Development and Verification of Inspection Method for Concrete Surface utilizing Digital Camera

2020 ◽  
Author(s):  
Shungo Matsui ◽  
Yoshimasa Nakata ◽  
Hidenori Shitashimizu ◽  
Ryota Nakatsuji ◽  
Takeshi Ueda ◽  
...  
Keyword(s):  
Digital Camera ◽  
Concrete Surface ◽  
Inspection Method

Development of Wire Suspended Robot System (ARANEUS 2.0) for Bridge Inspection

10.29007/zw9k ◽  
2020 ◽  
Author(s):  
Kazuhide Nakata ◽  
Kazuki Umemoto ◽  
Kenji Kaneko ◽  
Ryusuke Fujisawa
Keyword(s):  
Unmanned Aerial Vehicle ◽  
Concrete Surface ◽  
Wire Length ◽  
High Definition ◽  
Bridge Inspection ◽  
Robot System ◽  
Inspection Method ◽  
Aerial Vehicle ◽  
The Wire

This study addresses the development of a robot for inspection of old bridges. By suspending the robot with a wire and controlling the wire length, the movement of the robot is realized. The robot mounts a high-definition camera and aims to detect cracks on the concrete surface of the bridge using this camera. An inspection method using an unmanned aerial vehicle (UAV) has been proposed. Compared to the method using an unmanned aerial vehicle, the wire suspended robot system has the advantage of insensitivity to wind and ability to carry heavy equipments, this makes it possible to install a high-definition camera and a cleaning function to find cracks that are difficult to detect due to dirt.

scholarly journals Pixel-Wise Crack Detection Using Deep Local Pattern Predictor for Robot Application

Sensors ◽  
2018 ◽  
Vol 18 (9) ◽  
pp. 3042 ◽  
Author(s):  
Yundong Li ◽  
Hongguang Li ◽  
Hongren Wang
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Visual Inspection ◽  
Crack Detection ◽  
Concrete Surface ◽  
Concrete Bridges ◽  
Experimental Results ◽  
Inspection Method ◽  
Local Pattern ◽  
Robotic Vision

Robotic vision-based crack detection in concrete bridges is an essential task to preserve these assets and their safety. The conventional human visual inspection method is time consuming and cost inefficient. In this paper, we propose a robust algorithm to detect cracks in a pixel-wise manner from real concrete surface images. In practice, crack detection remains challenging in the following aspects: (1) detection performance is disturbed by noises and clutters of environment; and (2) the requirement of high pixel-wise accuracy is difficult to obtain. To address these limitations, three steps are considered in the proposed scheme. First, a local pattern predictor (LPP) is constructed using convolutional neural networks (CNN), which can extract discriminative features of images. Second, each pixel is efficiently classified into crack categories or non-crack categories by LPP, using as context a patch centered on the pixel. Lastly, the output of CNN—i.e., confidence map—is post-processed to obtain the crack areas. We evaluate the proposed algorithm on samples captured from several concrete bridges. The experimental results demonstrate the good performance of the proposed method.

Crack identification method for concrete structures considering angle of view using RGB-D camera-based sensor fusion

2020 ◽  
pp. 147592172093475
Author(s):  
Hyunjun Kim ◽  
Sahyeon Lee ◽  
Eunjong Ahn ◽  
Myoungsu Shin ◽  
Sung-Han Sim
Keyword(s):  
High Resolution ◽  
Sensor Fusion ◽  
Crack Width ◽  
Measurement Accuracy ◽  
Concrete Structures ◽  
Digital Camera ◽  
Concrete Surface ◽  
Structural Safety ◽  
Crack Identification ◽  
Angle Of View

Cracks on concrete structures are an important indicator for assessing concrete durability and structural safety. Although such cracks are typically monitored by manual visual inspection, this method has drawbacks in terms of inspection time, safety, cost-effectiveness, and measurement accuracy. An innovative alternative is digital image processing, which can be used to obtain crack information from images captured using a digital camera. However, in image-based crack detection, the crack width may vary depending on the angle of the camera with respect to the concrete surface. A skewed angle of view is often encountered, particularly when capturing images from unmanned aerial vehicles or from higher locations. This study proposes a crack identification strategy using a combination of RGB-D and high-resolution digital cameras to accurately measure cracks regardless of the angle of view. The camera system is equipped with a tailored sensor fusion algorithm for crack identification, enabling a high measurement resolution and a robust depth estimation considering the skewed angle problem. An approximate plane corresponding to the concrete surface is introduced to effectively handle the high noise in the depth measurement data of the RGB-D camera. Subsequently, the crack image captured using the high-resolution digital camera is mapped onto the obtained plane model, allowing the crack width to be determined using the three-dimensional coordinates of each crack pixel. The measurement accuracy of the proposed approach is experimentally validated on an actual concrete structure.

A Rapid Reserve Inspection Method for Opencast Mine Using Ordinary Digital Camera

2013 ◽  
Vol 333-335 ◽  
pp. 1533-1537
Author(s):  
Biao Yang ◽  
Ming Fei Wu ◽  
Hao Li
Keyword(s):  
Point Cloud ◽  
Stereo Matching ◽  
Three Dimensional ◽  
Digital Camera ◽  
Distortion Correction ◽  
Practical Application ◽  
Design Data ◽  
Inspection Method ◽  
Opencast Mine ◽  
Processing Steps

Reserve inspection is of great significance for rational mining and environmental protection of opencast mine. This paper proposes a method for rapid reserve inspection of opencast mine. The method uses ordinary digital camera which is calibrated rigorously to acquire images of opencast mine, and carries out a series of image processing steps including distortion correction, relative orientation, absolute orientation and stereo matching, thus generating the point cloud and reconstructing the three-dimensional mine model. According to the earlier topographic and design data, the variations of mine surface, volume and reserve are thereby calculated. The practical application of the method proposed has achieved great improvement in efficiency and accuracy for opencast mine reserve inspection.

Analysis of Coliform and Colifecal Total Pollution Test on Various Types of Drinking Water Using the MPN (Most Probable Number) Method

2020 ◽  
Vol 2 (2) ◽  
Author(s):  
Wanda Aulya ◽  
Fadhliani Fadhliani ◽  
Vivi Mardina
Keyword(s):  
Drinking Water ◽  
Fecal Coliform ◽  
Pathogenic Bacteria ◽  
Microbiological Quality ◽  
Coliform Bacteria ◽  
Most Probable Number ◽  
Inspection Method ◽  
Sample Number ◽  
Probable Number ◽  
Fecal Coliform Bacteria

Water is the main source for life and also the most severe substance caused by pollution. The mandatory parameters for determining microbiological quality of drinking water are total non-fecal Coliform bacteria and Coliform fecal (Escherichia coli). Coliform bacteria are a group of microorganisms commonly used as indicators, where these bacteria can be a signal to determine whether a water source has been contaminated by bacteria or not, while fecal Coliform bacteria are indicator bacteria polluting pathogenic bacteria originating from human feces and warm-blooded animals (mammals) . The water inspection method in this study uses the MPN (Most Probable Number) method which consists of 3 tests, namely, the presumption test, the affirmation test, and the reinforcement test. The results showed that of 15 drinking water samples 8 samples were tested positive for Coliform bacteria with the highest total bacterial value of sample number 1, 15 (210/100 ml), while 7 other samples were negative. From 8 positive Coliform samples only 1 sample was stated to be negative fecal Coliform bacteria and 7 other samples were positive for Coliform fecal bacteria with the highest total bacterial value of sample number 1 (210/100 ml).

Using a Digital Camera for Documentation

2002 ◽  
Vol 12 (4) ◽  
pp. 145-146
Author(s):  
Steven C. Chang
Keyword(s):  
Digital Camera

A testing paradigm for quantifying ICC profilers

2019 ◽  
Vol 2019 (1) ◽  
pp. 80-85
Author(s):  
Pooshpanjan Roy Biswas ◽  
Alessandro Beltrami ◽  
Joan Saez Gomez
Keyword(s):  
Digital Camera ◽  
Visual Assessment ◽  
Just Noticeable Difference ◽  
Color Management ◽  
Color Gamut ◽  
Gamut Mapping ◽  
Digital File ◽  
Mapping Process ◽  
Testing Paradigm

To reproduce colors in one system which differs from another system in terms of the color gamut, it is necessary to use a color gamut mapping process. This color gamut mapping is a method to translate a specific color from a medium (screen, digital camera, scanner, digital file, etc) into another system having a difference in gamut volume. There are different rendering intent options defined by the International Color Consortium [5] to use the different reproduction goals of the user [19]. Any rendering intent used to reproduce colors, includes profile engine decisions to do it, i.e. looking for color accuracy, vivid colors or pleasing reproduction of images. Using the same decisions on different profile engines, the final visual output can look different (more than one Just Noticeable Difference[16]) depending on the profile engine used and the color algorithms that they implement. Profile performance substantially depends on the profiler engine used to create them. Different profilers provide the user with varying levels of liberty to design a profile for their color management needs and preference. The motivation of this study is to rank the performance of various market leading profiler engines on the basis of different metrics designed specifically to report the performance of particular aspects of these profiles. The study helped us take valuable decisions regarding profile performance without any visual assessment to decide on the best profiler engine.

Sign in / Sign up

Export Citation Format

Share Document