Method for generating training data set, method for training artificial intelligence, training data set and computing unit, computer program product

Abstract

The invention relates to a computer-implemented method (300) for generating a training data set (143) for training artificial intelligence for operating a measuring device (100), in particular a wall diagnostic device, comprising: recording (301) sensor data (103) of at least one sensor unit (101) of the measuring device (100); carrying out (303) a position determination of the measuring device (100) relative to the wall body (105) and generating sensor data (103) with position information by a position determination system (145); tagging (305) the sensor data (103) with the position information taking into account the basic fact information, and generating tagged sensor data (103); and summarizing the tagged sensor data (103) into a training data set (143). The invention further relates to a training data set, a method (400) for training artificial intelligence (125), a computing unit and a computer program product.

Description

Technical Field

[0001] The present invention relates to a method for generating a training data set for training an artificial intelligence for a wall diagnosis device. In addition, the present invention also relates to a method for training an artificial intelligence for a wall diagnosis device.

[0002] Furthermore, the present invention relates to a training data set, a method for training artificial intelligence, a computing unit, and a computer program product. Background Art

[0003] Diagnostic devices for diagnosing walls and for detecting objects formed in walls are known from the prior art. Summary of the Invention

[0004] The object of the present invention is to provide an improved method for generating a training data set for training an artificial intelligence of a wall diagnosis device, as well as an improved method for training such an artificial intelligence.

[0005] This object is achieved by the method according to the invention. Advantageous embodiments are the subject of further developments.

[0006] According to one aspect, a computer-implemented method for generating a training data set for training an artificial intelligence for operating a measuring device, in particular a wall diagnostic device, is provided, wherein the method comprises:

[0007] recording sensor data of at least one sensor unit of the measuring device, wherein the sensor data maps the wall to be diagnosed;

[0008] carrying out a position determination of the measuring device relative to the wall and generating sensor data with position information by the position determination system, wherein, in the position determination, each recorded sensor data is assigned a position information, wherein the position information defines the position of the measuring device relative to the wall at which the measuring device was located relative to the wall at the time of recording the sensor data;

[0009] Labeling the sensor data with position information while taking into account basic fact information and generating labeled sensor data, wherein the basic fact information includes at least one piece of information about the presence of an object in a wall; and

[0010] Aggregate labeled sensor data into a training dataset.

[0011] This results in the following technical advantages: an improved method for generating a training data set for training an artificial intelligence for operating a measuring device, in particular a wall diagnostic device, can be provided. To this end, sensor data from at least one sensor unit of the measuring device, in particular a wall diagnostic device, is first recorded. The recorded sensor data is mapped to the wall to be diagnosed and any objects located therein.

[0012] Furthermore, the position of the measuring device relative to the wall is determined, and the position determination system generates sensor data with position information. The sensor data with position information includes the information of the recorded sensor data and is additionally expanded by position information, wherein the position information defines the position of the measuring device relative to the wall at which the measuring device was located at the time the sensor data was recorded.

[0013] Subsequently, the sensor data with position information is labeled. This involves ground fact information. The ground fact information includes at least one piece of information related to the presence of an object in the wall. Therefore, the ground fact information describes the actual presence of the object in the wall. Labeling the sensor data with position information involves identifying the sensor data with respect to the presence or position of the object.

[0014] The tagging thus identifies the sensor data at least as to whether the respective identified sensor data maps an object arranged in the wall. Determining the position of the measuring device at the time the sensor data were recorded enables tagging of the sensor data with respect to the presence of the object in the wall.

[0015] The basic factual information describes the locations in the wall at which the corresponding object is located. To assign this information to the sensor data recorded by the measuring device, position information of the sensor data is required, which defines the location at which the measuring device was located at the time the sensor data was recorded.

[0016] Using appropriately labeled sensor data from a training data set, the artificial intelligence of a measuring device, in particular a wall diagnostic device, can be trained. The artificial intelligence is trained to detect objects located in a wall based on the sensor data of the measuring device. Detection includes identifying whether an object is located at a position on the wall.

[0017] According to one embodiment, the basic fact information includes: classification information related to the object position and / or object type of the object, and / or object depth information related to the depth of the object inside the wall, and / or object extension scale information related to the object extension scale of the object.

[0018] This results in the following technical advantage: by taking into account additional classification information regarding the object position, object type, object depth information, and / or object extent of an object, additional information can be integrated into the training data set. This additional information enables additional training of the artificial intelligence, which can be trained, in particular, to determine the object position, object type, object depth, and / or object extent of detected objects based on sensor data of the measuring device.

[0019] In this case, the corresponding ground fact information describes the actual object position of the object in the wall, the actual object type of the object, the actual object depth of the object in the wall or the actual object extent of the object.

[0020] Given actual knowledge of the objects arranged in the wall, this ground truth information is integrated into the training data set or the recorded sensor data.

[0021] In the broadest sense of the present application, the basic factual information describes the actual existing state of the wall to be inspected.

[0022] According to one embodiment, the position determination system comprises at least one camera sensor and at least one position marker, wherein the position marker is formed on the surface of a wall, wherein the camera sensor is arranged at a predefined viewing angle relative to the wall, wherein the position determination of the measuring device relative to the wall is performed including:

[0023] The measuring device records camera data of the camera sensor during the recording of the sensor data of the sensor unit, wherein the camera data maps the measuring device positioned on the wall and the position marker arranged on the wall;

[0024] Determining the relative position of the measuring device relative to the position marker based on the camera data; and

[0025] Based on this relative position, the position of the measuring device relative to the wall is determined.

[0026] This results in the following technical advantage: the precise position of the measuring device relative to the wall can be determined. To this end, camera data from a camera sensor is first recorded. The camera data reflects the placement of the measuring device on the wall during the sensor data recording. Furthermore, the camera data also reflects position markings formed on the wall. Based on the camera data, the time-resolved relative position of the measuring device relative to the position markings can thus be determined, taking into account the position markings.

[0027] Finally, the time-resolved position of the measuring device relative to the wall can be determined based on this. This approach enables precise position determination of the measuring device relative to the wall. Using the timestamps in the camera data, the measuring device's position relative to the wall can be precisely determined for multiple points in time during the recording of the sensor data.

[0028] In the method according to the invention, the implementation of the position determination further comprises:

[0029] implementing a time synchronization between the recording of sensor data by the sensor unit and the recording of camera data by the camera sensor; and

[0030] Taking this time synchronization into account, position information of the measuring device relative to the wall is determined for each sensor data item of the sensor unit.

[0031] This provides the following technical advantages: it enables precise generation of sensor data with position information. By taking into account the timestamps of the camera data, the position of the measuring device relative to the wall can be determined for multiple points in time. The timestamps of the sensor data make it possible to determine the point in time at which the specific sensor data was recorded by the measuring device. By synchronizing the timestamps of the sensor data and the camera data, it is possible to determine the position of the measuring device relative to the wall at the time the sensor data was recorded for each recorded sensor data. Thus, precise position information is generated for each recorded sensor data item, defining the position at which the measuring device was located during the recording of the corresponding sensor data item.

[0032] According to one embodiment, determining the position further includes:

[0033] Obtaining a viewing angle of the camera sensor relative to the wall based on a predefined viewing angle position of the camera sensor relative to the wall;

[0034] Based on the relative position of the measuring device relative to the position mark determined based on the camera data, a perspective correction is performed to take into account the perspective position of the camera sensor relative to the wall, and the position of the measuring device on the wall is determined based on the perspective correction.

[0035] This results in the following technical advantage: by taking into account the viewing angle of the camera sensor relative to the wall, a perspective correction can be performed on the camera data. This perspective correction can correct distortions caused by the viewing angle when determining the position of the measuring device relative to the wall based on the camera data. This enables precise position determination relative to the wall based on the camera data.

[0036] According to one specific embodiment, the position marker is designed as an ArUco marker or a ChArUco marker.

[0037] This results in the following technical advantages: The position marker, designed as an ArUco marker or ChArUco marker, allows the relative position of the measuring device relative to the position marker to be precisely determined based on the camera data. Furthermore, the ArUco marker or ChArUco marker can be mounted on a wall as a correspondingly designed poster without having to modify the wall.

[0038] As the ArUco marker or ChArUco marker, an ArUco marker or a ChArUco marker known from the prior art can be used.

[0039] According to one embodiment, the location markers are formed by markers constructed on a wall and include: wallpaper patterns, light switches, sockets, windows, furniture.

[0040] This results in the following technical advantage: elements already constructed on the wall can be used as position markers. This makes it possible to dispense with position markers applied externally to the wall.

[0041] According to one embodiment, the camera sensor is arranged on a positioning device, wherein the camera sensor is positioned in a predetermined viewing angle position relative to the wall via the positioning device.

[0042] This provides the following technical advantage: by positioning the camera sensor with the positioning device, it can be precisely positioned at a predetermined viewing angle relative to the wall. The predefined viewing angle position minimizes the necessary viewing angle corrections to the camera data. This makes it easier to determine the position of the measuring device relative to the wall based on the camera data.

[0043] According to one aspect, a training data set for training artificial intelligence of a measuring device for wall diagnostic technology is provided, wherein the training data set is generated by the method for generating a training data set according to one of the above embodiments, and the training data set is used to train artificial intelligence for operating the measuring device.

[0044] According to one aspect, a computer-implemented method for training artificial intelligence of a measurement device for wall diagnostics technology is provided, comprising:

[0045] Providing a training data set by implementing the method for generating a training data set according to one of the above embodiments;

[0046] Artificial intelligence is trained based on the training data set to perform object recognition of objects constructed in the wall, wherein the object recognition includes at least object detection and object classification.

[0047] According to one aspect, a computing unit is provided which is configured to implement a method for generating a training data set for training an artificial intelligence for operating a measuring device and / or a method for training an artificial intelligence of a measuring device according to one of the above embodiments.

[0048] According to one aspect, a computer program product is provided comprising instructions which, when executed by a data processing unit, cause the data processing unit to implement a method for generating a training data set and / or a method for training an artificial intelligence of a measuring device according to one of the above-described embodiments, the training data set being used to train an artificial intelligence for operating a measuring device. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Embodiments of the present invention will be described with reference to the following drawings. The drawings show:

[0050] Figure 1 A schematic diagram of a measuring device according to one embodiment;

[0051] Figure 2 Another schematic diagram of a measuring device according to another embodiment;

[0052] Figure 3 Another schematic diagram of a measuring device according to another embodiment;

[0053] Figure 4 Schematic diagram of a measurement of a measuring device according to one embodiment;

[0054] Figure 5 Another schematic diagram of a measuring device according to another embodiment;

[0055] Figure 6 A schematic diagram of a system for generating a training data set according to another embodiment;

[0056] Figure 7 Schematic representation of the data recorded by the measuring equipment;

[0057] Figure 8 Another schematic diagram of a system for generating a training data set according to another embodiment;

[0058] Figure 9 A flowchart of a method for generating a training data set according to one embodiment;

[0059] Figure 10A flow chart of a method for training an artificial intelligence of a measuring device according to another embodiment;

[0060] Figure 11 Another flow chart of a method for generating a training dataset according to another embodiment; and

[0061] Figure 12 Schematic diagram of a computer program product. DETAILED DESCRIPTION

[0062] Figure 1 A schematic diagram of a measuring device 100 according to one embodiment is shown.

[0063] The present invention relates to a measuring device, and in particular to a wall diagnostic device for inspecting a wall 105 to be processed. Wall diagnostic devices for detecting objects arranged in a wall are known in the prior art. Such devices allow a user to inspect the wall to be processed based on the objects arranged in the wall, so that planned work, such as drilling a hole in the wall, can be carried out based on this information, in a manner that avoids damaging the objects arranged in the wall.

[0064] In the embodiment shown, the measuring device 100 comprises a housing 150 having a handle 152 for a user to hold the measuring device 100 , a display unit 111 for displaying a diagnosis result 109 of a wall diagnosis, and operating elements 154 for switching the measuring device 100 to different operating modes.

[0065] According to the present invention, measuring device 100 comprises at least one radar sensor unit 101. Radar sensor unit 101 can transmit radar signals in the direction of a wall 105 to be inspected and can receive radar signals reflected by wall 105.

[0066] Radar sensor unit 101 may be designed, for example, as a narrowband radar detector device in the frequency range of 2.4 GHz to 2.4835 GHz or as an ultra-wideband radar detector device in the frequency range of 1.8 GHz to 5.8 GHz.

[0067] In addition, to perform wall diagnostics, measuring device 100 includes a diagnostic module 107, which may be implemented on computing unit 151 of measuring device 100. Diagnostic module 107 is configured to perform appropriate diagnostics of the wall to be inspected based on radar data 103 from radar sensor unit 101. Radar data 103 from radar sensor unit 101 maps wall 105 to be inspected and objects 113 that may be located within wall 105.

[0068] The wall diagnosis performed by the diagnostic module 107 includes at least object recognition. Object recognition includes detecting and classifying objects 113 located in the wall 105. Object detection includes at least determining an object position 115. The object position describes the position of the object located in the wall 105 relative to the reference system determined by the measuring device 100. Classifying the detected object 113 includes at least determining an object type 117 of the detected object 113.

[0069] The diagnostic results of the wall diagnosis thus determined, i.e., at least the determined object position 115 and / or the determined object type 117 of the object 113 arranged in the wall 105, are then displayed to the user of the measuring device 100 on the display unit 111 of the measuring device 100. The display unit 111 can be designed, for example, as a corresponding display screen, and the diagnostic result 109 can be displayed visually. In addition, the display of the diagnostic result 109 can be supported by acoustic and / or haptic signals. The haptic signal can be implemented, for example, by a corresponding vibration signal.

[0070] Here, object 113 can be displayed, for example, by a corresponding symbol on a display screen. Object 113 can be displayed on a display screen at a corresponding object position 115. Object extent 121 can be visualized by the corresponding size of the displayed symbol. Individual object types 117 of object 113 can be visualized using corresponding terms, or by the color background of the symbol, or by a specific shape of the symbol representing object 113.

[0071] Alternatively, the wall diagnosis can also additionally include the determination of a wall type 123 in the form of a wall type classification of the wall 105 to be inspected. Wall type 123 describes the individual types of wall 105 to be inspected. For example, the wall type can be assigned to a corresponding wall type category, which can include: concrete wall, lightweight / dry-built wall, brick wall and / or brick and stone wall, floor heating system, wall heating system, or similar wall types found in buildings.

[0072] According to one embodiment, diagnostic module 107 is further configured to determine an object depth 119 of object 113 within wall 105 based on radar data 103. Object depth 119 is defined as the distance of an object formed within wall 105 from the surface of wall 105. On the object side, this distance can be defined, for example, with reference to the object surface or to the object's center point. The distance to the surface of wall 105 describes the shortest distance defined by a direction perpendicular to the surface of wall 105.

[0073] According to one embodiment, diagnostic module 107 is further configured to determine an object extent 121 of object 113 in at least one predefined direction based on radar data 103. Object extent 121 of object 113 describes the spatial extent of object 113 in at least one spatial direction, preferably in two spatial directions, and particularly preferably in three spatial directions. Thus, object 113 can be described as a one-dimensional, two-dimensional, or three-dimensional object 113.

[0074] In typical use, measuring device 100 is placed on the surface of a wall 105 to be inspected. Radar signals are transmitted in the direction of wall 105 via radar sensor unit 101, and radar signals reflected by wall 105 or objects 113 located behind the wall are received. Diagnostic module 107 performs the aforementioned wall diagnosis on radar data 103 from radar sensor unit 101 and determines corresponding diagnostic results 109.

[0075] Diagnosis result 109 may include, for example, object position 115 and / or object type 117 of object 113 arranged in wall 105. Alternatively or additionally, diagnosis result 109 may also include wall type 123 of wall 105 and / or object depth 119 and / or object extension 121 of object 113.

[0076] The thus configured diagnosis result 109 can then be displayed to the user of the measuring device 100 on the display unit 111 of the measuring device 100. The display unit 111 can be designed as a corresponding display screen, for example. The diagnosis result 109 can be displayed on the display unit 111 in graphical form or in text form.

[0077] According to one embodiment, measuring device 100 further includes a motion detection unit 141. Motion detection unit 141 can be used to detect the movement of measuring device 100 relative to wall 105. To this end, motion detection unit 141 can include, for example, at least one roller element. When the roller element is placed on the surface of wall 105, the movement of measuring device 100 relative to wall 105 can be detected when measuring device 100 rolls along motion direction 153 due to the rolling of the roller element. Alternatively, motion detection unit 141 can have another configuration that can detect the relative movement of measuring device 100 relative to wall 105.

[0078] By moving measuring device 100 relative to wall 105, radar data 103 of radar sensor unit 101 can be recorded for a plurality of different positionings of measuring device 100 relative to wall 105. This allows for the examination of wall 105 over a larger spatial area than that given by the range of action of radar sensor unit 101. This allows for the detection of objects 113 having a larger spatial extent than the range of action of radar sensor unit 101.

[0079] While measuring device 100 is moving in direction of movement 153, sensor data 103 from radar sensor unit 101 can be continuously recorded. Based on these radar data 103, wall diagnosis can be evaluated by diagnostic module 107 while measuring device 100 is moving in direction of movement 153. This enables accelerated wall diagnosis that takes into account the positioning of measuring device 100 relative to wall 105.

[0080] Depending on its embodiment, diagnostic module 107 is designed as a correspondingly trained artificial intelligence 125. Artificial intelligence 125 is trained to perform the aforementioned wall diagnosis based on radar data 103 from radar sensor unit 101 and to determine at least object position 115 and object type 117 of object 113 located in wall 105. Object classification or determination of object type 117 here includes assigning detected object 113 to a predefined object class.

[0081] Here, object categories may include: metal / non-metal objects, cables for low voltage, cables with single-phase AC signals, cables with multi-phase AC signals, wooden supports, metal supports, plastic pipes, plastic pipes filled with water (such as tap water pipes), plastic pipes not filled with water (such as sewage pipes), or other elements that are typically built into the walls of buildings.

[0082] Furthermore, artificial intelligence 125 is trained to determine wall type 123 of wall 105 to be inspected based at least on radar data 103 from radar sensor unit 101. Possible wall types 123 may include: concrete walls, lightweight / dry-built walls, brick walls and / or individual brickwork, floor heating systems, wall heating systems, or other common wall types constructed in buildings.

[0083] According to one embodiment, in addition to radar sensor unit 101, measuring device 100 may also include additional sensors, by means of which additional physical variables can be detected. For example, measuring device 100 may include an inductive sensor, an eddy current sensor, a capacitive sensor, an AC current sensor, a nuclear magnetic resonance (NMR) sensor, an ultrasonic sensor, or other sensors typically incorporated into wall diagnostic equipment.

[0084] Diagnostic module 107, in particular a correspondingly trained artificial intelligence 125, may be configured to perform the aforementioned wall diagnosis based on radar data 103 from radar sensor unit 101 and taking into account additional sensor information from further sensors. For this purpose, the additional information from the further sensors may be used, in particular, for object recognition of objects 113 located in wall 105. The additional sensor information may enable improved detection and, if necessary, improved classification of objects 113.

[0085] The material of object 113 , for example metallic or non-metallic, can be refined and classified, for example, by using additional sensor information.

[0086] Figure 2 A further schematic diagram of a measuring device 100 according to another specific embodiment is shown.

[0087] In the illustrated embodiment, in addition to the diagnostic module 107, the measuring device 100 also includes a preprocessing module 127. For wall diagnosis, the measuring device 100 first receives radar data 103 from the radar sensor 101. The received radar data 103 is preprocessed by the preprocessing module 127. Through the preprocessing by the preprocessing module 127, the radar data can be converted into a corresponding data structure required by the diagnostic module 107 for wall diagnosis, for example.

[0088] As described above, the diagnostic module 107 generates the diagnostic result 109 during the wall diagnosis. Here, the diagnostic result 109 may include, for example, the object position 115 and / or the object type 117 and / or the object depth 119 and / or the object extension 121 of the object 113 located in the wall 105 to be inspected, and / or the wall type 123 of the wall 105 to be inspected. The generated diagnostic result 109 may then be displayed on the display unit 111 of the measuring device 100.

[0089] According to one embodiment, in addition to radar data 103 from radar sensor unit 101, the aforementioned additional sensor information from the additional sensors is also considered in the wall diagnosis of diagnosis module 107. Preprocessing module 127 can accordingly preprocess the additional sensor information.

[0090] In the illustrated embodiment, the diagnosis module 107 includes a wall type classification module 129 and an object recognition module 131. The preprocessing module 127 includes a first preprocessing module 135 and a second preprocessing module 137. The first preprocessing module 135 includes an S-matrix reduction module 155. The second preprocessing module 137 includes a background correction module 157, an inverse fast Fourier transform 159, and a focus and shift module 161. When the radar data 103 is preprocessed by the preprocessing module 127, the radar data 103 is first preprocessed by the first preprocessing module 135 and the S-matrix reduction module 155 included in the first preprocessing module.

[0091] Here, the first preprocessing module 135 generates input data 133 based on the sensor data 103. This input data 133 serves as input data for the wall type classification module 129. Here, the wall type classification module 129 classifies the wall 105 to be inspected into a wall type based on the input data 133 and generates wall type information 139. The wall type information 139 includes the wall type 123 of the wall 105 to be inspected, which is determined in the wall type classification.

[0092] Subsequently, second preprocessing module 137 performs preprocessing based on radar data 103 and wall type information 139. Background correction 157 of radar data 103 is performed here, taking into account wall type 123 ascertained in wall type information 139. Depending on wall type 123 of wall 105 to be inspected, different effects may occur on radar data 103.

[0093] Background correction 157 can correct for these effects, which are primarily based on the respective wall type 123 and can affect object recognition. After background correction, further preprocessing can be performed by performing an inverse fast Fourier transform 159 or focusing and shifting 161, and new input data 133 for object recognition module 131 can be generated. Based on the input data 133 provided by second preprocessing module 137, object recognition module 133 recognizes objects 113 located in wall 105 to be inspected and determines at least object position 115 and object type 117 of the respective object 113. Object recognition module 131 can also determine object depth 119 and object extent 121.

[0094] According to one specific embodiment, the diagnostic module is further configured to determine an object depth of an object within the wall based on the radar data, wherein the object depth is defined by a distance of the object constructed in the wall from the surface of the wall.

[0095] Preprocessing is optional. Depending on the algorithm used by diagnostic module 107, completely unprocessed radar echoes with different frequencies can be used as radar data 103 and as input data for diagnostic module 107. Alternatively, radar data 103 processed through multiple steps can be preprocessed. Preprocessing steps include, for example, signal transformation from frequency space to time or range space, background removal, noise reduction, and normalization. For radar data 103 in complex form, only absolute values ​​can be processed. Alternatively or additionally, phase information can be considered.

[0096] Figure 3 A further schematic diagram of a measuring device 100 according to another specific embodiment is shown.

[0097] In the embodiment shown, the diagnostic module 107 comprises a plurality of processing paths 102 running in parallel. In each processing path 102 there is: a pre-processing module 127; a diagnostic module 107, which comprises, for example, a Figure 2 The wall type classification module 129 and / or object recognition module 131 described in the embodiment; and the post-processing module 163.

[0098] exist Figure 3 In the figure, radar data 103 is primarily shown as input data for wall diagnosis. However, in addition to the radar data shown, additional information from additional sensors can also be used as input data for wall diagnosis. Different information from different sensor types can be processed in separate, parallel processing paths 102, and corresponding wall diagnoses can be performed separately based on the different sensor information. After the wall diagnosis is completed, the summary of the individual analysis results can be combined into a wall diagnosis result 109 via a summary module.

[0099] Alternatively or additionally, different partial aspects of the wall diagnosis may also be performed by different processing paths 102 based on the same sensor information.

[0100] In this case, the various processing paths 102 can process, for example, different radar data 103 that were recorded for different positions of the measuring device 100 relative to the wall 105 during the movement of the measuring device 100 relative to the wall 105. Thus, the radar data 103 that map different areas of the wall 105 and were recorded sequentially in time during the movement of the measuring device 100 relative to the wall 105 can then be processed in the different processing paths 102 by the modules shown.

[0101] In this case, different processing paths perform independent wall diagnostics, which include at least determining an object position 115 and / or an object type 117 of an object 113 arranged in the wall 105 .

[0102] The partial results of the independent wall diagnosis of different areas of the wall 105 provided in each processing path 102 can be aggregated into a coherent Diagnostic result 109. A coherent diagnostic result describes a coherent spatial region that was scanned during the movement of measuring device 100 relative to wall 105 and mapped by the correspondingly recorded radar data 103. Therefore, parallel processing of radar data 103 or additional sensor information 104 from additional sensor elements in different processing paths 102 enables accelerated wall diagnosis.

[0103] Alternatively, different functions of the wall diagnosis can be implemented in different processing paths 102. Thus, for example, wall type classification and determination of wall type 123 of the wall to be inspected 105 can be implemented in one processing path 102. Object recognition of objects 113 arranged in the wall can be implemented in another processing path 102. In this case, object detection with determination of object position 115 and object classification with determination of object type 113 can be implemented in one processing path 102.

[0104] Alternatively, object detection and object classification can also be performed in two separate processing paths 102. In the other processing path 102, object depth determination, i.e., determination of object depth 119 and / or determination of object extent 121, can each be effected. In the aggregation module 165, the various partial results of the wall diagnosis can be aggregated into the corresponding diagnostic result 109.

[0105] Here, the diagnostic module 107 can be divided into different artificial intelligences 125, as has already been described. Figure 2As shown in the embodiment of FIG. Here, the diagnosis module 107 may include, for example, a wall type classification module 129 and an object recognition module 131. The object recognition module may be further divided into an object detection module and an object classification module. Furthermore, the diagnosis module 107 may also include an object depth determination module and an object extension scale module, which are configured to determine an object depth 119 and an object extension scale 121, respectively.

[0106] The corresponding modules can each be designed as a separate artificial intelligence 125, such as a neural network. Alternatively, the different modules can form parts of an overall artificial neural network, which are connected to form an overall neural network according to structures known from the prior art.

[0107] Figure 4 A schematic diagram shows a measurement of the measuring device 100 according to one embodiment.

[0108] For preprocessing, radar data 103 or additional sensor information 104 from other sensors is normalized, particularly for numerical stabilization in subsequent steps performed by diagnostic module 107 during wall diagnosis. For example, amplitude and / or offset compensation can be performed for this purpose. Furthermore, radar data 103 can be filtered to reduce interfering elements, and the corresponding sensor data can be downsampled to reduce the data rate. Furthermore, radar data 103 or additional sensor information 104 can be transformed into the required frequency or time range. Methods known from the prior art can be used for this purpose.

[0109] Furthermore, recorded radar data 103 or additional sensor information 104 can be divided into time or space windows 167. Here, time windows 167 can be generated by recording radar data 103 or additional sensor information or preprocessed radar data 103 over fixed time intervals. Conversely, space windows 167 can be generated by assigning radar data 103 or additional sensor information 104 to a position of measuring device 100 relative to wall 105 in direction of movement 153.

[0110] Figure 4 FIG. a) shows such a data matrix resulting from the above steps. The data matrix shown in FIG. a) in window 167 shows a plurality of sensor data, which may include, for example, radar data 103 or additional sensor information 104 from other sensors, and is plotted along a frequency channel axis 171 and along a space / time axis 169.

[0111] Here, the width of the time window 167 can be selected so that different sampling rates of the sensors can be balanced and a new window 167 can be provided frequently enough so that the diagnostic results 109 of the wall diagnosis can be displayed on the display unit 111 without excessive time delay while the measuring device 100 is performing the measurement or shortly after the measurement by the measuring device 100 ends.

[0112] For this purpose, a data recording rate of 2 to 20 windows per second of sensor data may be advantageous. For the spatial windows, the spatial sampling rate may be selected so as to achieve the desired local accuracy. Here, a sampling rate of 1 mm to 1 cm may be advantageous. This means that for every 1 mm to 1 cm of movement of the measuring device 100 in the direction of motion 153, corresponding sensor data is recorded.

[0113] The width of spatial window 167 can be selected such that coherent information about object 113 is contained in one window. Widths of 1 cm to 20 cm for each spatial window 167 may be advantageous. This results in 4 to 100 measured values ​​per window 167. This enables efficient further algorithmic processing of the corresponding recorded radar data 103 or additional sensor information by diagnostic module 107.

[0114] Here, once one or more sampling points are available, another time window 167 or space window 167 may be provided.

[0115] The diagnostic module 107 can be adapted so that as input data, for example also Figure 3 The input data of each processing path 102 in the embodiment of the present invention is recorded as a matrix corresponding to the window size of each space or time window 167. Here, according to Figure 2 In an embodiment, the corresponding input data may include respectively pre-processed sensor data, namely radar data 103 and additional sensor information 104 of the additional sensor.

[0116] As described above, the wall diagnosis can be performed by the diagnostic module 107 based on a correspondingly trained artificial intelligence. Alternatively, different processing paths can also be calculated by a rule-based algorithm. Artificial intelligence and rule-based algorithms can also be combined within the processing path 102 in a parallel or series connection.

[0117] The wall diagnosis result 109 can be represented as a numerical value, a vector, or a matrix. Furthermore, the probability of detection can be given for object detection, or the probability of a given object or wall type classification can be given for wall type classification or object classification. The same approach applies to position and / or depth determination, for which corresponding probability values ​​can also be given.

[0118] If, in addition to radar data 103 , additional sensor information from other sensor types is processed in a processing path 102 , these radar data and additional sensor information can be either aggregated within artificial intelligence 125 or combined by rule-based combination.

[0119] In the post-processing of each processing path 102, i.e. Figure 3 In the post-processing of the embodiment in , the summing module 165 can summarize the multiple algorithm results based on the multiple windows 167. This summing can be achieved in particular by taking a multiplier, summing, or by multiplying consecutive probability values.

[0120] Furthermore, by clustering a plurality of results, for example, a plurality of objects detected close to one another, it is possible to identify which objects are the same object, so that these objects are not mistakenly identified multiple times.

[0121] A weighting function 177 can also be multiplicatively applied when combining the results from multiple windows 167. Advantageously, the partial diagnostic results 175, which correspond to the corresponding data points in space, can be weighted with reference to their position relative to the center point of the respective window 167. This is illustrated by way of example in FIG. b), where individual partial diagnostic results 175 are weighted with reference to the center point of the illustrated window 167 according to the illustrated weighting function 177.

[0122] According to one embodiment, the result of one processing path 102 after post-processing 163 may influence the expansion of another processing path 102s. Here, a weighting parameter may be adjusted, which may be related to the corresponding result from the processing path 102 for each window.

[0123] For example, the result of the object classification for defining the object type 117 of an object arranged in the wall 105 can be used to increase the weight of the wall type classification for determining the wall type 123 of the corresponding wall 105 at locations where there are no objects 113 in post-processing, because the corresponding radar data 103 at these locations are less affected by the reflection of the object 113.

[0124] Figure 5 A further schematic diagram of a measuring device 100 according to another specific embodiment is shown.

[0125] Figure 5 Graphs a) and b) of FIG. 1 show two different alternatives for the joint data processing of radar data 103 and additional sensor information 104 by diagnostic module 107 .

[0126] FIG. a) illustrates the joint processing of radar data 103 and additional sensor information 104 from an additional sensor by diagnostic module 107. To this end, radar data 103 and additional sensor information 104 are jointly used as input data for diagnostic module 107, which is designed as an artificial intelligence, particularly an artificial neural network. Diagnostic module 107 includes a plurality of convolutional layers 108 and a plurality of dense layers 106. Radar data 103 and additional sensor information 104 are jointly processed as input data via these convolutional layers 108 and dense layers 106. Based on this, the aforementioned diagnostic result 109 is generated as output data from diagnostic module 107.

[0127] In contrast, in Figure b), radar data 103 and additional sensor information 104 are used as separate input data for diagnosis module 107. Diagnosis module 107 becomes a plurality of processing paths 102. Processing paths 102 each include a plurality of convolutional layers 108 and at least one dense layer 106. In different processing paths 102, diagnosis module 107 separately creates a wall diagnosis based on radar data 103 or additional sensor information 104.

[0128] The partial results of the partial diagnosis of the different processing paths 102 are combined in an additional connection layer 148 and then fed to the final dense layer 106. The output data of the diagnosis module 107 correspond to the diagnosis result 109 described above.

[0129] A correspondingly designed diagnostic module 107 is configured to carry out the above-described wall diagnosis with the above-described features based on the radar data 103 and the additional sensor information 104 .

[0130] In the embodiment shown, the diagnosis module 107 is designed as an artificial neural network, in particular as a convolutional network. A corresponding network structure with convolutional layers 108, dense layers 106 and connection layers 148 is known in the prior art.

[0131] Figure 6 A schematic diagram of a system 600 for generating a training dataset according to one embodiment is shown.

[0132] According to the present invention, to generate a training data set 143, sensor data 103, 104 is first recorded from at least one sensor unit 101 of a measuring device 100. To this end, a plurality of measurements can be performed by one measuring device 100 or by multiple measuring devices 100 on one wall 105 or on multiple different walls 105. During measurement 105, as described above, measuring device 100 can be moved along a direction of movement 153 along the wall 105 to be inspected and record corresponding sensor data 103, 104, which includes the wall 105 to be inspected and objects 113 that may be located therein. Sensor data 103, 104 can include radar data 103 and / or additional sensor information 104.

[0133] While measuring devices 100 are recording these sensor data 103, 104, position information 172 is determined for each measuring device 100 by position determination system 145. Position information 172 describes the position of measuring device 100 relative to wall 105, at which position measuring device 100 was positioned during the recording of sensor data 103, 104.

[0134] Position information 172 can then be integrated into sensor data 103 , 104 in order to thereby generate sensor data with position information.

[0135] Sensor data 103, 104 can be tagged based on position information 172. This position information 172 defines, for each piece of sensor data 103, 104, the position of measuring device 100 relative to wall 105 at the time the corresponding sensor data 103, 104 was recorded. When tagging sensor data 103, 104, ground truth information is provided for each piece of sensor data 103, 104. This ground truth information includes at least one piece of information indicating whether object 113 located in wall 105 is mapped by the corresponding sensor data 103, 104.

[0136] On the one hand, this ground truth information depends on whether object 113 is located in the wall to be inspected, as mapped by the corresponding sensor data. Furthermore, this ground truth information depends on whether object 113 located in wall 105 is located at object position 115, which at least partially corresponds to the position of measuring device 100 relative to wall 105 at the time the corresponding sensor data 103, 104 were recorded.

[0137] Additionally, the basic fact information may further include information about an actual object position 115 of object 113, and / or an object type 117 of object 113, and / or an object depth 119 of object 113, and / or an object extension 121 of object 113. Furthermore, the basic fact information may further include information about a wall type 123 of wall 105 to be inspected.

[0138] By labeling the sensor data 103 , 104 with respect to the basic fact information, each data is identified in relation to the basic fact information, thereby indicating at least whether the corresponding sensor data 103 , 104 maps the object 113 arranged in the wall 105 .

[0139] Labeling sensor data 103 , 104 here corresponds to identifying sensor data 103 , 104 with respect to corresponding basic factual information.

[0140] Position information 172 of position determination system 145 clearly defines for each sensor data 103, 104 the position of measuring device 100 relative to wall 105 at the time the corresponding sensor data 103, 104 was recorded. This allows, given knowledge of actual object position 115 of object 113 arranged in wall 105, to clearly and unambiguously label sensor data 103, 104 with respect to object position 115, i.e., whether the corresponding sensor data 103, 104 actually reflects object 113 arranged in wall 105.

[0141] The sensor data 103 , 104 labeled in this way are then assembled into a corresponding training data set 143 .

[0142] The labeling of the sensor data 103 , 104 , as well as the consideration of the position information 172 and the generation of the training data set 143 , can be performed by an external computing unit 170 .

[0143] Position determination system 145 may, for example, include a position sensor arranged on measuring device 100. The position of measuring device 100 relative to the wall can thus be determined via the position sensor.

[0144] Preferably, position determination system 145 includes a camera sensor positioned outside measuring device 100. Camera data can be recorded via this camera sensor, which reflects measuring device 100 during the recording of sensor data 103, 104. Therefore, the position of measuring device 100 relative to wall 105 during the recording of sensor data 103, 104 can be determined via this camera data.

[0145] The time stamp of the camera data allows the time-resolved determination of the position of measuring device 100 relative to wall 105. Thus, the respective position of measuring device 100 relative to wall 105 can be determined for multiple points in time. The time stamps of sensor data 103, 104 allow the points in time at which the corresponding sensor data 103, 104 were recorded by measuring device 100 to be determined.

[0146] Furthermore, in order to determine position information 172, a time synchronization of the camera data of the camera sensor and sensor data 103, 104 of measuring device 100 can also be performed. The time synchronization of the corresponding time stamps of sensor data 103, 104 and camera data makes it possible to assign the correct position information 172 to each sensor data 103, 104.

[0147] Figure 7 Another schematic diagram of a system 600 for generating a training dataset according to one embodiment is shown.

[0148] Figures a) and b) illustrate two camera data sets, i.e., two images or frames, from a camera sensor 147 of a position determination system 145. The images shown in Figures a) and b) show a wall 105. Position markers 148, in the form of ArUco / ChArUco posters 158, are located on the wall 105. Furthermore, a light switch 162, also defined as a position marker 148, is located on the wall. A door 160, also defined as a position marker 148, is located adjacent to the wall 105.

[0149] In addition, a measuring device 100 according to the present invention is arranged in FIG. The measuring device 100 can be moved in a direction of movement 153 to record the corresponding sensor data 103, 104, so that during the movement of the measuring device 100, a wall diagnosis can be performed on the spatial region of the wall 105 that the measuring device passes through.

[0150] According to one embodiment, position information 172, i.e., the position of measuring device 100 relative to wall 105 during the recording of sensor data, can be determined by using position marker 148 shown in FIG. By detecting position marker 148 and measuring device 100, the relative position of measuring device 100 relative to position marker 148 can be determined in the camera data. The relative position between measuring device 100 and position marker 148 determined in this way allows the position of measuring device 100 relative to wall 105 to be determined. Based on this, position information 172 can be generated accordingly.

[0151] Furthermore, in FIG. b), basic factual information about object 113 arranged in the wall is graphically presented in the area of ​​position marker 148 located in FIG. a) in the form of an ArUco / ChArUco poster 158. Here, this basic factual information includes at least the location of object 113 in wall 105.

[0152] In diagram b), a pipe is shown as object 113. This indicates that the corresponding information, namely object position 115, object type 117 and other information about object 113, is known as basic factual information.

[0153] The displayed ground truth information allows labeling of sensor data 103 , 104 recorded by the measuring device 100 in the area of ​​the ArUco / ChArUco poster 158 shown in FIG. a ), and thus generation of a corresponding data set.

[0154] Figure 8 A schematic diagram showing data recorded by the measuring device 100 is shown.

[0155] Figures a), b), and c) show various measuring surfaces 164 that define the spatial regions in which sensor data 103, 104 are recorded by moving measuring device 100 relative to wall 105. Here, measuring surface 164 can, for example, describe the surface of an ArUco / ChArUco poster 158.

[0156] Within the measuring surface 164, the measuring device 100 travels along a plurality of measuring tracks 166 in order to record the sensor data 103, 104. Along the measuring tracks 166, the sensor data 103, 104 are each recorded at different measuring points 168.

[0157] The measuring tracks 166 can be arranged mostly parallel to one another, as shown in FIG. a). In addition, the measuring tracks can also be arranged in a cross arrangement, as shown in FIG. b).

[0158] Position information 127 can be integrated with sensor data 103, 104 recorded at measuring points 168 along measuring trajectory 166 so that the position of measuring device 100 at the time of recording the corresponding sensor data 103, 104 can be determined for each measuring point 168 of different measuring trajectories 166. When measuring trajectories 166 intersect, already determined position information 162 can be reused. Furthermore, if measuring points 168 are closely adjacent to one another, the corresponding position information can be inferred based on the position information of adjacent measuring points 168.

[0159] By scanning the measuring surface 164 in this fine-grid manner in the illustrated measuring trajectory 166, due to the close spacing of the measuring points 168, a background correction can additionally be generated based on the sensor data 103, 104. Here, the background correction takes into account measurement signals that are reflected only by the wall 105 and have no influence on objects arranged in the wall 105. This allows for object determination by ascertaining changes in the sensor data 103, 104 recorded at different measuring points 168.

[0160] Figure 9 Another schematic diagram of a system 600 for generating a training data set 143 according to another embodiment is shown.

[0161] In the embodiment shown, the object detection system 145 comprises a camera sensor 147. The camera sensor 147 is arranged on a positioning device 156. The positioning device 156, in particular the camera sensor 147, is arranged remote from the wall 105. A position marker 149 in the form of an ArUco / ChArUco poster 158 is arranged on the wall 105. Figure 9 In FIG. 1 , the measuring device 100 is shown on the wall 105 in the area of ​​an ArUco / ChArUco poster 158 .

[0162] exist Figure 9 105 , the camera data recorded by the camera sensor 147 must be corrected for perspective in order to determine the position of the measuring device 100 relative to the wall 105 .

[0163] Perspective correction can be implemented using the mathematical relationship shown below:

[0164]

[0165] Here, E is the identity matrix, K is the camera matrix, which includes the camera data of the intrinsic parameters of the camera sensor 147, and T is the transformation vector, which describes the transformation of the world coordinate system to the camera coordinate system of the camera sensor 147. The terms u and v are pixel elements in the image plane. Here, the component X w , Y w , Z w Is the world coordinate of the world coordinate system. Component X c , Y c , Z c The camera sensor 147 is Figure 9 The coordinates of the camera coordinate system shown in .

[0166] Considering the matrix representation, the following equation is obtained:

[0167]

[0168] Here, f is the focal length of the camera sensor 147, r is the element of the rotation matrix R, and t is the element of the translation vector. A transformation calculation can then be performed to obtain the actual position of the camera sensor 147 in the world coordinate system. Here, the world coordinate system is represented by the ArUco / ChArUco poster 158. In order to convert the vector from the camera system to the world system, the following transformation relationship is required:

[0169]

[0170] Here, R is the rotation matrix. This association makes it possible to extract the real-world position and position information of the camera sensor 147 relative to the ArUco / ChArUco poster 158 from the camera data. For this purpose, the entire video or only individual frames of the camera data can be used. Furthermore, the position and position of the measuring device 100 mapped by the camera data can be converted through another vector-based transformation relationship. A vector relationship based on the image is generated, which should be solved by 3D projection. For this purpose, the positions in the camera data, that is, the points, must be converted into positions in the world coordinate system, and then the required vectors are calculated based on these positions. This is achieved in the following way:

[0171]

[0172] Finally, a vector x is obtained, which describes the transformation from the projected position of measuring device 100 in the camera data to the actual position of measuring device 100 in space, ie relative to wall 105 .

[0173] This association is Figure 9 is graphically displayed in .

[0174]

[0175] Here, C w is the camera coordinate of the camera sensor 147 in the world coordinate system, D w are the device coordinates of measuring device 100 in the world coordinate system, wherein the illustrated relationship shows the transformation of camera coordinates into the device coordinates of measuring device 100. In this approach, the accuracy of determining the position of measuring device 100 relative to wall 105 depends critically on the calibration quality of camera sensor 147 and the unambiguous identification of the position landmarks. Therefore, it may be advantageous to calibrate camera sensor 147 before executing the method and to perform sufficient test recordings to ensure that the identification of the position landmarks is reliable.

[0176] By implementing the above-described method, the position of measuring device 100 relative to wall 105 can be determined at each point in time. This can be used to assign sensor data 103, 104 recorded by the measuring device during the measurement to these positions of measuring device 100 relative to wall 105. In particular, multiple measurements can be combined into a measurement sequence and advantageously processed together.

[0177] Figure 10 A flow chart of a method 300 for generating a training data set 143 according to one embodiment is shown.

[0178] To generate a training data set 143 for training an artificial intelligence 125 for operating a measuring device 100, in particular a wall diagnosis device, sensor data 103, 104 are first recorded from at least one sensor unit 101 of the measuring device 100 in a first method step 301. The sensor data 103, 104 are mapped to a wall 105 to be diagnosed.

[0179] In a further method step 303, the position of measuring device 100 relative to wall 105 is determined, and sensor data 103, 104 with position information are generated by position determination system 145. During the position determination, each recorded sensor data 103, 104 is assigned a piece of position information 172. Position information 172 defines the position of measuring device 100 relative to wall 105 at which measuring device 100 was located relative to wall 105 at the time of the corresponding sensor data 103, 104.

[0180] According to one embodiment, position determination system 145 includes at least one camera sensor 147 and at least one position marker 149. Position marker 149 is formed on the surface of wall 105, and camera sensor 147 is arranged at a predefined viewing angle relative to wall 105.

[0181] Therefore, here, first in method step 309 , camera data of camera sensor 147 are recorded temporally during the recording of sensor data 103 , 104 by measuring device 100 , wherein these camera data map measuring device 100 positioned on wall 105 and position marker 149 arranged on wall 105 .

[0182] In method step 311 , the relative position of the measuring device relative to position marking 149 is ascertained based on the camera data.

[0183] Subsequently, in method step 315 , a time synchronization is carried out between the recorded sensor data 103 , 104 of measuring device 100 and the recorded camera data of camera sensor 147 .

[0184] Next, in method step 317 , for each sensor data item, position information 172 is determined taking into account the time synchronization, which defines the position of measuring device 100 relative to wall 105 at the time of recording of sensors 103 , 104 .

[0185] Next, in method step 313 , the position of measuring device 100 relative to wall 105 is ascertained.

[0186] For this purpose, in method step 319 , the viewing angle of camera sensor 107 relative to wall 105 is ascertained based on a predefined viewing angle position of camera sensor 147 relative to wall 105 .

[0187] Subsequently, in method step 321 , a perspective correction is performed based on the relative position of measuring device 100 relative to position marker 149 determined based on the camera data in order to take into account the perspective position of camera sensor 147 relative to wall 105 .

[0188] Subsequently, in a further method step 305 , the sensor data 103 with position information is labeled taking into account basic fact information and labeled sensor data 103 , 104 are generated. The basic fact information here includes at least one piece of information about the presence of at least one object 113 in wall 105 .

[0189] In a further method step 307 , labeled sensor data 103 , 104 are combined to form a training data set 143 .

[0190] Figure 11 A further flow chart of a method 300 for generating a training data set 143 according to another specific embodiment is shown.

[0191] In order to train the artificial intelligence 125 of the measuring device 100 for wall diagnosis, in method step 401 , a training data set 143 is first provided by carrying out the method 300 for generating a training data set 143 according to one of the above embodiments.

[0192] In a further method step 403 , artificial intelligence 125 is trained based on training data set 143 to carry out object recognition of object 113 formed in wall 105 , wherein object recognition includes at least object detection.

[0193] Figure 12 A schematic diagram of a computer program product 500 is shown, which includes instructions which, when executed by a data processing unit, cause the data processing unit to carry out the method 300 for generating a training data set 143 .

[0194] In the embodiment shown, the computer program product 500 is stored on a storage medium 501. In this case, the storage medium 501 may be any storage medium known from the prior art.

Claims

1. A computer-implemented method (300) for generating a training data set (143) for training an artificial intelligence for operating a measuring device (100), in particular a wall diagnostic device, comprising: Recording (301) sensor data (103) of at least one sensor unit (101) of the measuring device (100), wherein the sensor data (103) is mapped to a wall (105) to be diagnosed; carrying out (303) determining the position of the measuring device (100) relative to the wall (105) and generating sensor data (103) with position information by a position determination system (145), wherein, in the position determination, each recorded sensor data (103) is assigned a piece of position information (172), wherein the position information (172) defines the position of the measuring device (100) relative to the wall (105) at which the measuring device (100) was positioned relative to the wall (105) at the time of recording the sensor data (103); Tagging (305) the sensor data (103) with position information taking into account ground truth information and generating the tagged sensor data (103), wherein the ground truth information includes at least one piece of information about the presence of at least one object (113) in the wall (105); and The labeled sensor data (103) is aggregated (307) into a training dataset (143).

2. The method (300) of claim 1, wherein: The basic fact information includes: classification information about the object position (115) of the object (113) and / or the object type (117) of the object (113), and / or object depth information about the object depth (119) inside the wall (105), and / or object extension scale information about the object extension scale (121) of the object (113).

3. The method (300) according to any one of the preceding claims, wherein: The position determination system (145) comprises at least one camera sensor (147) and at least one position marker (149), wherein the position marker (149) is formed on the surface of the wall (105), wherein the camera sensor (147) is arranged in a predefined viewing angle position relative to the wall (105), wherein the implementation (303) of the position determination of the measuring device (100) relative to the wall (105) comprises: The measuring device (100) records camera data of the camera sensor (147) during the recording of the sensor data (103) of the sensor unit (101), wherein the camera data maps the measuring device (100) positioned on the wall (105) and the position marker (149) arranged on the wall (105); determining (311) the relative position of the measuring device (100) relative to the position marker (149) based on the camera data; and The position of the measuring device (100) relative to the wall (105) is determined (313) based on the relative position.

4. The method (300) according to any one of the preceding claims, wherein: Said implementation (303) of said position determination further comprises: performing (315) time synchronization between the recording of the sensor data (103) by the sensor unit (101) and the recording of the camera data by the camera sensor (147); and Taking into account the time synchronization, the position information (172) of the measuring device (100) relative to the wall (105) is determined (317) for each sensor data (103) of the sensor unit (101).

5. The method (300) according to any one of the preceding claims, wherein: The determining (313) of the position further comprises: Determining (319) a viewing angle of the camera sensor (147) relative to the wall (105) based on a predefined viewing angle position at which the camera sensor (147) is arranged relative to the wall (105); Based on the relative position of the measuring device (100) with respect to the position mark (149) determined based on the camera data (147), a perspective correction (321) is performed to take into account the perspective position of the camera sensor with respect to the wall, and the position of the measuring device (100) on the wall (105) is determined based on the perspective correction.

6. The method (300) according to any one of the preceding claims, wherein: The position identifier (149) is designed as an ArUco identifier (158) or a ChArUco identifier (158).

7. The method (300) according to any one of the preceding claims, wherein: The position markers (149) are formed by markers constructed on the wall (105) and include: wallpaper patterns, light switches (162), sockets, windows, and furniture.

8. The method (300) according to any one of the preceding claims, wherein: The camera sensor (147) is arranged on a positioning device (156), wherein the camera sensor (147) is positioned in a predetermined viewing angle position relative to the wall (105) via the positioning device (156).

9. A training data set (143) for training an artificial intelligence (125) of a measuring device (100) for wall diagnostics, wherein: The training data set (143) is generated by a method (300) for generating a training data set (143) according to any one of claims 1 to 8, which is used to train an artificial intelligence (125) for operating a measuring device (100).

10. A computer-implemented method (400) for training an artificial intelligence (125) of a measurement device (100) for wall diagnostics, the method comprising: Providing (401) a training data set (143) by implementing the method (300) for generating a training data set (143) according to any one of claims 1 to 8; The artificial intelligence (125) is trained (403) based on the training data set (143) for performing object recognition of an object (113) constructed in a wall (105), wherein the object recognition includes at least object detection.

11. A computing unit (151) configured to implement the method (300) for generating a training data set (143) according to any one of claims 1 to 8 and / or the method (400) for training an artificial intelligence (125) of a measuring device (100) according to claim 10, wherein the training data set (143) is used to train an artificial intelligence (125) for operating a measuring device (100).

12. A computer program product (500) comprising instructions which, when executed by a data processing unit, cause the data processing unit to implement the method (300) for generating a training data set (143) according to any one of claims 1 to 8 and / or the method according to claim 1. The method (400) for training an artificial intelligence (125) of a measuring device (100) according to claim 10, The training data set (143) is used to train an artificial intelligence (125) for operating the measuring device (100).

Images