METHOD AND SYSTEM FOR ANALYSING AN IMAGE GENERATED BY AT LEAST ONE CAMERA

Description

[0001] The present invention is directed to a method and system for analysing an image generated by at least one camera, wherein the at least one image is generated by the camera capturing at least one print media object.

[0002] In the prior art there are known applications which augment print media objects, such as conventional books, with virtual objects using the so called Augmented Reality (AR) technology: H.K.U.I.P. Mark Billinghurst, The Magic Book: A transitional AR interface, Computers and Graphics, 25(5), 2001, pages 745 - 753 and John McKenzie and Doreen Darnell, The eyeMagic Book - A Report into Augmented Reality Storytelling in the Context of a Children's Workshop, 2003.

[0003] In such application, a camera coupled to a computer takes a picture of a book read by a person, wherein the book is displayed on a display screen and virtual objects may be displayed in addition to the image of the real world containing the book, so that the book displayed on the display screen is augmented with virtual objects of any kind on a display screen. In such application, in order to augment the image with virtual objects, there is the need for the computer system to identify the real object, such as a respective page of the book, and its position and orientation with respect to the camera in order to correctly display the virtual object in the image taken by the camera.

[0004] Generally, each double page, i.e. the pages of the book which are simultaneously visible when reading the book, is represented by a respective data set stored in the computer system. When the book is positioned with an opened double page on a table, for example, and the camera is taking an image of the book, the image of the camera is capturing the double page opened in front of the camera. For identifying a particular double page of the book in order to correctly display the virtual object in the image of that double page, the computer system is required to compare one or more features of the image taken by the camera with all of the data sets stored in the computer system for the book, which process is rather time consuming and requires large processing performance of the computer system.

[0005] Antunez E. et al.: "HOTPAPER: Multimedia Interaction with Paper using Mobile Phones" INTERNET, [Online] 26 October - 31 October 2008, pages 399-408 discloses a document recognition algorithm that automatically determines the location of a patch of text in a large collection of document images given a small document image. A Brick Wall Coding (BWC) algorithm is given a query image from which word bounding boxes are extracted and represented with BWC feature vectors. BWC feature vectors are submitted as queries to a database, and the original document patches that contain BWC features in the query image are retrieved with hash-lookup. The top N candidate retrieved document patches having the highest number of BWC features are then identified for a subsequent geometric verification step. In this step, similarity of relative locations of their descriptors to the query image is computed searching for the document patch with the top score.

[0006] It is therefore an object of the invention to provide a method and a system for analysing an image of a real object generated by at least one camera which may be performed with reduced processing requirements and/or at a higher processing speed.

[0007] The invention is directed to a method according to the features of claim 1. Additionally, the invention is directed to a system according to the features of claim 12 and a computer programmable product according to claim 13.

[0008] According to a first aspect of the invention, there is disclosed a method for analysing an image of a real object generated by at least one camera, wherein the method comprises the following steps: generating at least a first image by the camera capturing at least one real object, defining a first search domain comprising multiple data sets of the real object, each of the data sets being indicative of a respective portion of the real object, and analysing at least one characteristic property of the first image of the camera with respect to the first search domain, in order to determine whether the at least one characteristic property corresponds to information of at least a particular one of the data sets of the first search domain. If it is determined that the at least one characteristic property corresponds to information of at least a particular one of the data sets, the method includes the step of defining a second search domain comprising a reduced number of the data sets compared to the first search domain and using the second search domain for analysing the first image and/or at least a second image generated by the camera.

[0009] Therefore, the method provides the advantage that for analysing at least a second and following images generated by the camera, any predefined search domain used for analysing the images may be significantly reduced to a smaller size, particularly to comprise only the data set or data sets for which a previous correspondence has been found, so that less processing power is needed for the analysing process and/or the processing speed can be increased.

[0010] An embodiment of the invention comprises that the real object is a printed media object which is an advantageous object for which the present invention may be applied.

[0011] The invention advantageously uses the inventors' finding that in certain applications all portions of a real object, such as all pages of a book, cannot be captured by the camera simultaneously. Rather, with taking an image of a real object, such as a book, only a particular portion of that object, such as a particular double page of a book, can be captured at a time by the camera. The invention uses this finding in that the search domain for the following analysing process is reduced to a reduced number of data sets once it has been found that there is a correspondence between at least one characteristic property of the current image and a particular one of the data sets.

[0012] Embodiments of a printed media object as understood in the context of the present invention include, for example, a book, a printed magazine, a newspaper, a catalog, a folder or any other type of device used in the same or a similar way or for the same or a similar purpose. Generally, a printed media object, as may be used with the present invention, may be a printed, substantially flat or even object comprising one or more printed pages which may be turned over by a user from one page or double page to another page or double page, respectively, and may be positioned in front of a camera. The invention may also be applied to other types of real objects having portions and corresponding data sets which are not visible simultaneously.

[0013] Particularly, the method includes the step of analysing at least one characteristic property of the second image of the camera with respect to the second search domain, in order to determine whether the at least one characteristic property of the second image corresponds to information of a particular one of the data sets of the second search domain.

[0014] According to an embodiment of the invention, the method further includes the step of setting a time period or a number of images captured by the camera for analysing following images with respect to the second search domain, and if it is determined that none of characteristic properties of the following images corresponds to information of a particular one of the data sets of the second search domain within the set time period or within the number of captured images, the first search domain is used for analysing at least one further image captured by the camera. Therefore, if the user is changing, for example, to another double page of the book so that the system cannot find a correspondence for that double page in the second search domain, again the first search domain is used for analysing the new image in order to find another particular one of the data sets corresponding to that double page.

[0015] For example, each of the data sets is indicative of a respective page or double page of the printed media object. This embodiment uses the finding that under normal circumstances only two pages of a double page of the printed media object are visible simultaneously, so that the search domain can be reduced accordingly.

[0016] The invention, in an embodiment thereof, may be used for augmenting one or more of the images with one or more virtual objects, so that an augmented reality system needs less processing power and/or may operate with higher processing speed. Accordingly, the method may include the steps of displaying the first and second images on image displaying means, wherein the at least one of the images is augmented with at least one virtual object using an Augmented Reality technology.

[0017] A further aspect of the invention is concerned with a system for analysing an image, comprising a camera for generating at least a first and second image capturing at least one real object, and a processing unit connected with the camera. The processing unit is programmed for performing the steps of defining a first search domain comprising multiple data sets of the real object, wherein each of the data sets is indicative of a respective portion of the real object, and analysing at least one characteristic property of the first image of the camera with respect to the first search domain, in order to determine whether the at least one characteristic property corresponds to information of at least a particular one of the data sets of the first search domain. If it is determined that the at least one characteristic property corresponds to information of at least a particular one of the data sets, a second search domain is defined comprising only the particular one of the data sets. This second search domain is then used for analysing the first image and/or at least a second image generated by the camera.

[0018] Further embodiments and aspects of the invention are evident from the dependent claims.

[0019] The invention will now be described in more detail in conjunction with the accompanying drawings which illustrate various embodiments of the invention.

Fig. 1

shows a schematic illustration of a first embodiment of a system according to the invention;

Fig. 2

shows a schematic illustration of a second embodiment of a system according to the invention;

Fig. 3

shows a schematic illustration of portions of a printed media object and data sets indicative of respective portions of the printed media object,

Fig. 4

shows a flowchart illustration of a method according to an embodiment of the invention.

[0020] In Fig. 1 there is shown a schematic illustration of a first embodiment of a system according to the invention. Particularly, Fig. 1 shows a system 1 in which a user 10 holds a camera 11 in his or her hand for generating at least one image of the real world, for example of the real object 12 as shown, which is in the present example a printed media object of the type as described herein before. According to a particular example, the real object 12 may be a book which is placed in front of the user 10, and the camera 11 takes an image of the book 12 to be displayed on a display screen. The book 12 is provided with an object coordinate system 17, such as shown in Fig. 1. Further, the camera 11 is coupled with an image displaying means 13, such as a display screen of a personal computer, or the like. However, any other image displaying means may be used which is suitable for displaying an image to a user, such as a head mounted display or any other type of mobile or stationary display device. Furthermore, a processing unit 14, which may be for example a personal computer (PC), is connected with the camera 11 and the image displaying means 13 in wired or wireless fashion. The invention is applicable to examples where the camera 11, the processing unit 14 and/or the displaying means 13 are integrated in an apparatus or are distributed components. For example, the camera 11, the processing unit 14 and/or the displaying means 13 may be integrated in a single apparatus such as a mobile phone.

[0021] In the situation as shown in Fig. 1 the user holds the camera 11 in his or her hand and is looking at the object 12 placed in front of the user. The camera images, such as a video flow of images, are displayed on the image displaying means 13 placed in front of the user 10. According to an embodiment of the invention, the images may be augmented with one or more virtual objects according to the augmented reality (AR) technology. According to a possible application, the user 10 is taking pictures or a video stream of a book 12, and on the image displaying means 13 the images of the book 12 are shown augmented with virtual information, such as a 3-dimensional virtual illustration of a 2-dimensional object printed on a double page of the book 12 and captured by the camera 11 (typical magic book application as described above).

[0022] In Fig. 2, there is shown another situation in which the system 1 substantially comprises the same components as described with reference to Fig. 1, however, in a different configuration. In the situation as shown in Fig. 2, the camera 11 is arranged opposite to the user 10, for example in front of the user 10 on an image displaying means 13, such as a display screen. By means of the camera 11, the user 10 may take images of a real object 12, such as a book, held in the user's hands or placed on a table in front of the user. The real object 12 is provided with an object coordinate system 17 similar as in Fig. 1. In the situation as shown in Fig. 2, the user 10 may move the book 12 with his or her hands in front of the camera 11, wherein the images taken by camera 11 are displayed as images on the display screen 13.

[0023] The image or images by the camera 11 are transmitted to the processing unit 14 which is adapted for performing an image analysing process according to an embodiment of the present invention. Particularly, the processing unit 14, such as a PC, includes a computer program product having software code sections which are adapted for carrying out the process according to the invention, when the code sections are loaded into an internal memory of the PC 14. For example, the software code sections may be stored in an internal memory of the PC or may be provided on a hard disc or any other suitable storage means, wherein the program is loaded into the internal memory of the computer during operation. The camera data may be transmitted to the PC 14 in wired or wireless fashion.

[0024] Taking the magic book application as a particular example of the invention, in order to augment the image with one or more virtual objects, there is the need for the processing unit 14 to identify the real object 12, such as a respective page of the book, and the position and orientation of its coordinate system 17 with respect to the camera 11 in order to correctly display the virtual object in the image taken by the camera. For this purpose, image processing and tracking algorithms, such as marker-based or markerless tracking algorithms, may be applied which are well known in the art, particularly in the augmented reality technology.

[0025] Generally, when the camera 11 is taking a picture of the book 12, two pages of an opened double page are visible and can be viewed simultaneously. In order to identify the opened double page of the book 12 and its position and orientation, the system has to identify at least one characteristic property of the double page, such as a characteristic feature of the respective double page, which distinguishes this double page from another double page of the same book 12. For this purpose, as illustrated in Fig. 3, each double page, i.e. the pages of the book 12 which are simultaneously visible when the book is opened in front of the user, is represented by a respective data set stored in the processing unit 14. For example, a left page P1 and a right page P2 of the book 12 are forming a first double page P1/P2 which is represented by the data set S1. In other words, the data set S1 is indicative of the double page P1/P2, thus contains data or information which allows the processing unit 14 to identify the double page P1/P2 and its position and orientation (pose).

[0026] In an example of the invention, the data set S1 may include two subsets S1a, S1b, with subset S1a being indicative of page P1 and subset S1b being indicative of page P2 of the book 12. In this regard, the data set S1 may include, in principal, any number of subsets.

[0027] Similarly, as the reader turns the page 1 of the book 12, the following pages P3 and P4 of the book 12 are forming a second double page P3/P4 which is represented by the data set S2, so that the data set S2 is indicative of the double page P3/P4 and its pose relative to the camera 11. Likewise, the data sets S3 to S5 are indicative of the double pages P5/P6, P7/P8 and P9/P10, respectively. Like data set S1, data sets S2 to S5 may also contain subsets S2a to S5b for each of the pages P3 to P10 as shown in Fig. 3. The organisation of the pages and respective data sets and the number thereof is only described as a particular example, wherein the skilled person will appreciate that also other types of data structures may be used for the purposes of the invention.

[0028] When the book is positioned with an opened double page, such as P1/P2 on a table, for example, and the camera 11 is taking a first image 15 of the book 12, the image 15 displayed on the display screen 13 is capturing the double page P1/P2 opened in front of the camera 11. For identifying this double page P1/P2 of the book in order to correctly display a virtual object in the image 15 of that double page, the processing unit 14 is required to compare one or more features of the image 15 taken by the camera 11 with all of the data sets S1 to S5 stored in the processing unit 14 for the book 12, which process is rather time consuming and requires large processing performance of the computer system.

[0029] A particular aim of the present invention is to provide a methodology for analysing an image of a real object, such as the book 12, generated by a camera which may be performed with reduced processing requirements and/or at a higher processing speed.

[0030] According to Fig. 4, there is illustrated a flow chart of an embodiment of an analysing process according to the invention which may be implemented in the processing unit 14 of the system 1 as shown in Figs. 1 and 2.

[0031] The process starts with step 1 for defining a first search domain D1 intended to be used for analysing at least a first image 15 taken by the camera 11. In the present example, the first search domain D1 comprises the multiple data sets S1 - S5 of the book 12 as described above with respect to Fig. 3. Particularly, the search domain D1 comprises the maximum number of data sets available for the book 12, which are in the present case data sets S1 to S5. This is because the processing unit 14 does not know which of the double pages of the book is opened.

[0032] In step 2, the camera 11 is taking a first image 15. The search domain being at maximum size, the processing unit 14 in step 3 has to analyse the image 15 with respect to all data sets S1 to S5 in order to find a particular one of the data sets S1 to S5 or S1a to S5b, respectively, which corresponds to the opened double page or at least one of the opened pages. The processing unit 14 analyses at least one characteristic property, such as a characteristic feature of the first image 15 of the camera with respect to the first search domain D1. The result of the analysing process is to determine whether the found characteristic property corresponds to information of at least a particular one of the data sets S1 - S5 (or S1a to S5b, respectively) of the first search domain D1. Particularly, the processing unit 14 may perform a feature detection algorithm within a markerless tracking process to identify whether any found characteristic feature of the image 15 corresponds to information, such as features F1 to F3 shown in Fig. 3, stored in the data set S1. If no such correspondence is found, the processing unit 14 changes to data set S2 and so on until it is determined whether any one of the data sets S1 to S5 corresponds to the image 15.

[0033] In case that the found characteristic feature of image 15 corresponds to information of at least a particular one of the data sets S1 to S5 (step 4), a second search domain D2 is defined comprising, in the present embodiment, only the particular one of the data sets S1 to S5 (step 5), or particular ones of the data sets S1a to S5b, respectively. In the present example where each of the data sets comprises multiple data (sub-)sets, the second search domain D2 is defined to comprise only the data sets (e.g. data sets S1a, S1b) being indicative of at least a part of the particular double page (such as P1/P2) comprising the found characteristic feature. In this regard, it is not required that all data sets of a double page be included in the search domain D2, rather the most significant ones may be sufficient.

[0034] For example, if it is determined that the found characteristic feature of image 15 corresponds to feature F2 of data set S1 (particularly data set S1a), the second search domain D2 is defined to comprise only the particular data set S1 (including data sets S1a, S1b), as shown in Fig. 3. This second search domain D2 is used for analysing the first image 15 and/or at least a following second image 16 generated by the camera 11 (returning to step 2), as it is supposed that the user is remaining for a while reading the double page P1/P2 without changing quickly to any other double page. Thus, for the further analysing process the search domain is reduced significantly. In the present example, once the feature F2 of data subset S1a has been identified, the system only has to search for the other subset S1b of the data set S1 defining the reduced search domain D2.

[0035] In an example of the invention, the search domain D2 may also include, for example, the data set of one or more adjacent double pages, such as data set S2 in order to be prepared if the user turns page P2 to view double page P3/P4. Also, the search domain D2 may be iteratively expanded to data sets covering adjacent double pages, after having not identified a particular data set for a certain period of time or a certain amount of images captured and analyzed.

[0036] For example, if the user moves the book 12 or double page P1/P2 in a plane parallel to the table, the system can quickly follow this movement as the processing unit 14 is analysing the following images only with respect to data set S1. Thus, the processing unit 14 can quickly associate features of the following images with corresponding features of the data set S1. Here, the invention makes use of the fact that the other double pages P3/P4, P5/P6 and so on cannot be seen by the user if double page P1/P2 has once been identified as being opened in front of the camera 11.

[0037] For example, a time period may be set for analysing the second image 16 or any following image with respect to the second search domain D2 (step 6). In case that, within the set time period, it is determined that the respective image does not correspond to information of a particular data set comprised in the second search domain D2 (in the present example, data set S1), i.e. a particular data set of the second search domain D2 is not identified (step 4), the first search domain D1 having the maximum number of available data sets S1 to S5 is used for analysing the respective or following images. This case can occur, for example, if the user turns the page P2 to view another double page which corresponds to another one of the data sets S1 to S5. In this case, the processing unit 14 has to search in the search domain D1 again in order to identify the corresponding data set.

[0038] Generally, according to the invention, objects belonging together (i.e. which are visible simultaneously), such as pages of a respective double page, may be grouped to a respective data set, which data sets exclude one another. If an element of a particular group or data set is visible, then elements of other groups or data sets cannot be visible, thus can be excluded when forming the second search domain.

[0039] An advantage of the invention is that the system is capable of reducing the search domain for analysing an image of the camera. Once the system knows which group is captured by the camera, the system only searches for features of that particular group. For example, if a feature or portion of a particular double page has been found, the system only searches for other portions of the particular double page, and does not search for all of the other double pages of the book.

[0040] In an embodiment of the invention, the method may further include that the step of analysing an image with respect to the first search domain includes a first algorithm and analysing an image with respect to the second search domain includes a second algorithm, which is different from the first algorithm.

[0041] Particularly, it is advantageous if the first algorithm requires a less memory-intensive data structure for matching of features than the second algorithm.

[0042] Many different feature descriptors are known in the state of the art. Each descriptor, its extraction and matching algorithms have different advantages and disadvantages. For example, one descriptor might function by generating an optimized data structure, storing the characteristics of a specific feature from many different views and being able to find and match a feature, relying on that data structure being present in the memory of the processing unit. These algorithms are usually limited in the number of features they can use by the physical memory available.

[0043] Other algorithms try to calculate a compact representation of a feature, which invariant to different camera positions, light changes and other factors. They usually need less memory to describe a feature, but the description has to be calculated from every frame in the image, often using a lot of processing power.

[0044] One aspect of the invention is the possibility to apply a slower algorithm with a smaller memory footprint for a large dataset of features and to apply a faster algorithm with a larger memory footprint, once the search domain is reduced.

[0045] Algorithms with smaller memory footprints are for example: David G. Lowe, "Distinctive image features from scale-invariant keypoints", International Journal of Computer Vision, 60, 2 (2004), pp. 91-110 and Herbert Bay, Tinne Tuyte-laars, Luc Van Gool, "SURF: Speeded Up Robust Features", Proceedings of the ninth European Conference on Computer Vision, May 2006 and Mikolajcryk, K., Zisserman, A. and Schmid, C., Shape recognition with edge-based features Proceedings of the British Machine Vision Conference (2003).

[0046] Algorithms with larger memory footprints are for example: V. Lepetit, P. Lagger and P. Fua, Randomized Trees for Real-Time Keypoint Recognition, Conference on Computer Vision and Pattern Recognition, San Diego, CA, June 2005 and S. Hinterstoisser, S. Benhimane, N. Navab, P. Fua, V. Lepetit, Online Learning of Patch Perspective Rectification for Efficient Object Detection, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Anchorage, Alaska (USA), June 2008.

[0047] While the invention has been described with reference to exemplary embodiments, it will be understood by those skilled in the art that various changes may be made without departing from the scope of the claims.

Claims

1. A method for analysing an image of a real object generated by at least one camera (11), comprising:

- generating at least a first image (15) by the camera (11) capturing at least one real object (12) provided with an object coordinate system (17),

- defining a first search domain (D1) comprising multiple data sets (S1 - S5) of the real object (12), each of the data sets being indicative of a respective portion (P1 - P10) of the real object,

- analysing at least one characteristic property of the first image of the camera with respect to the first search domain (D1), in order to determine whether the at least one characteristic property corresponds to information (F1 - F3) of at least a particular one of the data sets (S1 - S5) of the first search domain (D1),

- if it is determined that the at least one characteristic property corresponds to information (F1 - F3) of at least a particular one (S1, S1a, S1b) of the data sets, defining a second search domain (D2) comprising a reduced number (S1) of the data sets compared to the first search domain (D1) and using the second search domain (D2) for analysing at least a second image (16), or the first image (15) and at least a second image (16) generated by the camera,

- analysing at least one characteristic property of the second image (16) of the camera with respect to the second search domain (D2), in order to determine whether the at least one characteristic property of the second image corresponds to information (F1 - F3) of a particular one (S1, S1a, S1b) of the data sets of the second search domain,
and to identify the real object (12) and the position and orientation of the object coordinate system (17) with respect to the camera (11),
wherein analysing an image with respect to the first search domain includes a first algorithm and analysing an image with respect to the second search domain includes a second algorithm, which is different from the first algorithm, wherein the first algorithm calculates a compact representation of a feature which is invariant to different camera positions or light changes, and the second algorithm functions by being able to find and match a feature using an optimized data structure which is provided to the second algorithm and in which the characteristics of a specific feature from many different views are stored.

2. The method of claim 1, wherein the real object (12) is a printed media object.

3. The method of claim 1 or 2, wherein the second search domain (D2) is defined to comprise only the particular one (S1) of the data sets (S1 - S5) or only the data sets (S1a, S1b) being indicative of at least a part of a particular double page (P1/P2) comprising the characteristic property.

4. The method of one of claims 1 to 3, further including the steps of

- setting a time period or a number of images captured by the camera for analysing following images with respect to the second search domain (D2), and - if it is determined that none of characteristic properties of the following images corresponds to information (F1 - F3) of a particular one (S1, S1a, S1b) of the data sets of the second search domain (D2) within the set time period or within the number of captured images, using the first search domain (D1) for analysing at least one further image captured by the camera.

5. The method of one of claims 1 to 4, further including the steps of

- displaying the first and second images (15, 16) on image displaying means (13),

- wherein the at least one of the images (15, 16) is augmented with at least one virtual object using an Augmented Reality technology.

6. The method of one of claims 1 to 5, wherein the real object (12) is a printed media object and each of the data sets (S1 - S5) is indicative of a respective page or double page (P1 - P10) of the printed media object (12).

7. The method of one of claims 1 to 6, wherein the step of analysing the at least one characteristic property of the first image (15) and of the second image (16) includes analysing at least one feature of the respective image.

8. The method of one of claims 1 to 7, wherein
the step of analysing the at least one characteristic property of the first image (15) and of the second image (16) includes applying a markerless tracking algorithm.

9. A system (1) for analysing an image, comprising:

- a camera (11) for generating at least a first and second image (15, 16) capturing at least one real object (12),

- a processing unit (14) connected with the camera (11) and programmed for performing the following steps:

- defining a first search domain (D1) comprising multiple data sets (S1 - S5) of the real object (12), each of the data sets being indicative of a respective portion (P1 - P10) of the real object,

- analysing at least one characteristic property of the first image (15) of the camera with respect to the first search domain (D1), in order to determine whether the at least one characteristic property corresponds to information (F1 - F3) of at least a particular one of the data sets (S1 - S5) of the first search domain (D1),

- if it is determined that the at least one characteristic property corresponds to information (F1 - F3) of at least a particular one (S1) of the data sets, defining a second search domain (D2) comprising a reduced number (S1) of the data sets compared to the first search domain (D1) and using the second search domain (D2) for analysing at least a second image (16), or the first image (15) and at least a second image (16) generated by the camera,

- analysing at least one characteristic property of the second image (16) of the camera with respect to the second search domain (D2), in order to determine whether the at least one characteristic property of the second image corresponds to information (F1 - F3) of a particular one (S1, S1a, S1b) of the data sets of the second search domain,
and to identify the real object (12) and the position and orientation of an object coordinate system (17) with respect to the camera (11),
wherein analysing an image with respect to the first search domain includes a first algorithm and analysing an image with respect to the second search domain includes a second algorithm, which is different from the first algorithm, wherein the first algorithm calculates a compact representation of a feature which is invariant to different camera positions or light changes, and the second algorithm functions by being able to find and match a feature using an optimized data structure which is present in the memory of the processing unit and in which the characteristics of a specific feature from many different views are stored.

10. Computer programmable product having software code sections which are adapted for carrying out the method according to one of claims 1 to 9 when the code sections are loaded into an internal memory of a computer device.

Ansprüche

1. Verfahren zum Analysieren eines durch mindestens eine Kamera (11) erzeugten Bildes eines realen Objekts, aufweisend:

- Erzeugen wenigstens eines ersten Bildes (15) durch die Kamera (11), welche wenigstens ein reales Objekt (12) erfasst, das mit einem Objektkoordinatensystem (17) versehen ist,

- Definieren eines ersten Suchbereichs (D1) mit mehreren Datensätzen (S1-S5) des realen Objekts (12), wobei jeder der Datensätze für einen betreffenden Teil (P1-P10) des realen Objekts bezeichnend ist,

- Analysieren wenigstens einer charakteristischen Eigenschaft des ersten Bildes der Kamera mit Bezug auf den ersten Suchbereich (D1), um zu bestimmen, ob die wenigstens eine charakteristische Eigenschaft mit Information (F1-F3) wenigstens eines bestimmten der Datensätze (S1-S5) des ersten Suchbereichs (D1) korrespondiert,

- falls bestimmt wird, dass die wenigstens eine charakteristische Eigenschaft mit Information (F1-F3) wenigstens eines bestimmten (S1, S1a, S1b) der Datensätze korrespondiert, Definieren eines zweiten Suchbereichs (D2) mit einer reduzierten Anzahl (S1) der Datensätze im Vergleich zu dem ersten Suchbereich (D1) und Benutzen des zweiten Suchbereichs (D2) zum Analysieren wenigstens eines zweiten Bildes (16) oder des ersten Bildes (15) und wenigstens eines zweiten Bildes (16), welches durch die Kamera erzeugt wurde,

- Analysieren wenigstens einer charakteristischen Eigenschaft des zweiten Bildes (16) der Kamera mit Bezug auf den zweiten Suchbereich (D2), um zu bestimmen, ob die wenigstens eine charakteristische Eigenschaft des zweiten Bildes mit Information (F1-F3) eines bestimmten (S1, S1a, S1b) der Datensätze des zweiten Suchbereichs korrespondiert,
und um das reale Objekt (12) und die Position und Orientierung des Objektkoordinatensystems (17) mit Bezug auf die Kamera (11) zu identifizieren,
wobei ein Analysieren eines Bildes mit Bezug auf den ersten Suchbereich einen ersten Algorithmus und ein Analysieren eines Bildes mit Bezug auf den zweiten Suchbereich einen zweiten Algorithmus beinhaltet, welcher von dem ersten Algorithmus verschieden ist,
wobei der erste Algorithmus eine kompakte Repräsentation eines Merkmals berechnet, welches zu verschiedenen Kamerapositionen oder Lichtwechseln invariant ist, und der zweite Algorithmus funktioniert, indem er in der Lage ist, ein Merkmal unter Benutzung einer optimierten Datenstruktur zu finden und in Übereinstimmung zu bringen, welche an den zweiten Algorithmus bereitgestellt wird und in welcher die Charakteristiken eines spezifischen Merkmals von vielen verschiedenen Ansichten gespeichert sind.

2. Verfahren nach Anspruch 1, wobei das reale Objekt (12) ein gedrucktes Medienobjekt ist.

3. Verfahren nach Anspruch 1 oder 2, wobei der zweite Suchbereich (D2) derart definiert ist, dass er nur den bestimmten (S1) der Datensätze (S1-S5) oder nur die Datensätze (S1a, S1b) aufweist, die für wenigstens einen Teil einer bestimmten Doppelseite (P1/P2) mit der charakteristischen Eigenschaft bezeichnend sind.

4. Verfahren nach einem der Ansprüche 1 bis 3, weiterhin beinhaltend die Schritte

- Setzen einer Zeitperiode oder einer durch die Kamera erfasste Anzahl von Bildern zum Analysieren von folgenden Bildern mit Bezug auf den zweiten Suchbereich (D2), und

- falls bestimmt wird, dass keine der charakteristischen Eigenschaften der folgenden Bilder mit Information (F1-F3) eines bestimmten (S1, S1a, S1b) der Datensätze des zweiten Suchbereichs (D2) innerhalb der gesetzten Zeitperiode oder innerhalb der Anzahl von erfassten Bildern korrespondiert, Benutzen des ersten Suchbereichs (D1) zum Analysieren wenigstens eines weiteren durch die Kamera erzeugten Bildes.

5. Verfahren nach einem der Ansprüche 1 bis 4, weiterhin beinhaltend die Schritte:

- Darstellen des ersten und zweiten Bildes (15, 16) auf einer Bilddarstellungseinrichtung (13),

- wobei das wenigstens eine der Bilder (15, 16) mit wenigstens einem virtuellen Objekt unter Benutzung einer Augmented Reality Technologie angereichert wird.

6. Verfahren nach einem der Ansprüche 1 bis 5, wobei das reale Objekt (12) ein gedrucktes Medienobjekt ist und jeder der Datensätze (S1-S5) für eine jeweilige Seite oder Doppelseite (P1-P10) des gedruckten Medienobjekts (12) bezeichnend ist.

7. Verfahren nach einem der Ansprüche 1 bis 6, wobei der Schritt des Analysierens der wenigstens einen charakteristischen Eigenschaft des ersten Bildes (15) und des zweiten Bildes (16) ein Analysieren wenigstens eines Merkmals des jeweiligen Bildes beinhaltet.

8. Verfahren nach einem der Ansprüche 1 bis 7, wobei der Schritt des Analysierens der wenigstens einen charakteristischen Eigenschaft des ersten Bildes (15) und des zweiten Bildes (16) ein Anwenden eines markerlosen Tracking-Algorithmus beinhaltet.

9. System zum Analysieren eines Bildes, aufweisend:

- eine Kamera (11) zum Erzeugen wenigstens eines ersten und zweiten Bildes (15, 16), welche wenigstens ein reales Objekt (12) erfassen,

- eine Verarbeitungseinheit (14), welche mit der Kamera (11) verbunden ist, und welche zur Durchführung der folgenden Schritte programmiert ist:

- Definieren eines ersten Suchbereichs (D1) mit einer Mehrzahl von Datensätzen (S1-S5) des realen Objekts (12), wobei jeder der Datensätze für einen betreffenden Teil (P1-P10) des realen Objekts bezeichnend ist,

- Analysieren wenigstens einer charakteristischen Eigenschaft des ersten Bildes (15) der Kamera mit Bezug auf den ersten Suchbereich (D1), um zu bestimmen, ob die wenigstens eine charakteristische Eigenschaft mit Information (F1-F3) wenigstens eines bestimmten der Datensätze (S1-S5) des ersten Suchbereichs (D1) korrespondiert,

- falls bestimmt wird, dass die wenigstens eine charakteristische Eigenschaft mit Information (F1-F3) wenigstens eines bestimmten (S1) der Datensätze korrespondiert, Definieren eines zweiten Suchbereichs (D2) mit einer reduzierten Anzahl (S1) der Datensätze im Vergleich zu dem ersten Suchbereich (D1) und Benutzung des zweiten Suchbereichs (D2) zum Analysieren wenigstens eines zweiten Bildes (16) oder des ersten Bildes (15) und wenigstens eines zweiten Bildes (16), welches durch die Kamera generiert wurde,

- Analysieren wenigstens einer charakteristischen Eigenschaft des zweiten Bildes (16) der Kamera mit Bezug auf den zweiten Suchbereich (D2), um zu bestimmen, ob die wenigstens eine charakteristische Eigenschaft des zweiten Bildes mit Information (F1-F3) eines bestimmten (S1, S1a, S1b) der Datensätze des zweiten Suchbereichs korrespondiert,

und um das reale Objekt (12) und die Position und Orientierung eines Objektkoordinatensystems (17) mit Bezug auf die Kamera (11) zu identifizieren,
wobei das Analysieren eines Bildes mit Bezug auf den ersten Suchbereich einen ersten Algorithmus und das Analysieren eines Bildes mit Bezug auf den zweiten Suchbereich einen zweiten Algorithmus beinhaltet, welcher von dem ersten Algorithmus verschieden ist, wobei der erste Algorithmus eine kompakte Repräsentation eines Merkmals berechnet, welches zu verschiedenen Kamerapositionen oder Lichtwechseln invariant ist, und der zweite Algorithmus derart funktioniert, indem er in der Lage ist, ein Merkmal unter Benutzung einer optimierten Datenstruktur zu finden und in Übereinstimmung zu bringen, welche in dem Speicher der Verarbeitungseinheit vorhanden ist und in welcher die Charakteristiken eines spezifischen Merkmals von vielen verschiedenen Ansichten gespeichert sind.

10. Computerprogrammprodukt mit Software-Code-Abschnitten, welche angepasst sind, das Verfahren nach einem der Ansprüche 1 bis 9 auszuführen, wenn die Code-Abschnitte in einen internen Speicher einer Computervorrichtung geladen sind.

Revendications

1. Procédé pour analyser une image d'un objet réel générée par au moins une caméra (11), comprenant le fait de :

- générer au moins une première image (15) via la caméra (11) capturant au moins un objet réel (12) muni d'un système de coordonnées d'objet (17) ;

- définir un premier domaine de recherche (D1) comprenant plusieurs jeux de données (S1 - S5) de l'objet réel (12), chacun des jeux de données indiquant une portion respective (P1 - P10) de l'objet réel ;

- analyser au moins une propriété caractéristique de la première image de la caméra par rapport au premier domaine de recherche (D1) afin de déterminer le fait de savoir si ladite au moins une propriété caractéristique correspond à des informations (F1 - F3) d'au moins un jeu particulier parmi les jeux de données (S1 - S5) du premier domaine de recherche (D1) ;

- lorsqu'on détermine que ladite au moins une propriété caractéristique correspond à des informations (F1 - F3) d'au moins un jeu particulier (S1, S1a, S1b) parmi les jeux de données, définir un deuxième domaine de recherche (D2) comprenant un nombre réduit (S1) des jeux de données par rapport à celui du premier domaine de recherche (D1) et utiliser le deuxième domaine de recherche (D2) pour analyser au moins une deuxième image (16) ou la première image (15) et au moins une deuxième image (16) générées par la caméra ;

- analyser au moins une propriété caractéristique de la deuxième image (16) de la caméra par rapport au deuxième domaine de recherche (D2) afin de déterminer le fait de savoir si ladite au moins une propriété caractéristique de la deuxième image correspond à des informations (F1 - F3) d'un jeu particulier (S1, S1a, S1b) parmi les jeux de données du deuxième domaine de recherche (D2) et afin d'identifier l'objet réel (12) ainsi que la position et l'orientation du système de coordonnées d'objet (17) par rapport à la caméra (11) ;
dans lequel l'analyse d'une image par rapport au premier domaine de recherche englobe un premier algorithme et l'analyse d'une image par rapport au deuxième domaine de recherche englobe un deuxième algorithme qui est différent du premier algorithme ;
dans lequel le premier algorithme calcule une représentation compacte d'une particularité qui est invariable par rapport à différentes positions de la caméra ou par rapport à des changements de lumière, et les fonctions du deuxième algorithme permettent de trouver et de mettre en correspondance une particularité en utilisant une structure de données optimisée qui est fournie au deuxième algorithme et dans laquelle les caractéristiques d'une particularité spécifique émanant de plusieurs vues différentes sont stockées.

2. Procédé selon la revendication 1, dans lequel l'objet réel (12) est un objet sous forme de support imprimé.

3. Procédé selon la revendication 1 ou 2, dans lequel le deuxième domaine de recherche (D2) est défini de telle sorte qu'il comprend uniquement le jeu particulier (S1) parmi les jeux de données (S1 - S5) ou uniquement les jeux de données (S1a, S1b) indiquant au moins une partie d'une double page particulière (P1/P2) comprenant la propriété caractéristique.

4. Procédé selon l'une quelconque des revendications 1 à 3, englobant en outre les étapes consistant à :

- régler un laps de temps ou un nombre d'images capturées par la caméra pour l'analyse d'images suivantes par rapport au deuxième domaine de recherche (D2), et

- lorsqu'on détermine qu'aucune des propriétés caractéristiques des images suivantes ne correspond aux informations (F1 -F3) d'un jeu particulier (S1, S1a, S1b) parmi les jeux de données du deuxième domaine de recherche (D2) au sein du laps de temps ou dans le cadre du nombre des images capturées, utiliser le premier domaine de recherche (D1) pour analyser au moins une image supplémentaire capturée par la caméra.

5. Procédé selon l'une quelconque des revendications 1 à 4, englobant en outre les étapes consistant à :

- afficher la première et la deuxième image (15, 16) sur un moyen d'affichage d'images (13) ;

- dans lequel on augmente ladite au moins une des images (15, 16) avec au moins un objet virtuel en utilisant une technologie de réalité augmentée.

6. Procédé selon l'une quelconque des revendications 1 à 5, dans lequel l'objet réel (12) est un objet sous forme d'un support imprimé et chacun des jeux de données (S1 - S5) indique une page respective ou une double page respective (P1 - P10) de l'objet (12) sous forme de support imprimé.

7. Procédé selon l'une quelconque des revendications 1 à 6, dans lequel l'étape consistant à analyser ladite au moins une propriété caractéristique de la première image (15) et de la deuxième image (16) englobe l'analyse d'au moins une particularité de l'image respective.

8. Procédé selon l'une quelconque des revendications 1 à 7, dans lequel l'étape consistant à analyser ladite au moins une propriété caractéristique de la première image (15) et de la deuxième image (16) englobe l'application d'un algorithme de poursuite sans marqueur.

9. Système (1) pour analyser une image, comprenant :

- une caméra (11) pour générer lesdites au moins une première et une deuxième image (15, 16) capturant au moins un objet réel (12) ;

- une unité de traitement (14) reliée à la caméra (11) et programmée pour mettre en oeuvre les étapes suivantes consistant à :

- définir un premier domaine de recherche (D1) comprenant plusieurs jeux de données (S1 - S5) de l'objet réel (12), chacun des jeux de données indiquant une portion respective (P1 - P10) de l'objet réel ;

- analyser au moins une propriété caractéristique de la première image (15) de la caméra par rapport au premier domaine de recherche (D1) afin de déterminer le fait de savoir si ladite au moins une propriété caractéristique correspond à des informations (F1 - F3) d'au moins un jeu particulier parmi les jeux de données (S1 - S5) du premier domaine de recherche (D1) ;

- lorsqu'on détermine que ladite au moins une propriété caractéristique correspond à des informations (F1 - F3) d'au moins un jeu particulier (S1) parmi les jeux de données, définir un deuxième domaine de recherche (D2) comprenant un nombre réduit (S1) des jeux de données par rapport à celui du premier domaine de recherche (D1) et utiliser le deuxième domaine de recherche (D2) pour analyser au moins une deuxième image (16) ou la première image (15) et au moins une deuxième image (16) générées par la caméra ;

- analyser au moins une propriété caractéristique de la deuxième image (16) de la caméra par rapport au deuxième domaine de recherche (D2) afin de déterminer le fait de savoir si ladite au moins une propriété caractéristique de la deuxième image correspond à des informations (F1 - F3) d'un jeu particulier (S1, S1a, S1b) parmi les jeux de données du deuxième domaine de recherche et afin d'identifier l'objet réel (12) ainsi que la position et l'orientation du système de coordonnées d'objet (17) par rapport à la caméra (11) ;
dans lequel l'analyse d'une image par rapport au premier domaine de recherche englobe un premier algorithme et l'analyse d'une image par rapport au deuxième domaine de recherche englobe un deuxième algorithme qui est différent du premier algorithme ;
dans lequel le premier algorithme calcule une représentation compacte d'une particularité qui est invariable par rapport à différentes positions de la caméra ou par rapport à des changements de lumière, et les fonctions du deuxième algorithme permettent de trouver et de mettre en correspondance une particularité en utilisant une structure de données optimisée qui est présente dans la mémoire de l'unité de traitement et dans laquelle les caractéristiques d'une particularité spécifique émanant de plusieurs vues différentes sont stockées.

10. Produit informatique programmable possédant des sections de code de logiciels qui sont conçus pour mettre en oeuvre le procédé selon l'une quelconque des revendications 1 à 9 lorsque les sections de codes sont chargées dans une mémoire interne d'un ordinateur.

Drawing