A number of image processing techniques IPTs have been implemented for detecting civil infrastructure defects to partially replace human-conducted onsite inspections. These IPTs are primarily used to manipulate images to extract defect features, such as cracks in concrete and steel surfaces. However, the extensively varying real-world situations e.g., lighting and shadow changes can lead to challenges to the wide adoption of IPTs. To overcome these challenges, this article proposes a vision-based method using a deep architecture of convolutional neural networks CNNs for detecting concrete cracks without calculating the defect features. As CNNs are capable of learning image features automatically, the proposed method works without the conjugation of IPTs for extracting features. The designed CNN is trained on 40 K images of 256 × 256 pixel resolutions and, consequently, records with about 98% accuracy. The trained CNN is combined with a sliding window technique to scan any image size larger than 256 × 256 pixel resolutions. The robustness and adaptability of the proposed approach are tested on 55 images of 5,888 × 3,584 pixel resolutions taken from a different structure which is not used for training and validation processes under various conditions e.g., strong light spot, shadows, and very thin cracks. Comparative studies are conducted to examine the performance of the proposed CNN using traditional Canny and Sobel edge detection methods. The results show that the proposed method shows quite better performances and can indeed find concrete cracks in realistic situations.

/pdf/deep-learning-based-crack-damage-detection-using-1cucavd1rf.pdf

Deep Learning-Based Crack Damage Detection Using Convolutional Neural Networks

Principal component analysis is one of the most important and powerful methods in chemometrics as well as in a wealth of other areas. This paper provides a description of how to understand, use, and interpret principal component analysis. The paper focuses on the use of principal component analysis in typical chemometric areas but the results are generally applicable.

/pdf/principal-component-analysis-1sba76ou47.pdf

Principal component analysis

International Joint Conference on Neural Networks

https://nottingham-repository.worktribe.com/preview/745918/Manuscript_KochEtAl_2015_accepted.pdf

A review on computer vision based defect detection and condition assessment of concrete and asphalt civil infrastructure

The spatial characteristics of cracks are significant indicators to assess and evaluate the health of existing buildings and infrastructures However, the current manual crack description 

Automatic Pixel-Level Crack Detection and Measurement Using Fully Convolutional Network

In this paper, we introduce a novel image-based approach to detect cracks in concrete surfaces. Crack detection is important for the inspection, diagnosis, and maintenance of concrete structures. However, conventional image-based approaches cannot achieve precise detection since the image of the concrete surface contains various types of noise due to different causes such as concrete blebs, stain, insufficient contrast, and shading. In order to detect the cracks with high fidelity, we assume that they are composed of thin interconnected textures and propose an image-based percolation model that extracts a continuous texture by referring to the connectivity of brightness and the shape of the percolated region, depending on the length criterion of the scalable local image processing techniques. Additionally, noise reduction based on the percolation model is proposed. We evaluated the validity of the proposed technique by using precision recall and receiver operating characteristic (ROC) analysis by means of some experiments with actual concrete surface images. Copyright © 2007 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

Image-Based Crack Detection for Real Concrete Surfaces

For a complex autonomous robotic system such as a humanoid robot, motor-babbling-based sensorimotor learning is considered an effective method to develop an internal model of the self-body and the environment autonomously. In this paper, we propose a method of sensorimotor learning and evaluate it performance in active learning. The proposed model is characterized by a function we call the “confidence”, and is a measure of the reliability of state prediction and control. The confidence for the state can be a good measure to bias the next exploration strategy of data sampling, and to direct its attention to areas in the state domain less reliably predicted and controlled. We consider the confidence function to be a first step toward an active behavior design for autonomous environment adaptation. The approach was experimentally validated using the humanoid robot James.

/pdf/active-motor-babbling-for-sensorimotor-learning-4gef4i9tgf.pdf

Active motor babbling for sensorimotor learning

http://www.shalab.phys.waseda.ac.jp/pub/pdf/rs2.pdf

Nonlinear principal component analysis to preserve the order of principal components

We present an integrated approach allowing the humanoid robot iCub to learn the skill of archery. After being instructed how to hold the bow and release the arrow, the robot learns by itself to shoot the arrow in such a way that it hits the center of the target. Two learning algorithms are proposed and compared to learn the bi-manual skill: one with Expectation-Maximization based Reinforcement Learning, and one with chained vector regression called the ARCHER algorithm. Both algorithms are used to modulate and coordinate the motion of the two hands, while an inverse kinematics controller is used for the motion of the arms. The image processing part recognizes where the arrow hits the target and is based on Gaussian Mixture Models for color-based detection of the target and the arrow's tip. The approach is evaluated on a 53-DOF humanoid robot iCub.

/pdf/learning-the-skill-of-archery-by-a-humanoid-robot-icub-4xeeqb95oz.pdf

Learning the skill of archery by a humanoid robot iCub

This paper describes a developmental framework for action-driven perception in anthropomorphic robots. The key idea of the framework is that action generation develops the agent's perception of its own body and actions. Action-driven development is critical for identifying changing body parts and understanding the effects of actions in unknown or nonstationary environments. We embedded minimal knowledge into the robot's cognitive system in the form of motor synergies and actions to allow motor exploration. The robot voluntarily generates actions and develops the ability to perceive its own body and the effect that it generates on the environment. The robot, in addition, can compose this kind of learned primitives to perform complex actions and characterize them in terms of their sensory effects. After learning, the robot can recognize manipulative human behaviors with cross-modal anticipation for recovery of unavailable sensory modality, and reproduce the recognized actions afterward. We evaluated the proposed framework in the experiments with a real robot. In the experiments, we achieved autonomous body identification, learning of fixation, reaching and grasping actions, and developmental recognition of human actions as well as their reproduction.

Ryo Saegusa

Papers

Image-Based Crack Detection for Real Concrete Surfaces

Active motor babbling for sensorimotor learning

Nonlinear principal component analysis to preserve the order of principal components

Learning the skill of archery by a humanoid robot iCub

Developmental Perception of the Self and Action