CERES > School of Engineering (SoE) (2001-July 2014) > Staff publications - School of Engineering >

Please use this identifier to cite or link to this item: http://dspace.lib.cranfield.ac.uk/handle/1826/7589

Document Type: Conference paper
Title: Real-time people and vehicle detection from UAV imagery
Authors: Gaszczak, Anna
Breckon, Toby P.
Han, Jiwan
Issue Date: 2011
Citation: Anna Gąszczak, Toby P.Breckon and Jiwan Han. Real-time people and vehicle detection from UAV imagery. Proceeding of SPIE : Intelligent Robots and Computer Vision XXVIII : Algorithms and Techniques, 24-25 January 2011, San Francisco, California, US. Pages 78780B-1-13
Abstract: A generic and robust approach for the real-time detection of people and vehicles from an Unmanned Aerial Vehicle(UAV) is an important goal within the framework of fully autonomous UAV deployment for aerial reconnaissance andsurveillance. Here we present an approach for the automatic detection of vehicles based on using multiple trainedcascaded Haar classifiers with secondary confirmation in thermal imagery. Additionally we present a related approachfor people detection in thermal imagery based on a similar cascaded classification technique combining additionalmultivariate Gaussian shape matching. The results presented show the successful detection of vehicle and people undervarying conditions in both isolated rural and cluttered urban environments with minimal false positive detection.Performance of the detector is optimized to reduce the overall false positive rate by aiming at the detection of each objectof interest (vehicle/ person) at least once in the environment (i.e. per search patter flight path) rather than every object ineach image frame. Currently the detection rate for people is ~70% and cars ~80% although the overall episodic objectdetection rate for each flight pattern exceeds 90%.
URI: http://dx.doi.org/10.1117/12.876663
Appears in Collections:Staff publications - School of Engineering

Files in This Item:

File Description SizeFormat
Real-time_people_and_vehicle_detection-UVA_imagery-2011.pdf927.36 kBAdobe PDFView/Open

SFX Query

Items in CERES are protected by copyright, with all rights reserved, unless otherwise indicated.