Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Time-unfolding Object Existence Detection in Low-quality Underwater Videos using Convolutional Neural Networks

 
: Tödtmann, Helmut; Vahl, Matthias; Lukas, Uwe von; Ullrich, Torsten

:
Fulltext urn:nbn:de:0011-n-5896390 (975 KByte PDF)
MD5 Fingerprint: afe0dc9d223139ad349cd6b17c9229bd
(CC) by-nc-nd
Created on: 14.5.2020


Farinella, Giovanni Maria (Ed.) ; Institute for Systems and Technologies of Information, Control and Communication -INSTICC-, Setubal:
15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. Proceedings. Vol.5: VISAPP : February 27-29, 2020, Valletta, Malta
Setúbal: SciTe Press, 2020
ISBN: 978-989-758-402-2
pp.370-377
International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) <15, 2020, Valletta>
International Conference on Computer Vision Theory and Applications (VISAPP) <15, 2020, Valetta>
English
Conference Paper, Electronic Publication
Fraunhofer IGD ()
Fraunhofer Austria ()
Fraunhofer IGD-R ()
Convolutional Neural Networks (CNN); deep learning; environmental monitoring; detection

Abstract
Monitoring the environment for early recognition of changes is necessary for assessing the success of renaturation measures on a facts basis. It is also used in fisheries and livestock production for monitoring and for quality assurance. The goal of the presented system is to count sea trouts annually over the course of several months. Sea trouts are detected with underwater camera systems triggered by motion sensors. Such a scenario generates many videos that have to be evaluated manually. This article describes the techniques used to automate the image evaluation process. An effective method has been developed to classify videos and determine the times of occurrence of sea trouts, while significantly reducing the annotation effort. A convolutional neural network has been trained via supervised learning. The underlying images are frame compositions automatically extracted from videos on which sea trouts are to be detected. The accuracy of the resulting detection system reaches values of up to 97.7 %.

: http://publica.fraunhofer.de/documents/N-589639.html