Abstract: A method for highlight extraction capable of automatically extracting a highlight from a video including a sporting event is provided. The method for highlight extraction may include: identifying a video including a sporting event, log information that sequentially records events occurring in the sporting event, and a keyword related to the video; tagging the video with game information related to the video; extracting at least one piece of log information corresponding to the keyword and determining at least one frame that corresponds to the log information extracted from the tagged video; and creating a highlight video by combining the at least one determined frame.

Abstract: Provided are a camera and an image processing method of the camera. According to an aspect of the present disclosure, an image processing method of a camera includes receiving region information; receiving image data extracted from a corresponding region of an original resolution image corresponding to a region set according to the region information regarding an input image; and analyzing image data of the original resolution image and detecting an object corresponding to a set condition.

Abstract: An object detection system includes: a false detection storer to store one or more items of false detection information; an object detector to detect an object from an input image, compare object detection information corresponding to the object with the false detection information, and output a notification corresponding to the object detection information when false detection information corresponding to the object detection information does not exist; and a feedback receiver to receive a user response to the notification and, when a detection error response to the notification is received, store the object detection information corresponding to the notification as false detection information in the false detection storing unit, wherein the object detector does not output the notification when the object corresponding to the false detection information stored in the false detection storer is detected.

Abstract: Provided is a method for detecting fog from an image, the method including: generating a histogram based on a luminance signal of the image; calculating a histogram width from the histogram; calculating a color contrast value based on color signals of the image; and detecting a fog level of the image based on the histogram width and the color contrast value.

Abstract: A method and an apparatus using a power transistor in a fuel cell stack diagnostic system provides an apparatus using a power transistor in a fuel cell stack diagnostic system. The apparatus includes a regenerative braking detector that detects regenerative braking of a fuel cell vehicle equipped with a fuel cell stack diagnostic system; a voltage rise determiner that determines whether a voltage rise due to regenerative braking of a fuel cell vehicle is a predetermined value or more; and a power transistor controller that controls an AC signal generator so that the voltage due to the regenerative braking is discharged by the power transistor, when the voltage rise due to regenerative braking determined by the voltage rise determiner is a predetermined value or more.

Abstract: A diagnostic system and method for a fuel cell stack that diagnoses the state and/or failure of the fuel cell stack. More specifically, the diagnostic control analyzer diagnoses and analyzes the state of the fuel cell stack by measuring the voltage and the current received from the fuel cell stack. To do this, an AC signal generator cogenerates a diagnostic AC signal according to the control upon receiving a control command form the analyzer, and an AC component driving element is then driven upon receiving the AC signal that is output from the AC signal generator in order to include a diagnostic AC component within the current of the fuel cell stack. In particular, the diagnostic control analyzer diagnoses the fuel cell stack based on a voltage and a current received from the fuel cell stack that includes the AC component via a load.

Abstract: A failure diagnosis apparatus that includes an alternating current (AC) absorption unit that is connected to the fuel cell stack and switched based on an applied AC signal to enable a current from the fuel cell stack to flow. In addition, an AC signal generator is configured to generate the AC signal and supply the generated AC signal to the AC absorption unit. As the current from the fuel cell stack is absorbed by the AC absorption unit based on an alternating signal, a stack current input into a diagnosis processing unit includes an AC component, thus the diagnosis processing unit may diagnose fuel cell stack failure by analyzing a frequency of the AC component.

Abstract: To diagnose a fault of a fuel cell stack, an alternating current having a first optimal frequency of a first frequency domain to diagnose a drop in cell voltage and an alternating current having a second optimal frequency of a second frequency domain to diagnose a cause of the drop in cell voltage are supplied to the fuel cell stack are provided. A distortion rate is then calculated based on voltage of the fuel cell stack according to the alternating current of the first optimal frequency, and the drop in cell voltage is diagnosed based on the calculated distortion rate. Also, impedance is calculated based on voltage and a current of the fuel cell stack according to the alternating current of the second optimal frequency and amount of water is calculated based on the calculated in the fuel cell stack, and the cause of the drop in cell voltage is diagnosed based on the calculated impedance and amount of water.

Abstract: A technique is described herein for monitoring the operational state of a fuel cell stack by the detection of nonlinearity in such a manner that an external test signal for frequency response is generated and applied to the fuel cell stack during operation, the resulting signal output from the fuel cell stack is measured, and the harmonic content of the measured signal is analyzed, the method including: applying a multiple frequency test signal comprising at least two sinusoidal waves as the test signal for frequency response to the fuel cell stack; and analyzing the resulting current or voltage signal output from the fuel cell stack.

Abstract: An image processing method of separating an input image into a foreground image and a background image, the method including determining a pixel of the input image as a pixel of the foreground image if a foreground probability value of the pixel of the foreground image determined by using the Gaussian mixture model or the pixel determined to be included in a motion region is greater than a setting threshold.

Abstract: A method and an apparatus using a power transistor in a fuel cell stack diagnostic system provides an apparatus using a power transistor in a fuel cell stack diagnostic system. The apparatus includes a regenerative braking detector that detects regenerative braking of a fuel cell vehicle equipped with a fuel cell stack diagnostic system; a voltage rise determiner that determines whether a voltage rise due to regenerative braking of a fuel cell vehicle is a predetermined value or more; and a power transistor controller that controls an AC signal generator so that the voltage due to the regenerative braking is discharged by the power transistor, when the voltage rise due to regenerative braking determined by the voltage rise determiner is a predetermined value or more.

Abstract: A diagnostic system and method for a fuel cell stack that diagnoses the state and/or failure of the fuel cell stack. More specifically, the diagnostic control analyzer diagnoses and analyzes the state of the fuel cell stack by measuring the voltage and the current received from the fuel cell stack. To do this, an AC signal generator cogenerates a diagnostic AC signal according to the control upon receiving a control command form the analyzer, and an AC component driving element is then driven upon receiving the AC signal that is output from the AC signal generator in order to include a diagnostic AC component within the current of the fuel cell stack. In particular, the diagnostic control analyzer diagnoses the fuel cell stack based on a voltage and a current received from the fuel cell stack that includes the AC component via a load.

Abstract: A diagnostic and heat management system for a fuel cell stack is provided herein that includes a diagnostic control analyzer that diagnoses and analyzes a state of the fuel cell stack by measuring a voltage and a current of the fuel cell stack. Also, an AC signal generator generates a diagnostic AC signal, and an AC component driving element that is included in an AC component in a current of the fuel cell stack. Additionally, a termoelement is driven as a heat absorbing device when a temperature of the AC component driving element is equal to or greater than a predetermined temperature and is driven as a heat emitting device when a temperature of the AC component driving element is less than a predetermined temperature, in order to manage heat generation in the AC component driving element.

Abstract: A method and system for measuring impedance of a fuel cell stack that can rapidly measure impedance of a plurality of frequencies of the fuel cell stack using a sine wave signal in which a different plurality of frequencies are synthesized as an impedance measurement input signal, for diagnosis of the state of a fuel cell stack includes: synthesizing a plurality of sine wave signals having different frequencies; applying the synthesized signal as an input signal for measuring to the fuel cell stack; measuring a current and a voltage of the fuel cell stack; transforming the measured current and voltage of the fuel cell stack with a predetermined method; and calculating impedance of the fuel cell stack of the different frequencies based on the current and voltage of the fuel cell stack that is transformed with the predetermined method.

Abstract: A failure diagnosis apparatus that includes an alternating current (AC) absorption unit that is connected to the fuel cell stack and switched based on an applied AC signal to enable a current from the fuel cell stack to flow. In addition, an AC signal generator is configured to generate the AC signal and supply the generated AC signal to the AC absorption unit. As the current from the fuel cell stack is absorbed by the AC absorption unit based on an alternating signal, a stack current input into a diagnosis processing unit includes an AC component, thus the diagnosis processing unit may diagnose fuel cell stack failure by analyzing a frequency of the AC component.

Abstract: To diagnose a fault of a fuel cell stack, an alternating current having a first optimal frequency of a first frequency domain to diagnose a drop in cell voltage and an alternating current having a second optimal frequency of a second frequency domain to diagnose a cause of the drop in cell voltage are supplied to the fuel cell stack are provided. A distortion rate is then calculated based on voltage of the fuel cell stack according to the alternating current of the first optimal frequency, and the drop in cell voltage is diagnosed based on the calculated distortion rate. Also, impedance is calculated based on voltage and a current of the fuel cell stack according to the alternating current of the second optimal frequency and amount of water is calculated based on the calculated in the fuel cell stack, and the cause of the drop in cell voltage is diagnosed based on the calculated impedance and amount of water.

Abstract: A method and system of generating a super-resolution image is provided. fusing The method includes inputting an image; and generating an estimated high-resolution image of a current time by fusing an input image and an estimated high-resolution image of a previous time corresponding to the input image.

Abstract: A rifling angle calculating method according to the present invention expands a rifling angle by combining a Fourier function and a polynomial function to take only the advantages of the two functions, and thus boundary conditions at the start and end points of the rifling angle may be faithfully satisfied, and an optimum rifling angle for minimizing the maximum rifling force may be calculated.

Abstract: An image processing method of separating an input image into a foreground image and a background image, the method including determining a pixel of the input image as a pixel of the foreground image if a foreground probability value of the pixel of the foreground image determined by using the Gaussian mixture model or the pixel determined to be included in a motion region is greater than a setting threshold.

Abstract: A rifling angle calculating method according to the present invention expands a rifling angle by combining a Fourier function and a polynomial function to take only the advantages of the two functions, and thus boundary conditions at the start and end points of the rifling angle may be faithfully satisfied, and an optimum rifling angle for minimizing the maximum rifling force may be calculated.