False Ceiling Deterioration Detection and Mapping Using a Deep Learning Framework and the Teleoperated Reconfigurable 'Falcon' Robot

Archana Semwal; Rajesh Elara Mohan; Lee Ming Jun Melvin; Povendhan Palanisamy; Chanthini Baskar; Lim Yi; Sathian Pookkuttath; Balakrishnan Ramalingam

doi:10.3390/s22010262

False Ceiling Deterioration Detection and Mapping Using a Deep Learning Framework and the Teleoperated Reconfigurable 'Falcon' Robot

Archana Semwal, Rajesh Elara Mohan, Lee Ming Jun Melvin, Povendhan Palanisamy, Chanthini Baskar, Lim Yi, Sathian Pookkuttath Balakrishnan Ramalingam

Sensors (Basel, Switzerland), Vol.22(1), p.262

30/12/2021

: https://doi.org/10.3390/s22010262

: 35009802

Chemistry

Chemistry, Analytical

Engineering

Engineering, Electrical & Electronic

Instruments & Instrumentation

Physical Sciences

Science & Technology

Technology

Periodic inspection of false ceilings is mandatory to ensure building and human safety. Generally, false ceiling inspection includes identifying structural defects, degradation in Heating, Ventilation, and Air Conditioning (HVAC) systems, electrical wire damage, and pest infestation. Human-assisted false ceiling inspection is a laborious and risky task. This work presents a false ceiling deterioration detection and mapping framework using a deep-neural-network-based object detection algorithm and the teleoperated 'Falcon' robot. The object detection algorithm was trained with our custom false ceiling deterioration image dataset composed of four classes: structural defects (spalling, cracks, pitted surfaces, and water damage), degradation in HVAC systems (corrosion, molding, and pipe damage), electrical damage (frayed wires), and infestation (termites and rodents). The efficiency of the trained CNN algorithm and deterioration mapping was evaluated through various experiments and real-time field trials. The experimental results indicate that the deterioration detection and mapping results were accurate in a real false-ceiling environment and achieved an 89.53% detection accuracy.

(1)

url

https://doi.org/10.3390/s22010262

Published (Version of record)

: False Ceiling Deterioration Detection and Mapping Using a Deep Learning Framework and the Teleoperated Reconfigurable 'Falcon' Robot
: Archana Semwal - Singapore University of Technology and Design
Rajesh Elara Mohan - Singapore Univ Technol & Design SUTD, Engn Product Dev Pillar, Singapore 487372, Singapore
Lee Ming Jun Melvin - Singapore University of Technology and Design
Povendhan Palanisamy - Singapore University of Technology and Design
Chanthini Baskar - Vellore Institute of Technology University
Lim Yi - Singapore University of Technology and Design
Sathian Pookkuttath - Singapore University of Technology and Design
Balakrishnan Ramalingam - Singapore University of Technology and Design
: Sensors (Basel, Switzerland), Vol.22(1), p.262
: Mdpi
: 20
: 192 22 00108 / National Robotics Programme under its Robot Domain 192 25 00051 / National Robotics Programme under Robotics Enabling Capabilities and Technologies
: 9912325009846
: EPD Pillar
: English
: Journal article