Drone-Action: An Outdoor Recorded Drone Video Dataset for Action Recognition

Asanka G Perera,Yee Wei Law,Javaan Chahl

doi:10.3390/drones3040082

Asanka G Perera, Yee Wei Law + Show 1 more

Open Access

https://doi.org/10.3390/drones3040082

Copy DOI

Abstract

Aerial human action recognition is an emerging topic in drone applications. Commercial drone platforms capable of detecting basic human actions such as hand gestures have been developed. However, a limited number of aerial video datasets are available to support increased research into aerial human action analysis. Most of the datasets are confined to indoor scenes or object tracking and many outdoor datasets do not have sufficient human body details to apply state-of-the-art machine learning techniques. To fill this gap and enable research in wider application areas, we present an action recognition dataset recorded in an outdoor setting. A free flying drone was used to record 13 dynamic human actions. The dataset contains 240 high-definition video clips consisting of 66,919 frames. All of the videos were recorded from low-altitude and at low speed to capture the maximum human pose details with relatively high resolution. This dataset should be useful to many research areas, including action recognition, surveillance, situational awareness, and gait analysis. To test the dataset, we evaluated the dataset with a pose-based convolutional neural network (P-CNN) and high-level pose feature (HLPF) descriptors. The overall baseline action recognition accuracy calculated using P-CNN was 75.92%.

Highlights

Drones or Unmanned aerial vehicles (UAVs) are increasingly popular due to their affordability and applicability in numerous commercial applications
Recognizing the importance of datasets for action recognition research in the aerial domain, we present in this study, a new full high-definition (FHD) video dataset with rich human details, that was recorded on a drone in a controlled manner
We experimented with two popular feature types used in human action recognition; namely, pose-based Cheron et al.’s CNN features [29] and Jhuang et al.’s high-level pose features [30]

Summary

Introduction

Drones or Unmanned aerial vehicles (UAVs) are increasingly popular due to their affordability and applicability in numerous commercial applications. Some popular application areas of drones are photogrammetry [1], agriculture [2], crowd monitoring [3], sports activity recording [3], parcel delivery [3], and search and rescue [4,5]. These areas have experienced rapid advances through convergence of technologies [6]. For research in these areas, a series of datasets have been released in the past few years These datasets cover multiple research disciplines but mainly in the security, industrial, and agricultural sectors. Examples of such application-specific drone datasets include datasets for object detection [7,8], datasets for vehicle trajectory estimation [9,10], datasets for object tracking [11,12], datasets for human action recognition [13,14,15,16], datasets for gesture recognition [17,18,19], datasets for face recognition [20,21], a dataset for fault detection in photovoltaic plants [22], datasets for geographic information system [23,24], and datasets for agriculture [25,26]

Results

Discussion

Conclusion