A Conceptual Multi-Layer Framework for the Detection of Nighttime Pedestrian in Autonomous Vehicles Using Deep Reinforcement Learning

dc.authorscopusid56188064800
dc.authorscopusid57206231579
dc.authorscopusid56527072800
dc.authorscopusid57220342733
dc.authorscopusid57193309270
dc.authorscopusid57791962400
dc.authorscopusid6603865373
dc.authorscopusid57027754300
dc.authorwosidAAC-8760-2020
dc.authorwosidGBJ-9696-2022
dc.authorwosidAAK-8362-2021
dc.authorwosidAAZ-1887-2020
dc.authorwosidAHD-9118-2022
dc.authorwosidAAY-5207-2020
dc.authorwosidHMB-4167-2023
dc.authorwosidEGK-9763-2022
dc.contributor.authorFarooq, Muhammad Shoaib
dc.contributor.authorKhalid, Haris
dc.contributor.authorArooj, Ansif
dc.contributor.authorUmar, Tariq
dc.contributor.authorAsghar, Aamer Bilal
dc.contributor.authorRasheed, Jawad
dc.contributor.authorShubair, Raed M.
dc.contributor.authorYahyaoui, Amani
dc.contributor.authorRasheed, Jawad
dc.date.accessioned2024-03-16T10:12:50Z
dc.date.available2024-03-16T10:12:50Z
dc.date.issued2023
dc.departmentMühendislik ve Doğa Bilimleri Fakültesi
dc.description.abstractThe major challenge faced by autonomous vehicles today is driving through busy roads without getting into an accident, especially with a pedestrian. To avoid collision with pedestrians, the vehicle requires the ability to communicate with a pedestrian to understand their actions. The most challenging task in research on computer vision is to detect pedestrian activities, especially at nighttime. The Advanced Driver-Assistance Systems (ADAS) has been developed for driving and parking support for vehicles to visualize sense, send and receive information from the environment but it lacks to detect nighttime pedestrian actions. This article proposes a framework based on Deep Reinforcement Learning (DRL) using Scale Invariant Faster Region-based Convolutional Neural Networks (SIFRCNN) technologies to efficiently detect pedestrian operations through which the vehicle, as agents train themselves from the environment and are forced to maximize the reward. The SIFRCNN has reduced the running time of detecting pedestrian operations from road images by incorporating Region Proposal Network (RPN) computation. Furthermore, we have used Reinforcement Learning (RL) for optimizing the Q-values and training itself to maximize the reward after getting the state from the SIFRCNN. In addition, the latest incarnation of SIFRCNN achieves near-real-time object detection from road images. The proposed SIFRCNN has been tested on KAIST, City Person, and Caltech datasets. The experimental results show an average improvement of 2.3% miss rate of pedestrian detection at nighttime compared to the other CNN-based pedestrian detectors.
dc.identifier.citationFarooq, M. S., Khalid, H., Arooj, A., Umer, T., Asghar, A. B., Rasheed, J., ... & Yahyaoui, A. (2023). A conceptual multi-layer framework for the detection of nighttime pedestrian in autonomous vehicles using deep reinforcement learning. Entropy, 25(1), 135.
dc.identifier.doi10.3390/e25010135
dc.identifier.issn1099-4300
dc.identifier.issue1
dc.identifier.orcidMuhammad Shoaib Farooq |0000-0002-4095-8868
dc.identifier.orcidAnsif Arooj |0000-0001-7116-4545
dc.identifier.orcidTariq Umar |0000-0002-3333-8142
dc.identifier.orcidAamer Bilal Asghar |0000-0002-9708-257X
dc.identifier.orcidJawad Rasheed |0000-0003-3761-1641
dc.identifier.orcidRaed M. Shubair |0000-0002-2586-9963
dc.identifier.orcidAmani Yahyaoui |0000-0003-0603-6592
dc.identifier.pmid36673276
dc.identifier.scopus2-s2.0-85146755845
dc.identifier.scopusqualityQ1
dc.identifier.urihttps://doi.org/10.3390/e25010135
dc.identifier.urihttps://hdl.handle.net/20.500.12436/5850
dc.identifier.volume25
dc.identifier.wosWOS:000915061100001
dc.identifier.wosqualityQ2
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.indekslendigikaynakPubMed
dc.institutionauthorYahyaoui, Amani
dc.institutionauthorRasheed, Jawad
dc.language.isoen
dc.publisherMDPI
dc.relation.ispartofEntropy
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subjectAdvanced driving system
dc.subjectAutonomous vehicle
dc.subjectDeep Learning
dc.subjectIntelligent driving system
dc.subjectNeural Network
dc.subjectReinforcement Learning
dc.titleA Conceptual Multi-Layer Framework for the Detection of Nighttime Pedestrian in Autonomous Vehicles Using Deep Reinforcement Learning
dc.typeArticle
dspace.entity.typePublication
relation.isAuthorOfPublicationf9b9b46c-d923-42d3-b413-dd851c2e913a
relation.isAuthorOfPublication.latestForDiscoveryf9b9b46c-d923-42d3-b413-dd851c2e913a

Dosyalar

Orijinal paket

Listeleniyor 1 - 1 / 1
Yükleniyor...
Küçük Resim
İsim:
entropy-25-00135-v3.pdf
Boyut:
1.85 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Makale dosyası / Article file

Lisans paketi

Listeleniyor 1 - 1 / 1
Yükleniyor...
Küçük Resim
İsim:
license.txt
Boyut:
1.44 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama: