzola Liliana Lo Presti Edoardo Ardizzone Marco La Cascia |
| author_facet | Giuseppe Mazzola Liliana Lo Presti Edoardo Ardizzone Marco La Cascia |
| author_sort | Giuseppe Mazzola |
| collection | DOAJ |
| description | Omnidirectional (or 360°) cameras are acquisition devices that, in the next few years, could have a big impact on video surveillance applications, research, and industry, as they can record a spherical view of a whole environment from every perspective. This paper presents two new contributions to the research community: the CVIP360 dataset, an annotated dataset of 360° videos for distancing applications, and a new method to estimate the distances of objects in a scene from a single 360° image. The CVIP360 dataset includes 16 videos acquired outdoors and indoors, annotated by adding information about the pedestrians in the scene (bounding boxes) and the distances to the camera of some points in the 3D world by using markers at fixed and known intervals. The proposed distance estimation algorithm is based on geometry facts regarding the acquisition process of the omnidirectional device, and is uncalibrated in practice: the only required parameter is the camera height. The proposed algorithm was tested on the CVIP360 dataset, and empirical results demonstrate that the estimation error is negligible for distancing applications. |
| first_indexed | 2024-03-10T08:41:53Z |
| format | Article |
| id | doaj.art-5853c9abcc9b4f2d96d1838d1555d345 |
| institution | Directory Open Access Journal |
| issn | 2313-433X |
| language | English |
| last_indexed | 2024-03-10T08:41:53Z |
| publishDate | 2021-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Imaging |
| spelling | doaj.art-5853c9abcc9b4f2d96d1838d1555d3452023-11-22T08:14:14ZengMDPI AGJournal of Imaging2313-433X2021-08-017815810.3390/jimaging7080158A Dataset of Annotated Omnidirectional Videos for Distancing ApplicationsGiuseppe Mazzola0Liliana Lo Presti1Edoardo Ardizzone2Marco La Cascia3Dipartimento di Ingegneria, Università degli Studi di Palermo, 90128 Palermo, ItalyDipartimento di Ingegneria, Università degli Studi di Palermo, 90128 Palermo, ItalyDipartimento di Ingegneria, Università degli Studi di Palermo, 90128 Palermo, ItalyDipartimento di Ingegneria, Università degli Studi di Palermo, 90128 Palermo, ItalyOmnidirectional (or 360°) cameras are acquisition devices that, in the next few years, could have a big impact on video surveillance applications, research, and industry, as they can record a spherical view of a whole environment from every perspective. This paper presents two new contributions to the research community: the CVIP360 dataset, an annotated dataset of 360° videos for distancing applications, and a new method to estimate the distances of objects in a scene from a single 360° image. The CVIP360 dataset includes 16 videos acquired outdoors and indoors, annotated by adding information about the pedestrians in the scene (bounding boxes) and the distances to the camera of some points in the 3D world by using markers at fixed and known intervals. The proposed distance estimation algorithm is based on geometry facts regarding the acquisition process of the omnidirectional device, and is uncalibrated in practice: the only required parameter is the camera height. The proposed algorithm was tested on the CVIP360 dataset, and empirical results demonstrate that the estimation error is negligible for distancing applications.https://www.mdpi.com/2313-433X/7/8/158omnidirectional cameras360°video datasetdepth estimationdistancingvideo surveillance |
| spellingShingle | Giuseppe Mazzola Liliana Lo Presti Edoardo Ardizzone Marco La Cascia A Dataset of Annotated Omnidirectional Videos for Distancing Applications Journal of Imaging omnidirectional cameras 360° video dataset depth estimation distancing video surveillance |
| title | A Dataset of Annotated Omnidirectional Videos for Distancing Applications |
| title_full | A Dataset of Annotated Omnidirectional Videos for Distancing Applications |
| title_fullStr | A Dataset of Annotated Omnidirectional Videos for Distancing Applications |
| title_full_unstemmed | A Dataset of Annotated Omnidirectional Videos for Distancing Applications |
| title_short | A Dataset of Annotated Omnidirectional Videos for Distancing Applications |
| title_sort | dataset of annotated omnidirectional videos for distancing applications |
| topic | omnidirectional cameras 360° video dataset depth estimation distancing video surveillance |
| url | https://www.mdpi.com/2313-433X/7/8/158 |
| work_keys_str_mv | AT giuseppemazzola adatasetofannotatedomnidirectionalvideosfordistancingapplications AT lilianalopresti adatasetofannotatedomnidirectionalvideosfordistancingapplications AT edoardoardizzone adatasetofannotatedomnidirectionalvideosfordistancingapplications AT marcolacascia adatasetofannotatedomnidirectionalvideosfordistancingapplications AT giuseppemazzola datasetofannotatedomnidirectionalvideosfordistancingapplications AT lilianalopresti datasetofannotatedomnidirectionalvideosfordistancingapplications AT edoardoardizzone datasetofannotatedomnidirectionalvideosfordistancingapplications AT marcolacascia datasetofannotatedomnidirectionalvideosfordistancingapplications |