Human Detection in Depth Map Created from Point Cloud

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26620%2F22%3APU141816" target="_blank" >RIV/00216305:26620/22:PU141816 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1007/978-3-030-98260-7_16" target="_blank" >http://dx.doi.org/10.1007/978-3-030-98260-7_16</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-98260-7_16" target="_blank" >10.1007/978-3-030-98260-7_16</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Human Detection in Depth Map Created from Point Cloud

Popis výsledku v původním jazyce

This paper deals with human detection in the LiDAR data using the YOLO object detection neural network architecture. RGB-based object detection is the most studied topic in the field of neural networks and autonomous agents. However, these models are very sensitive to even minor changes in the weather or light conditions if the training data do not cover these situations. This paper proposes to use the LiDAR data as a redundant, and more condition invariant source of object detections around the autonomous agent. We used the publically available real-traffic dataset that simultaneously captures data from RGB camera and 3D LiDAR sensors during the clear-sky day and rainy night time and we aggregate the LiDAR data for a short period to increase the density of the point cloud. Later we projected these point cloud by several projection models, like pinhole camera model, cylindrical projection, and bird-view projection, into the 2D image frame, and we annotated all the images. As the main experiment, we trained the several YOLOv5 neural networks on the data captured during the day and validate the models on the mixed day and night data to study the robustness and information gain during the condition changes of the input data. The results show that the LiDAR-based models provide significantly better performance during the changed weather conditions than the RGB-based models.

Název v anglickém jazyce

Human Detection in Depth Map Created from Point Cloud

Popis výsledku anglicky

This paper deals with human detection in the LiDAR data using the YOLO object detection neural network architecture. RGB-based object detection is the most studied topic in the field of neural networks and autonomous agents. However, these models are very sensitive to even minor changes in the weather or light conditions if the training data do not cover these situations. This paper proposes to use the LiDAR data as a redundant, and more condition invariant source of object detections around the autonomous agent. We used the publically available real-traffic dataset that simultaneously captures data from RGB camera and 3D LiDAR sensors during the clear-sky day and rainy night time and we aggregate the LiDAR data for a short period to increase the density of the point cloud. Later we projected these point cloud by several projection models, like pinhole camera model, cylindrical projection, and bird-view projection, into the 2D image frame, and we annotated all the images. As the main experiment, we trained the several YOLOv5 neural networks on the data captured during the day and validate the models on the mixed day and night data to study the robustness and information gain during the condition changes of the input data. The results show that the LiDAR-based models provide significantly better performance during the changed weather conditions than the RGB-based models.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

Projekt

<a href="/cs/project/8A20002" target="_blank" >8A20002: Trustable architectures with acceptable residual risk for the electric, connected and automated cars</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

International Conference on Modelling and Simulation for Autonomous Systems

ISBN

9783030982607

ISSN

0302-9743

e-ISSN

—

Počet stran výsledku

12

Strana od-do

1-12

Název nakladatele

Neuveden

Místo vydání

neuveden

Místo konání akce

virtual

Datum konání akce

13. 10. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000787774900016