Articles producció científica> Enginyeria Informàtica i Matemàtiques

T-YOLO: Tiny vehicle detection based on YOLO and multi-scale convolutional neural networks

  • Datos identificativos

    Identificador: imarina:9243276
    Autores:
    Carrasco, Daniel PadillaRashwan, Hatem AGarcia, Miguel AngelPuig, Domenec
    Resumen:
    To solve real-life problems for different smart city applications, using deep Neural Network, such as parking occupancy detection, requires fine-tuning of these networks. For large parking, it is desirable to use a cenital-plane camera located at a high distance that allows the monitoring of the entire parking space or a large parking area with only one camera. Today’s most popular object detection models, such as YOLO, achieve good precision scores at real-time speed. However, if we use our own data different from that of the general-purpose datasets, such as COCO and ImageNet, we have a large margin for improvisation. In this paper, we propose a modified, yet lightweight, deep object detection model based on the YOLO-v5 architecture. The proposed model can detect large, small, and tiny objects. Specifically, we propose the use of a multi-scale mechanism to learn deep discriminative feature representations at different scales and automatically determine the most suitable scales for detecting objects in a scene (i.e., in our case vehicles). The proposed multi-scale module reduces the number of trainable parameters compared to the original YOLO-v5 architecture. The experimental results also demonstrate that precision is improved by a large margin. In fact, as shown in the experiments, the results show a small reduction from 7.28 million parameters of the YOLO-v5-S profile to 7.26 million parameters in our model. In addition, we reduced the detection speed by inferring 30 fps compared to the YOLO-v5-L/X profiles. In addition, the tiny vehicle detection performance was significantly improved by 33% compared to the YOLO-v5-X profile.
  • Otros:

    Autor según el artículo: Carrasco, Daniel Padilla; Rashwan, Hatem A; Garcia, Miguel Angel; Puig, Domenec
    Departamento: Enginyeria Informàtica i Matemàtiques
    Autor/es de la URV: Abdellatif Fatahallah Ibrahim Mahmoud, Hatem / GARCIA GARCIA, MIGUEL ANGEL / Puig Valls, Domènec Savi
    Palabras clave: Tiny objects Smart parking Object detection Feature extraction Detectors Convolutional neural networks Computational modeling Cameras Automobiles tiny objects smart parking feature extraction detectors convolutional neural networks computational modeling cameras automobiles
    Resumen: To solve real-life problems for different smart city applications, using deep Neural Network, such as parking occupancy detection, requires fine-tuning of these networks. For large parking, it is desirable to use a cenital-plane camera located at a high distance that allows the monitoring of the entire parking space or a large parking area with only one camera. Today’s most popular object detection models, such as YOLO, achieve good precision scores at real-time speed. However, if we use our own data different from that of the general-purpose datasets, such as COCO and ImageNet, we have a large margin for improvisation. In this paper, we propose a modified, yet lightweight, deep object detection model based on the YOLO-v5 architecture. The proposed model can detect large, small, and tiny objects. Specifically, we propose the use of a multi-scale mechanism to learn deep discriminative feature representations at different scales and automatically determine the most suitable scales for detecting objects in a scene (i.e., in our case vehicles). The proposed multi-scale module reduces the number of trainable parameters compared to the original YOLO-v5 architecture. The experimental results also demonstrate that precision is improved by a large margin. In fact, as shown in the experiments, the results show a small reduction from 7.28 million parameters of the YOLO-v5-S profile to 7.26 million parameters in our model. In addition, we reduced the detection speed by inferring 30 fps compared to the YOLO-v5-L/X profiles. In addition, the tiny vehicle detection performance was significantly improved by 33% compared to the YOLO-v5-X profile.
    Áreas temáticas: Telecommunications Materials science (miscellaneous) Materials science (all) General materials science General engineering General computer science Engineering, electrical & electronic Engineering (miscellaneous) Engineering (all) Engenharias iv Engenharias iii Electrical and electronic engineering Computer science, information systems Computer science (miscellaneous) Computer science (all) Ciência da computação
    Acceso a la licencia de uso: https://creativecommons.org/licenses/by/3.0/es/
    Direcció de correo del autor: miguelangel.garciag@urv.cat hatem.abdellatif@urv.cat domenec.puig@urv.cat
    Identificador del autor: 0000-0001-9972-2182 0000-0001-5421-1637 0000-0002-0562-4205
    Fecha de alta del registro: 2024-09-21
    Versión del articulo depositado: info:eu-repo/semantics/publishedVersion
    Enlace a la fuente original: https://ieeexplore.ieee.org/document/9658533
    URL Documento de licencia: https://repositori.urv.cat/ca/proteccio-de-dades/
    Referencia al articulo segun fuente origial: Ieee Access. 11 22430-22440
    Referencia de l'ítem segons les normes APA: Carrasco, Daniel Padilla; Rashwan, Hatem A; Garcia, Miguel Angel; Puig, Domenec (2023). T-YOLO: Tiny vehicle detection based on YOLO and multi-scale convolutional neural networks. Ieee Access, 11(), 22430-22440. DOI: 10.1109/ACCESS.2021.3137638
    DOI del artículo: 10.1109/ACCESS.2021.3137638
    Entidad: Universitat Rovira i Virgili
    Año de publicación de la revista: 2023
    Tipo de publicación: Journal Publications
  • Palabras clave:

    Computer Science (Miscellaneous),Computer Science, Information Systems,Engineering (Miscellaneous),Engineering, Electrical & Electronic,Materials Science (Miscellaneous),Telecommunications
    Tiny objects
    Smart parking
    Object detection
    Feature extraction
    Detectors
    Convolutional neural networks
    Computational modeling
    Cameras
    Automobiles
    tiny objects
    smart parking
    feature extraction
    detectors
    convolutional neural networks
    computational modeling
    cameras
    automobiles
    Telecommunications
    Materials science (miscellaneous)
    Materials science (all)
    General materials science
    General engineering
    General computer science
    Engineering, electrical & electronic
    Engineering (miscellaneous)
    Engineering (all)
    Engenharias iv
    Engenharias iii
    Electrical and electronic engineering
    Computer science, information systems
    Computer science (miscellaneous)
    Computer science (all)
    Ciência da computação
  • Documentos:

  • Cerca a google

    Search to google scholar