Object Detection in Equirectangular Panorama
Tutkimustuotos › › vertaisarvioitu
Yksityiskohdat
| Alkuperäiskieli | Englanti |
|---|---|
| Otsikko | 2018 24th International Conference on Pattern Recognition (ICPR) |
| Kustantaja | IEEE |
| Sivut | 2190-2195 |
| Sivumäärä | 6 |
| ISBN (elektroninen) | 978-1-5386-3788-3 |
| ISBN (painettu) | 978-1-5386-3789-0 |
| DOI - pysyväislinkit | |
| Tila | Julkaistu - elokuuta 2018 |
| OKM-julkaisutyyppi | A4 Artikkeli konferenssijulkaisussa |
| Tapahtuma | INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION - Kesto: 1 tammikuuta 1900 → … |
Julkaisusarja
| Nimi | |
|---|---|
| ISSN (painettu) | 1051-4651 |
Conference
| Conference | INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION |
|---|---|
| Ajanjakso | 1/01/00 → … |
Tiivistelmä
We introduce a high-resolution equirectangular panorama (aka 360-degree, virtual reality, VR) dataset for object detection and propose a multi-projection variant of the YOLO detector. The main challenges with equirectangular panorama images are i) the lack of annotated training data, ii) high-resolution imagery and iii) severe geometric distortions of objects near the panorama projection poles. In this work, we solve the challenges by I) using training examples available in the “conventional datasets” (ImageNet and COCO), II) employing only low resolution images that require only moderate GPU computing power and memory, and III) our multi-projection YOLO handles projection distortions by making multiple stereographic sub-projections. In our experiments, YOLO outperforms the other state-of-the-art detector, Faster R-CNN, and our multi-projection YOLO achieves the best accuracy with low-resolution input.