Abstract: A method and an apparatus for recognition a position and generating a path for autonomous driving of a mobile robot in an orchard environment are provided. The method converts three-dimensional (3D) point cloud data for the orchard environment into a 2D grid map, obtains a position of the mobile robot by performing local scan matching and global scan matching on the 2D grid map, and extracts a tree from the 2D grid map based on occupancy of each grid of the 2D grid map. Then, an effective line based on center points of extracted trees is obtained, a destination based on the obtained effective line is generated, and a driving path according to the generated destination and the position of the mobile robot is generated.

Abstract: A method and an apparatus for recognition a position and generating a path for autonomous driving of a mobile robot in an orchard environment are provided. The method converts three-dimensional (3D) point cloud data for the orchard environment into a 2D grid map, obtains a position of the mobile robot by performing local scan matching and global scan matching on the 2D grid map, and extracts a tree from the 2D grid map based on occupancy of each grid of the 2D grid map. Then, an effective line based on center points of extracted trees is obtained, a destination based on the obtained effective line is generated, and a driving path according to the generated destination and the position of the mobile robot is generated.

Abstract: Provided is a method of separating a foreground and a background by extracting a depth image through a stereo camera, generating an occupancy grid map on the basis of the depth image, predicting a free space, and computing a membership value, the method including setting a threshold value of a foreground object existing in a free space boundary region of the predicted free space, determining whether the membership value reaches the threshold value of the foreground object while the membership value is computed, terminating the computing of the membership value when it is determined that the membership value being computed reaches the threshold value of the foreground object in the determining, and separating a foreground and a background through the computed membership value.

Abstract: Provided is a technology for recognizing vehicle license plate information which includes detecting a position of a license plate from a vehicle image obtained by imaging a vehicle, extracting individual character images by separating a plurality of characters from a region of the detected license plate in the vehicle image and extracting a license plate type of the license plate according to a predetermined criterion, recognizing a license plate character string on the basis of the extracted individual character images and the license plate type and outputting the recognized license plate character string.

Abstract: Provided is a method of separating a foreground and a background by extracting a depth image through a stereo camera, generating an occupancy grid map on the basis of the depth image, predicting a free space, and computing a membership value, the method including setting a threshold value of a foreground object existing in a free space boundary region of the predicted free space, determining whether the membership value reaches the threshold value of the foreground object while the membership value is computed, terminating the computing of the membership value when it is determined that the membership value being computed reaches the threshold value of the foreground object in the determining, and separating a foreground and a background through the computed membership value.

Abstract: Provided is a technology for recognizing vehicle license plate information which includes detecting a position of a license plate from a vehicle image obtained by imaging a vehicle, extracting individual character images by separating a plurality of characters from a region of the detected license plate in the vehicle image and extracting a license plate type of the license plate according to a predetermined criterion, recognizing a license plate character string on the basis of the extracted individual character images and the license plate type and outputting the recognized license plate character string.

Abstract: Provided is an electrical system including an intelligent learning terminal to analyze biometric information associated with a user and calculate an intensity of electrical stimulation for the user based on a result of the analyzing, and at least one wireless electrical stimulator to provide electrical stimulation to the user based on the calculated intensity of electrical stimulation, wherein the intelligent learning terminal is connected to the at least one wireless electrical stimulator based on wired or wireless communication.

Abstract: Disclosed herein is an object image capture apparatus. The object image capture apparatus includes a first camera unit, a second camera unit, and a control unit. The first camera unit obtains a wide-area view image by capturing a wide-area view region. The second camera unit obtains a close-up view image by capturing the close-up view region of the wide-area view region. The control unit controls the second camera unit by dividing the wide-area view image into a plurality of blocks, analyzing the resulting blocks, and defining a target block, in which a moving object is detected, as a close-up view region from among the plurality of blocks.

Abstract: An apparatus for rapidly detecting an object of interest includes: a first object of interest detector configured to determine a region of an object of interest for an image, from which the object of interest is to be detected, by using a first training image; and a second object of interest detector configured to detect the object of interest from the region of the object of interest determined by the first object of interest detector by using a second training image, which is bigger in size than the first training image.

Abstract: Provided is an apparatus and method for detecting a vehicle number plate that may determine whether an input image includes a number plate, based on an optimal feature to be used to determine whether the input image includes a number plate.

Abstract: A method and apparatus for detecting and recognizing an object using a vector histogram based on a local binary pattern are disclosed. The apparatus of detecting and recognizing an object using a local binary pattern includes: a feature map creator configured to extract an object area in which a moving object exists from an input image, to create a local binary pattern by designating a local area in the object area, and to create a vector component map including information about magnitude vector components and direction vector components using the local binary pattern; a feature map configuring unit configured to divide the object area into a plurality of blocks and to create a feature vector map through a histogram using the vector component map in a unit of the block; and an object detector configured to detect and classify the moving object based on the feature vector map.

Abstract: Provided is an electrical system including an intelligent learning terminal to analyze biometric information associated with a user and calculate an intensity of electrical stimulation for the user based on a result of the analyzing, and at least one wireless electrical stimulator to provide electrical stimulation to the user based on the calculated intensity of electrical stimulation, wherein the intelligent learning terminal is connected to the at least one wireless electrical stimulator based on wired or wireless communication.

Abstract: A method and apparatus for detecting and recognizing an object using a vector histogram based on a local binary pattern are disclosed. The apparatus of detecting and recognizing an object using a local binary pattern includes: a feature map creator configured to extract an object area in which a moving object exists from an input image, to create a local binary pattern by designating a local area in the object area, and to create a vector component map including information about magnitude vector components and direction vector components using the local binary pattern; a feature map configuring unit configured to divide the object area into a plurality of blocks and to create a feature vector map through a histogram using the vector component map in a unit of the block; and an object detector configured to detect and classify the moving object based on the feature vector map.

Abstract: Disclosed herein is an apparatus and method for detecting a person from an input video image with high reliability by using gradient-based feature vectors and a neural network. The human detection apparatus includes an image preprocessing unit for modeling a background image from an input image. A moving object area setting unit sets a moving object area in which motion is present by obtaining a difference between the input image and the background image. A human region detection unit extracts gradient-based feature vectors for a whole body and an upper body from the moving object area, and detects a human region in which a person is present by using the gradient-based feature vectors for the whole body and the upper body as input of a neural network classifier. A decision unit decides whether an object in the detected human region is a person or a non-person.

Abstract: Disclosed herein are an apparatus and method for recognizing a human in an image. The apparatus includes a learning unit and a human recognition unit. The learning unit calculates a boundary value between a human and a non-human based on feature candidates extracted from a learning image, detects a feature candidate for which an error is minimized as the learning image is divided into the human and the non-human using the calculated boundary value, and determines the detected feature candidate to be a feature. The human recognition unit extracts a candidate image where a human may be present from an acquired image, and determines whether the candidate image corresponds to a human based on the feature that is determined by the learning unit.

Abstract: A fingerprint verification apparatus that adds chaff fingerprint information to real fingerprint information of a user and then, hides and stores the fingerprint information of the user with a polynomial generated by unique information of the individual, thereby safely protecting the important fingerprint information of the user stored in a storing unit from an external attacker and safely managing an private key using the fingerprint information when using the private key as the unique information for making the polynomial.

Abstract: A method for detecting a forged face using an infrared image includes: acquiring an infrared image and a photorealistic image captured by one or two cameras; extracting a face region from the photorealistic image; determining, based on analysis of quality characteristics of the infrared image, whether a current face is a forged face or not; and performing face recognition on the extracted face region if it is determined that the current face is a non-forged face. The method further includes capturing an infrared image and a photorealistic image again through the camera without performing face recognition if it is determined that the current face is a forged face.

Abstract: A forged face detecting method includes: acquiring a photorealistic image and an infrared image of a subject on which line beams are projected; extracting face features from the infrared image based on characteristics of a pattern of the line beams projected on the acquired infrared image; and detecting whether or not the infrared image is a forged face based on the extracted face features. Said detecting whether or not the infrared image is a forged face includes: checking whether the extracted face features falls within a preset permission range of face features; determining the infrared image to have the forged face if the extracted face features fall out of the range to acquire an infrared image of the subject again; and determining the infrared image to have a non-forged face if the extracted face features falls within the range to perform face recognition for the photorealistic image.

Abstract: A biometric register includes: a feature extraction unit for performing preprocessing for a fingerprint to extract a feature point m for the fingerprint; a transformation function generation unit for generating a transformation function which is composed of an arbitrary rotation matrix and an arbitrary vector; and a template generation unit for transforming a coordinate of the feature point m using the generated transformation function, and organizing a fuzzy vault using a randomly generated fake feature point and a feature point m1 applied by the transformed coordinate, thereby generating a one-time template.

Abstract: A method of detecting a facial image includes pre-processing an image; and detecting a face region from the pre-processed image to create facial records of the detected face region. Further, the method of detecting the facial image includes detecting the facial image by creating coordinates of the face and eyes in the input image by using the facial records.