DEVELOPING AUTOMATED ANNOTATION FOR VISUAL RECOGNITION OF CONSTRUCTION RESOURCES
Mohammad M. Soltani1, Zhenhua Zhu2 and Amin Hammad
1) Ph.D. Student, Department of Building, Civil, and Environmental Engineering, Concordia University, Montreal, QC, Canada.
2) Ph.D., Assist. Prof., Department of Building, Civil, and Environmental Engineering, Concordia University, Montreal, QC, Canada.
3) Ph.D., Prof., Concordia Institute for Information Systems Engineering, Concordia University, Montreal, QC, Canada.
Abstract: The recognition of construction equipment is always necessary and important to monitor the progress and the safety of a construction project. Recently, the potentials of Computer Vision (CV) techniques have been investigated to facilitate the current equipment recognition process. However, it is found that manually collecting and annotating a large image dataset of different equipment is one the most time consuming tasks to make the CV techniques applicable for construction equipment recognition. This research aims to introduce an automated method for creating and annotating synthetic images of construction equipment while reducing the required time significantly. The images of the equipment are created from the 3D models of the construction machines and various backgrounds’ images are taken from the construction sites. Combining these two sets of images results in generating the synthetic images of the construction equipment while the location of the equipment are known in the synthetic images for the annotation purpose. The test results show that the proposed method is able to reduce the required time for annotating the images compared to traditional annotation methods while improving the detection accuracy.
Keywords: Object recognition, Construction equipment, Synthetic images, Auto-Annotation.
Mohammad M. Soltani, Zhenhua Zhu, and Amin Hammad. “DEVELOPING AUTOMATED ANNOTATION FOR VISUAL RECOGNITION OF CONSTRUCTION RESOURCES.” In Proceedings of International Conference on Civil and Building Engineering Informatics (ICCBEI 2015), 81. Tokyo, Japan, 2015.