Threshold Determination for BIM User Image Segmentation Using Fuzzy C-Means for Development of Adaptive BIM
- 10.2991/aer.k.211129.019How to use a DOI?
- image processing; computer vision; thresholding; Fuzzy C-Mean; otsu; computational education; building information modeling
The Building Information Modeling (BIM) Repository is required to adapt to its users who access BIM objects independently through the Common Data Environment (CDE). BIM objects are not always easy for all users to understand and misperceptions may occur due to users’ varying abilities and learning styles. The solution can be done through the Intelligent Monitoring System (IMS) based learning technology to perform a visual analysis of BIM users. One important issue in the visual tracking system is the degradation of the model caused by inaccuracies in determining the segmentation threshold between the user’s foreground and background images. Segmentation is still difficult when performed on complex images that have a lot of noise, inhomogeneity intensity, textures, or multi-phase structures. The focus of this research is to determine the threshold value using the Fuzzy C-Mean (FCM) approach which is compared with the performance of the Otsu method. Results showed that FCM has a smaller error rate than the Otsu method, 1.15E + 02 perframe compared to 5.11E + 02. FCM processing time is longer than Otsu, 3.6057 units of time perframe compared to 0.0331. We hope that this research can be used to development of an adaptive BIM Repository.
- © 2021 The Authors. Published by Atlantis Press International B.V.
- Open Access
- This is an open access article under the CC BY-NC license.
Cite this article
TY - CONF AU - Stefanus Santosa AU - Sudirman S. Pana AU - De R. M. Setiadi AU - Aryo Satito AU - Anwar S. Ardjo AU - Yonathan P. Santosa PY - 2021 DA - 2021/11/30 TI - Threshold Determination for BIM User Image Segmentation Using Fuzzy C-Means for Development of Adaptive BIM BT - Proceedings of the International Conference on Innovation in Science and Technology (ICIST 2020) PB - Atlantis Press SP - 85 EP - 89 SN - 2352-5401 UR - https://doi.org/10.2991/aer.k.211129.019 DO - 10.2991/aer.k.211129.019 ID - Santosa2021 ER -