반도체디스플레이기술학회지 (Journal of the Semiconductor & Display Technology)

한국반도체디스플레이기술학회 (The Korean Society Of Semiconductor & Display Technology)
권호 표지

최적의 객체 검출 모델 개발을 위한 특화 데이터 세트 추출 방법

Specialized Dataset Extraction Method for Developing Optimal Pedestrian Detection Model

  • 박천수 (성균관대학교 컴퓨터교육과)
  • Chun-Su Park (Computer Education, Sungkyunkwan University)
  • 투고 : 2024.09.09
  • 심사 : 2024.09.12
  • 발행 : 2024.09.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Public datasets, which are freely available and often labeled, play a crucial role in training object detection models in computer vision. While public datasets are effective for developing general object detection models, they may not be ideal for specialized tasks. For specific object detection needs, it is more beneficial to create and use a dataset tailored to the target object. This paper proposes a method for extracting a target-specific dataset from public datasets to develop object detection models with superior performance for the target object. This approach not only improves detection accuracy, but also reduces training data requirements and complexity. We evaluate the performance of the proposed method using the latest object detection model YOLOv10.

키워드

과제정보

본 연구는 중소벤처기업부의 연구비지원(00264489)에 의해 수행되었습니다. 본 연구는 과학기술정보통신부 및 정보통신기획평가원의 메타버스 융합대학원의 연구 결과로 수행되었습니다. (IITP-2024-RS-2023-00254129)

참고문헌

  1. P. Helber, et al. "Eurosat: A novel dataset and deep learning benchmark for land use and land cover classification." IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 12, no. 7, pp. 2217-2226, 2019. https://doi.org/10.1109/JSTARS.2019.2918242
  2. J. G. A. Barbedo, "Impact of dataset size and variety on the effectiveness of deep learning and transfer learning for plant disease classification." Computers and electronics in agriculture, vol. 153, pp. 46-53, 2018. https://doi.org/10.1016/j.compag.2018.08.013
  3. https://velog.io/@markany/data-management-process
  4. "AI Learning Dataset Construction Guide", Ministry of Science and ICT, 2021.
  5. B. Kim, J. Lee, S. Lee, Y. Chung, "Evaluating object categorization quality of deep learning training data for object detection in computer vision app", pp. 667-669, Proceedings of the Korean Society of Computer Information Conference, 2020.
  6. D. Hoiem, S. K. Divvala, and J. H. Hays. "Pascal VOC 2008 challenge." World Literature Today, vol. 24, no. 1, pp. 1-4, 2009.
  7. J. Deng, et al. "Imagenet: A large-scale hierarchical image database." IEEE conference on computer vision and pattern recognition, pp. 248-255, 2009.
  8. T. Y. Lin, al. "Microsoft coco: Common objects in context." Computer Vision-ECCV 2014, pp. 740-755, 2014.
  9. G. Patterson, and J. Hays. "Coco attributes: Attributes for people, animals, and objects." Computer Vision- ECCV 2016: pp. 11-14, 2016.
  10. C. Mao, et al. "Mini-YOLOv3: real-time object detector for embedded applications." IEEE Access, vol. 7, pp. 133529-133538, 2019. https://doi.org/10.1109/ACCESS.2019.2941547
  11. S. Jha, C. Seo, F. Yang, and G. P. Joshi, "Real time object detection and tracking system for video surveillance system." Multimedia Tools and Applications, vol. 80, no. 3, pp. 3981-3996, 2021. https://doi.org/10.1007/s11042-020-09749-x
  12. C. S. Park, "YOLOv7 Model Inference Time Complexity Analysis in Different Computing Environments." Journal of the Semiconductor & Display Technology, vol. 21, no. 3, pp. 7-11, 2022.
  13. C. S. Park, "Performance Analysis of DNN inference using OpenCV Built in CPU and GPU Functions." Journal of the Semiconductor & Display Technology, vol. 21, no. 1, pp. 75-78, 2022.
  14. M. Sohan, et al. "A review on yolov8 and its advancements." International Conference on Data Intelligence and Cognitive Informatics, pp. 529-545, 2024.
  15. J. Terven and D. Cordova-Esparza. "A comprehensive review of YOLO: From YOLOv1 to YOLOv8 and beyond." arXiv preprint arXiv:2304.00501, 2023.
  16. P. Jiang, D. Ergu, F. Liu, Y. Cai, and B. Ma. "A Review of Yolo Algorithm Developments." Procedia Computer Science, pp. 1066-1073, 2022.
  17. https://github.com/meituan/YOLOv6
  18. G. Ang, et al. "A novel application for real-time arrhythmia detection using YOLOv8." arXiv preprint arXiv: 2305.16727, 2023.
  19. A. Wang, et al. "Yolov10: Real-time end-to-end object detection." arXiv preprint arXiv:2405.14458, 2024.
  20. https://docs.ultralytics.com/models/yolov10/#performance
  21. J. Kook and H. Lee, "A Research of a Traffic Light Signal Classification Model using YOLOv5 for Autonomous Driving." Journal of the Semiconductor & Display Technology, vol. 23, no. 1, pp. 61-64, 2024.