Saliency-Based Multiple Region of Interest Detection From a Single 360° Image
Saliency-Based Multiple Region of Interest Detection From a Single 360° Image
复制标题
DOI：
10.1109/access.2022.3200486
复制
发表时间：
2022-09
期刊：
影响因子：
3.9
通讯作者：
Yuuki Sawabe;Satoshi Ikehata;K. Aizawa
中科院分区：
文献类型：
--
作者：
Yuuki Sawabe;Satoshi Ikehata;K. Aizawa
360°图像信息量很大--它包含相机周围全方位的视觉信息。然而，360°图像覆盖的区域比人的视野大得多，因此不同视角方向的重要信息很容易被忽视。为了解决这一问题，我们提出了一种以视觉显著度为线索，从一幅360°图像中预测最佳感兴趣区域集合的方法。针对现有单一360°图像显著度预测数据集训练数据稀缺、偏倚大的问题，提出了一种基于球面随机数据轮换的数据增强方法。从预测的显著图和冗余候选区域出发，综合考虑区域内的显著程度和区域间的联合交互(IOU)，得到最优ROI集合。通过主观评价表明，该方法能够选择出对输入360°图像进行适当概括的区域。
360° images are informative – it contains omnidirectional visual information around the camera. However, the areas that cover a 360° image is much larger than the human’s field of view, therefore important information in different view directions is easily overlooked. To tackle this issue, we propose a method for predicting the optimal set of Region of Interest (RoI) from a single 360° image using the visual saliency as a clue. To deal with the scarce, strongly biased training data of existing single 360° image saliency prediction dataset, we also propose a data augmentation method based on the spherical random data rotation. From the predicted saliency map and redundant candidate regions, we obtain the optimal set of RoIs considering both the saliency within a region and the Interaction-Over-Union (IoU) between regions. We conduct the subjective evaluation to show that the proposed method can select regions that properly summarize the input 360° image.