A Real-Time Method to Detect and Track Moving Objects (DATMO) from Unmanned Aerial Vehicles (UAVs) Using a Single Camera

Remote Sensing

Gonzalo R. Rodríguez-Canosa²  Stephen Thomas¹  Jaime del Cerro²  Antonio Barrientos² 

[1] Department of Electrical and Computer Engineering, University of Auckland, Private Bag 92019, Auckland, New Zealand; E-Mails:;Centro de Automática & Robótica, Universidad Politécnica de Madrid, C/Jose Gutierrez Abascal nº2, E-28006 Madrid, Spain; E-Mails:

关键词: UAV;    DATMO;    optical flow;    surveillance;    homography-based optical flow;    Kalman Filter Tracking;   

DOI  :  10.3390/rs4041090

来源: mdpi

【 摘 要 】

We develop a real-time method to detect and track moving objects (DATMO) from unmanned aerial vehicles (UAVs) using a single camera. To address the challenging characteristics of these vehicles, such as continuous unrestricted pose variation and low-frequency vibrations, new approaches must be developed. The main concept proposed in this work is to create an artificial optical flow field by estimating the camera motion between two subsequent video frames. The core of the methodology consists of comparing this artificial flow with the real optical flow directly calculated from the video feed. The motion of the UAV between frames is estimated with available parallel tracking and mapping techniques that identify good static features in the images and follow them between frames. By comparing the two optical flows, a list of dynamic pixels is obtained and then grouped into dynamic objects. Tracking these dynamic objects through time and space provides a filtering procedure to eliminate spurious events and misdetections. The algorithms have been tested with a quadrotor platform using a commercial camera.

【 授权许可】

CC BY   
© 2012 by the authors; licensee MDPI, Basel, Switzerland.