Human detection and motion analysis from a quadrotor UAV
Paper
Paper/Presentation Title | Human detection and motion analysis from a quadrotor UAV |
---|---|
Presentation Type | Paper |
Authors | Perera, Asanka G., Al-Naji, Ali, Law, Al-Naji, Ali and Chahl, Javaan |
Journal or Proceedings Title | IOP Conference Series: Materials Science and Engineering |
Journal Citation | 405 |
Article Number | 012003 |
Number of Pages | 11 |
Year | 2018 |
Publisher | IOP Publishing |
Place of Publication | United Kingdom |
ISSN | 1757-8981 |
1757-899X | |
Digital Object Identifier (DOI) | https://doi.org/10.1088/1757-899X/405/1/012003 |
Web Address (URL) of Paper | https://iopscience.iop.org/article/10.1088/1757-899X/405/1/012003/meta |
Web Address (URL) of Conference Proceedings | https://iopscience.iop.org/issue/1757-899X/405/1 |
Conference/Event | AEROTECH VII - Sustainability in Aerospace Engineering and Technology |
Event Details | AEROTECH VII - Sustainability in Aerospace Engineering and Technology Delivery In person Event Date 07 to end of 08 Aug 2018 Event Location Putrajaya, Malaysia |
Abstract | This work focuses on detecting humans and estimating their pose and trajectory from an umnanned aerial vehicle (UAV). In our framework, a human detection model is trained using a Region-based Convolutional Neural Network (R-CNN). Each video frame is corrected for perspective using projective transformation. Using Histogram Oriented Gradients (HOG) of the silhouettes as features, the detected human figures are then classified for their pose. A dynamic classifier is developed to estimate forward walking and a turning gait sequence. The estimated poses are used to estimate the shape of the trajectory traversed by the human subject. An average precision of 98% has been achieved for the detector. Experiments conducted on aerial videos confirm our solution can achieve accurate pose and trajectory estimation for different kinds of perspective-distorted videos. For example, for a video recorded at 40m above ground, the perspective correction improves accuracy by 37.1% and 17.8% in pose and viewpoint estimation respectively. |
Keywords | UAV |
Contains Sensitive Content | Does not contain sensitive content |
ANZSRC Field of Research 2020 | 4007. Control engineering, mechatronics and robotics |
Byline Affiliations | University of South Australia |
Middle East Technical University, Turkey | |
Defence Science and Technology Group, Australia |
https://research.usq.edu.au/item/z77y7/human-detection-and-motion-analysis-from-a-quadrotor-uav
Download files
Published Version
Perera_2018_IOP_Conf._Ser.__Mater._Sci._Eng._405_012003.pdf | ||
License: CC BY 3.0 | ||
File access level: Anyone |
37
total views17
total downloads7
views this month2
downloads this month