Genetic algorithm optimization of a convolutional neural network for autonomous crack detection

Oullette, R.; Browne, Matthew; Hirasawa, K.

doi:10.1109/cec.2004.1330900

Cited by 34 publications

(26 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…by adding feature-rich objects such as plants, pictures, etc) and it has shown to be fairly reliable in those environments though, in comparison tests, it faired worse than the feature recognition engine used in Market Beholder 6 , based on work from [6].…”

Section: E Evolution Robotics' Vslam ("Visual" Slam)mentioning

confidence: 95%

“…It uses differential-steering on a rigid four-wheeled chassis, each 2-wheeled side driven by one of two motors, and, is battery operated. An RS232 interface is provided for connecting to a laptop computer and can be controlled by a wired joystick or, provided a computer is 6 Market Beholder is a logo recognition software package developed by Robert Ouellette and Izuru Senokuchi for SGI-Japan. The software is not yet publicly available.…”

Section: A "Blackship"mentioning

confidence: 99%

See 1 more Smart Citation

A comparison of SLAM implementations for indoor mobile robots

Ouellette

Hirasawa

2007

2007 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

This paper compares the performances of four different Simultaneous Localization and Mapping (SLAM) implementations: Teambotica 1,5 , ICP 6D-SLAM 2,5 , SGI-J DP SLAM 3 , and ERSP vSLAM 4,5 . All the tested implementations used odometry for dead-reckoning as a base position measurement, and all but vSLAM use lasers as a main sensor (ERSP vSLAM uses a video camera). The comparison was taken using two different types of robots in three different environments: an office corridor, an office entry area, and an indoor robot driving course. The comparison uses a novel approach for map accuracy evaluation, one of the key factors in evaluating the performance of a SLAM implementation. The results show that even for similar setups, the outcomes can vary significantly for the different implementations, suggesting that the underlying implementations likely play a significant role in the SLAM performance.

show abstract

Section: E Evolution Robotics' Vslam ("Visual" Slam)mentioning

confidence: 95%

Section: A "Blackship"mentioning

confidence: 99%

A comparison of SLAM implementations for indoor mobile robots

Ouellette

Hirasawa

2007

2007 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

show abstract

“…Within the first category (which would also involve our approach for corrosion detection), one can find a large collection of contributions for automatic vision-based crack detection, e.g., for concrete surfaces see the works by Fujita et al [34], Oulette et al [35], Yamaguchi and Hashimoto [36] and Zhao et al [37], for airplanes see the work by Mumtaz et al [38], etc. However, regarding corrosion, to the best of our knowledge, the number of works which can be found is rather reduced [38,39,40,41,42,43].…”

Section: Background and Related Workmentioning

confidence: 99%

Vision-Based Corrosion Detection Assisted by a Micro-Aerial Vehicle in a Vessel Inspection Application

Ortiz

Bonnín-Pascual

Garcia-Fidalgo

et al. 2016

Sensors

View full text Add to dashboard Cite

Vessel maintenance requires periodic visual inspection of the hull in order to detect typical defective situations of steel structures such as, among others, coating breakdown and corrosion. These inspections are typically performed by well-trained surveyors at great cost because of the need for providing access means (e.g., scaffolding and/or cherry pickers) that allow the inspector to be at arm’s reach from the structure under inspection. This paper describes a defect detection approach comprising a micro-aerial vehicle which is used to collect images from the surfaces under inspection, particularly focusing on remote areas where the surveyor has no visual access, and a coating breakdown/corrosion detector based on a three-layer feed-forward artificial neural network. As it is discussed in the paper, the success of the inspection process depends not only on the defect detection software but also on a number of assistance functions provided by the control architecture of the aerial platform, whose aim is to improve picture quality. Both aspects of the work are described along the different sections of the paper, as well as the classification performance attained.

show abstract

“…In combination with preliminary Gaussian smoothing, nonmaximum suppression, and hysteresis thresholding, this approach yields the commonly used Canny edge detector (Canny 1986). Oullette, Browne, and Hirasawa (2004) described an approach to crack detection in sewer pipe images using a convolutional neural network. ANNs have been used for crack detection in pavement images (Cheng et al 2001;Lee and Lee 2004).…”

Section: Introductionmentioning

confidence: 99%

Edge Detection in Pipe Images Using Classification of Haar Wavelet Transforms

Mashford

Rahilly

Lane

et al. 2014

Applied Artificial Intelligence

View full text Add to dashboard Cite

Automatic image interpretation for pipe inspection is a relatively recent area of research, which has great potential benefit. An important component of such systems is crack detection, or, more generally, edge or discontinuity detection. This paper describes a new approach to edge detection and applies it to pipe images. The method labels each pixel in an image as an edge pixel or a nonedge pixel by processing the Haar wavelet transform of the image in a window about the pixel using a support vector machine. As a pixel classifier, to within a moderate morphological tolerance, the detector has an accuracy of 99% on the images on which it has been tested and compares favorably with the commonly used Canny edge detector.

show abstract

Genetic algorithm optimization of a convolutional neural network for autonomous crack detection

Cited by 34 publications

References 7 publications

A comparison of SLAM implementations for indoor mobile robots

A comparison of SLAM implementations for indoor mobile robots

Vision-Based Corrosion Detection Assisted by a Micro-Aerial Vehicle in a Vessel Inspection Application

Edge Detection in Pipe Images Using Classification of Haar Wavelet Transforms

Contact Info

Product

Resources

About