| 摘要 |
Pixel-based and region-based methods, computer program products, and systems for detecting, flagging, highlighting on a display, and automatically fixing edge violations in stereoscopic images and video. The highlighting and display methods involve signed, clamped subtraction of one image of a stereo image pair from the other image, with the subtraction preferably isolated to a region of interest near the lateral edges. Various embodiments include limiting the detection, flagging, and highlighting of edge violations to objects causing a degree of perceptual discomfort greater than a user-set or preset threshold, or to objects having a certain size and/or proximity and/or degree of cut-off by a lateral edge of the left or right eye images of a stereo image pair. Methods of removing violations include automatic or semi-automatic cropping of the offending object, and depth shifting of the offending object onto the screen plane. |
| 主权项 |
1. A method of identifying an edge violation in a stereoscopic image pair having a left eye image and a right eye image, the method comprising:
analyzing the left eye image to determine whether the left eye image includes an object that is cut off by a lateral boundary of the left eye image; analyzing the right eye image to determine whether the right eye image includes an object that is cut off by a lateral boundary of the right eye image; and if at least one of the analyzing steps determines that one of the left eye and the right eye images includes an object that is cut off by a lateral boundary and is wholly contained within a region of interest:
if the object is cut off by a left lateral boundary of the left eye image, generating a difference image by performing a signed subtraction of at least the region of interest of the right eye image from a corresponding region of the left eye image with clamping of the resulting difference image to legal pixel values;if the object is cut off by a right lateral boundary of the right eye image, generating a difference image by performing a signed subtraction of at least the region of interest of the left eye image from a corresponding region of the right eye image with clamping of the resulting difference image to legal pixel values;if the stereoscopic image pair is encoded in a multi-channel color space, generating a gray-level difference image by converting multi-channel pixel values in the difference image to gray-level brightness values;generating a violation mask by performing a thresholding operation on the difference image; andon a graphical user interface of a media processing system, displaying an indication of a suspected edge violation of the object in a region of the stereo image pair corresponding to the violation mask. |
