Abstract: A method, a system, and a computing device for reconstructing three-dimensional planes are provided. The method includes the following steps: obtaining a series of color information, depth information and pose information of a dynamic scene by a sensing device; extracting a plurality of feature points according to the color information and the depth information, and marking part of the feature points as non-planar objects including dynamic objects and fragmentary objects; computing point cloud according to the unmarked feature points and the pose information, and instantly converting the point cloud to a three-dimensional mesh; and growing the three-dimensional mesh to fill vacancy corresponding to the non-planar objects according to the information of the three-dimensional mesh surrounding or adjacent to the non-planar objects.

Abstract: A system and a method for computing the relative rotation and the relative translation of back-to-back cameras comprise: a fixed mode and an adjustment mode. In the fixed mode, a reversible external camera is installed next to the back-to-back cameras, the external camera is flipped to shoot a calibration pattern from different positions and angles, the intrinsic and extrinsic parameters of each camera are computed, and then a reverse calculation is performed on the extrinsic parameters, as such the amount of translation and rotation of the back-to-back cameras are obtained. When the relative angle of the back-to-back cameras changes, the angle is automatically detected and the extrinsic parameters of the camera computed at the fixed mode is modified, and then the reverse calculation is performed on the extrinsic parameters to adjust the amount of translation and rotation of the back-to-back cameras.

Abstract: A method and a system for simultaneously tracking several 6 DoF poses of a movable object and a movable camera are provided. The method the following steps: A series of images are captured by a movable camera, several environmental feature points are extracted from the images and are matched to compute several camera matrixes of the movable camera, and the 6 DoF poses of the movable camera are computed using the camera matrixes. At the same time, several feature points of the movable object are inferred from the images captured by the movable camera, the coordinates of the feature points of the movable object are corrected using the camera matrixes corresponding to the images as well as the predefined geometric and temporal constraints. Then, the 6 DoF poses of the movable object are computed using the coordinates of the corrected feature points and their corresponding camera matrixes.

Abstract: A method and a system for simultaneously tracking several 6 DoF poses of a movable object and a movable camera are provided. The method the following steps: A series of images are captured by a movable camera, several environmental feature points are extracted from the images and are matched to compute several camera matrixes of the movable camera, and the 6 DoF poses of the movable camera are computed using the camera matrixes. At the same time, several feature points of the movable object are inferred from the images captured by the movable camera, the coordinates of the feature points of the movable object are corrected using the camera matrixes corresponding to the images as well as the predefined geometric and temporal constraints. Then, the 6 DoF poses of the movable object are computed using the coordinates of the corrected feature points and their corresponding camera matrixes.

Abstract: A motion tracking system includes a first image-capturing module, a computing module and a database. The first image-capturing module captures the full body motion of an object to obtain a depth image. The database provides a plurality of training samples, wherein the training samples include a plurality of depth feature information related to joint positions of the object. The computing module receives the depth image, performs an association operation and a prediction operation for the depth image to obtain a plurality of first joint positions of the object. The computing module projects the first joint positions to a three-dimensional space to generate a three-dimensional skeleton of the object. The depth image includes an image in which limbs of the object are not occluded or an image in which some of limbs of the object are not occluded and the others of limbs of the object are occluded.

Abstract: A method, a system, and a computing device for reconstructing three-dimensional planes are provided. The method includes the following steps: obtaining a series of color information, depth information and pose information of a dynamic scene by a sensing device; extracting a plurality of feature points according to the color information and the depth information, and marking part of the feature points as non-planar objects including dynamic objects and fragmentary objects; computing point cloud according to the unmarked feature points and the pose information, and instantly converting the point cloud to a three-dimensional mesh; and growing the three-dimensional mesh to fill vacancy corresponding to the non-planar objects according to the information of the three-dimensional mesh surrounding or adjacent to the non-planar objects.

Abstract: A depth camera calibration device and a method thereof are provided. The method comprises: disabling a projection function of a camera and photographing surface planes to obtain a first image; enabling the projection function of the camera and photographing the surface planes to obtain a second image, and a positional relationship between the camera and a calibration plate assembly remaining unchanged when obtaining the first image and the second image; and obtaining parameters of the camera by cropping an image boundary, calculating positions of characteristic points, reading a projection pattern, calculating positions of corresponding points and excluding abnormal points according to the first image and the second image.

Abstract: A three dimensional image measurement system including a first optical system and a second optical system is provided. The first optical system is adapted to output a structural light beam and a zero order light beam. There is an angle between the structural light beam and the zero order light beam. The first optical system performs an optical operation to project the structural light beam to a three dimensional object to obtain three dimensional information of the three dimensional object. The second optical system is adapted to receive the zero order light beam and perform another optical operation by using the zero order light beam. The first optical system includes a plurality of optical elements. The value of the angle between the structural light beam and the zero order light beam is determined according to position parameters of the optical elements.

Abstract: A depth sensing apparatus with self-calibration and a self-calibration method thereof are provided. The depth sensing apparatus includes a projection apparatus, an image capturing apparatus and a calibration module. The projection apparatus projects a calibration pattern and a depth computation pattern to a reference plane based on a predefined calibration pattern and a predefined depth computation pattern. The image capturing apparatus captures an image including the calibration pattern and the depth computation pattern. The calibration module coupled to the image capturing apparatus adjusts apparatus parameters of the depth sensing apparatus to calibrate a depth computation deviation according to the calibration pattern of the image, the predefined calibration pattern and a predefined lookup table corresponding to the predefined calibration pattern.

Abstract: An apparatus for dynamically adjusting depth resolution is provided. The apparatus includes a depth capture module, an image capture module and a computing unit. The depth capture module obtains a set of images for disparity computation. The image capture module obtains a high-resolution image. The computing unit computes a disparity map and a corresponding depth map using the set of images obtained by the depth capture module, and sets a 3D region of interest according to a pre-defined object feature, the high-resolution image and the depth map. The 3D region of interest can be dynamically adjusted by tracking the movement of the object. In the 3D region of interest, the computing unit re-computes the depth map in higher resolution along Z axis by re-computing the disparity map in appropriate sub-pixels and allocating the required number of bits to store the sub-pixel disparity values.

Abstract: A motion tracking system includes a first image-capturing module, a computing module and a database. The first image-capturing module captures the full body motion of an object to obtain a depth image. The database provides a plurality of training samples, wherein the training samples include a plurality of depth feature information related to joint positions of the object. The computing module receives the depth image, performs an association operation and a prediction operation for the depth image to obtain a plurality of first joint positions of the object. The computing module projects the first joint positions to a three-dimensional space to generate a three-dimensional skeleton of the object. The depth image includes an image in which limbs of the object are not occluded or an image in which some of limbs of the object are not occluded and the others of limbs of the object are occluded.

Abstract: A depth camera calibration device and a method thereof are provided. The method comprises: disabling a projection function of a camera and photographing surface planes to obtain a first image; enabling the projection function of the camera and photographing the surface planes to obtain a second image, and a positional relationship between the camera and a calibration plate assembly remaining unchanged when obtaining the first image and the second image; and obtaining parameters of the camera by cropping an image boundary, calculating positions of characteristic points, reading a projection pattern, calculating positions of corresponding points and excluding abnormal points according to the first image and the second image.

Abstract: A three dimensional image measurement system including a first optical system and a second optical system is provided. The first optical system is adapted to output a structural light beam and a zero order light beam. There is an angle between the structural light beam and the zero order light beam. The first optical system performs an optical operation to project the structural light beam to a three dimensional object to obtain three dimensional information of the three dimensional object. The second optical system is adapted to receive the zero order light beam and perform another optical operation by using the zero order light beam. The first optical system includes a plurality of optical elements. The value of the angle between the structural light beam and the zero order light beam is determined according to position parameters of the optical elements.

Abstract: A non-planar surface projecting system, an auto-calibration method thereof and an auto-calibration device thereof are provided. In an embodiment of the non-planar surface auto-calibration method, a depth map of a projection surface is measured, a corresponding area corresponding to a projecting area and a depth sensing area is calibrated; and in the corresponding area, an interactive content is adjusted according to the depth map of the projection surface.

Abstract: A tapping detecting device, a tapping detecting method and a smart projecting system using the same are provided. The tapping detecting device comprises a fingertip size providing unit, a laser emitting unit, a laser sensing unit and a processing unit. The fingertip size providing unit is used for providing the size of a fingertip of a finger. The laser emitting unit is used for providing a laser at a parallel surface above a plane. The laser sensing unit is used for capturing a reflecting image which shows the reflection of the laser caused by the fingertip. The processing unit is used for obtaining a reflecting region according to the reflecting image, and for adjusting a threshold value according to the size of the fingertip. If the area of the reflecting region is larger than the threshold value, then the processing unit deems that the fingertip touches the plane.

Abstract: A non-planar surface projecting system, an auto-calibration method thereof and an auto-calibration device thereof are provided. In an embodiment of the non-planar surface auto-calibration method, a depth map of a projection surface is measured, a corresponding area corresponding to a projecting area and a depth sensing area is calibrated; and in the corresponding area, an interactive content is adjusted according to the depth map of the projection surface.

Abstract: A depth sensing apparatus with self-calibration and a self-calibration method thereof are provided. The depth sensing apparatus includes a projection apparatus, an image capturing apparatus and a calibration module. The projection apparatus projects a calibration pattern and a depth computation pattern to a reference plane based on a predefined calibration pattern and a predefined depth computation pattern. The image capturing apparatus captures an image including the calibration pattern and the depth computation pattern. The calibration module coupled to the image capturing apparatus adjusts apparatus parameters of the depth sensing apparatus to calibrate a depth computation deviation according to the calibration pattern of the image, the predefined calibration pattern and a predefined lookup table corresponding to the predefined calibration pattern.

Abstract: An electronic apparatus and a method for incremental pose estimation and photographing are provided. In the method, at least two images of a 3D object are captured at different positions encircling the 3D object. Displacements and angular displacements are detected when capturing the images. Features of the 3D object in the images, the displacements and the angular displacements are used to estimate a central position of the 3D object and a distance between the electronic apparatus and the 3D object. A circumference suitable for capturing the images of the 3D object is estimated based on the distance and is divided into several segments, and a timing interval of a timer is adjusted based on a length of the segments. A camera of the electronic apparatus is triggered at intervals set by the timer to capture the images of the 3D object.

Abstract: An electronic apparatus and a method for incremental pose estimation and photographing are provided. In the method, at least two images of a 3D object are captured at different positions encircling the 3D object. Displacements and angular displacements are detected when capturing the images. Features of the 3D object in the images, the displacements and the angular displacements are used to estimate a central position of the 3D object and a distance between the electronic apparatus and the 3D object. A circumference suitable for capturing the images of the 3D object is estimated based on the distance and is divided into several segments, and a timing interval of a timer is adjusted based on a length of the segments. A camera of the electronic apparatus is triggered at intervals set by the timer to capture the images of the 3D object.

Abstract: A hole filling method for multi-view disparity maps is provided. At least one disparity map is respectively captured as a plurality of known views among a plurality of views for capturing an object. As for a plurality of virtual views among the views excluding the at least one known view, disparity maps of the virtual views are synthesized by sequentially using the disparity maps of the known views according to a distance of a virtual camera position or a transformed angle between each virtual view and each known view. Hole filling information of the disparity maps of other virtual views having the distances or the transformed angles smaller than that of the virtual view is used to fill holes in the synthesized disparity maps of the virtual views.