F2SD: A dataset for end-to-end group detection algorithms
This addresses the problem of costly 3D data collection for group detection in computer vision, though it is incremental as it builds on existing simulation and detection methods.
The authors tackled the lack of large-scale datasets for F-formation detection by developing F2SD, a simulated dataset with nearly 60,000 images from GTA-5, and introduced the first end-to-end baseline model for this task.
The lack of large-scale datasets has been impeding the advance of deep learning approaches to the problem of F-formation detection. Moreover, most research works on this problem rely on input sensor signals of object location and orientation rather than image signals. To address this, we develop a new, large-scale dataset of simulated images for F-formation detection, called F-formation Simulation Dataset (F2SD). F2SD contains nearly 60,000 images simulated from GTA-5, with bounding boxes and orientation information on images, making it useful for a wide variety of modelling approaches. It is also closer to practical scenarios, where three-dimensional location and orientation information are costly to record. It is challenging to construct such a large-scale simulated dataset while keeping it realistic. Furthermore, the available research utilizes conventional methods to detect groups. They do not detect groups directly from the image. In this work, we propose (1) a large-scale simulation dataset F2SD and a pipeline for F-formation simulation, (2) a first-ever end-to-end baseline model for the task, and experiments on our simulation dataset.