摘要:
본 발명은 과도 시차를 가지는 객체만을 분리하여 검출할 수 있는 과도시차 객체 검출방법에 관한 것이다. 본 발명에 따른 과도시차 객체 검출방법은 3차원 영상에 포함된 좌영상 및 우영상을 분석하여 상기 좌영상 및 우영상의 시차 맵을 형성하는 시차 맵 형성단계와, 상기 시차 맵에서 기설정된 문턱값 이상의 시차 값을 가지는 과도시차 후보영역을 설정하는 이진화단계와, 상기 좌영상 및 우영상 중 선택된 하나의 영상에서, 상기 과도시차 후보영역과 중첩되는 영역의 화소 값은 그대로 보존하고, 상기 과도시차 후보영역과 중첩되지 않는 영역의 화소 값은 기준화소 값으로 치환하는 마스킹단계와, 상기 화소 값이 보존된 영역에 대하여 화소 밝기 및 시차를 기준으로하여 영역분할을 하는 영역분할단계를 포함한다.
摘要:
Embodiments of the invention introduce the concept of a virtual fiducial marker (VFM). This marker will not be placed prior to preoperative imaging. It will therefore not initially appear in the preoperative 3D image. Instead, the marker will be virtually placed in the 3D data set prior to surgery, and as such the marker does not even need to be attached to the patient, if the patient is not expected to move during surgery. The idea behind such a VFM comes from the observation that there is a big variation in the difficulty of an image based registration depending on the quality of the images and their field of view. However, provided two initial registrations to high quality wide field of view images can be carried out, it then becomes possible to use these registrations to insert a virtual fiducial marker within the 3D preoperative image. Once inserted it may then be used to obtain a starting position for a registration procedure, and particularly to obtain in-plane translations. It may also be used at the end of a registration to provide a measure of registration accuracy, to verify the registration and detect mis-registrations..
摘要:
An apparatus and a method for hierarchical stereo matching are provided. In the method, a reduced image is formed by reducing left and right images, and a first Trellis is performed on the reduced image. Then, a magnified image is generated by magnifying the size and the brightness of the reduced image, and a second Trellis is performed on the magnified image.
摘要:
L'invention concerne une méthode de filtrage d'une carte de disparité associé à une des vues d'une image stéréoscopique comprenant les étapes d'identification des pixels (x n ) auxquels est associée une valeur de disparité erronée (d(x n )) par comparaison avec les valeurs de disparité des pixels avoisinants (x n-1 ,x n+1 ) et de correction des valeurs de disparité des pixels identifiés.
摘要:
A method for categorizing body shape is provided comprising the steps of providing a data set of body shape-defining measurements of a portion of the body of interest from a plurality of subjects' bodies, wherein the measurements define a silhouette and profile (front and side) perspectives of the portion of the body of interest; conducting a principal component (PC) analysis of the data set of measurements to calculate and generate PC scores; conducting cluster analysis using the PC scores as independent variables to produce cluster analysis results; and establishing one or more body shape categories from the cluster analysis results, thereby categorizing body shapes of the plurality of subjects. A shape prototyping system is also provided for designing a custom fit garment for an individual subject, the system being based on the method for categorizing body shape.
摘要:
A method identifies the presence of a three-dimensional (3D) image format in received image through the use of feature matching and correspondence. The received image is sampled using a candidate 3D format to generate two sub-images from the received image. Initially, these sub-images are compared to determine whether these sub-images are similar with respect to structure. If the sub-images are not similar, a new 3D format is selected and the method is repeated. If the sub-images are similar, features are detected in the two sub-images and a correspondence is formed between features that match in the two sub-images. Positional differences are computed between corresponding features. The amount and uniformity of the positional differences are then used to determine whether the format is 2D or 3D and, if 3D, which of the 3D formats was used for the received image.
摘要:
A first image capture component may capture a first image of a scene, and a second image capture component may capture a second image of the scene. There may be a particular baseline distance between the first image capture component and the second image capture component, and at least one of the first image capture component or the second image capture component may have a focal length. A disparity may be determined between a portion of the scene as represented in the first image and the portion of the scene as represented in the second image. Possibly based on the disparity, the particular baseline distance, and the focal length, a focus distance may be determined. The first image capture component and the second image capture component may be set to focus to the focus distance.