2016
DOI: 10.1061/(asce)be.1943-5592.0000811
|View full text |Cite
|
Sign up to set email alerts
|

Hybrid Sensor-Camera Monitoring for Damage Detection: Case Study of a Real Bridge

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
22
0

Year Published

2017
2017
2023
2023

Publication Types

Select...
7
1

Relationship

0
8

Authors

Journals

citations
Cited by 39 publications
(22 citation statements)
references
References 16 publications
0
22
0
Order By: Relevance
“…Yeum and Dyke proposed a vision‐based automated crack detection method for bridge; object detection and grouping techniques are utilized to extract images of possible damage regions; its performance is successfully validated using images collected by a handheld camera from a large‐scale rusted steel beam with cracks. Zauri et al proposed a monitoring system based on the combination of video images and conventional sensor network data to identify the possible damage on a movable steel beam bridge in Florida, USA; images and senor data are utilized to extract a series of unit influence lines, and the statistical outlier‐detection algorithm is combined to detect and localize common scenarios on the real‐world bridge successfully. Valenca et al proposed an automated crack detection method for concrete bridges based on image processing and laser scanning; terrestrial laser scanning technology is utilized to capture the geometric information of the bridge, which is used to correct images collected from the bridge; the method is validated by the experiment on a concrete viaduct at IC2 road, in Rio Maior, Portugal.…”
Section: Recent Progress On Damage Identification Methods For Beam Brmentioning
confidence: 99%
“…Yeum and Dyke proposed a vision‐based automated crack detection method for bridge; object detection and grouping techniques are utilized to extract images of possible damage regions; its performance is successfully validated using images collected by a handheld camera from a large‐scale rusted steel beam with cracks. Zauri et al proposed a monitoring system based on the combination of video images and conventional sensor network data to identify the possible damage on a movable steel beam bridge in Florida, USA; images and senor data are utilized to extract a series of unit influence lines, and the statistical outlier‐detection algorithm is combined to detect and localize common scenarios on the real‐world bridge successfully. Valenca et al proposed an automated crack detection method for concrete bridges based on image processing and laser scanning; terrestrial laser scanning technology is utilized to capture the geometric information of the bridge, which is used to correct images collected from the bridge; the method is validated by the experiment on a concrete viaduct at IC2 road, in Rio Maior, Portugal.…”
Section: Recent Progress On Damage Identification Methods For Beam Brmentioning
confidence: 99%
“…In addition to detection of local defects of structures, there are also studies on identifying global damages of the structures. Zaurin et al (2015) performed motion tracking algorithms to measure the mid-span deflections of bridges under the live traffic load (23). Computer Vision is also used to process ground penetration radar (GPR) and infrared thermography (IRT) images that are useful to identify delamination formed inside the concrete structures.…”
Section: Overview Of Deep Learning Approaches In Damage Detection Andmentioning
confidence: 99%
“…50 This method operates under the assumption that neighboring pixels have similar motion. With this assumption, it is possible to stack many of these equations into one system, as in equation (9), for a neighborhood of n pixels…”
Section: Feature Extractionmentioning
confidence: 99%