Two images are analyzed to compute a set of motion vectors that describes motion between the first and second images. A motion vector is computed for each pixel in an image at a time between the first and second images. This set of motion vectors may be defined at any time between the first and second images, such as the midpoint. The motion vectors may be computed using any of several techniques. An example technique is based on the constant brightness constraint, also referred to as optical flow. Each vector is specified at a pixel center in an image defined at the time between the first and second images. The vectors may point to points in the first and second images that are not on pixel centers. The motion vectors are used to warp the first and second images to a point in time of an output image between the first and second images using a factor that represents the time between the first and second image at which the output image occurs. The warped images are then blended using this factor to obtain the output image at the desired point in time between the first and second images. The point in time at which the output image occurs may be different from the time at which the motion vectors are determined. The same motion vectors may be used to determine two or more output images at different times between the first and second images. The images may be warped using a technique in which many small triangles are defined in an image corresponding in time to the point in time between the first and second images at which the motion vectors are determined. A transform for each small triangle from the point in time at which the motion vectors are determined to the desired interpolated image time is determined, e.g., the triangle is warped using the motion vectors associated with its vertices. For each pixel in each triangle in the output image, corresponding points in the first and second images are determined, and the first and second images are spatially sampled at these points. These samples for each pixel are combined to produce a value for that pixel in the output image.

Interpolation of a sequence of images using motion analysis

A system and process for video characterization that facilitates video classification and retrieval, as well as motion detection, applications. This involves characterizing a video sequence with a gray scale image having pixel levels that reflect the intensity of motion associated with a corresponding region in the sequence of video frames. The intensity of motion is defined using any of three characterizing processes. Namely, a perceived motion energy spectrum (PMES) characterizing process that represents object-based motion intensity over the sequence of frames, a spatio-temporal entropy (STE) characterizing process that represents the intensity of motion based on color variation at each pixel location, a motion vector angle entropy (MVAE) characterizing process which represents the intensity of motion based on the variation of motion vector angles.

Content-based characterization of video frame sequences

A system for stabilising video signals generated by a video camera which may be mounted in an unstable manner includes a digital processing means for manipulation of each incoming image that attempts to overlay features of the current image onto similar features of a previous image. A mask is-used that prevents parts of the image that are likely to cause errors in the overlaying process from being used in the calculation of the required movement to be applied to the image. The mask may include areas where small movements of the image have been detected, and may also include areas where image anomalies including excess noise have been detected. The invention also discloses means for dealing with wanted movements of the camera, such as pan or zoom, and also discloses means for dealing with the edges of video signals as processed by the system. A method is also disclosed.

Image stabilisation system and method

Example methods and systems may be implemented by a wearable computer to utilize optical-flow analysis to recognize a predetermined user-action, such as selecting an object. An example method may involve a wearable computing device: (a) receiving video data from a video camera of a wearable computing device: (b) determining optical flow for the video data; (c) determining that an optical-flow differential exists at an area within the optical flow for the video data; and (d) responsive to determining that the optical-flow differential exists at the area: (i) identifying an object that is located at the area where the optical-flow differential exists; (ii) performing a search on the object; and (iii) causing a graphical display to display information that corresponds to results from the search.

Point-of-View Object Selection

A retiming function that defines a rampable retiming effect is used to generate new audio and video samples at appropriate output times. In particular, for each output time, a corresponding input time is determined from the output time by using the retiming function. The retiming function may be a speed curve, a position curve that maps output times to input times directly or a mapping defining correspondence times between points in the video data and points in the audio data. An output sample is computed for the output time based on at least the data in the neighborhood of the corresponding input time, using a resampling function for the type of media data. Synchronization is achieved by ensuring that the input times determined to correspond to output times for video samples correspond to the input times determined to correspond to the same output times for audio samples.

Performance retiming effects on synchronized data in an editing system

An apparatus for generating an image motion vector field which describes a motion of individual image components of a first image frame and corresponding image components of a second image frame in a sequence of image frames. The apparatus comprises a first frame memory for receiving said first image frame, a second frame memory for receiving a second image frame, and an optical flow calculator. The optical flow calculator is configured for generating an image motion vector field by iteratively comparing a predicted image with the second image frame. The predicted image is generated according to a current motion estimate in proximity to an observation point, wherein the observation point migrates according to a previous motion estimate and is implemented by the calculator to generate a current motion estimate.

Siu-Leong Iu

Papers

Method and apparatus for estimating optical flow