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.

A motion detection method using an image processing device may include: based on the noise level of a current frame, obtaining a weighted average of a sum of absolute differences (SAD) value and an absolute difference of sums (ADS) value; setting the weighted average as an initial motion detection value of each pixel; and selectively performing max filtering on motion detection values of the pixels to obtain a final motion detection value.

A subject motion measuring apparatus includes a camera for imaging a subject, at least one memory storing a program, and at least one processor which, by executing the program, causes the subject motion measuring apparatus to acquire three-dimensional coordinate data on a patch set in frame data included in moving image data imaged by the camera. The processor tracks the patch in the moving image data imaged by the camera and generates motion data on the subject on the basis of the three-dimensional coordinate data on the tracked patch.

A visual search method, a computer device, and a non-transitory computer readable storage medium are provided. An i.sup.th image frame is received. The location and the classification of the subject in the i.sup.th image frame are extracted. A detection block corresponding to the subject is generated. In subsequent image frames of the i.sup.th image frame, the subject is tracked on the basis of the location of the subject in the i.sup.th image frame. The detection block is adjusted on the basis of the tracking result.

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.

A method for motion estimation based on perceived blur due to motion between a first image frame and a second image frame of a digital video sequence comprises estimating a motion vector between the frames for each of a plurality of pixel blocks in the first and second image frames. A patch motion vector is then estimated for each of a plurality of patches of the motion vectors based on one of vectors in each patch and motion vectors in proximate patches. The patch motion vector of its corresponding patch is allocated to each pixel in the first frame. A system and computer program for motion estimation based on perceived blur is also provided.

Various methods are provided for generating motion vectors in the context of 3D computer-generated images. An example method includes generating, based on a current frame to be rendered, a block-level motion vector with depth (MVD) texture comprising a set of block-level motion vectors each having an associated depth value, outputting the block-level MVD texture for image processing on a first channel, and outputting at least a portion of the current frame on a second channel.

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.

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.