Due to the recent increase of the importance and demand of security services, the importance of a surveillance monitor system that makes an automatic security system possible is increasing. As the market for surveillance monitor systems is growing, price competitiveness is becoming important. As a result of this trend, surveillance monitor systems based on an embedded system are widely used. In this paper, an object detection algorithm based on an embedded system for a surveillance monitor system is introduced. To apply the object detection algorithm to the embedded system, the most important issue is the efficient use of resources, such as memory and processors. Therefore, designing an appropriate algorithm considering the limit of resources is required. The proposed algorithm uses two background models; therefore, the embedded system is designed to have two independent processors. One processor checks the sub-background models for if there are any changes with high update frequency, and another processor makes the main background model, which is used for object detection. In this way, a background model will be made with images that have no objects to detect and improve the object detection performance. The object detection algorithm utilizes one-dimensional histogram distribution, which makes the detection faster. The proposed object detection algorithm works fast and accurately even in a low-priced embedded system.

In this paper, we present an effective system for the 3D scene labeling of objects from RGB-D videos. Our system uses a Markov Random Field (MRF) over a voxel representation of the 3D scene. In order to estimate the correct label of each voxel, the probabilistic graphical model integrates both scores from sliding window-based object detectors and also from object location prior maps. Both the object detectors and the location prior maps are pre-trained from manually labeled RGB-D images. Additionally, the model integrates the scores from considering the geometric constraints between adjacent voxels in the label estimation. We show excellent experimental results for the RGB-D Scenes Dataset built by the University of Washington, in which each indoor scene contains tabletop objects.

Depth calibration is a procedure for finding the conversion function that maps disparity data from a depth-sensing camera to actual distance information. In this paper, we present an optimal depth calibration method for Kinect$^{TM}$ sensors based on an experimental design and convex optimization. The proposed method, which utilizes multiple measurements from only two points, suggests a simplified calibration procedure. The confidence ellipsoids obtained from a series of simulations confirm that a simpler procedure produces a more reliable calibration function.

This paper proposes a method for detecting the front side of vehicles. The method can find the car side with a license plate even with complicated and cluttered backgrounds. A convolutional neural network (CNN) is used to solve the detection problem as a unified framework combining feature detection, classification, searching, and localization estimation and improve the reliability of the system with simplicity of usage. The proposed CNN structure avoids sliding window search to find the locations of vehicles and reduces the computing time to achieve real-time processing. Multiple responses of the network for vehicle position are further processed by a weighted clustering and probabilistic threshold decision method. Experiments using real images in parking lots show the reliability of the method.

Infrared (IR) target detection is one of the key technologies in Automatic Target Detection/Recognition (ATD/R) for military applications. However, IR sensors have limitations due to the weather sensitivity and atmospheric effects. In recent years, sensor information fusion study is an active research topic to overcome these limitations. SAR sensor is adopted to sensor fusion, because SAR is robust to various weather conditions. In this paper, a Boolean Map Visual Theory-Morphology (BMVT-M) method is proposed to detect targets in SAR and IR images. Moreover, we suggest the IR and SAR image registration and decision level fusion algorithm. The experimental results using OKTAL-SE synthetic images validate the feasibility of sensor fusion-based target detection.

For the attitude control of spacecraft, two variable-speed control moment gyros are proposed as main actuators in the article. Since a variable-speed control moment gyro (VSCMG) makes two control torques (gyroscopic torque and reaction torque), two VSCMGs are sufficient for controlling 3-axes attitude. Additionally, there are no singular conditions for two non-parallel VSCMGs. Since gyroscopic torque is usually much greater than reaction torque, the control performances of approximately 3 axes may not be the same. However, several missions can be accomplished by controlling two axes. For such missions, a selective axes control method is proposed. The method selects two axes for a certain task and controls the attitude of the selected axes. For the remaining axis, angular speed is controlled for stabilization. A hardware-in-the-loop simulation has been used to test VSCMG modules and to verify the proposed method. Two VSCMGs can be alternative actuators for small satellites.

In recent years in the field of robotics, various methods have been developed to create an intimate relationship between people and robots. These methods include speech, vision, and biometrics recognition as well as gesture-based interaction. These recognition technologies are used in various wearable devices, smartphones and other electric devices for convenience. Among these technologies, gesture recognition is the most commonly used and appropriate technology for wearable devices. Gesture recognition can be classified as contact or noncontact gesture recognition. This paper proposes contact gesture recognition with IMU and EMG sensors by using the hidden Markov model (HMM) twice. Several simple behaviors make main gestures through the one-stage HMM. It is equal to the Hidden Markov model process, which is well known for pattern recognition. Additionally, the sequence of the main gestures, which comes from the one-stage HMM, creates some higher-order gestures through the two-stage HMM. In this way, more natural and intelligent gestures can be implemented through simple gestures. This advanced process can play a larger role in gesture recognition-based UX for many wearable and smart devices.

When the study on the relationship between the Head-of-Bed (HOB) angle and ventilator-associated pneumonia is performed, the fact that the HOB angle can only be measured intermittently imposes a significant limitation on the study. Therefore, there has been demand for the development of a device that can measure the HOB angle continuously. In this paper, we propose the rapid prototyping of an HOB measurement system using open-source hardware and software. The proposed system helps to maintain the HOB angle at a particular angle by displaying the angle and helps the medical study of pneumonia patients by enabling continuous data acquisition. Firstly, we eliminate the process of making an MCU board by utilizing an open-source hardware mbed LPC1768. Secondly, we reduce the software development time by using libraries and hence enabling the easy use of peripherals. Thirdly, for rapid prototyping, we build the enclosure of the proposed system using a 3D printer. The proposed system can be attached and detached to and from a bed. Therefore, we can attach it to the bed of a patient for whom measurement of the HOB angle is necessary. Finally, we check the measurement performance and the validity of the proposed system through an experiment utilizing an incremental encoder.

This paper proposes an autonomous navigation system of mobile robots for indoor corridor environment. The system uses a laser scanner but does not use reflectors. The laser scanner measures the distance between robot and structures such as wall, pillar, and fixtures. Adaptive breakpoint detector and modified IEPF (iterative endpoint fit) are developed to find mark points from the distance data. The robot path for corridor is then generated using the angle histogram of the mark points. The experimental results are finally presented to show the effectiveness of the proposed method.

In this paper, we use the characteristics of electromagnetic waves underwater attenuation for estimating linear distance between a transmitting node and receiving node, and research underwater vertical plane attenuation model for constructing the underwater localization system. The underwater localization of 2 dimensional with the plane attenuation model in the horizontal plane (H-plane) was proposed previous research. But for the 3 dimensional underwater localization, the additional vertical plane (E-plane) model should be considered. Because the horizontal plane of omnidirectional antenna has the same attenuation tendency in x-y plane according to the distance, whereas in vertical plane shows an irregular pattern in x-z plane. For that reason, in the vertical plane environment, the attenuation should be changed by the position and inclination. Hence, in this paper the distance and angle between transmitting and receiving node are defined using spherical coordinate system and derive an antenna gain pattern using half power beam width (HPBW). The HPBW is called a term which defines antenna's performance between isotropic and other antennas. This paper derives omnidirectional antenna's maximum gain and attenuation pattern model and define vertical plane's gain pattern model using HPBW. Finally, experimental verifications for the proposed underwater vertical plane's attenuation model was executed.

This paper proposes a new nonlinear filtering algorithm that combines the unscented Kalman filter (UKF) and the finite impulse response (FIR) filter. The proposed filter is called the unscented Kalman/FIR hybrid filter (UKFHF). In the UKFHF algorithm, the UKF is used as the main filter, which produces state estimates under ideal conditions. When failures of the UKF are detected, the FIR filter is operated. Using the output of the FIR filter, the UKF is reset and rebooted. In this way, the UKFHF recovers from failures. The proposed UKFHF is applied to indoor human localization using wireless sensor networks. Through simulations, the performance of the UKFHF is demonstrated in comparison with that of the UKF.

Control Moment Gyro (CMG) has been used as an indirect actuator of a single-wheel robot system GYROBO, developed at Chungnam National University. The flip motion of the gimbal system produces the gyroscopic motion onto the body system while the body motion also produces the gyroscopic motion onto the gimbal system inversely. In this paper, the intuitive equation of the inverse gyroscopic effect is derived as the direct relation between the rate of the body system and the rate of the gimbal system. Experiments on the inverse gyroscopic effect under the chaotically generated disturbance are conducted. Experimental data are approximated by a linear equation using the least square method.

This paper proposes a calibration algorithm for a three-degree-of-freedom (DOF) planar cable-driven parallel robot (CDPR). To evaluate the proposed algorithm, we calibrated winches and an optical tracking sensor, measured the end-effector pose using the optical tracking sensor, and calculated the accurate robot configuration using the measurement information. To conduct an accuracy test on the end-effector pose, we followed guidelines from "Manipulating industrial robots - Performance criteria and related test methods." Through the test, it is verified that the position accuracy can be improved by up to 20% for a $2m{\times}2m$-sized planar cable robot using the proposed calibration algorithm.

An inventory control system was developed for a distribution system consisting of a single multiproduct warehouse serving a set of customers and purchasing products from multiple vendors. Purchase orders requesting multiple products are delivered to the warehouse in a process. The receipt of customer orders by the warehouse proceeded in order intervals and in order quantities that are subject to random fluctuations. The objective of warehouse operation is to minimize the total cost while maintaining inventory levels within the warehouse capacity by adjusting the purchase order intervals and quantities. An adaptive model predictive control algorithm was developed using a periodic square wave model to represent the material flows. The adaptive concept incorporated a stabilized minimum variance control-type input calculation coupled with input/output stream parameter predictions. The effectiveness of the scheme was demonstrated using simulations.

This article aims to provide a design method of warning thresholds for active safety systems based on the performance-based approach considering driver behaviors. Both positive and negative consequences of warnings are considered, and the main idea is to choose a warning threshold where the positive consequence is maximized, whereas the negative consequence is minimized. The process of the performance-based approach involves: Defining the operating scenarios; setting the trajectory models, including human characteristics; estimating the alert and nominal trajectories; estimating the performance metrics; generating a performance-metric plot; and determining the alert thresholds. This paper chose a lane-departure warning system as an example to show the usefulness of the performance-based approach. Both human and sensor characteristics were considered in the system design, and this paper provided a quantitative method to include human factors in designing active safety systems.