T-YOLO: Tiny Vehicle Detection Based on YOLO and Multi-Scale Convolutional Neural Networks
Open accessThe DOI matches its Crossref record, with a small difference in title or year; 40 of the 40 references it cites were found in a registry or an index; 3 of the 11 sources its claims cite were checked for support.
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.
Overview
CoChat Summary
## TL;DR
The paper proposes T-YOLO, a lightweight modification of YOLOv5 for tiny vehicle detection in cenital-view parking images, using a multi-scale module and attention mechanisms. On PKLot, the adapted model improved precision substantially over the baseline, reaching up to 96.34% precision versus 63.87% for baseline YOLOv5, while keeping roughly 30 fps.
## Key findings
- Replacing YOLOv5’s Focus layer with the proposed multi-scale module (MSM) improved precision from 0.6273 in YOLOv5s to 0.9203 in YOLOv5s_MSM.
- The best reported model, Yolov5s_MSM_CAM, achieved a precision of up to 96.34%; the paper reports the baseline YOLOv5 precision as 63.87%.
- The paper reports a small reduction in trainable parameters, from 7.28 million in YOLOv5-S to 7.26 million in the proposed model.
- The proposed adaptation ran at about 30 fps; the single-branch solution Yolov5_SM_x2 increased speed from 35 fps to 42 fps and was described as outperforming YOLOv5m in speed.
## Methods
- Design: The study modifies YOLOv5 by replacing the Focus layer with a multi-scale module based on ENet-style branches (x1, x2, x4) and by adding spatial/channel attention modules (SAM, CAM, SCAM) in different configurations.
- Data/sample: PKLot was used; the authors selected the cenital-plane subset (PUCPR) with 4,474 images and about 100 parking spots per image, totaling 424,269 tagged spots. The data were split 80% train and 20% test, and annotations were translated to COCO format.
- Analysis: The authors conducted ablation experiments comparing baseline YOLOv5, fine-tuned YOLOv5, MSM variants, attention variants, and pooling variants, evaluating precision, recall, mAP, inference speed (fps), and parameter count.
## Limitations
- The authors state that the model is designed for a specific application: tiny cars from a cenital-view camera in large parking areas, so generalization beyond this scenario is not demonstrated in the text.
- The paper notes that using a multi-scale approach can add redundancy and may degrade performance if not chosen carefully; they found the three-branch MSM may not be the most efficient for this dataset.
- Evident from the text: the dataset is restricted to a monitored/tagged region of PKLot, and the authors apply a mask to exclude nontagged cars, which limits what the model is evaluated on.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures

















Verification
Claims the paper makes
2 Valid · 5 Not valid · 7 Not checked · 53 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Most object detection models use generalpurpose datasets, such as COCO [12], ImageNet [13], and VOC [14]), where vehicle (i.e., cars) images are usually taken from a lateral or frontal view instead of a cenital plane.”
§ T-YOLO: Tiny Vehicle Detection Based on YOLO and Multi-Scale Convolutional Neural Networks > I. INTRODUCTION
What the sources say
- Partly supportedcites [12] 12. T.-Y. Lin, M. Maire, S. Belongie, L. Bourdev, R. Girshick, J. Hays, P. Perona, D. Ramanan, C. L. Zitnick, and P. Dollár, ''Microsoft COCO: Common objects in context,'' 2014, arXiv:1405.0312. sourceExperimental — accuracy not yet measured
The Introduction (p. 2) identifies COCO as a dataset for learning object models, and Dataset Statistics (p. 6) says it is designed for object detection. But the paper does not establish that most detection models use such datasets or that COCO car images are usually lateral or frontal rather than overhead; the Discussion (p. 10) instead describes COCO images as having varied viewpoints. (LLM, conf=0.85)
- Not checked — no full text of the sourcecites [13] 13. J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, ''ImageNet: A large-scale hierarchical image database,'' in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2009, pp. 248-255. source
- Partly supportedcites [14] 14. M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman, ''The PASCAL visual object classes (VOC) challenge,'' Int. J. Comput. Vis., vol. 88, no. 2, pp. 303-338, Jun. 2010, doi: 10.1007/ s11263-009-0275-4. sourceExperimental — accuracy not yet measured
The Introduction identifies VOC as a publicly available object-detection dataset that includes cars. Section 3.1 describes varied viewing conditions, and the Additional Information section says high-confidence car detections show varying poses; neither establishes that VOC car images are usually lateral or frontal rather than overhead. The paper also does not establish how widely object-detection models use such datasets. (LLM, conf=0.86)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As shown in Table 2, as expected, the COCO-trained YOLO-v5s and YOLO-v5m models yielded the worst results in terms of R and mAP.”
§ T-YOLO: Tiny Vehicle Detection Based on YOLO and Multi-Scale Convolutional Neural Networks > 5) RESULTS AND ANALYSIS
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Besides, Fig. 10 shows that the integration of MSM and CAM with the YOLOv5 model helps to maximize the overlap of predicted bound-boxes versus actual bounding boxes with IoU > 0.95 for tiny car detection.”
§ T-YOLO: Tiny Vehicle Detection Based on YOLO and Multi-Scale Convolutional Neural Networks > 5) RESULTS AND ANALYSIS
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Adding the MSM block to YOLOv5 was able to properly detect and classify cars in the images.Fig. 9 also showed the ability of the Yolov5_MSM model in localizing and classify the cars even in a crowed scenario.”
§ T-YOLO: Tiny Vehicle Detection Based on YOLO and Multi-Scale Convolutional Neural Networks > 5) RESULTS AND ANALYSIS
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“This technique allowed us to speed up the inference time of the initial block 10 times.”
§ T-YOLO: Tiny Vehicle Detection Based on YOLO and Multi-Scale Convolutional Neural Networks > II. METHOD
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
34 more claims
Create a free account to see all 67 claims and every source verdict.
- It may state two separate claims as one. 22
- Probably not a substantial claim. 9
Citations
Cites
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
(2016) · Cited by 31,590
Feature Pyramid Networks for Object Detection
Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.106 · Cited by 30,939
SSD: Single Shot MultiBox Detector
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., & Berg, A. C. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46448-0_2 · Cited by 22,128
The pascal visual object classes (VOC) challenge
Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2010) · International Journal of Computer Vision · doi:10.1007/s11263-009-0275-4 · Cited by 19,599
YOLOv3: An Incremental Improvement
Redmon, J., & Farhadi, A. (2018) · arXiv · doi:10.48550/arxiv.1804.02767 · Cited by 17,141
A Multi-Modal Distributed Real-Time IoT System for Urban Traffic Control (Invited Paper)
Khanam, Z., Achari, V. P. S., Boukhennoufa, I., Jindal, A., & Singh, A. K. (2024) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/oasics.ng-res.2024.2 · Cited by 14,040
Research works printed but not linked: 1
- 24. Smart Syst. Inventive Technol. (ICSSIT), Aug. 2020, pp. 1316-1321.
Cited by
Items 101–135 of 135
Bai, G., Gu, J. J., Xing, Y. T., et al. (2024) · IEEE International Conference on Electronic Technology, Communication and Information (ICETCI) · doi:10.1109/icetci61221.2024.10594543
Wang, X., Liu, P., Wang, Y., Liao, J., Guo, Y., We, W., Liu, Y., & Huang, J. F. (2025) · International Conference on Transportation Information and Safety · doi:10.1109/ictis68762.2025.11214791
Ressource-Efficient Moth Detection for Pest Monitoring with YOLOv5
Farooq, M. T., Leipert, M., Maier, A., & Christlein, V. (2023) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci52147.2023.10372041
Xu, G., Yu, E., Wang, H., Zhai, G., Hu, P., Han, Y., & Kareem, A. (2026) · Structures · doi:10.1016/j.istruc.2026.111235
Damage Detection Method for Road Ancillary Facilities Integrating Attention Mechanism
Yang, S., Wang, H., Wang, K., et al. (2025) · IEEE Access · doi:10.1109/access.2025.3546622
Bakri, M. F., Kurnia, S. T., Muhammad Fajar, B., Kaswar, A. B., Andayani, D. D., Adiba, F., Sanatang, & Syahrul (2026) · Proceedings of Engineering and Technology Innovation · doi:10.46604/peti.2026.16020
ERD-YOLOv5s: a Multi-Scale Feature Extraction Network for Object Detection in Driving Scenarios
Wang, R., Zhai, Y., Kong, F., et al. (2023) · International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI) · doi:10.1109/cisp-bmei60920.2023.10373332
An, J., Chen, W., Ni, Y., & Chang, F. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01801-z · Cited by 1
Li, Z. K., Shen, R., Shengjun, X. U., Ren, R., Xin, R., & He, B. (2026) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc69976.2026.11559885
Automatic detection of wood cracks based on improved YOLOv8 algorithm
Ning, J., Zhou, J., Wang, R., Zhang, J., & Zhang, S. (2024) · International Conference on Electronic Information Engineering and Data Processing (EIEDP) · doi:10.1117/12.3033057
Parking Space Detection in Different Weather Conditions Based on YOLOv5 Method
Asy'ari, M. F., Fatichah, C., & Suciati, N. (2023) · doi:10.1109/icsecs58457.2023.10256411
Research on Optimizing YOLOv8 Model to Improve The Detection Performance of Low Altitude UAV
Meng, J., Gao, Y., Shu, B., & Wang, Y. (2024) · International Conference on Electronic Communication and Artificial Intelligence (ICECAI) · doi:10.1109/icecai62591.2024.10675231
Wei, C., Peng, Z., Yang, L., et al. (2025) · IEEE International Conference on High Performance Computing and Communications (HPCC) · doi:10.1109/hpcc67675.2025.00237
Suvra, D. K., & Sanam, T. F. (2024) · International Conference on Computer and Information Technology (ICCIT) · doi:10.1109/iccit64611.2024.11022598
Research on Improved YOLO11 Network with MSCA for Small Object Detection Education
Shi, Y., Xu, L., Shen, X., Zhang, J., Yin, W., Yang, F., & Wang, Y. (2024) · International Conference on Information Education and Artificial Intelligence (ICIEAI) · doi:10.1145/3724504.3724602
YOLO for Urban Traffic: Insights from Helsinki Port Surveillance
Sharma, S., Singotam, S., Kayastha, A., Jafari, O., Happonen, A., Skön, J.-P., Heikkonen, J., & Kanth, R. K. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-5958-6_2
InterHier: Learning Interconnected Hierarchical Semantics for Open-Vocabulary Object Detection
Kim, Y.-J., Kim, H.-J., & Lee, S. (2026) · IEEE Access · doi:10.1109/access.2026.3655392
Intelligent Traffic Management: Enhancing Emergency Vehicle Navigation
Kavya, A., Sivaiah, B., Saikiran, P., & Reddy, C. S. (2026) · Lecture notes in networks and systems · doi:10.1007/978-981-96-9048-0_49
Huang, C., Zhang, L., Duan, W., Jia, G., Tang, R., & Huang, D. (2026) · Transportation Research Record Journal of the Transportation Research Board · doi:10.1177/03611981261465417
A CLAHE-MIRNet-YOLOv5 Pipeline for Vehicle Detection in Night Vision Surveillance
Venkatesh, V., Akash, A., Abhiraj, N., Panwar, M., Suhag, M., & Sunil (2025) · Asian Conference on Innovation in Technology (ASIANCON) · doi:10.1109/asiancon66527.2025.11280771
BATCH-DNN: Adaptive and Dynamic Batching for Multi-DNN Accelerators
Ranawaka, P., & Stenström, P. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-99857-7_8
Metadata
- Authors
- Padilla Carrasco, D., Rashwan, H. A., García, M. Á., & Puig, D.
- Affiliations
- Department of Computer Engineering and Mathematics, Universitat Rovira i Virgili, Tarragona, Spain
- Universitat Rovira i Virgili (ES)
- Universidad Autónoma de Madrid (ES)
- Venue
- IEEE Access
- Published
- 2023
- Volume
- 11
- Pages
- 22430-22440
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W4205762292
- Semantic Scholar
- 99fcb6a1865c0b3de0a134d0372c17971fc6b871
- Cited by
- 145
- References
- 37
- Citations by year
- 2026: 22 · 2025: 40 · 2024: 54 · 2023: 25
- FWCI
- 6.36
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- IEEE Access (publishedVersion, cc-by)
- Biblos-e Archivo (Universidad Autónoma de Madrid) (submittedVersion, public-domain)
- Rovira & Virgili repository (submittedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Hispana (submittedVersion)
- Funders
- Agncia de Gesti dAjuts Universitaris i de Recerca (2018 DI 054)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
- Keywords
- small object detection, vehicle detection, YOLOv5, multi-scale convolutional neural network, lightweight object detection model, parking occupancy detection, smart cities, parameter reduction, real-time inference
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.