We introduced a high-resolution equirectangular panorama (360-degree, virtual
reality) dataset for object detection and propose a multi-projection variant of
YOLO detector. The main challenge with equirectangular panorama image 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-art detector, Faster RCNN and our
multi-projection YOLO achieves the best accuracy with low-resolution input.

提出了一个高分辨率的全景图（360 度，虚拟现实）数据集，以进行对象检测，并提出了 YOLO 检测器的多投影变体。通过使用传统数据集中可用的训练示例，仅使用中等 GPU 计算能力和内存的低分辨率图像，以及采用多投影 YOLO 处理投影畸变，解决了全景图像缺乏注释训练数据，高分辨率和几何畸变的主要挑战。在实验中，YOLO 优于其他先进的检测器，而我们的多投影 YOLO 在低分辨率输入方面实现了最佳精度。