Journal of the Korean Society for Industrial and Applied Mathematics

  • 제27권4호
  • /
  • Pages.311-323
  • /
  • 2023
  • /
  • 1226-9433(pISSN)
  • /
  • 1229-0645(eISSN)
한국산업응용수학회 (Korean Society for Industrial and Applied Mathematics)
권호 표지
DOI QR코드

DOI QR Code

ANALYSIS OF THE FLOOR PLAN DATASET WITH YOLO V5

  • 투고 : 2023.11.29
  • 심사 : 2023.12.20
  • 발행 : 2023.12.25
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

This paper introduces the industrial problem, the solution, and the results of the research conducted with Define Inc. The client company wanted to improve the performance of an object detection model on the floor plan dataset. To solve the problem, we analyzed the operational principles, advantages, and disadvantages of the existing object detection model, identified the characteristics of the floor plan dataset, and proposed to use of YOLO v5 as an appropriate object detection model for training the dataset. We compared the performance of the existing model and the proposed model using mAP@60, and verified the object detection results with real test data, and found that the performance increase of mAP@60 was 0.08 higher with a 25% shorter inference time. We also found that the training time of the proposed YOLO v5 was 71% shorter than the existing model because it has a simpler structure. In this paper, we have shown that the object detection model for the floor plan dataset can achieve better performance while reducing the training time. We expect that it will be useful for solving other industrial problems related to object detection in the future. We also believe that this result can be extended to study object recognition in 3D floor plan dataset.

키워드

과제정보

This work was supported by National Institute for Mathematical Sciences(NIMS) grant funded by the Korean government(MSIT) (No.NIMS-B23810000).

참고문헌

  1. Li, Fei-Fei, et al., Spatial Localization and Detection., CS231n, Stanford, 2016. Retrieved from http://cs231n.stanford.edu/slides/2016/winter1516_lecture8.pdf. 
  2. Viola, Paul, and Michael Jones, Rapid object detection using a boosted cascade of simple features, IEEE, Proceedings of the CVPR 2001, HI, USA 2001. 
  3. Viola, Paul, and Michael J. Jones, Robust real-time face detection, International journal of computer, 57 (2004), 137-154. 
  4. Felzenszwalb, Pedro, David McAllester, and Deva Ramanan, A discriminatively trained, multiscale, deformable part model, IEEE, Proceedings of the CVPR 2008, AK, USA 2008. 
  5. Zou, Zhengxia, et al, Object detection in 20 years: A survey, Proceedings of the IEEE, 111 (2023), 257-276. 
  6. Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton, Imagenet classification with deep convolutional neural networks, Advances in neural information processing systems 25, NIPS, Proceedings of NIPS 2012, NV, USA 2012. 
  7. Girshick, Ross, et al, Rich feature hierarchies for accurate object detection and semantic segmentation, IEEE, Proceedings of the CVPR 2014, OH, USA 2014. 
  8. He, Kaiming, et al, Spatial pyramid pooling in deep convolutional networks for visual recognition, IEEE transactions on pattern analysis and machine intelligence, 37 (2015), 1904-1916.  https://doi.org/10.1109/TPAMI.2015.2389824
  9. Girshick, Ross, Fast r-cnn, IEEE, Proceedings of the IEEE international conference on computer vision, Santiago, Chile 2015. 
  10. Ren, Shaoqing, et al, Faster r-cnn: Towards real-time object detection with region proposal networks, Advances in neural information processing systems 28, NIPS, Proceedings of NIPS 2015, Montreal, Canada 2015. 
  11. Lin, Tsung-Yi, et al, Feature pyramid networks for object detection, IEEE, Proceedings of the CVPR 2017, HI, USA 2017. 
  12. Redmon, Joseph, et al, You only look once: Unified, real-time object detection, IEEE, Proceedings of the CVPR 2016, NV, USA 2016. 
  13. Liu, Wei, et al, Ssd: Single shot multibox detector, Computer Vision-ECCV 2016, Springer, Proceedings of the14th European Conference, Amsterdam, The Netherlands, 2016. 
  14. Lin, Tsung-Yi, et al, Focal loss for dense object detection, IEEE transactions on pattern analysis and machine intelligence, 42 (2018), 318 - 327.  https://doi.org/10.1109/TPAMI.2018.2858826
  15. Law, Hei, and Jia Deng, Cornernet: Detecting objects as paired keypoints, Proceedings of the European conference on computer vision (ECCV), Munich, Germany 2018. 
  16. Zhao, Zhong-Qiu, et al, Object detection with deep learning: A review, IEEE transactions on neural networks and learning systems, 30 (2019), 3212-3232.  https://doi.org/10.1109/TNNLS.2018.2876865
  17. Carion, Nicolas, et al, End-to-end object detection with transformers, Cham: Springer International Publishing, Proceedings of the European conference on computer vision (ECCV), online, 2020. 
  18. Padilla, Rafael, Sergio L. Netto, and Eduardo AB Da Silva, A survey on performance metrics for objectdetection algorithms, IEEE, Proceedings of 2020 international conference on systems, signals and image processing (IWSSIP), Niteroi, Brazil, 2020. 
  19. Jocher, Glenn, et al. Ultralytics/yolov5: V5.0 - Yolov5-p6 1280 Models, AWS, Supervise.ly and Youtube Integrations. v5.0, Zenodo, 2021, doi:10.5281/zenodo.4679653.