METHOD AND SYSTEM FOR DETERMINING GEOMETRY CHANGES OF AN OBJECT

Abstract

In a method for determining a change in the geometry of an object (1), initial image data of a first image (5) of a measurement object (2) attached to the object (1) are acquired. The first image depicts the measurement object (2) from a defined recording point (4) in a defined viewing direction (z) at a first time point. Furthermore, second image data of at least a second image of the measurement object (2) are acquired. The second image depicts the measurement object (2) from the defined recording point (4) in the defined viewing direction (z) at a later second time point. The second image data are compared with the first image data, and a change in the geometry of the object (1) is determined based on the result of the comparison.

Description

[0001] The present invention relates to a method and a system for determining geometric changes of an object, in particular low-frequency vibrations or deformations of the object.

[0002] Methods and systems exist for determining geometric changes in objects, such as buildings. In particular, such methods are used to determine vibrations or other changes, such as fatigue, in a building's structure. For example, within the framework of Structural Health Monitoring (SHM), the condition of an object, such as a building, is monitored, specifically whether the structure and foundation are still stable and intact.

[0003] For this purpose, a structure can be equipped with various sensors capable of measuring vibrations and similar phenomena. Other surveying methods are also known in the field of geodesy, such as optical surveying. For example, a laser can be directed at a point on a structure, where it is reflected by a reflector. Deviations in the reflected laser beam can then be analyzed, for example, to measure displacements or deformations.

[0004] However, with known methods, especially those using sensors to measure vibrations in structures, it can be difficult to detect very slow changes in the structure's geometry, such as very long-wavelength vibrations or non-periodic deformations, because these sensors can be inaccurate in such a low frequency range. Furthermore, such methods, and especially the technology used, are expensive and complex.

[0005] Optical measurement methods often require a complex setup with a measuring device at a fixed point remote from the structure, which can be difficult for offshore structures such as wind turbines. Furthermore, such structures are highly likely to experience particularly slow changes in their geometry, which can be caused by wave action.

[0006] The present invention is based on the objective of further improving the detection of geometric changes in an object. In particular, the detection of very slow geometric changes is to be improved.

[0007] The solution to this problem is achieved according to the teaching of the independent claims. Various embodiments and further developments of the invention are the subject of the dependent claims.

[0008] A first aspect of the invention relates to a method, particularly a computer-implemented one, for determining a change in the geometry of an object. In this method, first image data of a first image of a measurement object, which is attached to the object, are acquired. The first image depicts the measurement object from a defined recording point in a defined viewing direction at a first time. Furthermore, second image data of at least a second image of the measurement object are acquired. The second image depicts the measurement object from the defined recording point in the defined viewing direction at a later second time. The second image data are compared with the first image data, and a change in the geometry of the object is determined based on the result of this comparison.

[0009] The aforementioned method, as described in the first aspect, is therefore based primarily on the evaluation of image data from photographs of the object being measured at different times. Since the measuring device is attached to the object, corresponding geometric changes of the object can be deduced by comparing images of the object. In particular, a geometric change of the object can be detected by comparing the second image data with the first image data if the comparison reveals a difference between the two. Using simple image analysis, a method for determining geometric changes of an object can thus be provided that is simple and cost-effective. By using a measuring device that is attached to the object being monitored, such as a building, this method can be carried out without significant installation effort.Since the method does not require sensors on the object, but instead detects geometric changes by comparing image data, even very slow changes, such as very long-wavelength vibrations, can be reliably detected. Furthermore, the detection of instabilities, such as fatigue in an object, for example its structure or its foundation, can be improved.

[0010] For the purposes of this invention, a "geometric change" is understood to mean any change in the geometry of an object. This can include, in particular, deformations of the object, which may be dynamic or essentially static. Changes in the position, location, or orientation of an object relative to its environment can also constitute such a geometric change. These changes can be reversible or irreversible. In particular, periodic geometric changes, such as vibrations, are to be understood as geometric changes within the meaning of this invention. Likewise, non-periodic changes in the geometry of an object, static or near-static deformations, for example, during settling, decay, or other impairment of an object occurring over a longer period of time, are to be understood as geometric changes within the meaning of this invention.

[0011] For the purposes of this invention, the terms "low-frequency vibrations" or "long-wave vibrations" refer in particular to vibrations in a frequency range of 1 Hz or less, and especially also to vibrations with an even lower frequency of 0.1 Hz or less. Such low-frequency vibrations can occur particularly in structures that move very slowly, for example, due to the forces exerted by wind. Especially in offshore structures, i.e., structures anchored to the seabed, particularly slow or long-wave vibrations can occur due to wave action or tides. Astronomical phenomena, such as the influence of the sun or moon, can also cause slight geometric changes in an object, especially an offshore structure.

[0012] For the purposes of this invention, an "object" shall in particular comprise an immobile object, such as a building, structure, or natural landscape feature. Such immobile objects are firmly connected to their surroundings, for example, the ground or, at sea, the seabed. Immobile objects may also include objects that, while not firmly connected to their surroundings, cannot be moved without effort or tools due to their nature, such as their weight or shape, or that can only be made mobile by disassembly. A fixed connection may also include a detachable connection. The object may, for example, be a tall structure such as a wind turbine, a tower, a mast, a chimney, or a drilling platform. It may also be an elongated structure such as a bridge, a tunnel, or a pipeline.Natural landscape features whose geometric changes may be of interest include, for example, volcanoes, mountains, or rock faces. Determining changes in the geometry of the Earth's surface, particularly the movement of tectonic plates (plate tectonics), is also conceivable.

[0013] The term “capturing” image data of an image of the object being measured within the meaning of the invention includes in particular taking an image, for example with the aid of an image capture device, such as an optical instrument, in particular a digital camera, or receiving corresponding image data of a captured image.

[0014] The term "defined recording point" as used in the invention means, in particular, that the location of an image acquisition device, such as a digital camera, is defined and, in particular, fixed. The recording point can be located on the object, inside or outside the object, or at a distance from the object. In other words, images of the object being measured at different times are always taken from the same point, the defined recording point.

[0015] The term "defined viewing direction" as used in the invention means, in particular, that the viewing direction of the image acquisition device is defined and fixed. In other words, different images of the object being measured at different times are always captured in the same direction. The viewing angle is not changed.

[0016] Any terms used herein, such as "comprises," "includes," "features," "has," "with," or any other variant thereof, are intended to cover non-exclusive inclusion. For example, a method or apparatus that includes or features a list of elements is not necessarily limited to those elements but may include other elements not expressly listed or inherent in such method or apparatus.

[0017] Furthermore, unless explicitly stated otherwise, "or" refers to an inclusive or and not an exclusive "or". For example, a condition A or B is satisfied by one of the following: A is true (or present) and B is false (or not present), A is false (or not present) and B is true (or present), and both A and B are true (or present).

[0018] The terms "ein" or "eine," as used here, are defined as "one or more." The terms "ein anderer" and "ein Weitere," as well as any other variant thereof, are to be understood as "at least one more."

[0019] The term "plural", as used here, is to be understood in the sense of "two or more".

[0020] The terms "configured" or "set up" to perform a determined function (and their respective variations) are understood within the meaning of the invention to mean that the corresponding device already exists in a configuration or setting in which it can perform the function, or at least that it is adjustable—i.e., configurable—so that it can perform the function after appropriate adjustment. Configuration can be achieved, for example, by adjusting parameters of a process sequence or by using switches or similar devices to activate or deactivate functionalities or settings. In particular, the device can have several pre-determined configurations or operating modes, so that configuration can be carried out by selecting one of these configurations or operating modes.

[0021] Preferred embodiments of the method are described below, which, unless expressly excluded or technically impossible, can be combined with each other and with the other described aspects of the invention as desired.

[0022] In some embodiments, the first image is a reference image associated with a reference geometry of the object. By comparing the second image data with the first image data, a change in the object's geometry relative to the reference geometry is determined. In this way, an initial or resting position of the object, particularly at a specific point in time, can be calibrated. While it remains possible to compare image data from images taken at any different time, this also provides the alternative or additional possibility of determining a subsequent change in the object's geometry relative to an initial state.

[0023] In some implementations, a detected geometric change is classified as critical if the comparison reveals a difference between the first and second image data that exceeds a predefined threshold. This allows for a differentiated assessment of geometric changes. While vibrations or similar phenomena may occur to a certain extent under normal circumstances in an object such as a building, other geometric changes, such as very strong vibrations or excessive deformation, may be considered critical because they could indicate a hazard. For example, a structure may be overloaded or instability may be present. A warning may be issued when a critical geometric change is detected.

[0024] In some embodiments, the first and second images are part of a plurality of images that depict the object being measured from the defined recording point in the defined viewing direction at successive times. In other words, an image sequence can be provided that represents images of the object being measured over a period of time at successive points in time. Each image can also be considered a single image or frame of an image sequence. The image sequence can be recorded at a specific frame rate, for example, 10 to 60 fps (frames per second), in particular 16, 18, 24, 30, 50, or 60 fps, to achieve a desired temporal resolution of the geometric change.From the majority of images, successive images can be compared, or any images can be compared, for example, each image can be compared with the first image of the image sequence, as described above in connection with the reference geometry. A specific number of images can form an image cycle, which provides the basis for the evaluation. In this way, it can be determined within each specific cycle whether a change in geometry has occurred.

[0025] In some embodiments, determining a change in geometry includes determining a vibration of the object, in particular a vibration of the object with a frequency of 1 Hz or less, especially 0.1 Hz or less. As explained above, the method can determine such low-frequency or long-wavelength vibrations in a simple and accurate manner.

[0026] In some embodiments, determining a change in geometry includes determining a non-oscillatory, i.e., non-periodic, deformation of the object. Such changes in geometry can be of particular interest for detecting long-term changes in the geometry of an object, for example, fatigue in the structure or a foundation, as already explained above.

[0027] In some embodiments, determining a geometric change includes determining a geometric change with respect to at least one of the following degrees of freedom: translation in the x-direction, translation in the y-direction, translation in the z-direction, rotation about the x-axis, rotation about the y-axis, and rotation about the z-axis. The method is thus able to determine all degrees of freedom of a geometric change, which includes in particular changes in position, location, and / or orientation, in a simple manner, namely through the (digital) evaluation of image data. It is understood that any combination of the aforementioned six degrees of freedom can be detected. The x-, y-, and z-axes form an orthogonal coordinate system, whereby the x- and y-axes can extend substantially perpendicular to the defined viewing direction. The z-axis can extend substantially in the defined viewing direction. The comparison of the image data or...The evaluation of the comparison result, i.e., the detection of a change in geometry, can be divided into corresponding sub-evaluations, which together then provide an overall result.

[0028] In some embodiments, the object being measured has a pattern, in particular a two-dimensional pattern. While in principle any image or pattern is suitable for carrying out the method, a simple geometric pattern facilitates the evaluation of the image data. In particular, the pattern can be a geometric pattern, such as a line pattern, especially a cross pattern. Displacements in the x and y directions, i.e., displacements laterally to the viewing direction, can then be easily detected by displacements of the lines of the cross. Displacements in the z direction, i.e., displacements along the viewing direction (or in other words, a change in the distance between the object being measured and the recording point), cause a change in the line thickness in the representation of the pattern. Rotations or torsions cause a corresponding distortion of the lines or line thickness. Such changes or distortions can be detected by the image.Differences in the representation of the object being measured can be efficiently and easily detected using a two-dimensional pattern. The object being measured can be a substrate, such as a plate, on which the pattern is printed. However, it is also possible to apply the pattern directly to the object, for example, to a wall of a building.

[0029] In some embodiments, the object is a structure or a natural landscape feature as explained above. The method can be advantageously applied, for example, to tall structures such as wind turbines or towers. The height of the structure can be utilized by positioning the object far from the recording point. This greater distance allows even small geometric changes to be detected with higher accuracy, since geometric changes, especially displacements perpendicular to the line of sight (i.e., in the x and y directions), cause larger changes in the recorded image of the object with increasing distance.

[0030] In some embodiments, a geometric change determined over a period of time is transformed into a frequency domain using a transformation function in order to determine at least one frequency at which the determined geometric change occurs. For this purpose, a Fourier or Laplace transform can be performed, for example. This can be advantageous if, in particular, the frequency(ies) of an object's vibration are of interest. Deviations or changes in the frequencies, especially if they exceed a predefined threshold, can then indicate a critical geometric change.

[0031] In some embodiments, a measured geometric change is compared with a model of at least one predefined geometric change. If a match is found, the measured geometric change is classified as corresponding to the matching predefined geometric change. Such a comparison ("matching") of a measured geometric change with predefined geometric changes allows the determination of the type of geometric change. For example, various structural changes in an object, such as fatigue in concrete, loosening of connections, damage to structural elements, or the like, cause characteristic geometric changes. Various scenarios can be measured or simulated on a real model for this purpose.A detected change in geometry can then be classified accordingly, so that appropriate measures can be taken to rectify damage, perform maintenance, or similar actions if necessary. In particular, such a classification can be based on a frequency spectrum, which, as explained above, can be obtained by transforming it into a frequency domain.

[0032] In some embodiments, measurement data regarding a mechanical influence on the object are also acquired using at least one sensor device, and this measurement data is combined with the determined geometric change. In this way, a wide spectrum of frequencies, such as those occurring during object vibrations, can be covered. For example, very long-wavelength vibrations down to 0.1 Hz or up to 1 Hz can be determined using the method described above. Vibrations with a frequency greater than 0.1 Hz or greater than 1 Hz, for example up to 15 kHz, can then be determined using one or more additional sensor devices. Such higher-frequency vibrations can be detected, for example, using a vibration sensor such as a piezoelectric sensor.

[0033] A second aspect of the invention relates to a data processing system comprising at least one processor configured to perform the method according to the first aspect of the invention, wherein the first image data and the second image data are acquired as input data in the system. The system can, in particular, be a computer or a control unit for another or higher-level system, such as a surveying system.

[0034] A third aspect of the invention relates to a measuring arrangement with such a data processing system. The measuring arrangement further comprises an image acquisition device, such as a digital camera, and a measuring object, which can be attached to an object to be monitored for geometric changes in such a way that it is visible from a defined recording point in a defined viewing direction. The image acquisition device is configured to capture multiple images of the measuring object from the defined recording point in the defined viewing direction. For this purpose, a line of sight must be established between the measuring object and the image acquisition device. The measuring object can be attached to an object in such a way that the distance to the image acquisition device is variable.

[0035] A fourth aspect of the invention relates to a computer program with instructions which, when executed on a system according to the second aspect, cause the system to execute the method according to the first aspect.

[0036] The computer program can be stored, in particular, on a non-volatile data carrier. Preferably, this is a data carrier in the form of an optical data carrier or a flash memory module. This can be advantageous if the computer program itself is to be handled independently of a processor platform on which the one or more programs are to be executed. In another implementation, the computer program can exist as a file on a data processing unit, in particular on a server, and be downloadable via a data connection, for example, the Internet or a dedicated data connection, such as a proprietary or local network. Furthermore, the computer program can comprise a plurality of interacting individual program modules.

[0037] The system described in the second aspect may accordingly have a program memory in which the computer program is stored. Alternatively, the system may also be configured to access an external computer program, for example on one or more servers or other data processing units, via a communication link, in particular to exchange data with it that is used during the execution of the procedure or computer program or represents outputs of the computer program.

[0038] The features and advantages explained in relation to the first aspect of the invention also apply accordingly to the other aspects of the invention.

[0039] Further advantages, features and possible applications of the present invention will become apparent from the following detailed description in conjunction with the drawings.

[0040] This shows: Fig. 1a and b schematically show two examples of a measuring arrangement for determining geometric changes on different objects; Fig. 2 schematically illustrates the process of a method according to the invention; Fig. 3a, b, c and d schematically depict a measured object for various geometric changes in the form of displacements; and Fig. 4a, b and c schematically depict a measured object for different geometric changes in the form of rotations.

[0041] The same reference numerals are used throughout the figures for the same or corresponding elements of the invention.

[0042] Fig. Figure 1a schematically shows an embodiment of a measuring arrangement using the example of a tower, which here represents object 1. Such an arrangement can be used for any structure that extends upwards, such as wind turbine masts or the like. In this example, an image acquisition device 3 is arranged in a lower area of ​​object 1, for example at the base of the tower. The image acquisition device 3 can be a digital camera which has a plurality of Fig. The device can capture an image of a measurement object 2, in particular an image sequence with a specific frequency and resolution. Here, the measurement object 2 is located in an upper area of ​​the tower, for example on the ceiling, so that it is visible from a recording point 4 in a viewing direction z. Another arrangement is also conceivable, in which the image acquisition device 3 and the measurement object are located, for example, on opposite walls of the object 1. However, the arrangement shown allows the height of the tower to be utilized. Due to the large distance between the image acquisition device (or the recording point 4) and the measurement object 2 in the viewing direction z, deviations in the Fig. The effect is more pronounced with the same geometric changes than with smaller distances. Another advantage of this arrangement is that the recording point 4 is essentially fixed, while the object being measured, 2, moves along with object 1.

[0043] The measured object 2 exhibits a cross pattern that extends perpendicular to the viewing direction z in the x and y directions. Fig. of the object being measured is in Fig. 1a is also indicated. This can be a starting position or resting position, which can serve as a reference for further monitoring of object 1. In addition, in this embodiment, a sensor device 6 is arranged on object 1, for example on a wall of the tower, which can measure further mechanical influences, such as vibrations or the like, acting on object 1.

[0044] Another embodiment of a measuring arrangement is described in Fig. Figure 1b illustrates this. Object 1 is a tunnel, on the opposite walls of which the image acquisition device 3 and the measuring object 2 are arranged. Essentially, the above applies with reference to... Fig. 1a As stated above. In this embodiment, a different arrangement of image acquisition device 3 and measuring object 2 is also conceivable, for example at two distant points along the tunnel. The arrangement as in Fig. However, the diagram shown in 1b is advantageous for monitoring tunnel walls, for example, under the influence of an overlying mountain massif. Deformation can occur in a tunnel passing through a mountain, for example, during the formation of gneiss. The structure of gneiss forms in the solid state, whereby existing minerals can be deformed during metamorphism. This can cause external pressure to be exerted on the tunnel walls.

[0045] Referring to Fig. Section 2 now illustrates a method for determining a change in the geometry of an object 1. The image acquisition device 3 uses a series of Fig. of the measured object 2 on (S11). An image sequence can be recorded at a specific frame rate, such as 60 fps. Exemplary image sequences are shown with reference to Fig. 3 and Fig. 4 explained. Fig. Images of object 2 taken at different times are compared (S12). This can be easily done using digital image analysis. The comparison is then analyzed (S13) to determine geometric changes in object 1. This analysis can also include a transformation into a frequency domain, e.g., using Fourier or Laplace transforms. This method allows for the simple detection of very long-wavelength vibrations down to 0.1 Hz or 1 Hz, as well as non-periodic deformations of the object.

[0046] Fig. Figure 2 also shows another way to monitor object 1 for vibrations or the like. Using at least one sensor device 6, for example a vibration sensor such as a piezoelectric sensor, further mechanical influences on object 1 can be measured (S21). This measurement data (sensor data) is evaluated (S22) to draw conclusions about vibrations or the like. These could, for example, be higher-frequency vibrations in the range of 1 Hz to 15 kHz.

[0047] In a further step S31, the data on the geometric changes of the object obtained using image analysis (S11, S12, S13) can be combined with the measurement data from the sensor device (S21, S22). This allows for comprehensive monitoring of influences on object 1 across a broad frequency spectrum from below 1 Hz up to 15 kHz, including non-periodic or quasi-static deformations.

[0048] Fig. Figure 3 shows, by way of example and schematically, various sequences of Fig. of the object being measured 2 during vibrations of the object 1 and thus of the object being measured 2 in different directions. Fig. Figures 3a), b), and c) each show cycles of seven images, corresponding to one oscillation cycle, with image (i) representing a rest position at the beginning and end. At a high frame rate, such as 60 fps or more, a correspondingly high temporal resolution and thus high accuracy can be achieved.

[0049] Fig. 3a) illustrates Fig. , as they occur during vibrations of the object in the x-direction. While figure (i) represents the equilibrium position, figures (ii)-(vi) each show a displacement of the vertical line (i.e., the line running in the y-direction) of the cross pattern in the x-direction. Based on the deviation of the vertical line in the x-direction, a displacement of the measured object 2 in the x-direction, and thus a corresponding deflection of object 1 in the x-direction, can be determined by comparison with the respective preceding figure or with figure (i).

[0050] Analogous is in Fig. 3b) In figures (ii)-(vi), a displacement of the horizontal line (i.e., the line running in the x-direction) of the cross pattern in the y-direction can be observed, which is caused by a vibration of object 1 in the y-direction. Fig. 3c) In figures (ii)-(vi), a change in the line thickness of the cross pattern can be seen. This is caused by a vibration of object 1 in the z-direction. Since this corresponds to the viewing direction, it is equivalent to a change in the distance between the recording point 4 and the measured object 2. Fig. Figure 3d) illustrates a combination of the oscillations in all three directions.

[0051] Fig. Figure 4 shows, by way of example and schematically, various sequences of Fig. of the measured object 2 during rotations in different directions. As in Fig. Figure 3 shows the rest position. Fig. 4a) shows Fig. , as they occur when the measured object 2 is rotated around the x-axis. A distortion of the vertical line of the cross pattern is discernible, from which a corresponding rotation of object 1 can be inferred by comparison with a corresponding preceding figure or with figure (i).

[0052] When rotating around the y-axis, the horizontal line of the cross pattern appears distorted accordingly ( Fig. 4b). In contrast, rotations around the z-axis, i.e., rotations around the axis of the viewing direction, result in the entire pattern appearing rotated accordingly. In this way, rotations or torsions of object 1 can also be determined using this method. Similarly, combinations of rotations around all three axes can also be determined by mixing the data.

[0053] To evaluate an overall change in geometry, the following can be used: Fig. 3a), Fig. 3b), Fig.The isolated geometric changes shown in 3c), 4a), 4b), and 4c) in all six degrees of freedom can be determined. During image analysis, corresponding individual evaluations can be performed and then combined. An amplitude can be determined by ascertaining the magnitude of each difference yielded by the aforementioned image comparison, i.e., the magnitude of line displacement, the magnitude of line distortion (change in line thickness), and the magnitude of rotation. Since the temporal resolution of the image sequences is known, the individual geometric changes or the total geometric change can be plotted against time, allowing the frequency of each geometric change to be determined. By transforming this into a frequency domain, a frequency spectrum can then be determined.

[0054] The method according to the invention, in its various versions, can be used for a wide variety of applications. Such applications include, in particular, the separation of images of different body parts of a person, of different persons, or of one or more persons on the one hand and one or more other objects on the other, either from each other or from a background. In particular, the method can be used to separate one or more body parts of a person in a sensor-captured image in order to then, depending on the result of such separation or segmentation and the subsequent identification of the body parts as objects, perform gesture recognition with regard to any gestures performed by the person.

[0055] While at least one exemplary embodiment has been described above, it should be noted that a large number of variations exist. It should also be noted that the described exemplary embodiments are merely non-limiting examples, and it is not intended to restrict the scope, applicability, or configuration of the devices and methods described herein. Rather, the preceding description will provide the person skilled in the art with guidance for implementing at least one exemplary embodiment. It is understood that various modifications to the function and arrangement of the elements described in an exemplary embodiment can be made without derogating from the subject matter defined in the appended claims and their legal equivalents. REFERENCE MARK LIST 100 methods for determining a change in the geometry of an object 1 object 2. Measuring object 3 Image capture device 4 Recording point 5. Illustration of the object being measured 6 Sensor setup

Claims

[1] Method (100) for determining a change in the geometry of an object (1), comprising: - Acquisition of first image data of a first image (5) of a measurement object (2) which is attached to the object (1), wherein the first image (5) depicts the measurement object (2) from a defined recording point (4) in a defined viewing direction (z) at a first time point in time; - Acquisition of second image data of at least a second image of the object being measured (2), wherein the second image depicts the object being measured (2) from the defined recording point (4) in the defined viewing direction (z) at a later second time; - Comparing the second image data with the first image data; - Determining a change in the geometry of the object (1) depending on a result of the comparison. [2] Method according to claim 1, wherein the first image is a reference image which is associated with a reference geometry of the object (1), wherein a change in the geometry of the object (1) relative to the reference geometry is determined by comparing the second image data with the first image data. [3] Method according to claim 1 or 2, wherein a determined geometry change is classified as critical if the result of the comparison reveals a difference between the first image data and the second image data that exceeds a predetermined threshold. [4] Method according to one of the preceding claims, wherein the first image and the second image are part of a plurality of images which depict the object being measured from the defined recording point in the defined viewing direction at successive times. [5] Method according to any of the preceding claims, wherein determining a change in geometry includes determining a vibration of the object (1). [6] Method according to any of the preceding claims, wherein determining a change in geometry includes determining a non-vibrating deformation of the object (1). [7] Method according to one of the preceding claims, wherein determining a geometry change comprises determining a geometry change with respect to at least one of the following degrees of freedom: translation in the x-direction, translation in the y-direction, translation in the z-direction, rotation about the x-axis, rotation about the y-axis and rotation about the z-axis. [8] Method according to any of the preceding claims, wherein the object being measured (5) has a two-dimensional pattern. [9] Method according to any of the preceding claims, wherein the object (1) is a structure or a natural landscape feature. [10] Method according to one of the preceding claims, wherein a geometric change determined over a period of time is transformed into a frequency space by means of a transformation function in order to determine at least one frequency with which the determined geometric change occurs. [11] Method according to one of the preceding claims, wherein a determined geometry change is compared with a model of at least one predefined geometry change and, if there is a match, the determined geometry change is classified as a geometry change which corresponds to the appropriate predefined geometry change. [12] Method according to any of the preceding claims, further comprising: - Acquisition of measurement data relating to a mechanical influence on the object (1) by means of at least one sensor device (6); and - Combining the measurement data with the determined change in geometry. [13] Data processing system comprising at least one processor configured to perform the method according to one of the preceding claims, wherein the first image data and second image data are captured as input data in the system. [14] Measuring arrangement comprising a data processing system according to claim 12 as well as an image acquisition device (3) and a measurement object (2), wherein the measurement object (2) can be attached to the object (1) in such a way that it is visible from a defined recording point (4) in a defined viewing direction (z), and the image acquisition device (3) is configured to take a plurality of images (5) of the measurement object (2) from the defined recording point (4) in the defined viewing direction (z). [15] Computer program with instructions which, when executed on a system according to claim 12, cause the system to execute the method according to any one of claims 1 to 11.

Images