Timeline image capture systems and methods
Various approaches related to capturing content of erasable boards are discussed herein.
1. A method of capturing content on an erasable board or surface, the method comprising:
inputting camera data for a succession of image frames, wherein the camera data is from a camera configured to capture images of the board or surface and the image frames comprise successive images of the board or surface from the camera;
processing data from the image frames to remove parts of the image frames corresponding to parts of a user or user pen writing or drawing on the board or surface to determine a succession of processed images of content on the board or surface;
after determining a succession of processed images, then determining a content metric for each processed image, wherein the content metric is a metric of the amount of content in the processed image, and wherein the content metric comprises a measure of pixel values in the processed image;
determining key frame capture times from the content metrics for the processed images; and
capturing and storing processed images at the key frame capture times, wherein capturing processed images at the key frame capture times comprises selecting processed images corresponding to the key frame capture times, from the succession of processed images.
2. A method as claimed in claim 1 , wherein determining key frame capture times from the content metric comprises determining a reduction in the content metric for a processed image that indicates that the erasable board or surface has been partially or wholly erased.
3. A method as claimed in claim 2 , the method further comprising:
determining a reduction in the content metric of greater than a content reduction threshold, the method further comprising adapting the content reduction threshold to a noise level in the processed images.
4. A method as claimed in claim 3 , wherein adapting the content reduction threshold to the noise level comprising adapting the content reduction threshold dependent upon a gain of the camera.
5. A method as claimed in claim 1 , wherein determining key frame capture times from the content metrics comprises determining that the content metric has remained unchanged to within a content stationary threshold for a succession of processed images.
6. A method as claimed in claim 1 , wherein determining the content metric for each processed image comprises determining a local content metric for each of a plurality of different regions of the processed image.
7. A method as claimed in claim 6 , wherein determining key frame capture times from the content metrics comprises determining a key frame capture time from each local content metric.
8. A method as claimed in claim 1 , wherein capturing a processed image at a key frame capture time comprises one or both of selecting from a plurality of processed images around the key frame capture time a lowest noise version of the processed image, and combining a plurality of processed images around the key frame capture time to provide a reduced noise version of the captured processed images.
9. A method as claimed in claim 1 , the method further comprising further processing the captured images to remove artefacts.
10. A method as claimed in claim 9 , wherein the further processing comprises discarding a captured image within a sequence of captured images when images to either side of the discarded image in the sequence are the same to within a similarity threshold.
11. A method as claimed in claim 1 , wherein the capturing comprises retrieving an image from a buffer storing one or more processed images from a time prior to a current time.
12. A method as claimed in claim 1 , wherein capturing processed images at the key frame capture times comprises capturing a sequence of images or video and time stamping the captured sequence of images or video to identify the key frames.
13. A method as claimed in claim 1 , wherein capturing processed images at the key frame capture times comprises selectively storing only processed images corresponding to the key frame capture times.
14. A method as claimed in claim 1 , the method further comprising:
capturing an audio track for the succession of processed images, and synchronizing the audio track to the captured processed images.
15. A processing system, the system operable to:
input camera data for a succession of image frames, wherein the camera data is from a camera configured to capture images of the board or surface and the image frames comprise successive images of the board or surface from the camera;
process data from the image frames to remove parts of the image frames corresponding to parts of a user or user pen writing or drawing on the board or surface to determine a succession of processed images of content on the board or surface;
determine a local or global content metric for each processed image, wherein the content metric is a metric of the amount of local or global content in the processed image;
determine key frame capture times from the content metrics for the processed images;
capture and store processed images at the key frame capture times wherein capturing processed images at the key frame capture times comprises selecting processed images corresponding to the key frame capture times from the succession of processed images; and
wherein determining key frame capture times from the content metric comprises one or both of i) determining a reduction in the content metric for a processed image that indicates that the erasable board or surface has been partially or wholly erased and ii) determining that the content metric has remained unchanged, within a threshold, for a succession of processed images that indicates the content has remained approximately static.
16. A system as claimed in claim 15 further configured to determine a reduction in the content metric of greater than a content reduction threshold, and to adapt the content reduction threshold to a noise level in the processed images.
17. An erasable board or surface content capture system, the system comprising:
a camera to capture an image of a board or surface; and
a processor, coupled to the camera and configured to:
input camera data for a succession of image frames, wherein the image frames comprise successive images of the board or surface from the camera;
process data from the image frames to remove parts of the image frames corresponding to parts of a user or user pen writing or drawing on the board or surface to determine a succession of processed images of content on the board or surface;
after determining a succession of processed images, then determine a content metric for each processed image, wherein the content metric is a metric of the amount of content in the processed image and comprises a measure of pixel values in the processed image;
determine key frame capture times from the content metrics for the processed images; and
capture and store processed images at the key frame capture times wherein capturing processed images at the key frame capture times comprises selecting processed images corresponding to the key frame capture times, from the succession of processed images.