This paper proposes vision-based collision risk estimation method for an unmanned surface vehicle. A robust image-processing algorithm is suggested to detect target obstacles from the vision sensor. Vision-based Target Motion Analysis (TMA) was performed to transform visual information to target motion information. In vision-based TMA, a camera model and optical flow are adopted. Collision risk was calculated by using a fuzzy estimator that uses target motion information and vision information as input variables. To validate the suggested collision risk estimation method, an unmanned surface vehicle experiment was performed.

A camera-based real-time hand posture and gesture recognition system is proposed for controlling various devices inside automobiles. It uses an imaging system composed of a camera with a proper filter and an infrared lighting device to acquire images of hand-motion sequences. Several steps of pre-processing algorithms are applied, followed by a background normalization process before segmenting the hand from the background. The hand posture is determined by first separating the fingers from the main body of the hand and then by finding the relative position of the fingers from the center of the hand. The beginning and ending of the hand motion from the sequence of the acquired images are detected using pre-defined motion rules to start the hand gesture recognition. A set of carefully designed features is computed and extracted from the raw sequence and is fed into a decision tree-like decision rule for determining the hand gesture. Many experiments are performed to verify the system. In this paper, we show the performance results from tests on the 550 sequences of hand motion images collected from five different individuals to cover the variations among many users of the system in a real-time environment. Among them, 539 sequences are correctly recognized, showing a recognition rate of 98%.

This paper presents an improved learning-based visual inspection method for auto parts inspection in severe lighting changes. Automobile sunroof frames are produced automatically by robots in most production lines. In the sunroof frame manufacturing process, there is a quality problem with some parts such as volts are missed. Instead of manual sampling inspection using some mechanical jig instruments, a learning-based machine vision system was proposed in the previous research[1]. But, in applying the actual sunroof frame production process, the inspection accuracy of the proposed vision system is much lowered because of severe illumination changes. In order to overcome this capricious environment, some selective feature vectors and cascade classifiers are used for each auto parts. And we are able to improve the inspection accuracy through the re-learning concept for the misclassified data. The effectiveness of the proposed visual inspection method is verified through sufficient experiments in a real sunroof production line.

Fast inspection of solder ball bumps in ball grid array (BGA) is an important issue in the flip chip bonding technology. Particularly, semiconductor industry has required faster and more accurate inspection of micron-size solder bumps in flip chip bonding, as the density of balls increase dramatically. In this paper, we describe an inspection approach of BGA balls by using 5-step ring illumination device and normalized cross-correlation (NCC) method. The images of BGA ball by the illumination device show unique and distinguishable characteristic contours by their 3-D shapes, which are called as "iso-slope contours". Template images of reference ball samples can be produced artificially by the hybrid reflectance model and 3D data of balls. NCC values between test and template samples are very robust and reliable under well-structured condition. The 200 samples on real wafer are tested and show good practical feasibility of the proposed method.

This paper suggests a method of detecting traffic lights for vehicles by combining the HSV(hue saturation value) color model, morphometric characteristics, and location information appearing on consecutive images in daytime. In order to detect the traffic light, the color corresponding to the signal lights should be explored. It is difficult to detect traffic lights among colors of lights from buildings, taillight of cars, leaves, placards, etc. The proposed algorithm searches for the traffic lights from many candidates using morphometric characteristics and location information in consecutive images. The recognition process is divided into three steps. The first step is to detect candidates after converting RGB channel into HSV color model. The second step is to extract the boundaries between the housing of traffic lights and background by exploiting the assumption that the housing has lower brightness than the surrounding background. The last step is to recognize the signal light after eliminating the false candidates using morphometric characteristics and location information appearing on consecutive images. This paper demonstrates successful detection results of traffic lights from various images captured on the city roads.

The bond pull test is the most widely used technique for the evaluation and control of wire bond quality. The wire being tested is pulled upward until the wire or bond to the die or substrate breaks. The inspector test strength of wire by manually and it takes around 3 minutes to perform the test. In this paper, we develop a 3D vision system to measure 3D position of wire. It gives 3D position data of wire to move a hook into wires. The 3D measurement method to use here is a confocal imaging system. The conventional confocal imaging system is a spot scanning method which has a high resolution and good illumination efficiency. However, a conventional confocal systems has a disadvantage to perform XY axis scanning in order to achieve 3D data in given FOV (Field of View) through spot scanning. We propose a method to improve a parallel mode confocal system using a micro-lens and pin-hole array to remove XY scan. 2D imaging system can detect 2D location of wire and it can reduce time to measure 3D position of wire. In the experimental results, the proposed system can measure 3D position of wire with reasonable accuracy.

In this paper, we develop a sliding mode controller that uses a nonlinear sliding manifold for the permanent magnet synchronous motor. The proposed controller makes sure that both currents and velocity tracking error converge into equilibria. Nonlinear sliding manifold consists of current dynamics and nonlinear functions which are designed with velocity tracking error and its integrated term. The nonlinear functions are designed to guarantee that velocity tracking error converge into zero. The closed-loop stability is proven by Lyapunov theory. The effectiveness of proposed method is demonstrated by numerical simulation results.

In this paper, High performance torque control based on the flux mapping of 48V Wound Rotor Synchronous Motor has been studied to improve torque control. Flux map considering MTPA (Maximum Torque Per Ampere), MFPT (Minimum Flux Per Torque), Maximum efficiency point at the same torque command and flux command for each field current was produced. Current map using flux mapping of Each field current was applied to the MTPA, MFPT. Generating a current vector locus was to determine the characteristics of the operation region. Through the Matlab/Simulink simulation, difference between speed-torque map and flux map was represented. The suggested flux map was tested actual experiments on a dynamometer.

Switching power supply systems are widely used in many industrial fields. Power factor correction (PFC) circuits have a tendency to be applied in new power supply designs. The PFC circuit with a boost converter using an input power source is studied in this paper. In a boost PFC circuit, there are two feedback control loops: a current feedback loop and a voltage feedback loop. In this paper, the regulation performance gained by using the output voltage and compensator to improve the transient response presented at the continuous conduction mode (CCM) of the boost PFC circuit is analyzed. The validity of the designed boost PFC circuit is confirmed by both MATLAB simulation and experimental results.

This paper proposes a decentralized robust adaptive control scheme for robot manipulators with input torque saturation in the presence of uncertainties. The control system should consider the practical problems that the controller gain coefficients of each joint may be nonlinear time-varying and the input torques applied at each joint are saturated. The proposed robot controller overcomes the various uncertainties and the input saturation problem. The proposed controller is comparatively simple and has no robot model parameters. The proposed controller is adjusted by the adaptation laws and the stability of the control system is guaranteed by the Lyapunov function analysis. Simulation results show the validity and robustness of the proposed control scheme.

This paper describes the implementation of wearable AHRS for an electromagnetic motion capture system that can trace and analyze human motion on the principal nine axes of inertial sensors. The module provides a three-dimensional (3D) attitude and heading angles combining MEMS gyroscopes, accelerometers, and magnetometers based on the extended Kalman filter, and transmits the motion data to the 3D simulation via Wi-Fi to realize the unrestrained movement in open spaces. In particular, the accelerometer in AHRS is supposed to measure only the acceleration of gravity, but when a sensor moves with an external linear acceleration, the estimated linear acceleration could compensate the accelerometer data in order to improve the precision of measuring gravity direction. In addition, when an AHRS is attached in an arbitrary position of the human body, the compensation of the axis of rotation could improve the accuracy of the motion capture system.

This paper deals with estimating the acid concentration of pickling process using the Volterra inputs. To estimate the acid concentration, the whole pickling process is represented by the grey box model consists of the white box dealing with known system and the black box dealing with unknown system. Because there is a possibility of nonlinear term in the unknown system, the Volterra series are used to estimate the acid concentration. For the white box modeling, the acid tank solution level and concentration equations are used, and for the black box modeling, the acid concentration is estimated using the Volterra Least Mean Squares (LMS) algorithm and Least Squares (LS) algorithm. The LMS algorithm has the advantage of the simple structure and the low computation, and the LS algorithm has the advantage of lowest error. The simulation results compared to the measured data are included.

In conventional robotics, charge-coupled device (CCD) and complementary metal-oxide-semiconductor (CMOS) cameras have been utilized for acquiring vision information. These devices have problems, such as narrow optic angles and inefficiencies in visual information processing. Recently, biomimetic vision sensors for robotic applications have been receiving much attention. These sensors are more efficient than conventional vision sensors in terms of the optic angle, power consumption, dynamic range, and redundancy suppression. This paper presents recent research trends on biomimetic vision sensors and discusses future directions.

In this paper, a study of advanced sound source localization is conducted by eliminating the noise of the sound source using the discrete wavelet transform. And experiments are conducted to evaluate the performance of the proposed system that the mobile robot follows sound source stably. In addition, we compare the position estimation performance by applying a discrete wavelet transform to improve the reliability of the sound signal. The experimental results reveal that the de-nosing filter which removes the noise component in sound source can make the performance of position estimation more precisely and help the mobile robot distinguish the objective sound source clearly.

An effective swing trajectory of legged robots is different from the swing trajectories of humans or animals because of different dynamic characteristics. Therefore, it is important to find optimal parameters through experiments. This paper proposes a real-time nonlinear programming (RTNLP) method for optimization of the swing trajectory of the legged robot. For parameterization of the trajectory, the swing trajectory is approximated to parabolic and cubic spline curves. The robotic leg is position-controlled by a high-gain controller, and a cost function is selected such that the sum of the motor inputs and tracking errors at each joint is minimized. A simplified dynamic model is used to simulate the dynamics of a robotic leg. The purpose of the simulation is to find the feasibility of the optimization problem before an actual experiment occurs. Finally, an experiment is carried out on a real robotic leg with two degrees of freedom. For both the simulation and the experiment, the design variables converge to a feasible point, reducing the cost value.