FEASIBILITY ANALYSIS OF AN AUTOMATED DETECTION OF PHYSICAL DEFECT VIA COMPUTER VISION
DOI:
https://doi.org/10.11113/jt.v76.5880Keywords:
Defect detection, kinect, ANN, image processingAbstract
High demand of building construction has been taking places in the major city of Malaysia. However, despite this magnificent development, the lack of proper maintenance has caused a large portion of these properties deteriorated over time. The implementation of the project - Automated Detection of Physical Defect via Computer Vision - is a low cost system that helps to inspect the wall condition using Kinect camera. The system is able to classify the types of physical defects -crack and hole - and state its level of severity.The system uses artificial neural network as the image classifier due to its reliability and consistency. The validity of the system is shown using experiments on synthetic and real image data. This automated physical defect detection could detect building defect early, quickly, and easily, which results in cost saving and extending building life span.Â
References
Noorsidi Aizuddin Mat Noor, Chris Eves. 2010. Malaysia High-Rise Residential Property Management: 2004-2010 Trends & Scenario.
2012. Land Use Pattern of Peninsular Malaysia 2001-2010. National Physical Plan and Its Implementation. 15.
S. H. Zulkarnain, E. M. A Zawawi, M. Y. A. Rahman, N. K. F. Mustafa. 2011. A Review of Critical Success Factor in Building Maintenance Management Practice for University Sector. World of Academy of Science, Engineering and Technology. 195-199.
A. Georgopoulos, Ch. Ioannidis and A. Valanis. 2010. International Archieves of Photogrammetry, Remote Sensing and Spatial Information Sciences: Assessing the Performance of a Structured Light Scanner. 250-255.
Frank Boukamp, Burcu Akinci. 2009. Towards Automated Defect Detection: Object-Oriented Modeling of Construction Specifications.
Ishii Hirotake. 2013. Plant Maintenance and Dismantling Work Support Based on Three-Dimensional Scanning Technology. 97-104.
Michele Pirovano. 2012. An Open Source Implementation of Kinect Fusion and Case Study: Implementing a 3D Scanner with PCL.
Miika Santala. 2012. 3D Content Capturing and Reconstruction using Microsoft Kinect Depth Camera. 12-13.
Nathan Silberman, Rob Fergus. 2012. Indoor Scene Segmentation using a Structured Light Sensor. Dept of Computer Science, Courant Institute, New York University.
Javanta Kumar Basu, Debnath Battacharyya, Tai-hoon Kim. 2010. Use of Artificial Neural Network in Pattern Recognition. Interational Journal of Software Engineering and Its Application. 4(2): 23-34.
Hyeong-Gyeong, Moon, Jung-Hoon Kim. 2010. Intelligent Crack Detecting Algorithm on the Concrete Crack Image using Neural Network. Department of Civil and Environment Engineering, Yonsei University.1461-1467.
Downloads
Published
Issue
Section
License
Copyright of articles that appear in Jurnal Teknologi belongs exclusively to Penerbit Universiti Teknologi Malaysia (Penerbit UTM Press). This copyright covers the rights to reproduce the article, including reprints, electronic reproductions, or any other reproductions of similar nature.
