Deep Learning and Geometry Flow Vector Using Estimating Vehicle Cuboid Technology in a Monovision Environment

Autor:	Byeongjoon Noh, Tengfeng Lin, Sungju Lee, Taikyeong Jeong
Jazyk:	angličtina
Rok vydání:	2023
Předmět:	cuboid detection object detection deep learning road vehicle detection road geometry Chemical technology TP1-1185
Zdroj:	Sensors, Vol 23, Iss 17, p 7504 (2023)
Druh dokumentu:	article
ISSN:	1424-8220
DOI:	10.3390/s23177504
Popis:	This study introduces a novel model for accurately estimating the cuboid of a road vehicle using a monovision sensor and road geometry information. By leveraging object detection models and core vectors, the proposed model overcomes the limitations of multi-sensor setups and provides a cost-effective solution. The model demonstrates promising results in accurately estimating cuboids by utilizing the magnitudes of core vectors and considering the average ratio of distances. This research contributes to the field of intelligent transportation by offering a practical and efficient approach to 3D bounding box estimation using monovision sensors. We validated feasibility and applicability are through real-world road images captured by CCTV cameras.
Databáze:	Directory of Open Access Journals
Externí odkaz:	https://doaj.org/article/22c7eaa382cb4a888fd96f1c85358cdb Zobrazit plný text záznamu View record in DOAJ Plný text ve formátu PDF Plný text ve formátu HTML
Nepřihlášeným uživatelům se plný text nezobrazuje	K zobrazení výsledku je třeba se přihlásit.