Abstract: Various aspects of a method and system to process video content for extraction of moving objects from image sequences of the video content are disclosed herein. In an embodiment, the method includes determination of one or more object contours of one or more moving objects in the video content. A first object bounding box (OBB) that encompasses a first object contour of a first moving object is created based on the determined one or more object contours. A first object mask for the first moving object is generated in a first destination image frame, based on infilling of the first object contour in the created first OBB.

Abstract: An improved mechanism for image area selection upon which autofocusing is directed during image capture on a digital image capture device, such as a camera or cellular phone. This image area selection provides accurate selection of moving object even when the objects being focused upon are subject to intense or unpredictable motion. The image area selection is performed based on alignment of consecutive frames (images) for which a rough foreground mask, and moving object mask have been determined. Differences between these frames are utilized to determine a moving object contour, which also provides feedback through a delay to the moving object detection step.

Abstract: Various aspects of a method and system to process video content are disclosed herein. The method includes determination of a first frame identification value associated with a video content. The first frame identification value corresponds to an average color value of a frame of the video content. The method further includes determination of a second frame identification value associated with the video content. The second frame identification value corresponds to a global motion vector (GMV) value of the frame of the video content. The method further includes determination of a first intermediate frame based on one or both of the first frame identification value and the second frame identification value.

Abstract: An improved mechanism for image area selection upon which autofocusing is directed during image capture on a digital image capture device, such as a camera or cellular phone. This image area selection provides accurate selection of moving object even when the objects being focused upon are subject to intense or unpredictable motion. The image area selection is performed based on alignment of consecutive frames (images) for which a rough foreground mask, and moving object mask have been determined. Differences between these frames are utilized to determine a moving object contour, which also provides feedback through a delay to the moving object detection step.

Abstract: Various aspects of a method and system to process video content are disclosed herein. In accordance with an embodiment, the method includes determination of a plurality of motion vectors based on a pixel displacement of one or more pixels. The pixel displacement of the one or more pixels in a current frame of a video content is determined with respect to corresponding one or more pixels in a previous frame of the video content. Based on the determined plurality of motion vectors, motion direction of the current frame is extracted. Based on the extracted motion direction, real-time motion annotation information of the current frame is determined.

Abstract: Various aspects of a method and system to process video content are disclosed herein. The method includes determination of a first frame identification value associated with a video content. The first frame identification value corresponds to an average color value of a frame of the video content. The method further includes determination of a second frame identification value associated with the video content. The second frame identification value corresponds to a global motion vector (GMV) value of the frame of the video content. The method further includes determination of a first intermediate frame based on one or both of the first frame identification value and the second frame identification value.

Abstract: Various aspects of a method and system to process video content for extraction of moving objects from image sequences of the video content are disclosed herein. In an embodiment, the method includes determination of one or more object contours of one or more moving objects in the video content. A first object bounding box (OBB) that encompasses a first object contour of a first moving object is created based on the determined one or more object contours. A first object mask for the first moving object is generated in a first destination image frame, based on infilling of the first object contour in the created first OBB.

Abstract: An apparatus and method for extracting a static background image from a non-static image sequence or video sequence having at least three spatially overlapping frames is presented. Obscured static background areas are filled, according to the disclosure, with actual content as the background area becomes visible over time as non-static objects move with respect to the background. Consecutive image frames are stored in tracking buffers from which alignment is performed and absolute differences determined. Object contours are found in the difference image and bounding boxes determined as object masks. The background is then filled from areas outside these object masks to arrive at a static background image.

Abstract: Object detection and extraction is performed from image sequences utilizing circular buffers for both source images and tracking. The detection and extraction process is performed in relation to the previous and current image, and the current and next image, including: alignment, absolute difference, removal of non-overlaps, and contour detection in difference images. An intersection is performed on these two outputs to retain contours of the current image only. Recovery of missing contour information is performed utilizing gradient tracing, followed by morphological dilation. A splitting process is performed if additional objects are found in a bounding box area. A mask image bounded by object contour is created, color attributes assigned, object verification performed and outliers removed. Then untracked objects are removed from the mask and a mask is output for moving objects with rectangular boundary box information.

Abstract: Real-time generation of motion (stroboscopic) video is described which utilizes an object tracking process operating on downsized images in a circular buffer. Utilizing object information from the tracking, a background static scene is extracted into which multiple temporally displaced object images are inserted to create a stroboscopic video frame. Due to its low processing overhead, the apparatus and method is particularly well-suited for implementation on portable devices, such as cameras and cellular phones.

Abstract: Object detection and extraction is performed from image sequences utilizing circular buffers for both source images and tracking. The detection and extraction process is performed in relation to the previous and current image, and the current and next image, including: alignment, absolute difference, removal of non-overlaps, and contour detection in difference images. An intersection is performed on these two outputs to retain contours of the current image only. Recovery of missing contour information is performed utilizing gradient tracing, followed by morphological dilation. A splitting process is performed if additional objects are found in a bounding box area. A mask image bounded by object contour is created, color attributes assigned, object verification performed and outliers removed. Then untracked objects are removed from the mask and a mask is output for moving objects with rectangular boundary box information.

Abstract: An apparatus and method for extracting a static background image from a non-static image sequence or video sequence having at least three spatially overlapping frames is presented. Obscured static background areas are filled, according to the disclosure, with actual content as the background area becomes visible over time as non-static objects move with respect to the background. Consecutive image frames are stored in tracking buffers from which alignment is performed and absolute differences determined. Object contours are found in the difference image and bounding boxes determined as object masks. The background is then filled from areas outside these object masks to arrive at a static background image.

Abstract: Various aspects of a system and method for image processing may include a computing device having one or more processors. The computing device may be operable to determine luminance values of multiple pixels in a subset of a frame of a two-dimensional image. The computing device may be operable to determine texture values of the multiple pixels in the subset of the frame. The computing device may be operable to identify a subject region and a background region in the frame of the two-dimensional image based on the determined luminance values and the determined texture values of the plurality of pixels.

Abstract: Various aspects of a system and method for image processing may include a computing device having one or more processors. The computing device may be operable to determine luminance values of multiple pixels in a subset of a frame of a two-dimensional image. The computing device may be operable to determine texture values of the multiple pixels in the subset of the frame. The computing device may be operable to identify a subject region and a background region in the frame of the two-dimensional image based on the determined luminance values and the determined texture values of the plurality of pixels.

Abstract: The present invention relates to a method and system for evaluating the quality of video data without gaining access to the source data. The system is configured to estimate sharpness metrics by detecting edge pixels and enclosing them with 8×8 pixel blocks. For each block, the sharpness according to the Kurtosis of the DCT is computed. The final metric is the average sharpness of the blocks in the edge profile and includes a robust combination of spatial and frequency domain information.

Abstract: The present invention relates to a method and system for evaluating the quality of video data without gaining access to the source data. The system is configured to estimate sharpness metrics by detecting edge pixels and enclosing them with 8×8 pixel blocks. For each block, the sharpness according to the Kurtosis of the DCT is computed. The final metric is the average sharpness of the blocks in the edge profile and includes a robust combination of spatial and frequency domain information.