An analogy between various machine-learning techniques for detecting construction materials in digital images

被引:43
作者
Rashidi, Abbas [1 ]
Sigari, Mohamad Hoseyn [2 ]
Maghiar, Marcel [3 ]
Citrin, David [4 ]
机构
[1] Univ Tennessee, Dept Civil & Environm Engn, Knoxville, TN 37996 USA
[2] Univ Tehran, Coll Engn, Sch Elect & Comp Engn, CIPCE, Tehran 14399, Iran
[3] Georgia So Univ, Dept Civil Engn & Construct Management, Statesboro, GA 30460 USA
[4] Georgia Inst Technol, Sch Elect & Comp Engn, Atlanta, GA 30332 USA
关键词
digital images; Multilayer Perceptron (MLP); Radial Basis Function (RBF); Support Vector Machine (SVM); Construction Materials; Detection; RECOGNITION; RECONSTRUCTION; ALGORITHM;
D O I
10.1007/s12205-015-0726-0
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
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.
引用
收藏
页码:1178 / 1188
页数:11
相关论文
共 34 条
[1]   PCA-Based algorithm for unsupervised bridge crack detection [J].
Abdel-Qader, Ikhlas ;
Pashaie-Rad, Sara ;
Abudayyeh, Osama ;
Yehia, Sherif .
ADVANCES IN ENGINEERING SOFTWARE, 2006, 37 (12) :771-778
[2]  
Beale R., 1990, NEURAL COMPUTING AN, DOI DOI 10.1201/9781420050431
[3]   Material-based construction site image retrieval [J].
Brilakis, I ;
Soibelman, L ;
Shinagawa, Y .
JOURNAL OF COMPUTING IN CIVIL ENGINEERING, 2005, 19 (04) :341-355
[4]   Content-Based Search Engines for construction image databases [J].
Brilakis, I ;
Soibelman, L .
AUTOMATION IN CONSTRUCTION, 2005, 14 (04) :537-550
[5]   Progressive 3D reconstruction of infrastructure with videogrammetry [J].
Brilakis, Ioannis ;
Fathi, Habib ;
Rashidi, Abbas .
AUTOMATION IN CONSTRUCTION, 2011, 20 (07) :884-895
[6]  
CORTES C, 1995, MACH LEARN, V20, P273, DOI 10.1023/A:1022627411411
[7]   Comparison of Image-Based and Time-of-Flight-Based Technologies for Three-Dimensional Reconstruction of Infrastructure [J].
Dai, Fei ;
Rashidi, Abbas ;
Brilakis, Ioannis ;
Vela, Patricio .
JOURNAL OF CONSTRUCTION ENGINEERING AND MANAGEMENT, 2013, 139 (01) :69-79
[8]   Vision-based material recognition for automated monitoring of construction progress and generating building information modeling from unordered site image collections [J].
Dimitrov, Andrey ;
Golparvar-Fard, Mani .
ADVANCED ENGINEERING INFORMATICS, 2014, 28 (01) :37-49
[9]  
Feichtinger H. G., 1998, GABOR ANAL ALGORITHM
[10]  
Gutschoven B., 2000, P 3 INT C INF MAT FU