Dist-YOLO: fast object detection with distance estimation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61988987%3A17610%2F22%3AA2302C9E" target="_blank" >RIV/61988987:17610/22:A2302C9E - isvavai.cz</a>

Výsledek na webu

<a href="https://www.mdpi.com/2076-3417/12/3/1354/html" target="_blank" >https://www.mdpi.com/2076-3417/12/3/1354/html</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3390/app12031354" target="_blank" >10.3390/app12031354</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Dist-YOLO: fast object detection with distance estimation

Popis výsledku v původním jazyce

We present a scheme of how YOLO can be improved in order to predict the absolute distance of objects using only information from a monocular camera. It is fully integrated into the original architecture by extending the prediction vectors, sharing the backbone’s weights with the bounding box regressor, and updating the original loss function by a part responsible for distance estimation. We designed two ways of handling the distance, class-agnostic and class-aware, proving class-agnostic creates smaller prediction vectors than class-aware and achieves better results. We demonstrate that the subtasks of object detection and distance measurement are in synergy, resulting in the increase of the precision of the original bounding box functionality. We show that using the KITTI dataset, the proposed scheme yields a mean relative error of 11% considering all eight classes and the distance range within [0, 150] m, which makes the solution highly competitive with existing approaches. Finally, we show that the inference speed is identical to the unmodified YOLO, 45 frames per second.

Název v anglickém jazyce

Dist-YOLO: fast object detection with distance estimation

Popis výsledku anglicky

We present a scheme of how YOLO can be improved in order to predict the absolute distance of objects using only information from a monocular camera. It is fully integrated into the original architecture by extending the prediction vectors, sharing the backbone’s weights with the bounding box regressor, and updating the original loss function by a part responsible for distance estimation. We designed two ways of handling the distance, class-agnostic and class-aware, proving class-agnostic creates smaller prediction vectors than class-aware and achieves better results. We demonstrate that the subtasks of object detection and distance measurement are in synergy, resulting in the increase of the precision of the original bounding box functionality. We show that using the KITTI dataset, the proposed scheme yields a mean relative error of 11% considering all eight classes and the distance range within [0, 150] m, which makes the solution highly competitive with existing approaches. Finally, we show that the inference speed is identical to the unmodified YOLO, 45 frames per second.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10102 - Applied mathematics

Projekt

<a href="/cs/project/EF17_049%2F0008414" target="_blank" >EF17_049/0008414: Centrum pro výzkum a vývoj metod umělé intelligence v automobilovém průmyslu regionu</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 periodika

Applied Sciences

ISSN

2076-3417

e-ISSN

—

Svazek periodika

—

Číslo periodika v rámci svazku

3

Stát vydavatele periodika

CH - Švýcarská konfederace

Počet stran výsledku

14

Strana od-do

1-13

Kód UT WoS článku

000754896100001

EID výsledku v databázi Scopus

2-s2.0-85123507680