AUTOMATIC DETECTION OF TIMBER-CRACKS IN WOODEN ARCHITECTURAL HERITAGE USING YOLOv3 ALGORITHM
- 1School of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, No.15 Yongyuan Road, Daxing District, Beijing, China
- 2Beijing Key Laboratory for Architectural Heritage Fine Reconstruction & Health Monitoring, No.15 Yongyuan Road, Daxing District, Beijing, China
- 3Engineering Research Center of Representative Building and Architectural Heritage Database, Ministry of Education, No.15 Yongyuan Road, Daxing District, Beijing, China
- 4School of Civil and Transportation Engineering, Beijing University of Civil Engineering and Architecture, No.15 Yongyuan Road, Daxing District, Beijing, China
Keywords: Wooden architectural heritage, Timber-cracks, Detection, YOLOv3 algorithm, DarkNet-53, Dataset
Abstract. As there usually exist widespread crack, decay, deformation and other damages in the wooden architectural heritage (WAH). It is of great significance to detect the damages automatically and rapidly in order to grasp the status for daily repairs. Traditional methods use artificial feature-driven point clouds and image processing technology for object detection. With the development of big data and GPU computing performance, data-driven deep learning technology has been widely used for monitoring WAH. Deep learning technology is more accurate, faster, and more robust than traditional methods.In this paper, we conducted a case study to detect timber-crack damages in WAH, and selected the YOLOv3 algorithm with DarkNet-53 as the backbone network in the deep learning technology according to the characteristics of the crack. A large timber-crack dataset was first constructed, based on which the timber-crack detection model was trained and tested. The results were analyzed both qualitatively and quantitatively, showing that our proposed method was able to reach an accuracy of more than 90% through processing each image for less than 0.1s. The promising results illustrate the validity of our self-constructed dataset as well as the reliability of YOLOv3 algorithm for the crack detection of wooden heritage.