An Analogy between Various Machine-learning Techniques for Detecting Construction Materials in Digital Images

다국어 초록 (Multilingual Abstract)

Digital images and video clips collected at construction jobsites are commonly used for extracting useful information. Exploring new applications for image processing techniques within the area of construction engineering and management is a steady growing field of research. One of the initial steps for various image processing applications is automatically detecting various types of construction materials on construction images. In this paper, the authors conducted a comparison study to evaluate the performance of different machine learning techniques for detection of three common categorists of building materials: Concrete, red brick, and OSB boards. The employed classifiers in this research are: Multilayer Perceptron (MLP), Radial Basis Function (RBF), and Support Vector Machine (SVM). To achieve this goal, the feature vectors extracted from image blocks are classified to perform a comparison between the efficiency of these methods for building material detection. The results indicate that for all three types of materials, SVM outperformed the other two techniques in terms of accurately detecting the material textures in images. The results also reveals that the common material detection algorithms perform very well in cases of detecting materials with distinct color and appearance (e.g., red brick); while their performance for detecting materials with color and texture variance (e.g., concrete) as well as materials containing similar color and appearance properties with other elements of the scene (e.g., ORB boards) might be less accurate.

참고문헌 (Reference)

1 Dimitrov, A., "Vision-based material recognition for automated monitoring of construction progress and generating building information modelling from unordered site image collections" 28 (28): 37-49, 2014

2 Neto, J., "Using colors to detect structural components in digital pictures" 17 (17): 61-67, 2002

3 Hagan, M. T., "Training feed forward networks with the Marquardt algorithm" 5 (5): 989-993, 1994

4 Cortes, C., "Support-vector networks" 20 (20): 273-297, 1995

5 Zhao, B., "Support vector machines and its application in handwritten numerical recognition" 2000

6 Zhao, L., "Study on key techniques of image processing and automatic recognition of tunnel cracks" 2012

7 Torfi, F., "Selection of project managers in construction firms using AHP and Fuzzy TOPSIS: A case study" 16 (16): 69-89, 2013

8 Brilakis, I., "Progressive 3D reconstruction of infrastructure with videogrammetry" 20 (20): 884-895, 2011

9 Zhu, Z., "Parameter optimization for automated concrete detection in image data" 19 (19): 944-953, 2010

10 Abdel-Qader, I., "PCA-based algorithm for unsupervised bridge crack detection" 37 (37): 771-778, 2006

11 Rashidi, A., "Optimized Selection of Key Frames for Monocular Videogrammetric Surveying of Civil Infrastructure" 27 (27): 270-282, 2013

12 Pinto, A. M., "Object recognition using laser range finder and machine learning techniques" 29 (29): 12-22, 2013

13 Rashidi, A., "Neurofuzzy genetic system for selection of construction project managers" 137 (137): 17-29, 2011

14 Beale, R., "Neural computing-an introduction" Adam Hilger 1990

15 Gutschoven, B., "Multi-modal identity verification using Support Vector Machines (SVM)" 2000

16 Brilakis, I., "Material-based construction site image retrieval" 19 (19): 341-355, 2005

17 Rashidi, A., "Innovative stereo visionbased approach to generate dense depth map of transportation infrastructure" 2215 : 93-99, 2011

18 Higgins, C., "Imaging tools for evaluation of gusset plate connections in steel truss bridges" 18 (18): 380-387, 2013

19 Feichtinger, H. G., "Gabor analysis and Algorithms: Theory and applications, Applied and Numerical Harmonic Analysis" Birkhauser 1998

20 Brilakis, I., "Content-based search engines for construction image databases" 14 (14): 537-550, 2005

21 Valentin, D., "Connectionist models of face processing: A survey" 27 (27): 1209-1230, 1994

22 Zhu, Z., "Concrete column recognition in images and videos" 24 (24): 478-487, 2010

23 Dai, F., "Comparison of image-based and time-of-flight-based technologies for three-dimensional reconstruction of infrastructure" 1 (1): 69-79, 2013

24 Song, S., "Comparative study of SVM methods combined with voxel selection for object category classification on fMRI data" 6 (6): 2011

25 Xu, G., "Automatic recognition of pavement surface crack based on BP neural network" 2008

26 Lee, S., "Automated recognition of surface defects using digital color image processing" 15 (15): 540-549, 2006

27 Son, H., "Automated color model–based concrete detection in construction-site images by using machine learning algorithms" 26 (26): 421-433, 2012

28 Man, Z., "An optimal weight learning machine for handwritten digit image recognition" 93 (93): 1624-1638, 2013

29 Tang, J., "An integrated digital image processing pavement management information system" 2012

30 Jahanshahi, M. R., "An innovative methodology for detection and quantification of cracks through incorporation of depth perception" 24 (24): 227-241, 2013

31 Jazebi, F., "An automated procedure for selecting project managers in construction firms" 19 (19): 97-106, 2013

32 Xanthopoulos, P., "A weighted support vector machine method for control chart pattern recognition" 70 : 134-149, 2014

33 Nawi, N. M., "A new Levenberg Marquardt based back propagation algorithm trained with cuckoo search" 11 : 18-23, 2013

34 Edson, J. R., "A comparison of SVM and HMM classifiers in the off-line signature verification" 26 (26): 1377-1385, 2005