UAV-GESTURE: A Dataset for UAV Control and Gesture Recognition

TL;DR

This paper introduces UAV-GESTURE, an outdoor UAV gesture dataset with 119 high-definition videos of 13 gestures, enabling research in UAV control, gesture recognition, and human pose analysis.

Contribution

It provides the first outdoor UAV gesture dataset with detailed annotations, facilitating advancements in gesture-based UAV control and related research areas.

Findings

Baseline gesture recognition accuracy is 91.9%.

Dataset includes 37,151 frames with body joint annotations.

Supports research in gesture, action, and human pose recognition.

Abstract

Current UAV-recorded datasets are mostly limited to action recognition and object tracking, whereas the gesture signals datasets were mostly recorded in indoor spaces. Currently, there is no outdoor recorded public video dataset for UAV commanding signals. Gesture signals can be effectively used with UAVs by leveraging the UAVs visual sensors and operational simplicity. To fill this gap and enable research in wider application areas, we present a UAV gesture signals dataset recorded in an outdoor setting. We selected 13 gestures suitable for basic UAV navigation and command from general aircraft handling and helicopter handling signals. We provide 119 high-definition video clips consisting of 37151 frames. The overall baseline gesture recognition performance computed using Pose-based Convolutional Neural Network (P-CNN) is 91.9 %. All the frames are annotated with body joints and gesture classes in order to extend the dataset's applicability to a wider research area including gesture recognition, action recognition, human pose recognition and situation awareness.