A vision-based motion capture and recognition framework for behavior-based safety management

Abstract In construction, about 80%–90% of accidents are associated with workers' unsafe acts. Nevertheless, the measurement of workers' behavior has not been actively applied in practice, due to the difficulties in observing workers on jobsites. In an effort to provide a robust and automated means for worker observation, this paper proposes a framework of vision-based unsafe action detection for behavior monitoring. The framework consists of (1) the identification of critical unsafe behavior, (2) the collection of relevant motion templates and site videos, (3) the 3D skeleton extraction from the videos, and (4) the detection of unsafe actions using the motion templates and skeleton models. For a proof of concept, experimental studies areundertaken to detect unsafe actions during ladder climbing (i.e., reaching far to a side) in motion datasets extracted from videos. The result indicates that the proposed framework can potentially perform well at detecting predefined unsafe actions in videos.

[1]  H Laitinen,et al.  The validity of the TR safety observation method on building construction. , 1999, Accident; analysis and prevention.

[2]  Thierry Peynot,et al.  Reliable automatic camera-laser calibration , 2010, ICRA 2010.

[3]  John G. Everett.  Overexertion Injuries in Construction , 1999 .

[4]  Terry E. McSween,et al.  Values-Based Safety Process: Improving Your Safety Culture With Behavior-Based Safety , 1995 .

[5]  L Punnett,et al.  PATH: a work sampling-based approach to ergonomic job analysis for construction and other non-repetitive work. , 1996, Applied ergonomics.

[6]  Arnold W. M. Smeulders,et al.  Real-Time Visual Concept Classification , 2010, IEEE Transactions on Multimedia.

[7]  Russell K. Schutt,et al.  Research Methods in Psychology: Investigating Human Behavior , 2011 .

[8]  O Karhu,et al.  Correcting working postures in industry: A practical method for analysis. , 1977, Applied ergonomics.

[9]  Ronald Poppe,et al.  Vision-based human motion analysis: An overview , 2007, Comput. Vis. Image Underst..

[10]  Markku Mattila,et al.  Effective supervisory behaviour and safety at the building site , 1994 .

[11]  Bernhard Schölkopf,et al.  Nonlinear Component Analysis as a Kernel Eigenvalue Problem , 1998, Neural Computation.

[12]  Olufemi A. Omitaomu,et al.  Weighted dynamic time warping for time series classification , 2011, Pattern Recognit..

[13]  Bernt Schiele,et al.  Monocular 3D pose estimation and tracking by detection , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[14]  J. Komaki,et al.  A behavioral approach to occupational safety: pinpointing and reinforcing safe performance in a food manufacturing plant. , 1978, The Journal of applied psychology.

[15]  K. J. Seymour,et al.  Long-term evaluation of a behavior-based method for improving safety performance : a meta-analysis of 73 interrupted time-series replications , 1999 .

[16]  Patricio A. Vela,et al.  Personnel tracking on construction sites using video cameras , 2009, Adv. Eng. Informatics.

[17]  Ioannis Brilakis,et al.  Progressive 3D reconstruction of infrastructure with videogrammetry , 2011 .

[18]  Jagdeep S. Chhokar,et al.  Improving safety through applied behavior analysis , 1984 .

[19]  Helen Lingard,et al.  Occupational health and safety in construction project management , 2004 .

[20]  SangUk Han,et al.  A Machine-Learning Classification Approach to Automatic Detection of Workers' Actions for Behavior-Based Safety Analysis , 2012 .

[21]  Chris Hendrickson,et al.  Project Management for Construction: Fundamental Concepts for Owners, Engineers, Architects, and Builders , 1989 .

[22]  Silvio Savarese,et al.  Application of D4AR - A 4-Dimensional augmented reality model for automating construction progress monitoring data collection, processing and communication , 2009, J. Inf. Technol. Constr..

[23]  George L. Germain,et al.  Practical loss control leadership , 1996 .

[24]  Jie Gong,et al.  Computer Vision-Based Video Interpretation Model for Automated Productivity Analysis of Construction Operations , 2010 .

[25]  Feniosky Peña-Mora,et al.  Application of dimension reduction techniques for motion recognition: Construction worker behavior monitoring , 2011 .

[26]  P. Buckle,et al.  Current techniques for assessing physical exposure to work-related musculoskeletal risks, with emphasis on posture-based methods. , 1999, Ergonomics.

[27]  Adrian Hilton,et al.  A survey of advances in vision-based human motion capture and analysis , 2006, Comput. Vis. Image Underst..

[28]  R Kadefors,et al.  A cube model for the classification of work with hand tools and the formulation of functional requirements. , 1993, Applied ergonomics.

[29]  J. Komaki,et al.  Development of an operant-based taxonomy and observational index of supervisory behavior. , 1986 .

[30]  S Salminen,et al.  Human errors in fatal and serious occupational accidents in Finland. , 1996, Ergonomics.

[31]  Antonio Torralba,et al.  SIFT Flow: Dense Correspondence across Scenes and Its Applications , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[32]  SangHyun Lee,et al.  Computer Vision Techniques for Worker Motion Analysis to Reduce Musculoskeletal Disorders in Construction , 2011 .

[33]  Peter Buckle,et al.  The development of the Quick Exposure Check (QEC) for assessing exposure to risk factors for work-related musculoskeletal disorders. , 2008, Applied ergonomics.

[34]  Harshad Suresh Lotlikar,et al.  A BEHAVIOR-BASED SAFETY APPROACH FOR CONSTRUCTION COMPANIES , 2005 .

[35]  Joann E D’Esposito.  Bureau of Labor Statistics Web Site , 2000 .

[36]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[37]  Steve C. Maddock,et al.  Motion Capture File Formats Explained , 2001 .

[38]  Abhinav Peddi.  Development of human pose analyzing algorithms for the determination of construction productivity in real-time , 2009 .

[39]  Ivan T. Robertson,et al.  Improving safety by the modification of behaviour , 1994 .

[40]  Janaka Y. Ruwanpura,et al.  AUTOMATED DATA ACQUISITION SYSTEM TO ASSESS CONSTRUCTION WORKER PERFORMANCE , 2009 .

[41]  Ioannis Brilakis,et al.  Comparative study of vision tracking methods for tracking of construction site resources , 2011 .

[42]  Richard Szeliski,et al.  Computer Vision - Algorithms and Applications , 2011, Texts in Computer Science.

[43]  Vincent Lepetit,et al.  DAISY: An Efficient Dense Descriptor Applied to Wide-Baseline Stereo , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[44]  Thomas R. Krause,et al.  The Behavior-Based Safety Process: Managing Involvement for an Injury-Free Culture , 1990 .

[45]  Tilak Dutta,et al.  Evaluation of the Kinect™ sensor for 3-D kinematic measurement in the workplace. , 2012, Applied ergonomics.

[46]  Jie Gong,et al.  Learning and Classifying Motions of Construction Workers and Equipment Using Bag of Video Feature Words and Bayesian Learning Methods , 2011 .

[47]  Ioannis Brilakis,et al.  Concrete Column Recognition in Images and Videos , 2010, J. Comput. Civ. Eng..

[48]  Jimmie Hinze,et al.  AN EVALUATION OF SAFETY PERFORMANCE MEASURES FOR CONSTRUCTION PROJECTS , 2003 .

[49]  Andrew Zisserman,et al.  Multiple View Geometry in Computer Vision (2nd ed) , 2003 .

[50]  Raymond E. Levitt,et al.  Construction safety management , 1987 .

[51]  Zhongke Shi,et al.  Tracking multiple workers on construction sites using video cameras , 2010, Adv. Eng. Informatics.