SHD360: A Benchmark Dataset for Salient Human Detection in 360° Videos
This addresses the problem of advancing human-centric research in 360° panoramic data for applications like robotics and augmented reality, but it is incremental as it primarily provides a dataset and benchmark rather than a new method.
The authors tackled the lack of datasets for salient human detection in 360° videos by introducing SHD360, a benchmark dataset with large-scale omnidirectional videos and rich annotations, and they benchmarked 11 state-of-the-art salient object detection methods on it, achieving results that serve as a baseline for future research.
Salient human detection (SHD) in dynamic 360° immersive videos is of great importance for various applications such as robotics, inter-human and human-object interaction in augmented reality. However, 360° video SHD has been seldom discussed in the computer vision community due to a lack of datasets with large-scale omnidirectional videos and rich annotations. To this end, we propose SHD360, the first 360° video SHD dataset which contains various real-life daily scenes. Since so far there is no method proposed for 360° image/video SHD, we systematically benchmark 11 representative state-of-the-art salient object detection (SOD) approaches on our SHD360, and explore key issues derived from extensive experimenting results. We hope our proposed dataset and benchmark could serve as a good starting point for advancing human-centric researches towards 360° panoramic data. The dataset is available at https://github.com/PanoAsh/SHD360.