Author, as appears in the article.: Carrasco, Daniel Padilla; Rashwan, Hatem A; Garcia, Miguel Angel; Puig, Domenec
Department: Enginyeria Informàtica i Matemàtiques
URV's Author/s: Abdellatif Fatahallah Ibrahim Mahmoud, Hatem / GARCIA GARCIA, MIGUEL ANGEL / Puig Valls, Domènec Savi
Keywords: 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
Abstract: 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.
Thematic Areas: 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
licence for use: https://creativecommons.org/licenses/by/3.0/es/
Author's mail: miguelangel.garciag@urv.cat hatem.abdellatif@urv.cat domenec.puig@urv.cat
Author identifier: 0000-0001-9972-2182 0000-0001-5421-1637 0000-0002-0562-4205
Record's date: 2024-09-21
Papper version: info:eu-repo/semantics/publishedVersion
Link to the original source: https://ieeexplore.ieee.org/document/9658533
Licence document URL: https://repositori.urv.cat/ca/proteccio-de-dades/
Papper original source: Ieee Access. 11 22430-22440
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
Article's DOI: 10.1109/ACCESS.2021.3137638
Entity: Universitat Rovira i Virgili
Journal publication year: 2023
Publication Type: Journal Publications