Advancing Vehicle Logo Detection with DETR to Handle Small Logos and Low-Quality Images
DOI:
https://doi.org/10.29207/resti.v9i4.6236Keywords:
detection transformers, logo, object detection, vehicleAbstract
Image-based vehicle logo detection is an important component in the implementation of vehicle information recognition technology, which supports the development of intelligent transportation systems. Vehicle logos, as elements that represent the identities of vehicle brands and models, play a significant role in completing vehicle identity data. The information obtained from this logo can be utilized to solve various traffic problems, such as vehicle document counterfeiting and theft, and for better traffic planning and management purposes. However, the main challenge in developing an accurate logo detection system lies in the wide variety of shapes, sizes, and positions of logos in different types of vehicles. In addition, the generally small size of logos, especially on certain vehicles, often makes it difficult for computer-based detection systems to recognize logos consistently, thus affecting the overall performance of the detection model. In this research, the Detection Transformers (DETR) method is used to build a vehicle logo detection system that focuses on small-scale logo. The testing process was conducted using the VL-10 dataset, which was specifically designed for vehicle logo detection evaluation. The results show that the DETR model can detect vehicle logos very well, even for small-scale logos. The model achieved an AP50 value of 0.952, which indicates a high level of accuracy and reliability in detecting the vehicle logo in the dataset used.
Downloads
References
A. Eldho, T. Francis, and C. V. Hari, “YOLO based Logo detection,” in 2019 9th International Conference on Advances in Computing and Communication (ICACC), IEEE, Nov. 2019, pp. 283–289. doi: 10.1109/ICACC48162.2019.8986207.
J. Zhang, S. Yang, C. Bo, and Z. Zhang, “Vehicle logo detection based on deep convolutional networks,” Computers & Electrical Engineering, vol. 90, p. 107004, Mar. 2021, doi: 10.1016/j.compeleceng.2021.107004.
S. Sahel, M. Alsahafi, M. Alghamdi, and T. Alsubait, “Logo Detection Using Deep Learning with Pretrained CNN Models,” Engineering, Technology & Applied Science Research, vol. 11, no. 1, pp. 6724–6729, Feb. 2021, doi: 10.48084/etasr.3919.
J. Zhang, L. Chen, C. Bo, and S. Yang, “Multi-Scale Vehicle Logo Detector,” Mobile Networks and Applications, vol. 26, no. 1, pp. 67–76, Feb. 2021, doi: 10.1007/s11036-020-01722-0.
F. C. Soon, H. Y. Khaw, J. H. Chuah, and J. Kanesan, “Hyper‐parameters optimisation of deep CNN architecture for vehicle logo recognition,” IET Intelligent Transport Systems, vol. 12, no. 8, pp. 939–946, Oct. 2018, doi: 10.1049/iet-its.2018.5127.
Y. Huang, R. Wu, Y. Sun, W. Wang, and X. Ding, “Vehicle Logo Recognition System Based on Convolutional Neural Networks with a Pretraining Strategy,” IEEE Transactions on Intelligent Transportation Systems, vol. 16, no. 4, pp. 1951–1960, Aug. 2015, doi: 10.1109/TITS.2014.2387069.
F. C. Soon, H. Y. Khaw, J. H. Chuah, and J. Kanesan, “Vehicle logo recognition using whitening transformation and deep learning,” Signal Image Video Process, vol. 13, no. 1, pp. 111–119, Feb. 2019, doi: 10.1007/s11760-018-1335-4.
A. Omidi, A. Heydarian, A. Mohammadshahi, B. A. Beirami, and F. Haddadi, “An Embedded Deep Learning-based Package for Traffic Law Enforcement,” in 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), IEEE, Oct. 2021, pp. 262–271. doi: 10.1109/ICCVW54120.2021.00034.
S. Yang, J. Zhang, C. Bo, M. Wang, and L. Chen, “Fast vehicle logo detection in complex scenes,” Opt Laser Technol, vol. 110, pp. 196–201, Feb. 2019, doi: 10.1016/j.optlastec.2018.08.007.
T. Diwan, G. Anirudh, and J. V. Tembhurne, “Object detection using YOLO: challenges, architectural successors, datasets and applications,” Multimed Tools Appl, vol. 82, no. 6, pp. 9243–9275, Mar. 2023, doi: 10.1007/s11042-022-13644-y.
M. A. M. Ali, T. Aly, A. T. Raslan, M. Gheith, and E. A. Amin, “Advancing Crowd Object Detection: A Review of YOLO, CNN and ViTs Hybrid Approach,” Journal of Intelligent Learning Systems and Applications, vol. 16, no. 03, pp. 175–221, 2024, doi: 10.4236/jilsa.2024.163011.
S. Dalal, U. K. Lilhore, M. Radulescu, S. Simaiya, V. Jaglan, and A. Sharma, “A hybrid LBP-CNN with YOLO-v5-based fire and smoke detection model in various environmental conditions for environmental sustainability in smart city,” Environmental Science and Pollution Research, Jan. 2024, doi: 10.1007/s11356-024-32023-8.
G. Dai, L. Hu, and J. Fan, “DA-ActNN-YOLOV5: Hybrid YOLO v5 Model with Data Augmentation and Activation of Compression Mechanism for Potato Disease Identification.,” Comput Intell Neurosci, vol. 2022, p. 6114061, 2022, doi: 10.1155/2022/6114061.
M. Lin et al., “DETR for Crowd Pedestrian Detection,” Dec. 2020.
Z. Sultan, M. U. Farooq, and R. H. Raza, “Improved Vehicle Logo Detection and Recognition for Complex Traffic Environments Using Deep Learning Based Unwarping of Extracted Logo Regions in Varying Angles,” 2023, pp. 12–25. doi: 10.1007/978-3-031-37649-8_2.
M. Jin and J. Zhang, “Research on Microscale Vehicle Logo Detection Based on Real-Time DEtection TRansformer (RT-DETR).,” Sensors (Basel), vol. 24, no. 21, Oct. 2024, doi: 10.3390/s24216987.
Y. Kong, X. Shang, and S. Jia, “Drone-DETR: Efficient Small Object Detection for Remote Sensing Image Using Enhanced RT-DETR Model,” Sensors, vol. 24, no. 17, p. 5496, Aug. 2024, doi: 10.3390/s24175496.
J. Huang and H. Wang, “Small Object Detection by DETR via Information Augmentation and Adaptive Feature Fusion,” Jan. 2024.
N. Carion, F. Massa, G. Synnaeve, N. Usunier, A. Kirillov, and S. Zagoruyko, “End-to-End Object Detection with Transformers,” May 2020.
U. Farooq, “Vehicle Logos (VL) - 10.” Accessed: Dec. 07, 2023. [Online]. Available: https://www.kaggle.com/datasets/mufarooqq/vl-10/data
J. Zhang, T. He, S. Sra, and A. Jadbabaie, “Why gradient clipping accelerates training: A theoretical justification for adaptivity,” May 2019.
Ian Goodfellow, Yoshua Bengio, and Aaron Courville, Deep Learning. London: The MIT Press, 2016.
Sebastian Raschka, “Finetuning LLMs on a Single GPU Using Gradient Accumulation.” Accessed: Jul. 11, 2024. [Online]. Available: https://lightning.ai/blog/gradient-accumulation/
J. Lamy-Poirier, “Layered gradient accumulation and modular pipeline parallelism: fast and efficient training of large language models,” Jun. 2021.
Z. Huang, B. Jiang, T. Guo, and Y. Liu, “Measuring the Impact of Gradient Accumulation on Cloud-based Distributed Training,” in 2023 IEEE/ACM 23rd International Symposium on Cluster, Cloud and Internet Computing (CCGrid), IEEE, May 2023, pp. 344–354. doi: 10.1109/CCGrid57682.2023.00040.
Pytorch Lightning, “Effective Training Techniques.” Accessed: Jul. 08, 2024. [Online]. Available: https://lightning.ai/docs/pytorch/stable/advanced/training_tricks.html#accumulate-gradients
Jiaqian Yu, Jingtao Xu, Yiwei Chen, and Weiming Li, “Learning Generalized Intersection Over Union for Dense Pixelwise Prediction,” Proceedings of the 38th International Conference on Machine Learning, 2021.
R. Padilla, S. L. Netto, and E. A. B. da Silva, “A Survey on Performance Metrics for Object-Detection Algorithms,” in 2020 International Conference on Systems, Signals and Image Processing (IWSSIP), IEEE, Jul. 2020, pp. 237–242. doi: 10.1109/IWSSIP48289.2020.9145130.
COCO - Common Objects in Context, “Detection Evaluation.” Accessed: Sep. 08, 2024. [Online]. Available: https://cocodataset.org/#detection-eval
A. Benali Amjoud and M. Amrouch, “Convolutional Neural Networks Backbones for Object Detection,” 2020, pp. 282–289. doi: 10.1007/978-3-030-51935-3_30.
E. Suherman, B. Rahman, D. Hindarto, and H. Santoso, “Implementation of ResNet-50 on End-to-End Object Detection (DETR) on Objects,” SinkrOn, vol. 8, no. 2, pp. 1085–1096, Apr. 2023, doi: 10.33395/sinkron.v8i2.12378.
I. Loshchilov and F. Hutter, “Decoupled Weight Decay Regularization,” Nov. 2017.
Downloads
Published
Issue
Section
License
Copyright in each article belongs to the author
- The author acknowledges that the RESTI Journal (System Engineering and Information Technology) is the first publisher to publish with a license Creative Commons Attribution 4.0 International License.
- Authors can enter writing separately, arrange the non-exclusive distribution of manuscripts that have been published in this journal into other versions (eg sent to the author's institutional repository, publication in a book, etc.), by acknowledging that the manuscript has been published for the first time in the RESTI (Rekayasa Sistem dan Teknologi Informasi) journal ;





