TY - JOUR
T1 - Vision-based material recognition for automated monitoring of construction progress and generating building information modeling from unordered site image collections
AU - Dimitrov, Andrey
AU - Golparvar-Fard, Mani
N1 - Copyright:
Copyright 2014 Elsevier B.V., All rights reserved.
PY - 2014/1
Y1 - 2014/1
N2 - 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 χ2 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 200×200 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 30×30 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.
AB - 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 χ2 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 200×200 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 30×30 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.
KW - Building information models
KW - Material recognition
KW - Support vector machine
KW - Texton
UR - http://www.scopus.com/inward/record.url?scp=84893782757&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84893782757&partnerID=8YFLogxK
U2 - 10.1016/j.aei.2013.11.002
DO - 10.1016/j.aei.2013.11.002
M3 - Article
AN - SCOPUS:84893782757
SN - 1474-0346
VL - 28
SP - 37
EP - 49
JO - Advanced Engineering Informatics
JF - Advanced Engineering Informatics
IS - 1
ER -