Abstract: A steel for a gear includes, based on a total weight of the steel: C: 0.10-0.30 wt %, Si: 0.60-0.80 wt %, Mn: 0.25-0.75 wt %, Cr: 1.80-2.20 wt %, Ni: 0.50-1.50 wt %, Mo: 0.20-0.40 wt %, Nb: 0.025-0.050 wt %, V: 0.030-0.050 wt %, and a balance of Fe and inevitable impurities, wherein contents of Nb and V satisfy the following <Relationship Formula 1>: 0.055<[Nb]+[V]<0.100??<Relationship Formula 1>, wherein [Nb] represents a content of Nb and [V] represents a content of V.

Abstract: A depth-wise convolution acceleration device using an MAC array processor structure according to the present invention may include a data output unit, which receives a data of each row of the image from the data buffer and inputs the data into convolution operation blocks while shifting the data N?1 times according to the kernel size (N×N) and a weight output unit, which receives the kernel data from the kernel buffer and sequentially inputs a weight value constituting the kernel data to each of the row convolution operation blocks, and inputs the weight delaying by N clocks if the row increases as N rows.

Abstract: An embodiment vehicle door opening/closing system includes an inner panel defining a door open portion of a vehicle, the inner panel including an installation groove having a protruding or recessed shape, a driving device disposed in the installation groove of the inner panel, and a link mechanism installed on a chassis through a rotating shaft, a first end of the link mechanism being connected to the driving device such that power is transferred thereto, and a second end of the link mechanism being connected to a door such that, during driving of the driving device, the link mechanism rotates with reference to the rotating shaft to open/close the door.

Abstract: Disclosed are a bin-picking system and a bin-picking method. A bin-picking system includes a transformable bin-picking box; a supporting unit configured to support the bottom part of the bin-picking box and be movable upward and downward; and a control unit configured to change an alignment of at least one bin-picking candidate object by transforming the bin-picking box by controlling a movement of the supporting unit if no bin-picking target object is detected from the at least one bin-picking candidate object existing inside bin-picking box and placed on the supporting unit to facilitate detection of a bin-picking target object and bin-picking.

Abstract: Disclosed are a personalized exercise service providing method and an apparatus thereof. A personalized exercise service providing apparatus according to an example includes a user class identifier configured to identify user class of a user; an exercise data acquirer configured to acquire exercise data of the user; and a model generator configured to generate a personalized exercise model of the user based on a standard exercise model corresponding to the determined user class and the acquired exercise data of the user to provide the most effective exercise model to each user through user recognition.

Abstract: The present invention relates to an apparatus for recognizing intention of a horse-riding simulator user, and a method thereof, and the apparatus for recognizing intention of a horse-riding simulator user can provide a safe and realistic horse-riding simulation environment to a user by recognizing an aid signal and an intention signal of the user to sense a dangerous situation and accordingly coping with the situation. According to the present invention, it is possible to increase the sense of the real for the user by enabling the horse-riding simulator user to perform similar interaction to actual horse-riding, and to increase effects of horse-riding training using the horse-riding simulator. Particularly, there is an advantage that the dangerous situation is sensed for safe riding, and it is possible to contribute to formation of a related technology market by providing an effective method for recognition of the intention of the horse-riding simulator user.

Abstract: The present invention relates to a device and a method of detecting arbitrarily piled objects, and a device and a method for picking a detected object. The present invention may provide a device and a method of detecting an object, which extract a unique local characterized part of the object by using a visual sensor, detect an object region, and estimate a posture from the detected object region. Also the present invention may provide an object picking system capable of being applied to an actual production process, such as assembling or packaging, in a cell producing method.

Abstract: Disclosed is a working method using a sensor, which increases recognition of a component to increase mounting of a component and enhancing productivity. The working method includes: extracting an object to be picked from a pile of objects using the sensor; picking the extracted object to move the picked object to a predetermined place; and estimating an angle of the moved object in the current position using the sensor. Accordingly, the working method can perform precise component recognition and posture estimation by two steps: a component picking step and a component recognition step, and effectively apply to a manufacturing line, thereby improving mounting of a component and enhancing productivity of a product.

Abstract: Disclosed are a bin-picking system and a bin-picking method. A bin-picking system includes a transformable bin-picking box; a supporting unit configured to support the bottom part of the bin-picking box and be movable upward and downward; and a control unit configured to change an alignment of at least one bin-picking candidate object by transforming the bin-picking box by controlling a movement of the supporting unit if no bin-picking target object is detected from the at least one bin-picking candidate object existing inside bin-picking box and placed on the supporting unit to facilitate detection of a bin-picking target object and bin-picking.

Abstract: Disclosed are a personalized exercise service providing method and an apparatus thereof. An personalized exercise service providing apparatus according to an example includes a user class identifier configured to identify user class of a user; an exercise data acquisitor configured to acquire exercise data of the user; and a model generator configured to generate a personalized exercise model of the user based on a standard exercise model corresponding to the determined user class and the acquired exercise data of the user to provide the most effective exercise model to each user through user recognition.

Abstract: An apparatus for recognizing a user's posture in a horse-riding simulator, the apparatus comprising: a standard posture model generation module configured to find out a standard posture model by selecting feature points from an expert database, and generate the standard posture model; and a posture recognizing module configured to obtain a user's posture from the horse-riding simulator, recognize a user's horse-riding posture by matching the obtained user's posture with the standard posture model generated in the standard posture model generation module, and suggest a standard posture model appropriate for a user's level.

Abstract: Provided is a simulator managing apparatus and method for analyzing the posture of a user. The simulator managing apparatus includes: an input configured to acquire environment information and image information with respect to a simulator and a user; a controller configured to recognize a position and a posture of the user by analyzing the information acquired by the input, and to generate control information that includes coaching information for posture correction of the user according to the recognized position and posture; and an output configured to provide the analysis and the control information generated by the controller.

Abstract: The present invention relates to a device and a method of detecting arbitrarily piled objects, and a device and a method for picking a detected object. The present invention may provide a device and a method of detecting an object, which extract a unique local characterized part of the object by using a visual sensor, detect an object region, and estimate a posture from the detected object region. Also the present invention may provide an object picking system capable of being applied to an actual production process, such as assembling or packaging, in a cell producing method.

Abstract: Disclosed are a wearable behavioral pattern collecting apparatus for generating collected information by analyzing a behavioral pattern of a wearer, and generating and thereby transmitting emergency call information when an emergency situation occurs, a network including a repeater to transmit information received from the behavioral pattern collecting apparatus to a remote monitoring server, and a behavioral pattern analyzing system and method for transmitting information on an emergency accident and a position of the wearer to a corresponding institution or a corresponding person in charge when an emergency situation such as a falling accident or the emergency accident occurs by observing a change in the behavioral pattern of the wearer.

Abstract: The present invention relates to an apparatus for recognizing intention of a horse-riding simulator user, and a method thereof, and the apparatus for recognizing intention of a horse-riding simulator user can provide a safe and realistic horse-riding simulation environment to a user by recognizing an aid signal and an intention signal of the user to sense a dangerous situation and accordingly coping with the situation. According to the present invention, it is possible to increase the sense of the real for the user by enabling the horse-riding simulator user to perform similar interaction to actual horse-riding, and to increase effects of horse-riding training using the horse-riding simulator. Particularly, there is an advantage that the dangerous situation is sensed for safe riding, and it is possible to contribute to formation of a related technology market by providing an effective method for recognition of the intention of the horse-riding simulator user.

Abstract: A space recognition system obtains available RSSI (Received Signal Strength Indicator) information for a plurality of fixing devices in the vicinity of a user device in the wireless sensor network environment, collects environment information in a space where the user device is located, and collects environment information in a plurality of spaces in which the fixing devices are respectively located. The system combines the RSSI information and the environment information and performs a recognition function on the combined environment information to recognize the space in which a user having the user device is located.

Abstract: An apparatus for recognizing a user's posture in a horse-riding simulator, the apparatus comprising: a standard posture model generation module configured to find out a standard posture model by selecting feature points from an expert database, and generate the standard posture model; and a posture recognizing module configured to obtain a user's posture from the horse-riding simulator, recognize a user's horse-riding posture by matching the obtained user's posture with the standard posture model generated in the standard posture model generation module, and suggest a standard posture model appropriate for a user's level.

Abstract: Disclosed is a typewriter system and a text input method capable of accurately recognizing words by correcting words input using a mediated interface device based on a dictionary. A plurality of texts are combined by referencing a text recognition order set in which recognition results of texts are arranged according to a recognition order from texts input through the mediated interface device and the combined text is filtered using part index maps formed of part words that are an accumulated set of texts forming complete words. The part words passing through the part index maps is again filtered using a dictionary including context information formed of a set of words in a specific category, thereby making it possible to accurately recognize the words. The part words that cannot form words in a dictionary are removed in advance using the part index maps, thereby improving the recognition efficiency.

Abstract: Disclosed is a working method using a sensor, which increases recognition of a component to increase mounting of a component and enhancing productivity. The working method includes: extracting an object to be picked from a pile of objects using the sensor; picking the extracted object to move the picked object to a predetermined place; and estimating an angle of the moved object in the current position using the sensor. Accordingly, the working method can perform precise component recognition and posture estimation by two steps: a component picking step and a component recognition step, and effectively apply to a manufacturing line, thereby improving mounting of a component and enhancing productivity of a product.

Abstract: Disclosed is a horseback riding simulator configured to operate in an adaptive manner with respect to a user and a method using the same, the horseback riding simulator including a user identification unit to identify a user through user identification information based on user facial information extracted from an input image, a posture recognition unit to calculate user posture information by extracting information related to each of designated body parts of the user from the input image, a coaching unit to provide the user with instruction in horseback riding posture, based on the user identification information and the user posture information, and a sensory realization unit to control a horseback riding mechanism based on a user-intended posture calculated through analysis of the user posture information. Accordingly, user-customized horseback riding instruction is provided through identification of a user and recognition of a user's horseback riding posture.