ICUAS 2020 Paper Abstract

Close

Paper ThB3.2

McGee, Joseph John (Queensland University of Technology), Joseph Mathew, Sajith (Queensland University of Technology), Gonzalez, Luis Felipe (Queensland University of Technology (QUT)/ QUT Centre for Roboti)

Unmanned Aerial Vehicle and Artificial Intelligence for Thermal Target Detection in Search and Rescue Applications

Scheduled for presentation during the Regular Session "UAS Applications II" (ThB3), Thursday, September 3, 2020, 15:20−15:40, Edessa

2020 International Conference on Unmanned Aircraft Systems (ICUAS), September 1-4, 2020 (Postponed from June 9-12, 2020), Athens, Greece

This information is tentative and subject to change. Compiled on September 25, 2020

Keywords UAS Applications, Manned/Unmanned Aviation, Air Vehicle Operations

Abstract

Recent developments in unmanned aerial vehicles (UAV), artificial intelligence and miniaturized thermal imaging systems represent a new opportunity for SAR experts to survey relatively large areas. The system presented in this paper includes thermal image acquisition as well as a video processing pipeline to perform object detection, classification and of people in need for SAR in forest or open areas. The system is tested on thermal video data from ground based and test flight footage and is found to be able to detect all the target people located in the surveyed area. The system is flexible in that the user can readily define the types of objects to classify and the object characteristics that should be considered during classification. The training dataset is a combination of gathered data and internet sourced data. The initial data procurement utilised online academic thermal databases and also the simulation of the UAV mounted camera environment. The simulated data was completed at Kangaroo Point cliffs, Brisbane, Australia giving an approximate elevation of 26 m. Datasets were also collected at South Bribie Island, QLD, Australia at a range of heights and vegetation density. These datasets where collected at different times of the day allowing for a range of contrast level between background and intended target. Once all data was collected, individual frames where extracted from each image and augmentation and annotation was completed. The images were gaussian blurred, lightened and darkened, once all annotation was completed. A total of 2751 original images were annotated, with the augmented dataset comprising of 10380 images.Two main models were trained using different hyperparameters for comparison.

 

 

All Content © PaperCept, Inc.

This site is protected by copyright and trademark laws under US and International law.
All rights reserved. © 2002-2020 PaperCept, Inc.
Page generated 2020-09-25  15:50:24 PST  Terms of use