The architecture shown can perform global search, local search and local sub pixel search in a parallel or in a pipelined mode. All operations are in a streaming mode without the requirement of external intermediate data storage.

The architecture shown can perform global search, local search and local sub pixel search in a parallel or in a pipelined mode. All operations are in a streaming mode without the requirement of external intermediate data storage.

An image processing apparatus including a pixel shifting super-resolution image generation circuit configured to generate a high-resolution composite image from a plurality of images, an evaluation area setting circuit configured to set a plurality of evaluation areas within an area extraction range of the composite image, a synthesis accuracy evaluation circuit configured to evaluate, for each of the plurality of evaluation areas, a pixel filling rate for the evaluation area and calculate a plurality of pixel filling rate evaluation values, and a determination circuit configured to determine a determination area from among the plurality of evaluation areas based on the plurality of pixel filling rate evaluation values.

Systems and methods are provided for initiating transfer of image data corresponding to at least one predetermined level of an image pyramid comprising higher resolution to a graphic processing unit (GPU) of the computing device, calculating, by the central processing unit (CPU) of the computing device, optical flow of at least one predetermined coarse level of the image pyramid, transferring, by the CPU of the computing device, the calculated optical flow of the at least one predetermined coarse level of the image pyramid to the GPU, calculating, by the GPU of the computing device, the optical flow of the at least one predetermined level of the image pyramid comprising higher resolution, and outputting, by the GPU of the computing device, the optical flow of the image data.

During tracking, a rough search is performed on a face image area detected in a current frame, and when the reliability of the result of the rough search is equal to or smaller than a threshold value, a value obtained by multiplying a reliability of a rough search result detected in one previous frame by a predetermined coefficient is set as a new threshold value, and it is determined whether or not the reliability of the rough search result detected in the current frame exceeds the newly set threshold value. Then, when the reliability of the rough search result exceeds the new threshold value, the decrease in reliability of the rough search result is considered as temporary, and a tracking flag is kept on while tracking information is also held.

During tracking, a rough search is performed on a face image area detected in a current frame, and when the reliability of the result of the rough search is equal to or smaller than a threshold value, a value obtained by multiplying a reliability of a rough search result detected in one previous frame by a predetermined coefficient is set as a new threshold value, and it is determined whether or not the reliability of the rough search result detected in the current frame exceeds the newly set threshold value. Then, when the reliability of the rough search result exceeds the new threshold value, the decrease in reliability of the rough search result is considered as temporary, and a tracking flag is kept on while tracking information is also held.

Methods, devices and computer-readable mediums for detecting occlusions which occur due to foreground object movement with respect to a background between first and second successive frames. Occlusion detection may use motion estimation with respect to at least a third frame temporally preceding the first frame. Occlusion detection may be based on one or more assumptions such as: occlusion motion vectors are different than other background motion vectors; occlusion motions are likely to be similar to foreground occluding motion; and/or motion estimation will match an occlusion block with a block belonging to a common background object. Occlusion detection may be combined with motion error detection based on a motion field divergence using a motion vector assigned to the occlusion, e.g., for generating an intermediate frame in frame up rate conversion (FRUC).

Regions for texture-based coding are identified using a spatial segmentation and a motion flow segmentation. For frames of a group of frames in a video sequence, a frame is segmented using a first classifier into at least one of a texture region or a non-texture region of an image in the frame. Then, the texture regions of the group of frames are segmented using a second classifier into a texture coding region or a non-texture coding region. The second classifier uses motion across the group of frames as input. Each of the classifiers is generated using a machine-learning process. Blocks of the non-texture region and the non-texture coding region of the current frame are coded using a block-based coding technique, while blocks of the texture coding region are coded using a coding technique that is other than the block-based coding technique.

An image processing system includes a processor and optical flow (OF) determination logic for quantifying relative motion of a feature present in a first frame of video and a second frame of video that provide at least one of temporally and spatially ordered images with respect to the two frames of video. The OF determination logic configures the processor to implement performing OF estimation between the first frame and second frame using a pyramidal block matching (PBM) method to generate an initial optical flow (OF) estimate at a base pyramid level having integer pixel resolution, and refining the initial OF estimate using at least one pass of a modified Lucas-Kanade (LK) method to provide a revised OF estimate having fractional pixel resolution.

An image processing system includes a processor and optical flow (OF) determination logic for quantifying relative motion of a feature present in a first frame of video and a second frame of video that provide at least one of temporally and spatially ordered images with respect to the two frames of video. The OF determination logic configures the processor to implement performing OF estimation between the first frame and second frame using a pyramidal block matching (PBM) method to generate an initial optical flow (OF) estimate at a base pyramid level having integer pixel resolution, and refining the initial OF estimate using at least one pass of a modified Lucas-Kanade (LK) method to provide a revised OF estimate having fractional pixel resolution.