Abstract: A power supply system is provided. The power supply system includes a power supply system comprises a first rectifier receiving an AC power from a first input AC power source, converting the AC power into a first DC power and outputting the first DC power to a connection node, one or more motors connected in parallel to the connection node, the motors being respectively connected to inverters converting the DC power provided from the connection node into an AC power to control the motors, and an auxiliary power source supplying a second DC power to the connection node when the supply of the first DC power is interrupted, or when an overload of the motors occurs.

Abstract: A power supply system is provided. The power supply system includes a power supply system comprises a first rectifier receiving an AC power from a first input AC power source, converting the AC power into a first DC power and outputting the first DC power to a connection node, one or more motors connected in parallel to the connection node, the motors being respectively connected to inverters converting the DC power provided from the connection node into an AC power to control the motors, and an auxiliary power source supplying a second DC power to the connection node when the supply of the first DC power is interrupted, or when an overload of the motors occurs.

Abstract: Disclosed herein is a method for predicting a chlorophyll-a concentration in a river using satellite image data and a nonlinear RANSAC method. In detail, the method includes (1) receiving a chlorophyll-a concentration, which was actually measured at a measurement station at a prescribed basin and an image from a satellite on a same date and at a same site as when and where the chlorophyll-a concentration was measured at the measurement station, (2) correcting a distortion of the image received from the satellite, (3) applying the chlorophyll-a concentration actually measured at the measurement station and data of the corrected satellite image to a nonlinear RANSAC method to extract a second-order function, and (4) inputting corrected data of a satellite image collected at the prescribed basin to the extracted second-order function to predict a chlorophyll-a concentration at the prescribed basin.

Abstract: Disclosed are an unmanned monitoring system and a monitoring method for performing 360° unmanned monitoring work in equipment having a low storage capacity, such as a robot, by using one omni-directional camera. When an image is input through the omni-directional camera, a movement of an object is detected from the image. Then, the movement region is sampled by tracing the object and the image for the movement region is rotated into a frontal image while compensating for inclination of the image in order to allow a user to easily view the image. Thus, the frontal image is transmitted to a mobile communication terminal of a user, such as a mobile phone or a PDA.

Abstract: Disclosed is an apparatus and method for detecting a face from an image. The apparatus and method uses color components and enables a Support Vector Machine (SVM) having superior recognition performance to previously learn face and non-face images and determine whether an image is a face image based on a learned image database by reducing the size of a feature vector of a face as compared to conventional systems. Accordingly, the apparatus converts a face image into a mosaic image having a minimum size to reduce the dimension of the feature vector, in order to rapidly and correctly detect a face image.

Abstract: Disclosed are an apparatus and a method for recognizing a specific subject from a still image or a moving image at a high speed. An object of the apparatus and the method is to reduce the amount of information required for image recognition. One feature vector value is extracted by using one feature template for dividing an image into a plurality of areas, and learning and image recognition is performed with respect to a subject to be recognized in the image using the extracted feature vector value.

Abstract: Disclosed are an unmanned monitoring system and a monitoring method for performing 360° unmanned monitoring work in equipment having a low storage capacity, such as a robot, by using one omni-directional camera. When an image is input through the omni-directional camera, a movement of an object is detected from the image. Then, the movement region is sampled by tracing the object and the image for the movement region is rotated into a frontal image while compensating for inclination of the image in order to allow a user to easily view the image. Thus, the frontal image is transmitted to a mobile communication terminal of a user, such as a mobile phone or a PDA.

Abstract: Disclosed is an apparatus and method for detecting a face from an image. The apparatus and method uses color components and enables a Support Vector Machine (SVM) having superior recognition performance to previously learn face and non-face images and determine whether an image is a face image based on a learned image database by reducing the size of a feature vector of a face as compared to conventional systems. Accordingly, the apparatus converts a face image into a mosaic image having a minimum size to reduce the dimension of the feature vector, in order to rapidly and correctly detect a face image.

Abstract: The invention relates to an apparatus and a method for distinguishing between camera movement and object movement, and for extracting an object in a video surveillance system for detecting an invader based upon object movement. The apparatus and method distinguish actual invader detection owing to object movement from erroneous invader detection owing to a camera's movement or shaking. In the case of actual invader detection owing to object movement, a corresponding object is extracted. In this way, optical flow is obtained from an input dynamic image, and is converted into angle values and classified. If an angle value exceeds a predetermined critical value, it is determined that object movement is detected. If the angle value does not exceed the predetermined critical value, it is determined that camera movement or shaking is detected.

Abstract: Disclosed are an apparatus and a method for recognizing a specific subject from a still image or a moving image at a high speed. An object of the apparatus and the method is to reduce the amount of information required for image recognition. One feature vector value is extracted by using one feature template for dividing an image into a plurality of areas, and learning and image recognition is performed with respect to a subject to be recognized in the image using the extracted feature vector value.

Abstract: A template-based face detection method includes: producing an average face image from a face database, wavelet-converting the produced face image, and removing a low frequency component of high and low frequency components of the converted image, the low frequency component being sensitive to illumination; producing a face template with only high horizontal and vertical frequency components of the high frequency components; and retrieving an initial face position using the face template when an image is inputted, and detecting the face in a next frame by using, as a face template for the next frame, a template obtained by linearly combining the face template with a high frequency wavelet coefficient corresponding to the position of the face in a current frame. Thus, the method has a shortened calculation time for face detection, and can accurately detect a face irrespective of skin color and illumination.