2015 CII Annual Conference August 3–5 • Boston, Massachusetts
Visual Sensing and Analytics for Construction and
Infrastructure Management
Academic Committee Annual Conference Speaker
General research question
• What are different types of visual sensing technologies?
– Current and coming in the horizon
• How do they perform for construction/infrastructure data
collection/situation awareness needs?
• What types of analytics can be performed on this data?
• How do they help in supporting a variety of construction and
infrastructure management decisions?
Panel
Lincoln Wood, Manager,
Virtual Design &
Construction, Turner Construction
Daniel Huber,
Senior Systems Scientist at Robotics Institute,
Carnegie Mellon Univ.
Mani Golparvar-Fard,
Assist. Prof of Civil & Env.
Eng.& Computer Scien.,
University of Illinois
Burcu Akinci,
Paul Christiano Prof. of Civil & Env. Eng.,
Carnegie Mellon Univ.
Image based sensing and analytics for
construction
Terrestrial scanners and analytics for construction and
infrastructure management
Aerial Robots for Infrastructure
Management
Visual Sensing and analytics current usages
IMAGE BASED SENSING AND
ANALYTICS FOR CONSTRUCTION
Smooth flow of production in construction
• Identifying different forms of waste
• 25-50% waste in coordination labor and equipment
and in managing, moving, and installation material.
• Cost overrun and delays
• 90% of projects exhibit average 28% higher cost than
their forecasted cost.
• What do I need for minimizing waste?
• Continuous downstream feedback.• Awareness on “who does what task, and where”
Opportunity- 5D BIM for progress analysis
Turner Construction
Operation-Level 4D (3D + Schedule) 5D (3D + Schedule + Cost)
PB
Extend the application of BIM/CIM primarily used for clash prevention
and constructability review as
a basis for monitoring work in progress
Opportunities for Reality capture (Images & Videos)
Unordered construction pictures Time-lapse photography and videosDrones equipped with cameras
Icarusaerials – U of Illinois Collaboration, 2015, FL
Autonomous Image Data Collection
Automatic creation of flight path
Opportunity- 4D As-built Models + 4D BIM
$500M Sacramento King’s Stadium Sacramento, California
Turner Construction
Automated Detection of Progress Deviations
Color-coding BIM elements based on traffic light color metaphor
Components ahead of schedule Components behind schedule
Weekly Work Plan Updates
Video-based Activity Analysis via Crowdsourcing
Worker with Role “A” is conducting Activity “B” with Tool “C”
LIDAR FOR CONSTRUCTION
Opportunity – LIDAR for reality capture
Hand-held laser scanners Terrestrial scanning
Mobile ground scanning Scanning with Drones Airborne lidar http://cenews.com/article/8332/mobile_laser_scanning
http://www.geoconnexion.com/news/optech-to-deliver-state-of-the-art-airborne-lidar-and-thermal-imaging-solut/_
Increased spatial
coverage and efficiency Increased precision and
Opportunity – Integration of Virtual with Reality
Context
Assessing the capabilities of 3D imaging technologies
Surface 1 Surface 3 Surface 2 Edge 1 Edge 2 0.914 m 0.920 m 0.926 m 0.931 m 0.888 m 0.859 m 0.893 m 0.858 mEdge detection and
Boundary effects
Surface flatness
Points to BIM
Sensor / Data
Construction decision support
AERIAL ROBOTS FOR
INFRASTRUCTURE MANAG.
ARIA – The Aerial Robotic Infrastructure Analyst
• Benefits
– Go in difficult to reach places – Comprehensive monitoring – Reduced footprint
– Offline access
• Challenges
– Difficult to get hands on
ARIA Research Objectives
Algorithms transform 3D and imagery from the MAV into a high-level semantic model, and finally a finite element model.
Rapid infrastructure modeling and analysis
The robot acts as an inspector’s apprentice, learning to accomplish inspection tasks with
various levels of autonomy.
Robotic inspection assistant
A visualization environment provides an immersive virtual infrastructure representation to aid in inspection and assessment tasks.
Immersive inspection and assessment
VISUAL SENSING CURRENT
USAGES
Problem
• We are great planners but we are poor at adjusting as we go
• Results in large delta between as-planned vs.as-built dataSwitch primary focus from Office to field to field to office
As-planned vs. as-built comparison and documentation requires images/videos to be located within BIM environment
Data Requirements
• Reliable/Trust
• Relevant- that impacts 3 week look-ahead plan
• Speed (must be at the pace of the conversation/meeting)
Location-based monitoring for tasks not associated with physical elements Highlighting as-risk locations with
Integrated point cloud and BIM
Task Readiness Level = R Location Entropy = TL
Social
• Patchwork or small batch is OK (crowd sourced with "infill" capture)
• Ownership of the builder / data collector
Conclusion
• Visual Sensing and Analytics can
– Reduce the gap between as-built and as-planned data
– Minimize the challenges for data collection, synthesis, and analytics
– Enable root-cause assessment on potential/actual deviations