摘要:
The orientation of each index is estimated from a sensed image, and the index detected from the image is identified based on the orientation of an image sensing device and that of the index estimated from known coordinate information of the index. In this way, indices which are located at nearby positions but have different orientations are never misidentified, and can be stably identified. Indices can be stably identified from the sensed image in which indices located in the physical space appear.
摘要:
A sensed image of the physical space is acquired by an image sensing apparatus. One or more indices are detected from the sensed image. The reliability of each of the detected results is determined by calculating a first reliability value based on the sensed image and a second reliability value based on orientation information of the image sensing apparatus. Each of the detected indices is then identified based on its first and second reliability values.
摘要:
A sensed image of the physical space is acquired by an image sensing apparatus. One or more indices are detected from the sensed image. A first reliability based on the sensed image and a second reliability based on orientation information of the image sensing apparatus are calculated for each of the detected results. Each of the detected indices is then identified based on its first and second reliabilities.
摘要:
A system is provided for obtaining parameters about the position and orientation of a camera, where the camera has a fixed position and orientation, by using the image coordinates and world coordinates of markers included in an image photographed by the camera. This system uses a live-image display mode for successively obtaining images input to the camera and a still-image display mode for obtaining an image input to the camera at predetermined time. The markers can be extracted by using the image obtained in either mode. The system can select either automatic-extraction mode or manual-extraction mode for extracting the marker in live images, so that the markers can be extracted with a high degree of accuracy under all conditions to obtain the position and orientation parameters of the camera.
摘要:
A position and orientation determination apparatus for identifying a parameter indicating the position and orientation of image sensing apparatus which performs image sensing on actual space where plural feature points exist in already-known positions. In the position and orientation determination apparatus, the position and orientation of the image sensing apparatus can be measured by a method other than utilization of video image obtained by image sensing, and a parameter indicating the position and orientation of the image sensing apparatus is obtained. Then, the parameter is corrected based on the plural feature points in the video image of actual space obtained by image sensing by the image sensing apparatus, and a parameter indicating the position and orientation of the image sensing apparatus is identified. Upon correction of the parameter, first, the parameter is corrected by a general method using the feature points, and then correction is performed by rotation about a visual axis, thereby the position and orientation of the image sensing apparatus can be detected with high accuracy.
摘要:
An image processing apparatus obtains location information of each image feature in a captured image based on image coordinates of the image feature in the captured image. The image processing apparatus selects location information usable to calculate a position and an orientation of the imaging apparatus among the obtained location information. The image processing apparatus obtains the position and the orientation of the imaging apparatus based on the selected location information and an image feature corresponding to the selected location information among the image features included in the captured image.
摘要:
A marker detection method includes the steps of acquiring a captured image, detecting a marker from the captured image, and determining whether or not a surrounding region of the detected marker includes a pixel of a predetermined color. An additional step includes determining, as a valid marker, a marker for which it is determined that the surrounding region does not include any pixel of the predetermined color.
摘要:
This invention relates to a mixed reality presentation apparatus for obtaining the position and orientation of an image sensing unit using markers. Whether or not a marker detected in a captured image has suspicion of partial occlusion is determined by checking if a region that neighbors a marker region includes a predetermined color, thus inhibiting information obtained from the marker with suspicion of partial occlusion from being used in position and orientation estimation of the image sensing unit. The precision of the obtained position and orientation can be improved.
摘要:
A view transformation matrix that represents the position/attitude of an HMD is generated based on a signal that represents the position/attitude of the HMD (S602). On the other hand, landmarks and their locations are detected based on a captured picture (S604) and a calibration matrix ΔMc is generated using the detected locations of the landmarks (S605). The position/attitude of the HMD is calibrated using the view transformation matrix and calibration matrix ΔMc generated by the above processes (S606), a picture of a virtual object is generated based on external parameters that represent the position/attitude of the calibrated HMD, and a mixed reality picture is generated (S607). The generated mixed reality picture is displayed in the display section (S609).
摘要:
An image processing apparatus obtains location information of each image feature in a captured image based on image coordinates of the image feature in the captured image. The image processing apparatus selects location information usable to calculate a position and an orientation of the imaging apparatus among the obtained location information. The image processing apparatus obtains the position and the orientation of the imaging apparatus based on the selected location information and an image feature corresponding to the selected location information among the image features included in the captured image.