Autonomous Driving Road Environment Recognition with Multiscale Object Detection

Ensuring precise perception of the surrounding road environment is crucial for the safe functioning of autonomous vehicles in the domain of autonomous driving. Using cutting-edge deep learning techniques, this research presents a novel way for autonomous road environment classification and item dete...

Full description

Saved in:
Bibliographic Details
Main Authors: Jeny J.R.V., Divya Phulari, Varsha Kolanu, Mrunalini Anantha, Irfan S.K.M.
Format: Article
Language:English
Published: EDP Sciences 2025-01-01
Series:E3S Web of Conferences
Subjects:
Online Access:https://www.e3s-conferences.org/articles/e3sconf/pdf/2025/19/e3sconf_icsget2025_03017.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849736976596467712
author Jeny J.R.V.
Divya Phulari
Varsha Kolanu
Mrunalini Anantha
Irfan S.K.M.
author_facet Jeny J.R.V.
Divya Phulari
Varsha Kolanu
Mrunalini Anantha
Irfan S.K.M.
author_sort Jeny J.R.V.
collection DOAJ
description Ensuring precise perception of the surrounding road environment is crucial for the safe functioning of autonomous vehicles in the domain of autonomous driving. Using cutting-edge deep learning techniques, this research presents a novel way for autonomous road environment classification and item detection. It focuses on combining Yolov5 and multiscale small object detection models. Modern object detection frameworks allow for the accurate and efficient processing of a wide range of things that are met on the road, such as cars, bikes, pedestrians, and traffic signals. By means of the smooth integration of these models, the proposed system exhibits resilience and efficiency in various real-life situations, indicating noteworthy progressions in the field of autonomous driving technology. The efficacy and dependability of the proposed strategy have been confirmed by extensive testing and assessment. The system delivers significant gains in efficiency and accuracy of detection by incorporating the deep learning models, providing a solid basis for the creation of safer and more reliable autonomous cars. This study opens the door to a future in which self-driving cars navigate roadways with increased safety and efficiency by demonstrating the critical role that cutting-edge deep learning algorithms play in enabling precise perception and decision-making capabilities within autonomous driving systems.
format Article
id doaj-art-8f413b944fe94de58a72ebe30e3b929a
institution DOAJ
issn 2267-1242
language English
publishDate 2025-01-01
publisher EDP Sciences
record_format Article
series E3S Web of Conferences
spelling doaj-art-8f413b944fe94de58a72ebe30e3b929a2025-08-20T03:07:06ZengEDP SciencesE3S Web of Conferences2267-12422025-01-016190301710.1051/e3sconf/202561903017e3sconf_icsget2025_03017Autonomous Driving Road Environment Recognition with Multiscale Object DetectionJeny J.R.V.0Divya Phulari1Varsha Kolanu2Mrunalini Anantha3Irfan S.K.M.4Professor, Department of Computer Science and Engineering (AI&ML), Vignan Institute of Technology and ScienceUG Scholar, Department of Computer Science and Engineering (AI&ML), Vignan Institute of Technology and ScienceUG Scholar, Department of Computer Science and Engineering (AI&ML), Vignan Institute of Technology and ScienceUG Scholar, Department of Computer Science and Engineering (AI&ML), Vignan Institute of Technology and ScienceUG Scholar, Department of Computer Science and Engineering (AI&ML), Vignan Institute of Technology and ScienceEnsuring precise perception of the surrounding road environment is crucial for the safe functioning of autonomous vehicles in the domain of autonomous driving. Using cutting-edge deep learning techniques, this research presents a novel way for autonomous road environment classification and item detection. It focuses on combining Yolov5 and multiscale small object detection models. Modern object detection frameworks allow for the accurate and efficient processing of a wide range of things that are met on the road, such as cars, bikes, pedestrians, and traffic signals. By means of the smooth integration of these models, the proposed system exhibits resilience and efficiency in various real-life situations, indicating noteworthy progressions in the field of autonomous driving technology. The efficacy and dependability of the proposed strategy have been confirmed by extensive testing and assessment. The system delivers significant gains in efficiency and accuracy of detection by incorporating the deep learning models, providing a solid basis for the creation of safer and more reliable autonomous cars. This study opens the door to a future in which self-driving cars navigate roadways with increased safety and efficiency by demonstrating the critical role that cutting-edge deep learning algorithms play in enabling precise perception and decision-making capabilities within autonomous driving systems.https://www.e3s-conferences.org/articles/e3sconf/pdf/2025/19/e3sconf_icsget2025_03017.pdfautonomous drivingobject detectionroad environment recognitiondeep learningreal-time detection
spellingShingle Jeny J.R.V.
Divya Phulari
Varsha Kolanu
Mrunalini Anantha
Irfan S.K.M.
Autonomous Driving Road Environment Recognition with Multiscale Object Detection
E3S Web of Conferences
autonomous driving
object detection
road environment recognition
deep learning
real-time detection
title Autonomous Driving Road Environment Recognition with Multiscale Object Detection
title_full Autonomous Driving Road Environment Recognition with Multiscale Object Detection
title_fullStr Autonomous Driving Road Environment Recognition with Multiscale Object Detection
title_full_unstemmed Autonomous Driving Road Environment Recognition with Multiscale Object Detection
title_short Autonomous Driving Road Environment Recognition with Multiscale Object Detection
title_sort autonomous driving road environment recognition with multiscale object detection
topic autonomous driving
object detection
road environment recognition
deep learning
real-time detection
url https://www.e3s-conferences.org/articles/e3sconf/pdf/2025/19/e3sconf_icsget2025_03017.pdf
work_keys_str_mv AT jenyjrv autonomousdrivingroadenvironmentrecognitionwithmultiscaleobjectdetection
AT divyaphulari autonomousdrivingroadenvironmentrecognitionwithmultiscaleobjectdetection
AT varshakolanu autonomousdrivingroadenvironmentrecognitionwithmultiscaleobjectdetection
AT mrunalinianantha autonomousdrivingroadenvironmentrecognitionwithmultiscaleobjectdetection
AT irfanskm autonomousdrivingroadenvironmentrecognitionwithmultiscaleobjectdetection