Vision-based material recognition for automated monitoring of construction progress and generating building information modeling from unordered site image collections

被引:184
作者
Dimitrov, Andrey [1 ]
Golparvar-Fard, Mani [2 ,3 ]
机构
[1] Columbia Univ, Dept Civil Engn & Engn Mech, New York, NY 10027 USA
[2] Univ Illinois, Dept Civil & Environm Engn, Urbana, IL USA
[3] Univ Illinois, Dept Comp Sci, Urbana, IL USA
关键词
Material recognition; Building information models; Texton; Support vector machine; 3D; INFRASTRUCTURE; RECONSTRUCTION; VISUALIZATION; RETRIEVAL; TEXTURE; OBJECTS;
D O I
10.1016/j.aei.2013.11.002
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Automatically monitoring construction progress or generating Building Information Models using site images collections - beyond point cloud data - requires semantic information such as construction materials and inter-connectivity to be recognized for building elements. In the case of materials such information can only be derived from appearance-based data contained in 2D imagery. Currently, the state-of-the-art texture recognition algorithms which are often used for recognizing materials are very promising (reaching over 95% average accuracy), yet they have mainly been tested in strictly controlled conditions and often do not perform well with images collected from construction sites (dropping to 70% accuracy and lower). In addition, there is no benchmark that validates their performance under real-world construction site conditions. To overcome these limitations, we propose a new vision-based method for material classification from single images taken under unknown viewpoint and site illumination conditions. In the proposed algorithm, material appearance is modeled by a joint probability distribution of responses from a filter bank and principal Hue-Saturation-Value color values and classified using a multiple one-vs.-all chi(2) kernel Support Vector Machine classifier. Classification performance is compared with the state-of-the-art algorithms both in computer vision and AEC communities. For experimental studies, a new database containing 20 typical construction materials with more than 150 images per category is assembled and used for validation. Overall, for material classification an average accuracy of 97.1% for 200 x 200 pixel image patches are reported. In cases where image patches are smaller, our method can synthetically generate additional pixels and maintain a competitive accuracy to those reported above (90.8% for 30 x 30 pixel patches). The results show the promise of the applicability of the proposed method and expose the limitations of the state-of-the-art classification algorithms under real world conditions. It further defines a new benchmark that could be used to measure the performance of future algorithms. (C) 2013 Elsevier Ltd. All rights reserved.
引用
收藏
页码:37 / 49
页数:13
相关论文
共 57 条
[1]  
[Anonymous], MACHINE VISION BASED
[2]  
[Anonymous], IS T SPIE ELECT IMAG
[3]  
[Anonymous], IEEE C COMP VIS PATT
[4]  
[Anonymous], P 5 BERK S MATH STAT
[5]  
[Anonymous], CONSTR RES C ASCE RE
[6]  
[Anonymous], P 28 ANN C COMP GRAP
[7]  
[Anonymous], THEORY APPL DIGITAL
[8]  
[Anonymous], ASCE J COMPUT CIVIL
[9]  
[Anonymous], TECHNICAL REPORT
[10]  
[Anonymous], ADV ENG INFORM