SHD360: A Benchmark Dataset for Salient Human Detection in 360{\deg} Videos

TL;DR

SHD360 introduces the first large-scale 360-degree video dataset for salient human detection, providing a benchmark for evaluating existing methods and fostering advancements in human-centric 360-degree vision research.

Contribution

This paper presents SHD360, the first comprehensive 360-degree video dataset for salient human detection, along with benchmarking of 11 state-of-the-art methods.

Findings

Existing SOD methods show limited performance on 360-degree data.

Key challenges in 360-degree SHD are identified through extensive experiments.

The dataset enables future research in human-centric panoramic video analysis.

Abstract

Salient human detection (SHD) in dynamic 360{\deg} immersive videos is of great importance for various applications such as robotics, inter-human and human-object interaction in augmented reality. However, 360{\deg} 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{\deg} video SHD dataset which contains various real-life daily scenes. Since so far there is no method proposed for 360{\deg} 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{\deg} panoramic data. The dataset is available at https://github.com/PanoAsh/SHD360.