摘要:
An image matching apparatus includes a bilateral filter that filters a left image and a right image to output a second left image and a second right image; a census cost calculation unit performing census transform on a window based on a first pixel of the second left image and a window based on a second pixel of the second right image to calculate a census cost corresponding to a pair of pixels of the first and second pixels; a support weight calculation unit obtaining support weights of the left and right images or the second left and second right images; a cost aggregation unit obtaining energy values of nodes corresponding to the pair of pixels of the first and second pixels using the census cost and the support weights; and a dynamic programming unit performing image matching using dynamic programming by the energy values of each node obtained.
摘要:
A robot vision system for outputting a disparity map includes a stereo camera for receiving left and right images and outputting a disparity map between the two images; an encoder for encoding either the left image or the right image into a motion compensation-based video bit-stream; and a decoder for extracting an encoding type of an image block, a motion vector, and a DCT coefficient from the video bit-stream. Further, the system includes a person detector for detecting and labeling person blocks in the image using the disparity map between the left image and the right image, the block encoding type, and the motion vector, and detecting a distance from the labeled person to the camera; and an obstacle detector for detecting a closer obstacle than the person using the block encoding type, the motion vector, and the DCT coefficient extracted from the video bit-stream, and the disparity map.
摘要:
Provided are a human recognition apparatus and a human recognition method identifying a user based on a walking pattern. The human recognition apparatus includes a detecting unit detecting a vibration according to a user's walking, and outputting an electric signal, a pattern calculating unit acquiring a walker's walking pattern from the electric signal, and a user determining unit comparing the walking pattern with a previously measured reference data by user and identifying the user based on the comparison result. The human recognition apparatus and the human recognition method are robust against peripheral noise and can increase an acceptance rate through a simple structure and procedure by using the waling pattern, which is one-dimensional time information requiring no vast data throughput, as the user identification data.
摘要:
An image object detection apparatus includes a noise filtering block for removing image noise an input image, an image scaling block for scaling the noise-removed input image to produce a scaled input image, an image conversion block for dividing the scaled input image into multiple regions and converting the divided image by a modified census transform (MCT) method, a data processing block for comparing MCT values of the image converted by the MCT method with a preset threshold, detecting at least one candidate region and identifying a human region from said at least one detected candidate region, and an image output block for marking the identified human region on the noise-removed input image.
摘要:
Provided are a face detection apparatus and a distance measurement method using the same. The face detection apparatus detects a face using left and right images which are acquired from a stereo camera. The face detection apparatus measures distance from the stereo camera to the face using an image frame which is provided from the stereo camera without a stereo matching process. Accordingly, the face detection apparatus simultaneously performs face detection and distance measurement even in a low-performance system.
摘要:
A system and a method for detecting a face are provided. The system includes a vision processing unit and a face detection unit. The vision processing unit calculates distance information using a plurality of images including a face pattern, and discriminates between a foreground image including the face pattern and a background image not including the face pattern, using the distance information. The face detection unit scales the foreground image according to the distance information, and detects the face pattern from the scaled foreground image.
摘要:
Provided are an image matching apparatus and method, and the image matching apparatus includes a determining unit determining whether a node, in which a first pixel of a left image of a subject and a second pixel of a right image of the subject corresponding to the first pixel are calculated, is a matchable region, and an operating unit calculating a disparity value by using the brightness information of a left window composed of the first pixel corresponding to the node and peripheral pixels surrounding the first pixel and the brightness information of a right window composed of the second pixel corresponding to the node and peripheral pixels surrounding the second pixel, when the node is the matchable region as a result of the determination.
摘要:
There are provided an apparatus and method for vision processing on a network based intelligent service robot system and a system using the same. A robot can move to a target object, avoiding obstacles without helps of a robot server interfaced with a robot terminal over network, by extracting/processing three-dimensional distance information of external objects, using a stereo camera, a low price image processing dedicated chip and an embedded processor. Therefore, the intelligent robot can travel and move using only a stereo camera image processing without other sensors, and further provides users with various functional services with low expense.
摘要:
A data transmission apparatus of an intelligent robot system and a method thereof are provided. The data transmission apparatus includes a vision processor collector, a communicating unit, and a controller. The vision processor collects images captured through a camera, and performs an image process on the collected image to minimize a quantity of information about unnecessary regions in the collected image. The communicating unit communicates with the robot server, transmits the processed image data from the vision processor to the robot server, and receives corresponding result data from the robot server. The controller controls the image process and the transmission of the processed image data in the vision processor, and a corresponding operation of the robot terminal performed according to result data received from the robot server.
摘要:
Disclosed are an apparatus and a method for extracting an edge to be used for extracting a feature point of an object in an image. The present invention proposes an image edge extracting apparatus and method that remove noise in an input image, calculate a gradient of an image in a noise-removed image, measure magnitude of the gradient, extract an edge having a maximum thickness value, and then calculate a threshold using a ratio of the extracted edge, and detect a final edge robust against noise based on the threshold.