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

With the continuous increase in complexity and expense of industrial systems, there is less tolerance for performance degradation, productivity decrease, and safety hazards, which greatly necessitates to detect and identify any kinds of potential abnormalities and faults as early as possible and implement real-time fault-tolerant operation for minimizing performance degradation and avoiding dangerous situations. During the last four decades, fruitful results have been reported about fault diagnosis and fault-tolerant control methods and their applications in a variety of engineering systems. The three-part survey paper aims to give a comprehensive review of real-time fault diagnosis and fault-tolerant control, with particular attention on the results reported in the last decade. In this paper, fault diagnosis approaches and their applications are comprehensively reviewed from model- and signal-based perspectives, respectively.

/pdf/a-survey-of-fault-diagnosis-and-fault-tolerant-techniques-9uuf1uqysf.pdf

A Survey of Fault Diagnosis and Fault-Tolerant Techniques—Part I: Fault Diagnosis With Model-Based and Signal-Based Approaches

Intelligent vehicles have increased their capabilities for highly and, even fully, automated driving under controlled environments. Scene information is received using onboard sensors and communication network systems, i.e., infrastructure and other vehicles. Considering the available information, different motion planning and control techniques have been implemented to autonomously driving on complex environments. The main goal is focused on executing strategies to improve safety, comfort, and energy optimization. However, research challenges such as navigation in urban dynamic environments with obstacle avoidance capabilities, i.e., vulnerable road users (VRU) and vehicles, and cooperative maneuvers among automated and semi-automated vehicles still need further efforts for a real environment implementation. This paper presents a review of motion planning techniques implemented in the intelligent vehicles literature. A description of the technique used by research teams, their contributions in motion planning, and a comparison among these techniques is also presented. Relevant works in the overtaking and obstacle avoidance maneuvers are presented, allowing the understanding of the gaps and challenges to be addressed in the next years. Finally, an overview of future research direction and applications is given.

A Review of Motion Planning Techniques for Automated Vehicles

Haptic perception plays a very important role in surgery. It enables the surgeon to feel organic tissue hardness, measure tissue properties, evaluate anatomical structures, and allows him/her to commit appropriate force control actions for safe tissue manipulation. However, in minimally invasive surgery, the surgeon's ability of perceiving valuable haptic information through surgical instruments is severely impaired. Performing the surgery without such sensory information could lead to increase of tissue trauma and vital organic tissue damage. In order to restore the surgeon's perceptual capability, methods of force and tactile sensing have been applied with attempts to develop instruments that can be used to detect tissue contact forces and generate haptic feedback to the surgeon. This paper reviews the state-of-the-art in force and tactile sensing technologies applied in minimally invasive surgery. Several sensing strategies including displacement-based, current-based, pressure-based, resistive-based, capacitive-based, piezoelectric-based, vibration-based, and optical-based sensing are discussed.

State-of-the-Art in Force and Tactile Sensing for Minimally Invasive Surgery

Computer Solution of Linear Algebraic Systems. By G. Forsythe and C. B. Moler. Pp. xi, 148. 1967. (Prentice-Hall.)

A stereo vision-based obstacle detection system in vehicles

Even though some of the driver assistant systems have been commercialized to provide safety and convenience to the driver, they can be applied for autonomous driving in limited situations such as highways. In this paper, we propose a supervisor agent that can enhance the driver assistant systems by using deep distributional reinforcement learning. The supervisor agent is trained using end-to-end approach that directly maps both a camera image and LIDAR data into action plan. Because the well-trained network of deep reinforcement learning can lead to unexpected actions, collision avoidance function is added to prevent dangerous situations. In addition, the highway driving case is a stochastic environment with inherent randomness and, thus, its training is performed through the distributional reinforcement learning algorithm, which is specialized for stochastic environment. The optimal action for autonomous driving is selected through the return value distribution. Finally, the proposed algorithm is verified through a highway driving simulator, which is implemented by the Unity ML-agents.

Deep Distributional Reinforcement Learning Based High-Level Driving Policy Determination

The importance of monitoring the cutting force in the turning process has been well recognized in industry as well as in the open literature. This paper proposes a cutting force monitoring approach that does not utilize force dynamometers but rather estimates the cutting force based on the spindle motor current and speed as well as a model that relates these measurements to the cutting force. Motor current and speed can not only be inexpensively and reliably measured but, in addition, can be shown, along with the properly chosen model for the model-based estimator, to accurately estimate the cutting force. This method is demonstrated on a CNC lathe and its advantages and limitations are discussed.

Monitoring cutting forces in turning: A model-based approach

Information on contact forces in robot manipulators is indispensable for fast and accurate force control. Instead of expensive force sensors, estimation algorithms for contact forces have been widely developed. However, it is not easy to obtain the accurate values due to uncertainties. In this article, a new robust estimator is proposed to estimate three-dimensional contact forces acting on a three-link robot manipulator. The estimator is based on the extended Kalman filter (EKF) structure combined with a Lyapunov-based adaptation law for estimating the contact force. In contrast to the conventional EKF the new estimator is designed such that it is robust to the deterministic uncertainties such as the modelling error and the sensing bias. The performance of the proposed estimator is evaluated through simulations of a robot manipulator and demonstrates robustness in estimating the contact force. The estimation results show that it can be potentially used to replace the expensive force sensors in ro...

Kunsoo Huh

Papers

A stereo vision-based obstacle detection system in vehicles

Deep Distributional Reinforcement Learning Based High-Level Driving Policy Determination

Monitoring cutting forces in turning: A model-based approach

Robust contact force estimation for robot manipulators in three-dimensional space

Vehicle sideslip angle estimation using deep ensemble-based adaptive Kalman filter