Detecting Surface Cracks on Buildings Using Computer Vision: An Experimental Comparison of Digital Image Processing and Deep Learning

Author(s):  
Ramshankar Yadhunath ◽  
Srivenkata Srikanth ◽  
Arvind Sudheer ◽  
C. Jyotsna ◽  
J. Amudha
Sensors ◽  
2020 ◽  
Vol 20 (16) ◽  
pp. 4505
Author(s):  
Yarens J. Cruz ◽  
Marcelino Rivas ◽  
Ramón Quiza ◽  
Gerardo Beruvides ◽  
Rodolfo E. Haber

One of the most important operations during the manufacturing process of a pressure vessel is welding. The result of this operation has a great impact on the vessel integrity; thus, welding inspection procedures must detect defects that could lead to an accident. This paper introduces a computer vision system based on structured light for welding inspection of liquefied petroleum gas (LPG) pressure vessels by using combined digital image processing and deep learning techniques. The inspection procedure applied prior to the welding operation was based on a convolutional neural network (CNN), and it correctly detected the misalignment of the parts to be welded in 97.7% of the cases during the method testing. The post-welding inspection procedure was based on a laser triangulation method, and it estimated the weld bead height and width, with average relative errors of 2.7% and 3.4%, respectively, during the method testing. This post-welding inspection procedure allows us to detect geometrical nonconformities that compromise the weld bead integrity. By using this system, the quality index of the process was improved from 95.0% to 99.5% during practical validation in an industrial environment, demonstrating its robustness.


2020 ◽  
Vol 48 ◽  
pp. 947-958
Author(s):  
Thomas Bergs ◽  
Carsten Holst ◽  
Pranjul Gupta ◽  
Thorsten Augspurger

2021 ◽  
Author(s):  
Bianka Tallita Passos ◽  
Moira Cristina Cubas Fatiga Tillmann ◽  
Anita Maria da Rocha Fernandes

Medical practice in general, and dentistry in particular, generatesdata sources, such as high-resolution medical images and electronicmedical records. Digital image processing algorithms takeadvantage of the datasets, enabling the development of dental applicationssuch as tooth, caries, crown, prosthetic, dental implant, andendodontic treatment detection, as well as image classification. Thegoal of image classification is to comprehend it as a whole and classifythe image by assigning it to a specific label. This work presentsthe proposal of a tool that helps the dental prosthesis specialist toexchange information with the laboratory. The proposed solutionuses deep learning to classify image, in order to improve the understandingof the structure required for modeling the prosthesis. Theimage database used has a total of 1215 images. Of these, 60 wereseparated for testing. The prototype achieved 98.33% accuracy.


Author(s):  
Abhishek C

Abstract: Nowadays many robotic systems are developed with lot of innovation, seeking to get flexibility and efficiency of biological systems. Hexapod Robot is the best example for such robots, it is a six-legged robot whose walking movements try to imitate the movements of the insects, it has two sets of three legs alternatively which is used to walk, this will provide stability, flexibility and mobility to travel on irregular surfaces. With these attributes the hexapod robots can be used to explore irregular surfaces, inhospitable places, or places which are difficult for humans to access. This paper involves the development of hexapod robot with digital image processing implemented on Raspberry Pi, to study in the areas of robotic systems with legged locomotion and robotic vision. This paper is an integration of a robotic system and an embedded system of digital image processing, programmed in high level language using Python. It is equipped with a camera to capture real time video and uses a distance sensor that allow the robot to detect obstacles. The Robot is Self-Stabilizing and can detect corners. The robot has 3 degrees of freedom in each six legs thus making a 18 DOF robotic movement. The use of multiple degrees of freedom at the joints of the legs allows the legged robots to change their movement direction without slippage. Additionally, it is possible to change the height from the ground, introducing a damping and a decoupling between the terrain irregularities and the body of the robot servo motors. Keywords: Hexapod, Raspberry Pi, Computer vision, Object detection, Yolo, Servo Motor, OpevCV.


2021 ◽  
Author(s):  
Vinay M. Shivanna ◽  
Kuan-Chou Chen ◽  
Bo-Xun Wu ◽  
Jiun-In Guo

The aim of this chapter is to provide an overview of how road signs can be detected and recognized to aid the ADAS applications and thus enhance the safety employing digital image processing and neural network based methods. The chapter also provides a comparison of these methods.


Sign in / Sign up

Export Citation Format

Share Document