Abstract: A method of generating an internally consistent model of the state of a book captured in a video image is provided. The method comprises obtaining a plurality of pieces of evidence relating to the state of a corresponding plurality of aspects of the book in the video image, associating a quality score with each piece of evidence, generating an initial model of the state of the book wherein the state of the book is constrained by physical properties of the book and at least the highest scoring piece of evidence, and sequentially constraining the model in response to one or more successive pieces of evidence whose scores meet a respective predetermined first threshold value.

Abstract: A book for use with augmented reality applications includes a plurality of stiff leaves, each side of which forms a page of the book. On each page a respective fiduciary marker is positioned substantially in the middle of the page. Each fiduciary marker comprises a different respective asymmetric pattern capable of indicating the scale and orientation of the book to an augmented reality application and of indicating the respective page, and a non-alphanumeric pattern positioned closer to an outside edge of the page of the book than the fiduciary marker. The non-alphanumeric pattern on a respective page is capable of indicating at least the opposing page pair comprising the respective page on which the non-alphanumeric pattern is positioned, when used in conjunction with the scale and orientation of the book as indicated by a fiduciary marker on a different page to that of the respective non-alphanumeric pattern.

Abstract: A method of book leaf tracking comprises receiving a video image comprising a book, estimating the current position and orientation of the book within the video image in response to a fiduciary marker of the book visible in the image, estimating the visibility of one or more predetermined features of the book, calculating a range of leaf turning angles that is consistent with the detected visibility of the or each predetermined feature of the book for the estimated current position and orientation of the book, and estimating the angle of a turning leaf of the book responsive to the calculated range.

Abstract: A book for use in an augmented reality system comprises a plurality of leaves, each side forming a page of the book, with each page comprising a fiduciary marker. The book also includes a cover having larger dimensions than the book's leaves. Thus, the cover's extremhities extend beyond the outer edges of the pages. The inside of the cover comprises a first high contrast pattern along at least a first such extremity. An entertainment device for use in the augmented reality system comprises input means to receive a video image of the book, and image processing means to estimate a position and orientation of the book from a fiduciary marker of the book captured in the video image, to estimate a position and orientation of the first high contrast pattern, and to distinguish between one or more leaves of the book being turned independently of the cover of the book.

Abstract: A method of augmenting a video image comprises the steps of estimating the extent of an identified surface captured within the video image and identifying skin pixels within a test area corresponding to the estimated extent of the identified surface within the video image. The method also includes extrapolating positions for skin pixels within the video image that are outside the estimated extent of the identified surface based upon the identified skin pixels, generating a mask from a combination of identified skin pixels and extrapolated skin pixels, and setting an extent of a computer graphic to be superposed substantially on top of the identified surface within the video image. The extent is greater than the estimated extent of the identified surface. The method further includes superposing the graphical augmentation of the video image responsive to the generated mask.

Abstract: A book for use in an augmented reality system includes first and second pages. The first page is on a first leaf of the book and includes a first fiduciary marker for indicating the orientation of the book to a recognition system. The second page is on a second leaf of the book and includes a second fiduciary marker for indicating the orientation of the book to the recognition system and also page marker for indicating the page number of the second page to the recognition system. The page marker orientation is ambiguous without reference to a fiduciary marker. The page marker is positioned on the second page closer to an edge of the page than the second fiduciary marker to become visible to the recognition system before the second fiduciary marker, as the book is turned to the second page.

Abstract: An entertainment device comprises an input, a marker detector and a failure boundary calculation processor. The input is operable to receive a captured image from a video camera. The marker detector is operable to detect a fiduciary marker within the captured image, and is also operable to estimate a distance and angle of the fiduciary marker. The failure boundary calculation processor is operable to calculate at least one of an additional distance and an additional angle from the currently estimated distance and angle of the fiduciary marker at which recognition of the fiduciary marker is assumed to fail.

Abstract: A method of image augmentation for an image of a book includes capturing an image of the book, detecting at least a portion of at least one fiduciary marker of the book within the image, estimating placement of the book's spine based upon the detected portion of the fiduciary marker, hypothesising possible positions for edges of a rigid leaf being turned in the book based upon estimated placement of the spine, processing the book image to identify edges within the image, comparing elements of the identified edges with the hypothesized positions for edges of the rigid leaf, selecting one of the hypothesized positions that best coincides with the compared elements of the processed image as representative of the position of the rigid leaf being turned in the book, and augmenting the book image with a virtual graphic element arranged in accordance with the selected representative position of the rigid leaf.

Abstract: An entertainment device comprises an input, a marker detector and a failure boundary calculation processor. The input is operable to receive a captured image from a video camera. The marker detector is operable to detect a fiduciary marker within the captured image, and is also operable to estimate a distance and angle of the fiduciary marker. The failure boundary calculation processor is operable to calculate at least one of an additional distance and an additional angle from the currently estimated distance and angle of the fiduciary marker at which recognition of the fiduciary marker is assumed to fail.

Abstract: A method of generating an internally consistent model of the state of a book captured in a video image is provided. The method comprises obtaining a plurality of pieces of evidence relating to the state of a corresponding plurality of aspects of the book in the video image, associating a quality score with each piece of evidence, generating an initial model of the state of the book wherein the state of the book is constrained by physical properties of the book and at least the highest scoring piece of evidence, and sequentially constraining the model in response to one or more successive pieces of evidence whose scores meet a respective predetermined first threshold value.

Abstract: A method of book leaf tracking comprises receiving a video image comprising a book, estimating the current position and orientation of the book within the video image in response to a fiduciary marker of the book visible in the image,estimating the visibility of one or more predetermined features of the book, calculating a range of leaf turning angles that is consistent with the detected visibility of the or each predetermined feature of the book for the estimated current position and orientation of the book, and estimating the angle of a turning leaf of the book responsive to the calculated range.

Abstract: A book for use in an augmented reality system includes first and second pages. The first page is on a first leaf of the book and includes a first fiduciary marker for indicating the orientation of the book to a recognition system. The second page is on a second leaf of the book and includes a second fiduciary marker for indicating the orientation of the book to the recognition system and also page marker for indicating the page number of the second page to the recognition system. The page marker orientation is ambiguous without reference to a fiduciary marker.

Abstract: A method of image augmentation for an image of a book includes capturing an image of the book, detecting at least a portion of at least one fiduciary marker of the book within the image, estimating placement of the book's spine based upon the detected portion of the fiduciary marker, hypothesising possible positions for edges of a rigid leaf being turned in the book based upon estimated placement of the spine, processing the book image to identify edges within the image, comparing elements of the identified edges with the hypothesised positions for edges of the rigid leaf, selecting one of the hypothesised positions that best coincides with the compared elements of the processed image as representative of the position of the rigid leaf being turned in the book, and augmenting the book image with a virtual graphic element arranged in accordance with the selected representative position of the rigid leaf.