Concrete Crack Detection Based on Well-Known Feature Extractor Model and the YOLO_v2 Network

This paper compares the crack detection performance (in terms of precision and computational cost) of the YOLO_v2 using 11 feature extractors, which provides a base for realizing fast and accurate crack detection on concrete structures. Cracks on concrete structures are an important indicator for assessing their durability and safety, and real-time crack detection is an essential task in structural maintenance. The object detection algorithm, especially the YOLO series network, has significant potential in crack detection, while the feature extractor is the most important component of the YOLO_v2. Hence, this paper employs 11 well-known CNN models as the feature extractor of the YOLO_v2 for crack detection. The results confirm that a different feature extractor model of the YOLO_v2 network leads to a different detection result, among which the AP value is 0.89, 0, and 0 for ‘resnet18’, ‘alexnet’, and ‘vgg16’, respectively meanwhile, the ‘googlenet’ (AP = 0.84) and ‘mobilenetv2’ (AP = 0.87) also demonstrate comparable AP values. In terms of computing speed, the ‘alexnet’ takes the least computational time, the ‘squeezenet’ and ‘resnet18’ are ranked second and third respectively; therefore, the ‘resnet18’ is the best feature extractor model in terms of precision and computational cost. Additionally, through the parametric study (influence on detection results of the training epoch, feature extraction layer, and testing image size), the associated parameters indeed have an impact on the detection results. It is demonstrated that: excellent crack detection results can be achieved by the YOLO_v2 detector, in which an appropriate feature extractor model, training epoch, feature extraction layer, and testing image size play an important role.

Download Full-text

Performance Evaluation of Deep CNN-Based Crack Detection and Localization Techniques for Concrete Structures

Sensors ◽

10.3390/s21051688 ◽

2021 ◽

Vol 21 (5) ◽

pp. 1688

Author(s):

Luqman Ali ◽

Fady Alnajjar ◽

Hamad Al Jassmi ◽

Munkhjargal Gochoo ◽

Wasif Khan ◽

...

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Crack Detection ◽

Concrete Structures ◽

Model Performance ◽

Training Data ◽

Computational Time ◽

Data Heterogeneity ◽

Public Datasets ◽

Detection And Localization

This paper proposes a customized convolutional neural network for crack detection in concrete structures. The proposed method is compared to four existing deep learning methods based on training data size, data heterogeneity, network complexity, and the number of epochs. The performance of the proposed convolutional neural network (CNN) model is evaluated and compared to pretrained networks, i.e., the VGG-16, VGG-19, ResNet-50, and Inception V3 models, on eight datasets of different sizes, created from two public datasets. For each model, the evaluation considered computational time, crack localization results, and classification measures, e.g., accuracy, precision, recall, and F1-score. Experimental results demonstrated that training data size and heterogeneity among data samples significantly affect model performance. All models demonstrated promising performance on a limited number of diverse training data; however, increasing the training data size and reducing diversity reduced generalization performance, and led to overfitting. The proposed customized CNN and VGG-16 models outperformed the other methods in terms of classification, localization, and computational time on a small amount of data, and the results indicate that these two models demonstrate superior crack detection and localization for concrete structures.

Download Full-text

A research on an improved Unet-based concrete crack detection algorithm

Structural Health Monitoring ◽

10.1177/1475921720940068 ◽

2020 ◽

pp. 147592172094006

Author(s):

Lingxin Zhang ◽

Junkai Shen ◽

Baijie Zhu

Keyword(s):

Deep Learning ◽

Crack Detection ◽

Detection Algorithm ◽

Important Indicator ◽

Test Dataset ◽

Training Time ◽

Damage Level ◽

Detection Algorithms ◽

Concrete Crack ◽

Model Affect

Crack is an important indicator for evaluating the damage level of concrete structures. However, traditional crack detection algorithms have complex implementation and weak generalization. The existing crack detection algorithms based on deep learning are mostly window-level algorithms with low pixel precision. In this article, the CrackUnet model based on deep learning is proposed to solve the above problems. First, crack images collected from the lab, earthquake sites, and the Internet are resized, labeled manually, and augmented to make a dataset (1200 subimages with 256 × 256 × 3 resolutions in total). Then, an improved Unet-based method called CrackUnet is proposed for automated pixel-level crack detection. A new loss function named generalized dice loss is adopted to detect cracks more accurately. How the size of the dataset and the depth of the model affect the training time, detecting accuracy, and speed is researched. The proposed methods are evaluated on the test dataset and a previously published dataset. The highest results can reach 91.45%, 88.67%, and 90.04% on test dataset and 98.72%, 92.84%, and 95.44% on CrackForest Dataset for precision, recall, and F1 score, respectively. By comparing the detecting accuracy, the training time, and the information of datasets, CrackUnet model outperform than other methods. Furthermore, six images with complicated noise are used to investigate the robustness and generalization of CrackUnet models.

Download Full-text

Entropy Ensemble Filter: Does information content assessment of bootstrapped training datasets before model training lead to better trade-off between ensemble size and predictive performance?

10.5194/egusphere-egu2020-1963 ◽

2020 ◽

Author(s):

Hossein Foroozand ◽

Steven V. Weijs

Keyword(s):

Machine Learning ◽

Computational Cost ◽

Predictive Performance ◽

Original Data ◽

Training Data ◽

Computational Time ◽

Limiting Factor ◽

Ensemble Size ◽

Content Assessment ◽

Model Training

<p>Machine learning is the fast-growing branch of data-driven models, and its main objective is to use computational methods to become more accurate in predicting outcomes without being explicitly programmed. In this field, a way to improve model predictions is to use a large collection of models (called ensemble) instead of a single one. Each model is then trained on slightly different samples of the original data, and their predictions are averaged. This is called bootstrap aggregating, or Bagging, and is widely applied. A recurring question in previous works was: how to choose the ensemble size of training data sets for tuning the weights in machine learning? The computational cost of ensemble-based methods scales with the size of the ensemble, but excessively reducing the ensemble size comes at the cost of reduced predictive performance. The choice of ensemble size was often determined based on the size of input data and available computational power, which can become a limiting factor for larger datasets and complex models&#8217; training. In this research, it is our hypothesis that if an ensemble of artificial neural networks (ANN) models or any other machine learning technique uses the most informative ensemble members for training purpose rather than all bootstrapped ensemble members, it could reduce the computational time substantially without negatively affecting the performance of simulation.</p>

Download Full-text

LogEvent2vec: LogEvent-to-Vector Based Anomaly Detection for Large-Scale Logs in Internet of Things

Sensors ◽

10.3390/s20092451 ◽

2020 ◽

Vol 20 (9) ◽

pp. 2451 ◽

Cited By ~ 4

Author(s):

Jin Wang ◽

Yangning Tang ◽

Shiming He ◽

Changqing Zhao ◽

Pradip Kumar Sharma ◽

...

Keyword(s):

Feature Extraction ◽

Internet Of Things ◽

Anomaly Detection ◽

Language Processing ◽

Large Scale ◽

Naive Bayes ◽

Computational Cost ◽

Naïve Bayes ◽

Computational Time ◽

Transformation Methods

Log anomaly detection is an efficient method to manage modern large-scale Internet of Things (IoT) systems. More and more works start to apply natural language processing (NLP) methods, and in particular word2vec, in the log feature extraction. Word2vec can extract the relevance between words and vectorize the words. However, the computing cost of training word2vec is high. Anomalies in logs are dependent on not only an individual log message but also on the log message sequence. Therefore, the vector of words from word2vec can not be used directly, which needs to be transformed into the vector of log events and further transformed into the vector of log sequences. To reduce computational cost and avoid multiple transformations, in this paper, we propose an offline feature extraction model, named LogEvent2vec, which takes the log event as input of word2vec to extract the relevance between log events and vectorize log events directly. LogEvent2vec can work with any coordinate transformation methods and anomaly detection models. After getting the log event vector, we transform log event vector to log sequence vector by bary or tf-idf and three kinds of supervised models (Random Forests, Naive Bayes, and Neural Networks) are trained to detect the anomalies. We have conducted extensive experiments on a real public log dataset from BlueGene/L (BGL). The experimental results demonstrate that LogEvent2vec can significantly reduce computational time by 30 times and improve accuracy, comparing with word2vec. LogEvent2vec with bary and Random Forest can achieve the best F1-score and LogEvent2vec with tf-idf and Naive Bayes needs the least computational time.

Download Full-text

Motion and Geometric Feature Analysis for Real-time Automatic Micro-expression Recognition Systems

F1000Research ◽

10.12688/f1000research.72970.1 ◽

2021 ◽

Vol 10 ◽

pp. 1029

Author(s):

Adamu Muhammad Buhari ◽

Chee-Pun Ooi ◽

Vishnu Monn Baskaran ◽

Wooi-Haw Tan

Keyword(s):

Feature Extraction ◽

Real Time ◽

Recognition Performance ◽

Detection Algorithm ◽

Geometric Feature ◽

Expression Recognition ◽

Image Size ◽

Recognition Systems ◽

Full Face ◽

Micro Expression

The trend of real-time micro-expression recognition systems has increased with recent advancements in human-computer interaction (HCI) in security and healthcare. Several studies in this field contributed towards recognition accuracy, while few studies look into addressing the computation costs. In this paper, two approaches for micro-expression feature extraction are analyzed for real-time automatic micro-expression recognition. Firstly, motion-based approach, which calculates motion of subtle changes from an image sequence and present as features. Then, secondly, a low computational geometric-based feature extraction technique, a very popular method for facial expression recognition in real-time. These approaches were integrated in a developed system together with a facial landmark detection algorithm and a classifier for real-time analysis. Moreover, the recognition performance were evaluated using SMIC, CASME, CAS(ME)2 and SAMM datasets. The results suggest that the optimized Bi-WOOF (leveraging on motion-based features) yields the highest accuracy of 68.5%, while the full-face graph (leveraging on geometric-based features) yields 75.53% on the SAMM dataset. On the other hand, the optimized Bi-WOOF processes sample at 0.36 seconds and full-face graph processes sample at 0.10 seconds with a 640x480 image size. All experiments were performed on an Intel i5-3470 machine.

Download Full-text

Improving the Computational Cost for Copied Region Detection in Forensic Images

Journal of Science and Technology Issue on Information and Communications Technology ◽

10.31130/jst.2016.28 ◽

2016 ◽

Vol 2 (1) ◽

pp. 55

Author(s):

Tu Huynh-Kha ◽

Thuong Le-Tien ◽

Synh Ha ◽

Khoa Huynh-Van

Keyword(s):

Wavelet Transform ◽

Euclidean Distance ◽

Research Work ◽

Computational Cost ◽

Correlation Coefficients ◽

Zernike Moments ◽

Computational Time ◽

Discrete Wavelet ◽

Feature Vectors ◽

Region Detection

This research work develops a new method to detect the forgery in image by combining the Wavelet transform and modified Zernike Moments (MZMs) in which the features are defined from more pixels than in traditional Zernike Moments. The tested image is firstly converted to grayscale and applied one level Discrete Wavelet Transform (DWT) to reduce the size of image by a half in both sides. The approximation sub-band (LL), which is used for processing, is then divided into overlapping blocks and modified Zernike moments are calculated in each block as feature vectors. More pixels are considered, more sufficient features are extracted. Lexicographical sorting and correlation coefficients computation on feature vectors are next steps to find the similar blocks. The purpose of applying DWT to reduce the dimension of the image before using Zernike moments with updated coefficients is to improve the computational time and increase exactness in detection. Copied or duplicated parts will be detected as traces of copy-move forgery manipulation based on a threshold of correlation coefficients and confirmed exactly from the constraint of Euclidean distance. Comparisons results between proposed method and related ones prove the feasibility and efficiency of the proposed algorithm.

Download Full-text

A divide-and-conquer algorithm for quantum state preparation

Scientific Reports ◽

10.1038/s41598-021-85474-1 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Israel F. Araujo ◽

Daniel K. Park ◽

Francesco Petruccione ◽

Adenilton J. da Silva

Keyword(s):

Computational Cost ◽

Quantum Circuit ◽

Divide And Conquer ◽

Computational Time ◽

Quantum Computers ◽

Dimensional Vector ◽

Quantum Devices ◽

Divide And Conquer Algorithm ◽

Quantum State Preparation ◽

Quantum Device

AbstractAdvantages in several fields of research and industry are expected with the rise of quantum computers. However, the computational cost to load classical data in quantum computers can impose restrictions on possible quantum speedups. Known algorithms to create arbitrary quantum states require quantum circuits with depth O(N) to load an N-dimensional vector. Here, we show that it is possible to load an N-dimensional vector with exponential time advantage using a quantum circuit with polylogarithmic depth and entangled information in ancillary qubits. Results show that we can efficiently load data in quantum devices using a divide-and-conquer strategy to exchange computational time for space. We demonstrate a proof of concept on a real quantum device and present two applications for quantum machine learning. We expect that this new loading strategy allows the quantum speedup of tasks that require to load a significant volume of information to quantum devices.

Download Full-text

Deep Learning based Thermal Crack Detection on Structural Concrete Exposed to Elevated Temperature

Advances in Structural Engineering ◽

10.1177/1369433220986637 ◽

2021 ◽

pp. 136943322098663

Author(s):

Diana Andrushia A ◽

Anand N ◽

Eva Lubloy ◽

Prince Arulraj G

Keyword(s):

Deep Learning ◽

Crack Detection ◽

Detection Method ◽

Concrete Structures ◽

Vital Role ◽

Subjective Knowledge ◽

Thermal Cracks ◽

Reinforced Cement ◽

Novel Method ◽

Human Inspection

Health monitoring of concrete including, detecting defects such as cracking, spalling on fire affected concrete structures plays a vital role in the maintenance of reinforced cement concrete structures. However, this process mostly uses human inspection and relies on subjective knowledge of the inspectors. To overcome this limitation, a deep learning based automatic crack detection method is proposed. Deep learning is a vibrant strategy under computer vision field. The proposed method consists of U-Net architecture with an encoder and decoder framework. It performs pixel wise classification to detect the thermal cracks accurately. Binary Cross Entropy (BCA) based loss function is selected as the evaluation function. Trained U-Net is capable of detecting major thermal cracks and minor thermal cracks under various heating durations. The proposed, U-Net crack detection is a novel method which can be used to detect the thermal cracks developed on fire exposed concrete structures. The proposed method is compared with the other state-of-the-art methods and found to be accurate with 78.12% Intersection over Union (IoU).

Download Full-text

A Stochastic Model for Block Segmentation of Images Based on the Quadtree and the Bayes Code for It

Entropy ◽

10.3390/e23080991 ◽

2021 ◽

Vol 23 (8) ◽

pp. 991

Author(s):

Yuta Nakahara ◽

Toshiyasu Matsushima

Keyword(s):

Computational Cost ◽

Block Size ◽

Input Image ◽

Generative Model ◽

Image Size ◽

Variable Block ◽

General Data ◽

The Difference ◽

Segmentation Of Images ◽

Target Data

In information theory, lossless compression of general data is based on an explicit assumption of a stochastic generative model on target data. However, in lossless image compression, researchers have mainly focused on the coding procedure that outputs the coded sequence from the input image, and the assumption of the stochastic generative model is implicit. In these studies, there is a difficulty in discussing the difference between the expected code length and the entropy of the stochastic generative model. We solve this difficulty for a class of images, in which they have non-stationarity among segments. In this paper, we propose a novel stochastic generative model of images by redefining the implicit stochastic generative model in a previous coding procedure. Our model is based on the quadtree so that it effectively represents the variable block size segmentation of images. Then, we construct the Bayes code optimal for the proposed stochastic generative model. It requires the summation of all possible quadtrees weighted by their posterior. In general, its computational cost increases exponentially for the image size. However, we introduce an efficient algorithm to calculate it in the polynomial order of the image size without loss of optimality. As a result, the derived algorithm has a better average coding rate than that of JBIG.

Download Full-text

Computing Expectiles Using k-Nearest Neighbours Approach

Symmetry ◽

10.3390/sym13040645 ◽

2021 ◽

Vol 13 (4) ◽

pp. 645

Author(s):

Muhammad Farooq ◽

Sehrish Sarfraz ◽

Christophe Chesneau ◽

Mahmood Ul Hassan ◽

Muhammad Ali Raza ◽

...

Keyword(s):

Computational Cost ◽

Real Life ◽

Distance Measures ◽

Computational Time ◽

High Dimensional ◽

Test Error ◽

Nearest Neighbours ◽

Comparable Performance ◽

Asymmetric Least Squares ◽

Low Computational Cost

Expectiles have gained considerable attention in recent years due to wide applications in many areas. In this study, the k-nearest neighbours approach, together with the asymmetric least squares loss function, called ex-kNN, is proposed for computing expectiles. Firstly, the effect of various distance measures on ex-kNN in terms of test error and computational time is evaluated. It is found that Canberra, Lorentzian, and Soergel distance measures lead to minimum test error, whereas Euclidean, Canberra, and Average of (L1,L∞) lead to a low computational cost. Secondly, the performance of ex-kNN is compared with existing packages er-boost and ex-svm for computing expectiles that are based on nine real life examples. Depending on the nature of data, the ex-kNN showed two to 10 times better performance than er-boost and comparable performance with ex-svm regarding test error. Computationally, the ex-kNN is found two to five times faster than ex-svm and much faster than er-boost, particularly, in the case of high dimensional data.

Download Full-text