Human Detection and Motion Analysis from a Quadrotor UAV

AEROTECH VII - Sustainability in Aerospace Engineering and Technology

航空航天工程

Perera, Asanka G.^1 ; Al-Naji, Ali^1,2 ; Law, Yee Wei^1 ; Chahl, Javaan^1,3

School of Engineering, University of South Australia, Mawson Lakes

SA

5095, Australia^1

Electrical Engineering Technical College, Middle Technical University, Al Doura, Baghdad

10022, Iraq^2

Joint and Operations Analysis Division, Defence Science and Technology Group, Melbourne

VIC

3207, Australia^3

关键词: Convolutional neural network;    Dynamic classifiers;    Human detection;    Oriented gradients;    Perspective corrections;    Projective transformation;    Quad-rotor UAV;    Trajectory estimation;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/405/1/012003/pdf
DOI  :  10.1088/1757-899X/405/1/012003

学科分类：航空航天科学

来源: IOP

【 摘 要 】

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.