Abstract: A vehicle control apparatus includes a camera that obtains a surrounding image of a vehicle, and a controller that estimates a position of a first corner point and a position of a second corner point of a trailer connected to the vehicle based on the surrounding image, estimates a position of a third corner point of the trailer using a position of the camera, the position of the first corner point, and the position of the second corner point, and estimates a length of the trailer based on the position of the first corner point and the position of the third corner point. The vehicle control apparatus improves the stability of autonomous driving by reducing the risk of lane encroachments and vehicle collisions, by allowing an autonomous vehicle towing a trailer to actively estimate the length of the trailer.

Abstract: An apparatus for recognizing an object using an image includes a depth map generator that generates a depth map using a feature map of the image based on a dilated convolutional neural network (DCNN) and an object recognition device that recognizes the object using the depth map generated by the depth map generator and the image.

Abstract: An apparatus for recognizing an object using an image includes a depth map generator that generates a depth map using a feature map of the image based on a dilated convolutional neural network (DCNN) and an object recognition device that recognizes the object using the depth map generated by the depth map generator and the image.

Abstract: An apparatus for scanning a parking slot includes: a parking slot detecting processor configured to: extract line segments from obstructions around a vehicle using a light detection and ranging (LIDAR) sensor and detect a parking slot candidate by comparing a distance between the line segments extracted from the obstructions with width or length information of the vehicle; a posture information calculating processor configured to calculate posture information of the vehicle with respect to the detected parking slot candidate; a path generating processor configured to generate a parking path for autonomous parking in the detected parking slot candidate with respect to the posture information of the vehicle; and a determining processor configured to determine whether it is possible to park in the corresponding parking slot candidate based on the generated parking path and determine the parking slot candidate as a target parking slot.

Abstract: A method for extracting an eye center point includes: photographing a left eye using a left camera resulting in a left eye image; extracting a light reflection point from the left eye image using a first lighting; extracting a first reflection point which is the brightest point on a horizontal line of the light reflection point using a second lighting; photographing the left eye using a right camera; extracting a second reflection point and a third reflection point from an epipolar line by computing an epipolar line of an image corresponding to the light reflection point using the first lighting and the second lighting; and extracting the eye center point using the light reflection point, the first reflection point, the second reflection point, and the third reflection point.

Abstract: A gaze detection apparatus and method are provided. The method includes storing, by a controller, a reference gaze, a first reference vector, and a second reference vector. An image is then captured by an imaging device that includes user eyes. In addition, the controller detects central points of a pupil and an eyeball from the captured image and generates a gaze vector for one eyeball and a normal vector of a plane at which three central points are formed, when the three central points are detected. A first rotation angle and a second rotation angle are calculated by comparing the gaze vector and the normal vector, respectively, with the first reference vector and the second reference vector and a mean value thereof is calculated. Further, a gaze is then detected by rotating the reference gaze as much as the mean value.

Abstract: A method for extracting an eye center point includes: photographing a left eye using a left camera resulting in a left eye image; extracting a light reflection point from the left eye image using a first lighting; extracting a first reflection point which is the brightest point on a horizontal line of the light reflection point using a second lighting; photographing the left eye using a right camera; extracting a second reflection point and a third reflection point from an epipolar line by computing an epipolar line of an image corresponding to the light reflection point using the first lighting and the second lighting; and extracting the eye center point using the light reflection point, the first reflection point, the second reflection point, and the third reflection point.

Abstract: A technique for controlling a heads up display for a vehicle capable of directly controlling contents using gaze information received from a camera for gaze tracking and coordinates of a recognizable specific object such as a hand. The technique for controlling a head up display for a vehicle includes: tracking a driver's gaze using a camera; when the gaze stares at the HUD, detecting a gaze vector based on the gaze tracking; detecting the gaze vector and then detecting a hand between the camera and the driver's gaze and tracking coordinates of a tip of the hand; matching a final coordinate of the driver's gaze staring at the HUD and a final coordinate of the tip of the hand; and controlling the HUD using the driver's hand.

Abstract: A method for generating a three dimensional image using a monoscopic camera, includes controlling light intensity of illumination stepwise at a plurality of light intensity steps. Subject is photographed to generate images for each of the plurality of light intensity steps using the monoscopic camera. Each of the images for each light intensity step is converted into binary images. A difference image between the converted binary images is obtained. The difference images are reconstructed to generate the three dimensional image.

Abstract: A pupil detecting apparatus includes a first detector configured to binarize an image including an eye region according to brightness values and detect a pupil region from the image including an eye region, a second detector configured to detect edges from the image including an eye region and detect a pupil boundary region by using the detected edges, and a pupil detector configured to determine a final pupil region by using the detected pupil region and the detected pupil boundary region.

Abstract: A gaze detection apparatus and method are provided. The method includes storing, by a controller, a reference gaze, a first reference vector, and a second reference vector. An image is then captured by an imaging device that includes user eyes. In addition, the controller detects central points of a pupil and an eyeball from the captured image and generates a gaze vector for one eyeball and a normal vector of a plane at which three central points are formed, when the three central points are detected. A first rotation angle and a second rotation angle are calculated by comparing the gaze vector and the normal vector, respectively, with the first reference vector and the second reference vector and a mean value thereof is calculated. Further, a gaze is then detected by rotating the reference gaze as much as the mean value.

Abstract: An advertising method on a network comprises displaying a plurality of advertisement objects in a virtual three-dimensional area, and allowing a user to select at least one of the plurality of advertisement objects. Moreover, the present invention relates to an advertisement method of additionally displaying a representation of a user, wherein the representation can be used by the user to move around the virtual three-dimensional area and to select at least one of the plurality of objects. Particularly, an Internet advertisement system uses virtual reality spaces based on three-dimensional graphics, wherein three-dimensional virtual reality programs are provided through an Internet home page. Also, virtual Web signboards, virtual Web advertising balloons (ad-balloons) and virtual Web shops move in a three-dimensional perspective representation manner with the movement of a specific character within a selected one of the virtual reality spaces as if they were really present around the character.