Detail publikace

EVALUATIONOFTHENEURALNETWORKOBJECT DETECTIONINMULTI-MODALIMAGES

LIGOCKI, A.

Originální název

EVALUATIONOFTHENEURALNETWORKOBJECT DETECTIONINMULTI-MODALIMAGES

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

This paper studies the information gain of various data domains that are commonly used in the modern Advanced Driving Assistant Systems (ADAS) to develop robust systems that would increase traffic safety. We could see a fast growth of many Deep Convolutional Neural Networks (DCNN) based solutions during the last several years. These methods are state-of-the-art in object detection and semantic scene segmentation. We created a small annotated dataset of synchronized RGB, grayscale, thermal, and depth map images and used the modern DCNN framework tool to evaluate the object detection robustness of different data domains and their information gain process understanding the surrounding environment of the semi-autonomous driving agent.

Klíčová slova

Multi-modal, Object Detection, Convolutional Neural Network, RGB, Grayscale, Thermal, IR, Depth Map

Autoři

LIGOCKI, A.

Vydáno

27. 4. 2021

Nakladatel

Brno University of Technology, Faculty of Electrical Engineering and Communication

Místo

Brno

ISBN

978-80-214-5943-4

Kniha

PROCEEDINGS II OF THE 27TH STUDENT EEICT 2021 selected papers

Edice

1

Strany od

156

Strany do

160

Strany počet

5

URL

https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2021_sbornik_2_v3_DOI.pdf

BibTex

@inproceedings{BUT171475,
  author="Adam {Ligocki}",
  title="EVALUATIONOFTHENEURALNETWORKOBJECT DETECTIONINMULTI-MODALIMAGES",
  booktitle="PROCEEDINGS II OF THE 27TH STUDENT EEICT 2021 selected papers",
  year="2021",
  series="1",
  pages="156--160",
  publisher="Brno University of Technology, Faculty of Electrical Engineering and Communication",
  address="Brno",
  doi="10.13164/eeict.2021.156",
  isbn="978-80-214-5943-4",
  url="https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2021_sbornik_2_v3_DOI.pdf"
}