1461088449-05431750-ecf2-4ee3-a8ce-30aef45e7f1b

1. A position and orientation measurement apparatus comprising:
obtaining means for obtaining a range image of a target object captured by image capturing means;
detection means for detecting a lost image region where distance values are not measured from the obtained range image;
first search means for searching a geometric model which indicates a given three-dimensional shape of the target object for a lost model region corresponding to the detected lost image region;
second search means for searching for combinations of pixels on the range image and corresponding points on the geometric model based on information indicating positions of the pixels on the range image, and information indicating positions of the points on the geometric model;
determination means for determining whether or not each corresponding point on the geometric model detected by said second search means with respect to the pixel on the range image falls within the lost model region;
correction means for, when said determination means determines that the corresponding point on the geometric model falls within the lost model region, correcting that combination of the pixel on the range image and the corresponding point on the geometric model detected by said second search means; and
calculation means for calculating a position and an orientation of the target object based on the combinations of the pixels on the range image and the points on the geometric model, which are corrected by said correction means.
2. The apparatus according to claim 1, wherein said correction means deletes combinations of points on the geometric model and pixels on the range image, which are determined to fall within the lost model region, from the combinations obtained by said second search means.
3. The apparatus according to claim 1, wherein said second search means searches for the combinations to have, as corresponding points, points on the geometric model, which have minimum distances from pixels on the range image.
4. The apparatus according to claim 3, wherein said calculation means calculates a position and an orientation of the geometric model, which minimize a sum total of distances between the pixels on the range image and the points on the geometric model in the combinations, as measurement values of the position and the orientation of the target object.
5. The apparatus according to claim 4, wherein said correction means performs a correction for multiplying distances in combinations of points on the geometric model and pixels on the range image, which are determined to fall within the lost model region, by a weight which is smaller than that for distances in combinations of points on the geometric model and pixels on the range image, which are determined to fall outside the lost model region, of the combinations obtained by said second search means.
6. The apparatus according to claim 5, wherein said correction means sets a first weight for distances in combinations of points on the geometric model and pixels on the range image, which are determined to fall within the lost model region, and sets a second weight, which assumes a larger value than the first weight, for distances in combinations of points on the geometric model and pixels on the range image, which are determined to fall outside the lost model region.
7. The apparatus according to claim 6, wherein said correction means determines for the combinations of the pixels on the range image and the points on the geometric model, which are corrected by the weighting, whether or not a sum total of the distances calculated by said calculation means is less than a threshold, and
after the sum total is less than the threshold, said correction means deletes combinations of points on the geometric model and pixels on the range image, which are determined to fall within the lost model region, from the combinations obtained by said second search means.
8. The apparatus according to claim 1, wherein said first search means projects the lost image region onto the geometric model with reference to a position and an orientation of the image capturing means, and extracts the projected region as the lost model region.
9. A position and orientation measurement method executed by a position and orientation measurement apparatus, comprising:
an obtaining step of obtaining a range image of a target object captured by image capturing means;
a detection step of detecting a lost image region where distance values are not measured from the range image obtained in the obtaining step;
a first search step of searching a geometric model which indicates a given three-dimensional shape of the target object for a lost model region corresponding to the detected lost image region;
a second search step of searching for combinations of pixels on the range image and corresponding points on the geometric model based on information indicating positions of the pixels on the range image, and information indicating positions of the points on the geometric model;
a determination step of determining whether or not each corresponding point on the geometric model obtained in the second search step with respect to the pixel on the range image falls within the lost model region;
a correction step of correcting, when it is determined in the determination step that the corresponding point on the geometric model falls within the lost model region, that combination of the pixel on the range image and the corresponding point on the geometric model obtained in the second search step; and
a calculation step of calculating a position and an orientation of the target object based on the combinations of the pixels on the range image and the points on the geometric model, which are corrected in the correction step.
10. A program for controlling a computer to function as respective means of a position and orientation measurement apparatus according to claim 1.

The claims below are in addition to those above.
All refrences to claim(s) which appear below refer to the numbering after this setence.

1. A method for improving detection of a change in arrangement of sections of a content, comprising:
detecting a first watermark message from a first location of multimedia content, the first detected watermark message being a strong watermark message with an associated first false positive detection probability value that is below a first predetermined threshold;
determining a presence of at least a portion of a second watermark message from a second location of the multimedia content, including:
based on watermark symbol values of the detected strong watermark message, constructing a template of watermark symbol values,
extracting watermark symbols from the second location of the multimedia content to form at least a portion of a candidate watermark message,
comparing all or part of the constructed watermark template to at least the portion of the candidate watermark message to determine, based on an error threshold value, that at least the portion of the second watermark message is present in the multimedia content, the error threshold value corresponding to a predetermined number of errors that, when detected in the candidate watermark message without using the template of watermark symbol values, corresponds to a second false positive detection probability value that is larger than the first predetermined threshold; and

detecting a location of a change in arrangement of the sections of the multimedia content based on at least the portion of the second watermark message, wherein the location of the change is detected with improved granularity compared to detection of the location of the change that is solely based on the first watermark message.
2. The method of claim 1, wherein the watermark symbol values of the second watermark message are identical to corresponding symbol values of the first watermark message.
3. The method of claim 1, wherein the watermark symbol values of the second watermark message have a predefined relationship to corresponding symbols of the first watermark message.
4. The method of claim 3, wherein the predefined relationship includes a difference between the watermark symbol values of the first watermark message and corresponding symbols of the second watermark message due to having a first packet number value in the first watermark message that is different from a second packet number value in the second watermark message.
5. The method of claim 4, further comprising:
detecting the first packet number from the first watermark message and the second packet number from the second watermark message, and
using the first packet number and the second packet number to determine whether the change in arrangement of sections of the multimedia content includes a cut, an insertion or a reordering of multimedia content segments.
6. The method of claim 1, wherein the comparing includes comparing a fraction of the constructed watermark template to the candidate watermark message to establish the presence of a fraction of the second watermark message that identifies a boundary of the location of the change in arrangement of the sections of the multimedia content with an improved granularity.
7. The method of claim 1, wherein the comparing includes comparing the entire constructed watermark template to the candidate watermark message to establish the presence of the full second watermark message.
8. A computer program product embodiment on one or more non-transitory computer readable media, comprising:
program code for detecting a first watermark message from a first location of a multimedia content, the first detected watermark message being a strong watermark message with an associated first false positive detection probability value that is below a first predetermined threshold;
program code for determining a presence of at least a portion of a second watermark message from a second location of the multimedia content, including:
based on watermark symbol values of the detected strong watermark message, constructing a template of watermark symbol values,
extracting watermark symbols from the second location of the multimedia content to form at least a portion of a candidate watermark message,
comparing all or part of the constructed watermark template to at least the portion of the candidate watermark message to determine, based on an error threshold value, that at least the portion of the second watermark message is present in the multimedia content, the error threshold value corresponding to a predetermined number of errors that, when detected in the candidate watermark message without using the template of watermark symbol values, corresponds to a second false positive detection probability value that is above the first predetermined threshold; and

program code for detecting a location of a change in arrangement of the sections of the multimedia content based on at least the portion of the second watermark message, wherein the location of the change is detected with improved granularity compared to detection of the location of the change that is solely based on the first watermark message.
9. The computer program product of claim 8, wherein the watermark symbol values of the second watermark message are identical to corresponding symbol values of the first watermark message.
10. The computer program product of claim 8, wherein the watermark symbol values of the second watermark message have a predefined relationship to corresponding symbols of the first watermark message.
11. The computer program product of claim 10, wherein the predefined relationship includes a difference between the watermark symbol values of the first watermark message and corresponding symbols of the second watermark message due to having a first packet number value in the first watermark message that is different from a second packet number value in the second watermark message.
12. The computer program product of claim 11, further comprising:
program code for detecting the first packet number from the first watermark message and the second packet number from the second watermark message, and
program code for using the first packet number and the second packet number to determine whether the change in arrangement of sections of the multimedia content includes a cut, an insertion or a reordering of multimedia content segments.
13. The computer program product of claim 8, wherein the comparing includes comparing a fraction of the constructed watermark template to the candidate watermark message to establish the presence of a fraction of the second watermark message that identifies a boundary of the location of the change in arrangement of the sections of the multimedia content with an improved granularity.
14. The computer program product of claim 8, wherein the comparing includes comparing the entire constructed watermark template to the candidate watermark message to establish the presence of the full second watermark message.
15. A device, comprising:
a processor; and
a memory including processor executable code, the processor executable code, when executed by the processor, causes the processor to:
detect a first watermark message from a first location of a multimedia content, the first detected watermark message being a strong watermark message with an associated first false positive detection probability value that is below a first predetermined threshold;
determine a presence of at least a portion of a second watermark message from a second location of the multimedia content, including:
based on watermark symbol values of the detected strong watermark message, construct a template of watermark symbol values,
extract watermark symbols from the second location of the multimedia content to form at least a portion of a candidate watermark message,
compare all or part of the constructed watermark template to at least the portion of the candidate watermark message to determine, based on an error threshold value, that at least the portion of the second watermark message is present in the multimedia content, the error threshold value corresponding to a predetermined number of errors that, when detected in the candidate watermark message without using the template of watermark symbol values, corresponds to a second false positive detection probability value that is above the first predetermined threshold; and

detect a location of a change in arrangement of the sections of the multimedia content based on at least the portion of the second watermark message, wherein the location of the change is detected with improved granularity compared to detection of the location of the change that is solely based on the first watermark message.
16. The device of claim 15, wherein the watermark symbol values of the second watermark message are identical to corresponding symbol values of the first watermark message.
17. The device of claim 15, wherein the watermark symbol values of the second watermark message have a predefined relationship to corresponding symbols of the first watermark message.
18. The device of claim 17, wherein the predefined relationship includes a difference between the watermark symbol values of the first watermark message and corresponding symbols of the second watermark message due to having a first packet number value in the first watermark message that is different from a second packet number value in the second watermark message.
19. The device of claim 18, wherein the processor executable code, when executed by the processor, causes the processor to:
detect the first packet number from the first watermark message and the second packet number from the second watermark message, and
use the first packet number and the second packet number to determine whether the change in arrangement of sections of the multimedia content includes a cut, an insertion or a reordering of multimedia content segments.
20. The device of claim 15, wherein the processor executable code, when executed by the processor, causes the processor to compare a fraction of the constructed watermark template to the candidate watermark message to establish the presence of a fraction of the second watermark message that identifies a boundary of the location of the change in arrangement of the sections of the multimedia content with an improved granularity.
21. The device of claim 15, wherein the processor executable code, when executed by the processor, causes the processor to compare the entire constructed watermark template to the candidate watermark message to establish the presence of the full second watermark message.