Computer Vision and Hybrid Reality for Construction Safety Risks: A Pilot Study

Construction sites are among the most hazardous venues. While most of the previous research has shed light on the human aspect, we propose to utilise the fast R-CNN object detection method to detect the construction hazard on sites and employ mixed reality to enable the artificial intelligence to detect the hazard. Fast region-based convolutional neural network object detection acquires expert knowledge to identify objects in the image. Unlike image classification, the complexity of object detection always implies an increase in complexity which demands solutions with regard to speed, accuracy and simplicity.

[1]  Mao Ye,et al.  Accurate object detection using memory-based models in surveillance scenes , 2017, Pattern Recognit..

[2]  Paul Milgram,et al.  A Taxonomy of Real and Virtual World Display Integration , 1999 .

[3]  Gudrun Klinker,et al.  Augmented 3D Arrows Reach Their Limits In Automotive Environments , 2009 .

[4]  Xinkai Wu,et al.  Car Detection from Low-Altitude UAV Imagery with the Faster R-CNN , 2017 .

[5]  Hui Wang,et al.  Distributed Augmented Reality for Visualizing Collaborative Construction Tasks , 2009 .

[6]  Xiaochun Luo,et al.  Detecting non-hardhat-use by a deep learning method from far-field surveillance videos , 2018 .

[7]  Rita Yi Man Li,et al.  An Economic Analysis on Automated Construction Safety , 2018 .

[8]  Marc Aurel Schnabel,et al.  Digital and Tangible Sensation: An Augmented Reality Urban Design Studio , 2005 .

[9]  Wang Huiqian,et al.  Vehicle type detection based on deep learning in traffic scene , 2018 .

[10]  Hirokazu Kato,et al.  Collaborative Mixed Reality , 1999 .

[11]  Hervé Glotin,et al.  Pedestrian Detection Based on Fast R-CNN and Batch Normalization , 2017, ICIC.

[12]  Holger Regenbrecht,et al.  Using Augmented Virtuality for Remote Collaboration , 2004, Presence: Teleoperators & Virtual Environments.

[13]  Heng Li,et al.  Computer vision aided inspection on falling prevention measures for steeplejacks in an aerial environment , 2018, Automation in Construction.

[14]  Peter E.D. Love,et al.  Falls from heights: A computer vision-based approach for safety harness detection , 2018, Automation in Construction.

[15]  Marc Aurel Schnabel.  Framing Mixed Realities , 2009 .

[16]  Xiangyu Wang,et al.  Mixed Reality-Based Visualization Interfaces for Architecture, Engineering, and Construction Industry , 2005 .

[17]  Teng Li,et al.  Facial Expression Recognition with Faster R-CNN , 2017 .

[18]  Nathan Rackliffe.  An Augmented Virtuality Display for Improving UAV Usability , 2005 .

[19]  Peter Anders.  Cynergies: Technologies that Hybridize Physical and Cyberspaces , 2003 .

[20]  Ava Fatah gen. Schieck,et al.  ARTHUR: A Collaborative Augmented Environment for Architectural Design and Urban Planning , 2004, J. Virtual Real. Broadcast..

[21]  Dieter Schmalstieg,et al.  The Studierstube Augmented Reality Project , 2002, Presence: Teleoperators & Virtual Environments.

[22]  Demis Hassabis,et al.  A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play , 2018, Science.