Abstract: Methods for cascade elimination of candidates in spatial relation operations are performed by systems, devices, and apparatuses. Spatial relation operations include counts of geometric objects against geographies/geometries, and data points associated with vertices of shapes representing the geographies/geometries are reduced to form smaller sets of data points that represent the initial shapes. Elimination of geometric objects for operations is performed using inner- and outer-reductions in cascade. Data points are reduced until a representation of the original shape with a specified area or number of data points is generated. Multi-polygon geometries are joined by union based on preservation of area and data points of the polygons therein prior to reducing data points. Cascade reductions are also performed at specified times during spatial operations based on costs associated therewith.

Abstract: Methods for cascade elimination of candidates in spatial relation operations are performed by systems, devices, and apparatuses. Spatial relation operations include counts of geometric objects against geographies/geometries, and data points associated with vertices of shapes representing the geographies/geometries are reduced to form smaller sets of data points that represent the initial shapes. Elimination of geometric objects for operations is performed using inner- and outer-reductions in cascade. Data points are reduced until a representation of the original shape with a specified area or number of data points is generated. Multi-polygon geometries are joined by union based on preservation of area and data points of the polygons therein prior to reducing data points. Cascade reductions are also performed at specified times during spatial operations based on costs associated therewith.

Abstract: An example apparatus includes a kernel size estimator to estimate a blur kernel size of a captured image. The example apparatus also further includes a frame checker to discard the captured image if the estimated blur kernel size of the captured images exceeds a threshold kernel size. The captured image is to be used in a set if the estimated blur kernel size does not exceed the threshold kernel size. The example apparatus further includes a composite generator to generate a composite image based on the set of images.

Abstract: An example apparatus includes a kernel size estimator to estimate a blur kernel size of a captured image. The example apparatus also further includes a frame checker to discard the captured image if the estimated blur kernel size of the captured images exceeds a threshold kernel size. The captured image is to be used in a set if the estimated blur kernel size does not exceed the threshold kernel size. The example apparatus further includes a composite generator to generate a composite image based on the set of images.

Abstract: Video stabilization is described using content-aware camera motion estimation. In some versions a luminance target frame and a luminance source frame of a sequence of video frames of a scene are received. Motion is extracted from the received luminance target and source frames and the motion is represented as a motion vector field and weights. The weights are divided into a first set of zeros weights for motion in the motion vector field that is near zero motion and a second set of peak weights for motion in the motion field that is not near zero. The zeros weights are compared to a threshold to determine whether there is motion in the scene and if the zeros weights exceed the threshold then selecting a zero motion motion model. A frame of the video sequence is adjusted corresponding to the target frame based on the selected motion model.

Abstract: Video stabilization is described using content-aware camera motion estimation. In some versions a luminance target frame and a luminance source frame of a sequence of video frames of a scene are received. Motion is extracted from the received luminance target and source frames and the motion is represented as a motion vector field and weights. The weights are divided into a first set of zeros weights for motion in the motion vector field that is near zero motion and a second set of peak weights for motion in the motion field that is not near zero. The zeros weights are compared to a threshold to determine whether there is motion in the scene and if the zeros weights exceed the threshold then selecting a zero motion motion model. A frame of the video sequence is adjusted corresponding to the target frame based on the selected motion model.