<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>1160</id>
    <completedYear>2022</completedYear>
    <publishedYear>2021</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber>xvi, 108</pageNumber>
    <edition/>
    <issue/>
    <volume/>
    <articleNumber/>
    <type>masterthesis</type>
    <publisherName/>
    <publisherPlace>Ingolstadt</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2022-02-09</completedDate>
    <publishedDate>2021-08-20</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Evaluation of CNN-based object detection algorithms of thermal and color image sensors under adverse environment conditions</title>
    <abstract language="eng">Functional safety is becoming increasingly important in current ADAS systems, especially with technology facing an evolution as responsibility is gradually transferred from the driver to the car. The systems must perceive their environment correctly in any situation but sensors have their limitations. Thus, different sensor types must be combined to compensate the weakness of each sensor. The aim of this work is to find out whether thermal cameras have an added value for object detection in adverse environmental conditions such as rain, fog and different light conditions compared to conventional color cameras.&#13;
To answer this question, three state-of-the-art algorithms for object detection on images based on neural networks are analyzed and compared. Current state-of-the-art algorithms are based on neural networks and need a large amount of labeled data. This data is generated using IPG CarMaker, a simulation tool, to simulate labeled color and thermal images. Besides synthetic data, also real sensor data is recorded in the CARISSMA test facility, where real adverse environmental conditions can be reproduced. This dataset is used for evaluation, i.e. by comparing the ground-truth data with the neural network predictions from the color and thermal images. With the evaluationdata statements can be done in which situations the algorithm is able to detect the object based on the color and thermal images and thereby what performance the algorithm achieves.</abstract>
    <identifier type="urn">urn:nbn:de:bvb:573-11609</identifier>
    <enrichment key="opus.import.date">2022-02-09T14:13:39+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">primuss</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">true</enrichment>
    <licence>Urheberrechtsschutz</licence>
    <advisor>
      <first_name>Werner</first_name>
      <last_name>Huber</last_name>
    </advisor>
    <author>
      <first_name>Felix Korbinian</first_name>
      <last_name>Fröhling</last_name>
    </author>
    <advisor>
      <first_name>Andreas</first_name>
      <last_name>Riener</last_name>
    </advisor>
    <collection role="Import" number="import">Import</collection>
    <collection role="institutes" number="19311">Fakultät Elektro- und Informationstechnik</collection>
    <collection role="degree_programme" number="19348">Automatisiertes Fahren und Fahrzeugsicherheit (M. Eng.)</collection>
    <thesisPublisher>Technische Hochschule Ingolstadt</thesisPublisher>
    <thesisGrantor>Technische Hochschule Ingolstadt</thesisGrantor>
    <file>https://opus4.kobv.de/opus4-haw/files/1160/I000977549Thesis.pdf</file>
  </doc>
</export-example>
