From the Publisher: 
The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

비만아 부모의 돌봄 경험: q 방법론

Applications of machine learning to machine fault diagnosis: A review and roadmap

1D convolutional neural networks and applications: A survey

During the last decade, Convolutional Neural Networks (CNNs) have become the de facto standard for various Computer Vision and Machine Learning operations. CNNs are feed-forward Artificial Neural Networks (ANNs) with alternating convolutional and subsampling layers. Deep 2D CNNs with many hidden layers and millions of parameters have the ability to learn complex objects and patterns providing that they can be trained on a massive size visual database with ground-truth labels. With a proper training, this unique ability makes them the primary tool for various engineering applications for 2D signals such as images and video frames. Yet, this may not be a viable option in numerous applications over 1D signals especially when the training data is scarce or application-specific. To address this issue, 1D CNNs have recently been proposed and immediately achieved the state-of-the-art performance levels in several applications such as personalized biomedical data classification and early diagnosis, structural health monitoring, anomaly detection and identification in power electronics and motor-fault detection. Another major advantage is that a real-time and low-cost hardware implementation is feasible due to the simple and compact configuration of 1D CNNs that perform only 1D convolutions (scalar multiplications and additions). This paper presents a comprehensive review of the general architecture and principals of 1D CNNs along with their major engineering applications, especially focused on the recent progress in this field. Their state-of-the-art performance is highlighted concluding with their unique properties. The benchmark datasets and the principal 1D CNN software used in those applications are also publically shared in a dedicated website.

1D Convolutional Neural Networks and Applications: A Survey

This paper investigates an algorithm for fault diagnosis in robot manipulators using a novel neural second-order sliding mode observer. Differently from the conventional neural network observer and first-order sliding mode observer for the robust fault estimation schemes, the second-order sliding mode observer is first designed and compared with them. Although the second-order sliding mode observer converges faster and with less error than each of the neural network and the first-order sliding mode observer does, it requires prior knowledge of the upper bound of the fault function. Because of this disadvantage, a neural second-order sliding mode observer is designed, which combines the second-order sliding mode observer with the neural network observer. The resulting observer not only preserves the features of the second-order sliding mode observer but also can improve it by removing the need for prior knowledge of the fault function upper bound. Computer simulation results for a PUMA560 industrial robot are also shown to verify the effectiveness of the proposed strategy.

A novel neural second-order sliding mode observer for robust fault diagnosis in robot manipulators

Bearing is one of the key components of a rotating machine Hence, monitoring health condition of the bearing is of paramount importace This paper develops a novel particle swarm optimization (PSO)-least squares wavelet support vector machine (PSO-LSWSVM) classifier, which is designed based on a combination between a PSO, a least squares procedure, and a new wavelet kernel function-based support vector machine (SVM), for bearing fault diagnosis In this work, bearing fault classification is transformed into a pattern recognition problem, which consists of three stages of data processing Firstly, a rich information dataset is built by extracting the features from the signals, which are decomposed by the nonlocal means (NLM) and empirical mode decomposition (EMD) Secondly, a minimum-redundancy maximum-relevance (mRMR) method is employed to determine a subset of feature that can provide an optimal performance Thirdly, a novel classifier, namely LSWSVM, is proposed with the aid of a PSO, to provide higher classification accuracy The key innovative science of this work is to propropose a new classifier with the aid of an new wavelet kernel type to increase the classification precision of bearing fault diagnosis The merit features of the proposed approach are demonstrated based on a benchmark bearing dataset and a comprehensive comparison procedure

/pdf/bearing-fault-diagnosis-using-a-particle-swarm-optimization-1hx6x0hti2.pdf

Bearing Fault Diagnosis Using a Particle Swarm Optimization-Least Squares Wavelet Support Vector Machine Classifier.

This paper is concerned with orientation estimation using inertial and magnetic sensors. A new measurement equation is proposed for the quaternion-based indirect Kalman filter. Instead of using magnetic sensor data directly in the measurement equation, the data are modified so that the magnetic sensor data almost do not affect pitch and roll estimation during the measurement update. The proposed algorithms can be used for an application, where pitch and roll estimation is critical and there are large magnetic disturbances. Through an experiment and simulations, the proposed algorithms are compared with the standard method that uses magnetic sensor data for pitch and roll estimation. Using 50 simulation data, it is shown that pitch and roll estimation errors are significantly smaller when there are magnetic disturbances.

Quaternion-Based Indirect Kalman Filter Discarding Pitch and Roll Information Contained in Magnetic Sensors

In this paper, a robust output feedback tracking control scheme for motion control of uncertain robot manipulators without joint velocity measurement based on a second-order sliding mode (SOSM) observer is presented. Two second-order sliding mode observers with finite time convergence are developed for velocity estimation and uncertainty identification, respectively. The first SOSM observer is used to estimate the state vector in finite time without filtration. However, for uncertainty identification, the values are constructed from the high switching frequencies, necessitating the application of a filter. To estimate the uncertainties without filtration, a second SOSM-based nonlinear observer is designed. By integrating two SOSM observers, the resulting observer can theoretically obtain exact estimations of both velocity and uncertainty. An output feedback tracking control scheme is then designed based on the observed values of the state variables and the direct compensation of matched modelling uncertainty using their identified values. Finally, results of a simulation for a PUMA560 robot are shown to verify the effectiveness of the proposed strategy.

/pdf/second-order-sliding-mode-based-output-feedback-tracking-1klb9q197k.pdf

Second order sliding mode-based output feedback tracking control for uncertain robot manipulators

In this paper, a fault-tolerant control (FTC) method for robotic manipulators is proposed to deal with the lumped uncertainties and faults in case of lacking tachometer sensors in the system. First, the third-order sliding mode (TOSM) observer is performed to approximate system velocities and the lumped uncertainties and faults. This observer provides estimation information with high precision, low chattering phenomenon, and finite-time convergence. Then, an FTC method is proposed based on a non-singular fast terminal switching function and the TOSM observer. This combination provides robust features in dealing with the lumped uncertainties and faults, increases the control performance, reduces chattering phenomenon, and guarantees fast finite-time convergence. Especially, this paper considers both two periods of time, in which before and after the convergence process takes place. The stability and the finite-time convergence of the proposed controller-observer technique is demonstrated using the Lyapunov theory. Finally, to verify the effectiveness of the proposed controller-observer technique, computer simulation on a serial two-link robotic manipulator is performed.

/pdf/a-finite-time-fault-tolerant-control-using-non-singular-fast-4o0ehvp9iz.pdf

A Finite-Time Fault-Tolerant Control Using Non-Singular Fast Terminal Sliding Mode Control and Third-Order Sliding Mode Observer for Robotic Manipulators

Hee-Jun Kang

Papers

A novel neural second-order sliding mode observer for robust fault diagnosis in robot manipulators

Bearing Fault Diagnosis Using a Particle Swarm Optimization-Least Squares Wavelet Support Vector Machine Classifier.

Quaternion-Based Indirect Kalman Filter Discarding Pitch and Roll Information Contained in Magnetic Sensors

Second order sliding mode-based output feedback tracking control for uncertain robot manipulators

A Finite-Time Fault-Tolerant Control Using Non-Singular Fast Terminal Sliding Mode Control and Third-Order Sliding Mode Observer for Robotic Manipulators