Abstract: A battery pressure measuring sensor according to an embodiment of the present disclosure includes a substrate; a plurality of variable resistor units provided at a plurality of locations in consideration of a swelling characteristic of a battery on the substrate and configured to change a resistance value within a corresponding resistance range according to a pressure applied to each unit; and a plurality of sensing lines configured to be connected to the plurality of variable resistor units, respectively.

Abstract: A battery diagnosis apparatus for diagnosing a battery including battery cells, the apparatus according to an embodiment may include a voltage measurer for measuring the voltage of each battery cell during a preset period of time, a voltage variation calculator for calculating an individual voltage variation of each battery cell during the preset period of time, an average voltage variation calculator for calculating an average voltage variation of the battery cells during the preset period of time, and an abnormality detector for determining that a voltage abnormality has occurred in at least one battery cell among the battery cells when a difference between the voltage variation of the at least one battery cell and the average voltage variation of the at least one battery cell is greater than a threshold value.

Abstract: A parking assistance apparatus includes at least one camera sensor installed in a vehicle, a control unit configured to analyze an image obtained through the camera sensor to recognize a space and object in a parking lot by matching a detailed parking lot map to an object, search for an available parking space by calculating a parking region on the basis of recognized space and object information, and generate a path to the available parking space searched for, or perform autonomous parking until reaching the available parking space, and a storage unit configured to store the detailed parking lot map for recognizing the space and object.

Abstract: A hologram detection method according to an aspect of the disclosure, includes: inputting a first image, obtained by capturing a detection object on the basis of first flash intensity, to a neural network model to obtain a first detection result value representing the detection or not of a hologram for each of predetermined at least one detection unit regions; and comparing a threshold value with the first detection result value obtained for each detection unit region to determine the detection or not of a hologram in the first image and a first detection unit region where a hologram is detected.

Abstract: A hologram detection method according to an aspect of the disclosure, includes: inputting a first image, obtained by capturing a detection object on the basis of first flash intensity, to a neural network model to obtain a first detection result value representing the detection or not of a hologram for each of predetermined at least one detection unit regions; and comparing a threshold value with the first detection result value obtained for each detection unit region to determine the detection or not of a hologram in the first image and a first detection unit region where a hologram is detected.

Abstract: A hologram detection method according to an aspect of the disclosure, includes: inputting a first image, obtained by capturing a detection object on the basis of first flash intensity, to a neural network model to obtain a first detection result value representing the detection or not of a hologram for each of predetermined at least one detection unit regions; and comparing a threshold value with the first detection result value obtained for each detection unit region to determine the detection or not of a hologram in the first image and a first detection unit region where a hologram is detected.

Abstract: An identification card authenticity determining method based on deep learning according to the disclosure for automatically checking authenticity of an identification card includes: inputting identification card data to a feature information extraction model to extract pieces of feature information, expressing an indicator for checking authenticity of the identification card, from the identification card data; inputting the extracted pieces of feature information to a classification model to determine authenticity of the identification card; and when it is determined that the identification card is falsified, extracting a class activation map, where a falsification region of the identification card data is activated, from the pieces of feature information.

Abstract: A hologram detection method according to an aspect of the disclosure, includes: inputting a first image, obtained by capturing a detection object on the basis of first flash intensity, to a neural network model to obtain a first detection result value representing the detection or not of a hologram for each of predetermined at least one detection unit regions; and comparing a threshold value with the first detection result value obtained for each detection unit region to determine the detection or not of a hologram in the first image and a first detection unit region where a hologram is detected.

Abstract: An identification card authenticity determining method based on deep learning according to the disclosure for automatically checking authenticity of an identification card includes: inputting identification card data to a feature information extraction model to extract pieces of feature information, expressing an indicator for checking authenticity of the identification card, from the identification card data; inputting the extracted pieces of feature information to a classification model to determine authenticity of the identification card; and when it is determined that the identification card is falsified, extracting a class activation map, where a falsification region of the identification card data is activated, from the pieces of feature information.

Abstract: A vehicle battery case includes: a housing in which a battery is mounted and which has a side surface part formed to cover the side surface of the battery; a side upper panel coupled to the side surface part of the housing and extending in a longitudinal direction along the side surface part; a side lower panel coupled to the side surface part of the housing while being spaced downward apart from the side upper panel and extending in the longitudinal direction along the side surface part of the housing, an end of the side lower panel being coupled to an end of the side upper panel so as to form an impact absorption space between the side lower panel and the side upper panel; and a reinforcement panel inserted into the impact absorption space and extending in the longitudinal direction along the side surface part of the housing.

Abstract: A parking assistance apparatus includes at least one camera sensor installed in a vehicle, a control unit configured to analyze an image obtained through the camera sensor to recognize a space and object in a parking lot by matching a detailed parking lot map to an object, search for an available parking space by calculating a parking region on the basis of recognized space and object information, and generate a path to the available parking space searched for, or perform autonomous parking until reaching the available parking space, and a storage unit configured to store the detailed parking lot map for recognizing the space and object.

Abstract: A class labeling system for autonomous driving includes a detection module, a segmentation module, and a lane road boundary detection module. The detection module is configured to detect objects for autonomous driving from an image captured by a camera to generate a bounding box for each of the objects and detect property information about the object. The segmentation module is configured to determine classes for each pixel of the bounding box detected by the detection module and process at least one of the classes as don't care. The lane road boundary detection module is configured to detect at least one of lane and road boundaries using the bounding box detected by the detection module.

Abstract: A parking assistance apparatus includes at least one camera sensor installed in a vehicle, a control unit configured to analyze an image obtained through the camera sensor to recognize a space and object in a parking lot by matching a detailed parking lot map to an object, search for an available parking space by calculating a parking region on the basis of recognized space and object information, and generate a path to the available parking space searched for, or perform autonomous parking until reaching the available parking space, and a storage unit configured to store the detailed parking lot map for recognizing the space and object.

Abstract: An automatic image synthesizing apparatus including an image search unit configured to search for and extract a frame image having an object to be learned or replaced from a plurality of frame images inputted through a vehicle camera; an instance object detection unit configured to detect an instance object to be learned or replaced from the extracted frame image; an image extraction and object class information detection unit configured to extract mask-segmented objects from the extracted frame image and form a data-structure; a standard image mapping unit configured to map a standard image matching a class value of the mask-segmented object; and a generative adversarial network (GAN) network unit configured to receive the selected standard image and the mask segmentation image and learn a replacement image or produce a replacement image based on a learning result.

Abstract: A parking assistance apparatus includes at least one camera sensor installed in a vehicle, a control unit configured to analyze an image obtained through the camera sensor to recognize a space and object in a parking lot by matching a detailed parking lot map to an object, search for an available parking space by calculating a parking region on the basis of recognized space and object information, and generate a path to the available parking space searched for, or perform autonomous parking until reaching the available parking space, and a storage unit configured to store the detailed parking lot map for recognizing the space and object.

Abstract: A class labeling system for autonomous driving includes a detection module, a segmentation module, and a lane road boundary detection module. The detection module is configured to detect objects for autonomous driving from an image captured by a camera to generate a bounding box for each of the objects and detect property information about the object. The segmentation module is configured to determine classes for each pixel of the bounding box detected by the detection module and process at least one of the classes as don't care. The lane road boundary detection module is configured to detect at least one of lane and road boundaries using the bounding box detected by the detection module.

Abstract: An automatic image synthesizing apparatus including an image search unit configured to search for and extract a frame image having an object to be learned or replaced from a plurality of frame images inputted through a vehicle camera; an instance object detection unit configured to detect an instance object to be learned or replaced from the extracted frame image; an image extraction and object class information detection unit configured to extract mask-segmented objects from the extracted frame image and form a data-structure; a standard image mapping unit configured to map a standard image matching a class value of the mask-segmented object; and a generative adversarial network (GAN) network unit configured to receive the selected standard image and the mask segmentation image and learn a replacement image or produce a replacement image based on a learning result.

Abstract: There are provided an apparatus and method for photographing an object. An apparatus for photographing an object using top and bottom buttons includes: a head part including a camera; a connection part coupled to the head part and extended in a length direction thereof, and having a first button for manipulating the camera on an extension line in the length direction from a formation position of the head part and a second button for manipulating the camera formed on a surface opposite to the first button; and a body part including a power source means coupled to the connection part and supplying power to the camera, and a display means displaying a state of the camera or a power state.

Abstract: The present invention relates to an X-ray photographing apparatus and method capable of variously and finely adjusting a magnification power by sliding a rotating portion supporting an X-ray source portion and a sensor portion facing each other in a state in which an interval between the X-ray source portion and the sensor portion is maintained to change an interval between the sensor portion and a head of a subject to be examined. The X-ray photographing apparatus includes: a rotating portion including an X-ray source portion and a sensor portion facing each other and provided at a shaft through a moving means so as to be movable in an X-ray irradiation direction; and an actuating portion adjusting a magnification power by changing an interval between the sensor portion and a head of a subject to be examined in a state in which an interval between the X-ray source portion and the sensor portion is maintained.

Abstract: A method of fabricating a semiconductor light emitting device includes forming a first conductivity type semiconductor layer, forming an active layer by alternately forming a plurality of quantum well layers and a plurality of quantum barrier layers on the first conductivity type semiconductor layer, and forming a second conductivity type semiconductor layer on the active layer. The plurality of quantum barrier layers include at least one first quantum barrier layer adjacent to the first conductivity type semiconductor layer and at least one second quantum barrier layer adjacent to the second conductivity type semiconductor layer. The forming of the active layer includes allowing the at least one first quantum barrier layer to be grown at a first temperature and allowing the at least one second quantum barrier layer to be grown at a second temperature lower than the first temperature.