Method for generating training data set, training data set, computing unit and 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: receiving (301), by a classifier module (183), unclassified sensor data (172) of at least one sensor unit (101) of the measuring device (100); classifying (303) the unclassified sensor data (172) by implementing a classifier module (183) on the unclassified sensor data (172) and providing classified sensor data (174); and adding (305) the classified sensor data (174) to a training data set (143). The invention also relates to a training data set, 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 artificial intelligence for a wall diagnosis device.

[0002] The invention further relates to a training data set, 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.

[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, the method comprising:

[0007] receiving, by a classifier module, unclassified sensor data of at least one sensor unit of the measuring device, wherein the sensor data maps a wall to be diagnosed, the wall having an object of an object type arranged in an object position in the wall;

[0008] classifying the unclassified sensor data by executing a classifier module on the unclassified sensor data and providing the classified sensor data, wherein the classifier module is designed as an artificial intelligence and is configured to perform object recognition based on the unclassified sensor data and to determine an object position and / or an object type of an object and to classify the unclassified sensor data with respect to the object position and / or the object type; and

[0009] Add the classified sensor data to the training dataset.

[0010] This provides the following technical advantage: an improved method for generating a training dataset for training an artificial intelligence for operating a measuring device, particularly a wall diagnostic device, can be provided. To this end, a classifier module generates classified sensor data based on unclassified sensor data and adds this classified sensor data to the training dataset. Both the unclassified and classified sensor data represent a wall to be inspected by the measuring device, the wall including at least one object of an object type positioned in an object position within the wall.

[0011] Here, the classifier module classifies the unclassified sensor data with respect to the object position and / or object type of objects located in the wall. The classifier module is constructed as an artificial intelligence and is configured to perform object recognition based on the unclassified sensor data, including determining the object position and / or object type, for objects located in the wall mapped by the sensor data, and to classify the unclassified sensor data with respect to the object position and / or object type based on the object recognition. This allows for automatic classification of the unclassified sensor data. The classified sensor data is labeled sensor data within the context of the present application, as is known in the art of machine learning.

[0012] According to one embodiment, the unclassified sensor data include two-dimensional unclassified radar data, wherein a classifier module is trained based on the unclassified radar data and taking into account classification additional information in order to generate radar data classified with respect to object position and / or object type, wherein the classified sensor data include the classified radar data and a mapping of a wall with objects constructed therein with respect to two spatial dimensions, wherein the classification additional information includes information about the object position and / or object type with respect to a third spatial dimension.

[0013] This results in the following technical advantages: improved object recognition by the classifier module and, associated therewith, improved classification of unclassified sensor data by the classifier module can be achieved. Reliable object recognition by the classifier module can be achieved by training the classifier module based on classified sensor data. Incorporating additional classification information can further improve object recognition by the classifier module and the classification of unclassified sensor data based on this object recognition.

[0014] According to one embodiment, the classified additional information is generated by applying further artificial intelligence to the classified two-dimensional radar data, wherein the further artificial intelligence is trained to determine the object position and / or object type related to three spatial dimensions based on the classified two-dimensional radar data.

[0015] This results in the technical advantage that the use of further artificial intelligence to generate the classification additional information makes it possible to provide meaningful classification additional information, with the aid of which the training of the classifier module can be carried out.

[0016] According to one embodiment, two spatial dimensions of classified and / or unclassified two-dimensional radar data are defined by first and second directions pointing perpendicularly to each other and parallel to the surface of a wall mapped by the radar data, wherein a third spatial dimension is given by a third direction perpendicular to the first and second directions and toward the wall, wherein the classified and / or unclassified radar data describe data of a plurality of scanning processes of a measuring device performed side by side along the second direction and along the first direction, wherein during these scanning processes the measuring device moves relative to the wall along the first direction and records radar data, wherein the radar data include information about the signal strength along the third direction toward the wall.

[0017] This provides the following technical advantage: the wall to be inspected is mapped in three spatial dimensions using radar data. Within the meaning of this application, a scanning process of the measuring device refers to measurements performed by the measuring device while the measuring device is moving relative to the wall in a first direction. Radar data of the wall is recorded as the measuring device moves relative to the wall. The radar data includes signal information in a third direction toward the wall. Thus, by arranging multiple scanning processes along a second spatial direction, three-dimensional information about the wall to be inspected can be obtained.

[0018] According to one embodiment, the classification includes:

[0019] The object position along the first direction is determined based on the information regarding the signal strength along the third direction, wherein the object position is defined as a position along the first direction having a maximum signal strength along the third direction.

[0020] This provides the following technical advantages: the object position along the first direction can be accurately determined. By interpreting the object position along the first direction as the position with the maximum signal strength along the third direction, accurate object detection can be achieved based on radar data.

[0021] According to one embodiment, the classification additional information includes information related to the signal strength along the third direction.

[0022] This results in the following technical advantage: persuasive additional classification information can be provided.

[0023] According to one embodiment, the classified and / or unclassified radar data is displayed as a two-dimensional plane diagram. The data from a plurality of scanning processes are combined in these plan views, wherein the determination of the object position is carried out jointly for a plurality of scanning processes.

[0024] This results in the technical advantage that radar data can be processed more simply by the classifier module.

[0025] According to one specific embodiment, the classifier module is designed as a neural network.

[0026] This provides the following technical advantages: a powerful and reliable classifier module can be provided.

[0027] According to one specific embodiment, the sensor data are also classified with regard to the object depth and / or the object extent of the object.

[0028] This results in the technical advantage that additional information from the training data set relating to further features of the object arranged in the wall to be inspected can be taken into account in the training of the diagnosis module and thus in its wall diagnosis.

[0029] According to one embodiment, the object category of the object type of the object includes: metal / non-metallic objects, cables for low voltage, cables with single-phase AC signals, cables with multi-phase AC signals, wooden brackets, metal brackets, plastic pipes, plastic pipes filled with water (such as tap water pipes), plastic pipes not filled with water (such as sewage pipes), and / or the wall type category of the wall type of the wall includes: concrete wall, light structure / dry structure wall, brick wall and / or brick stone of the wall, floor heating facility, wall heating facility.

[0030] This results in the following technical advantages: a large number of different objects of different object types can be identified or classified. The measuring device or diagnostic module can be trained to detect and classify typical objects built into building walls. This enables particularly precise wall diagnostics, in which detected objects can be precisely and unambiguously assigned to the corresponding object class.

[0031] Precise object classification and providing the user with corresponding classification information via the display unit enables the most convincing possible wall diagnosis. Knowing not only where the object is located within the wall but also the object type of the detected object, the user can accordingly decide how to further process the wall with respect to the detected object. Therefore, providing the object type of the detected object classification is a key area of ​​wall diagnosis, as the user can adjust the planned wall processing accordingly based on the given object type.

[0032] 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.

[0033] 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.

[0034] 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

[0035] Embodiments of the present invention will be described with reference to the following drawings. The drawings show:

[0036] Figure 1 A schematic diagram of a measuring device according to one embodiment;

[0037] Figure 2 Another schematic diagram of a measuring device according to another embodiment;

[0038] Figure 3 Another schematic diagram of a measuring device according to another embodiment;

[0039] Figure 4 Schematic diagram of a measurement of a measuring device according to one embodiment;

[0040] Figure 5 Another schematic diagram of a measuring device according to another embodiment;

[0041] Figure 6A schematic diagram of a system for generating a training dataset according to one embodiment;

[0042] Figure 7 A flowchart of a method for generating a training data set according to one embodiment;

[0043] Figure 8 Graphical display of two-dimensional plots of radar data;

[0044] Figure 9 Graphical display of two-dimensional plots of radar data; and

[0045] Figure 10 Schematic diagram of a computer program product. DETAILED DESCRIPTION

[0046] Figure 1 A schematic diagram of a measuring device 100 according to one embodiment is shown.

[0047] 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.

[0048] 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.

[0049] 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.

[0050] 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.

[0051] 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.

[0052] 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.

[0053] 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.

[0054] 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.

[0055] 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.

[0056] 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.

[0057] 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.

[0058] In typical use, measuring device 100 is placed on the surface of a wall 105 to be inspected. Radar signals are transmitted toward wall 105 via radar sensor unit 101, and radar signals reflected by wall 105 or objects 113 positioned 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.

[0059] 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.

[0060] 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.

[0061] 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.

[0062] 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.

[0063] 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.

[0064] 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.

[0065] 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.

[0066] 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.

[0067] 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.

[0068] 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.

[0069] The material of object 113 , for example metallic or non-metallic, can be refined and classified, for example, by using additional sensor information.

[0070] Figure 2 A further schematic diagram of a measuring device 100 according to another specific embodiment is shown.

[0071] 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.

[0072] 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.

[0073] 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.

[0074] 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.

[0075] 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.

[0076] 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.

[0077] 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.

[0078] 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 a surface of the wall.

[0079] 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.

[0080] Figure 3 A further schematic diagram of a measuring device 100 according to another specific embodiment is shown.

[0081] 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.

[0082] exist Figure 3In 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.

[0083] 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.

[0084] 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.

[0085] 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 .

[0086] 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.

[0087] 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.

[0088] 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.

[0089] Here, the diagnostic module 107 can be divided into different artificial intelligences 125, as has already been described. Figure 2 As 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.

[0090] 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.

[0091] Figure 4 A schematic diagram shows a measurement of the measuring device 100 according to one embodiment.

[0092] 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.

[0093] 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.

[0094] Figure 4FIG. 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.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] Here, once one or more sampling points are available, another time window 167 or space window 167 may be provided.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] Figure 5 A further schematic diagram of a measuring device 100 according to another specific embodiment is shown.

[0109] 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 .

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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 .

[0114] 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.

[0115] Figure 6 A schematic diagram of a system 600 for generating a training dataset 143 according to one embodiment is shown.

[0116] In the illustrated embodiment, the system for generating training data set 143 includes at least one classifier module 183. Classifier module 183 is configured as a trained artificial intelligence and is configured to generate classified sensor data 174 for training data set 143 based on unclassified sensor data 172. Classifier module 183 is trained to perform object recognition based on unclassified sensor data 172 for objects 113 located in wall 105 mapped by sensor data 172. Object recognition includes object detection, which determines an object position 115 of each object 113, and / or object classification, which determines an object type 117 of each object 113.

[0117] In the embodiment in FIG. b), in addition to the classifier module 183, the system 600 also includes a further artificial intelligence 132. The further artificial intelligence 132 is trained here to determine the classification additional information 130 based on the classified radar data 128. The classified radar data 128 here map the wall 105 to be inspected and the objects 113 arranged in the wall. Here, the classified radar data 128 are classified at least with respect to the object position 115 and / or the object type 117 of the objects 113 arranged in the mapped wall 105. Here, the classified radar data 128 are in two-dimensional form and include a plurality of scanning processes of the measuring device 100 along a first spatial direction, wherein the plurality of scanning processes are arranged side by side along a second direction. Here, the first and second directions are along Figure 1 The X or Y axis of the coordinate system extends and is therefore arranged parallel to the surface of the wall 105 to be inspected.

[0118] Although applied to two-dimensional radar data 128, further artificial intelligence 132 is trained to determine object position 115 of object 113 arranged in wall 105 in three spatial directions X, Y, Z. Classification additional information 130 generated by further artificial intelligence 132 describes object position 115 and / or object type 117 in relation to a third spatial direction. In this case, the third spatial direction is along Figure 1 The Z-axis of the coordinate system shown in is oriented so as to extend into the mapped wall 105 .

[0119] The further artificial intelligence 132 is trained to determine object recognition in all three spatial directions of an object 113 arranged in a wall 105 mapped by the radar data 128 based on the classified radar data 128. Therefore, the further artificial intelligence 132 is configured to determine the relative position of the object 113 based on the two-dimensional classified radar data 128. Figure 1 The object position 115 relative to the three spatial directions X, Y, and Z of the coordinate system shown in FIG.

[0120] Here, classifier module 183 is trained based on unclassified radar data 126, taking into account the classified additional information 130 provided by further artificial intelligence 132. Unclassified radar data 126 is again two-dimensional and includes multiple radar data sets recorded during multiple scanning processes 140. Scanning processes 140 describe measurements performed by measuring device 100, wherein measuring device 100 moves relative to wall 105 to be inspected along a first spatial direction X, while recording radar data 103. The scanning processes are performed at different locations on wall 105 arranged along a second spatial direction Y. This allows a two-dimensional spatial region of wall 105 to be inspected and mapped using the corresponding recorded radar data. To this end, the data recorded during multiple different scanning processes 140 are arranged side by side along second spatial direction Y and combined into two-dimensional radar data.

[0121] Based on two-dimensional unclassified radar data 126 and taking into account classification additional information 130, classifier module Z is trained according to a training method known from the prior art to generate classified radar data 128. Radar data 128 classified by correspondingly trained classifier module 183 are classified at least with respect to object position 115 and / or object type 117 of object 113.

[0122] Classified radar data 128 used in diagram b) for training further artificial intelligence 132 and classified radar data 128 generated during training classifier module 183 do not have to be the same radar data but may represent different data.

[0123] Unclassified radar data 126 used to train classifier module 183 may be generated by a plurality of different measurements performed by a plurality of different measurement devices 100 .

[0124] Figure 7 A flow chart of a method 300 for generating a training data set 143 according to one embodiment is shown.

[0125] To generate training data set 143, in a first method step 301, unclassified sensor data 172 of at least one sensor unit of measuring device 100 is first received by classifier module 183. Sensor data 172 represents wall 105 to be diagnosed and objects 113 arranged therein. Sensor data 172 may include radar data 103 and additional sensor information 104.

[0126] In a further method step 303, classifier module 183 classifies unclassified sensor data 173 and generates classified sensor data 174. Classifier module 183 is designed as a correspondingly trained artificial intelligence and is configured to perform object recognition based on unclassified sensor data 172 and to determine object position 115 and / or object type 117 of object 113. Based on the object recognition, classifier module 183 is configured to perform a corresponding classification of unclassified sensor data 172 with respect to object position 115 and / or object type 117 of object 113.

[0127] According to one embodiment, unclassified sensor data 172 is two-dimensional unclassified radar data 126. Classifier module 183 is trained based on the unclassified radar data to generate radar data 128 classified with respect to object position 115 and / or object type 117. Unclassified radar data 126 and classified radar data 128 comprise two-dimensional radar data and map wall 105 to be inspected with reference to a first spatial direction X and a second spatial direction Y arranged perpendicular thereto. In this embodiment, first and second spatial directions X, Y are parallel to the surface of wall 105. Additional classification information 130 includes information regarding object position 115 and / or object type 117, which is associated with a third spatial direction Z arranged perpendicular to first and second spatial directions X, Y.

[0128] According to one embodiment, classification information 130 is generated by executing further artificial intelligence 132 on classified two-dimensional radar data 128. Further artificial intelligence 132 is trained to determine object position 115 and / or object type 117 relative to the three spatial dimensions X, Y, and Z based on classified two-dimensional radar data 128.

[0129] Here, classified and / or unclassified radar data 126, 128 include data from a plurality of scanning processes 140 of measuring device 100, performed side by side in a second direction Y and extending in a first direction X. Here, scanning processes 140 of measuring device 100 describe measurements performed by measuring device 100 while measuring device 100 is moving in the first direction X, wherein corresponding radar data 103 are recorded during these measurements. Here, radar data 103 include information about the signal strength in a third spatial direction toward wall 105.

[0130] Classification 303 here comprises, in a further method step 307 , determining an object position 115 along the first direction X based on information about the signal strength along the third direction Z, wherein the object position 115 is defined as the position along the first direction X which has a maximum signal strength along the third direction Z.

[0131] In a further method step 305 , the sensor data 174 classified by the classifier module 183 are combined to form a training data set 143 .

[0132] Figure 8 A graphical representation of a two-dimensional plot 142 of radar data 103 is shown.

[0133] Figure 8 A plot 142 of two-dimensional radar data 103 is shown. Plot 142 shows radar data relative to a first spatial direction X, which extends parallel to the surface of wall 105 to be inspected, and along a third spatial direction Z, which extends toward the wall. Plot 142 also shows a measurement signal 146. Measurement signal 146 is arranged along the first spatial direction X. The signal strength of measurement signal 146 is plotted along the third spatial direction Z. Plot 142 also shows an envelope curve 144 of the signal strength.

[0134] According to one embodiment, object position 115 of object 113 located in wall 105 mapped by radar data of plan view 142 along first spatial direction X can be determined based on the signal strength of measurement signal 146 in third spatial direction Z. Therefore, object position 115 of object 113 along first spatial direction X, as indicated by measurement signal 146, can be identified as the position along first spatial direction X at which the signal strength of measurement signal 146 with respect to third spatial direction Z reaches a maximum. This maximum is indicated by the peak of envelope curve 144. The corresponding object position 115 with respect to first direction X is indicated by an X symbol within plan view 142.

[0135] Figure 9 A graphical representation of a two-dimensional plot 142 of radar data 103 is shown.

[0136] Figure 9 Another plan view 142 is shown. Plan view 142 shows radar data extending along a first spatial direction X and along a second spatial direction Y. Plan view 142 again shows a measurement signal 146 .

[0137] Plane map 142 is constructed by a plurality of scanning processes 140 arranged side by side in a second spatial direction Y. Scanning processes 140 extend in a first spatial direction X. Therefore, to create plane map 142, radar data is recorded during the execution of a plurality of scanning processes 140 by moving measuring device 100 in first direction X and recording radar data 103 during this process. To generate a plurality of scanning processes 140, measuring device 100 is arranged at different positions in second spatial direction Y. Starting from these positions, measuring device 100 is moved in first spatial direction X to record the data of scanning processes 140.

[0138] Figure 10 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 .

[0139] 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: Unclassified sensor data (172) of at least one sensor unit (101) of a measuring device (100) are received (301) by a classifier module (183), wherein the sensor data (172) represent a wall (105) to be diagnosed, the wall (105) to be diagnosed having an object (113) of an object type (117) arranged in an object position (115) in the wall (115); The unclassified sensor data (172) are classified (303) by executing the classifier module (183) on the unclassified sensor data (172) and providing classified sensor data (174), wherein the classifier module (183) is designed as an artificial intelligence and is configured to perform object recognition based on the unclassified sensor data (172) and to determine the object position (115) and / or the object type (117) of the object (113) and to classify the unclassified sensor data (172) with respect to the object position (115) and / or the object type (117); and The classified sensor data (174) is added (305) to the training dataset (143).

2. The method (300) of claim 1, wherein: The unclassified sensor data (172) comprises two-dimensional unclassified radar data (126), wherein the classifier module (183) is trained based on the unclassified radar data (126) and taking into account classification additional information (130) to generate radar data (128) classified with respect to the object position (115) and / or the object type (117), wherein the classified sensor data (174) comprises the classified radar data (128) and a mapping of the wall (105) with respect to two spatial dimensions, the wall having an object (113) constructed in the wall (105), wherein the classification additional information (130) comprises information with respect to the object position (115) and / or the object type (117) with respect to a third spatial dimension.

3. The method (300) according to claim 1 or 2, wherein: The classified additional information (130) is generated by applying a further artificial intelligence (132) to the classified two-dimensional radar data (128), wherein the further artificial intelligence (132) is trained to determine the object position (115) and / or the object type (117) in relation to three spatial dimensions based on the classified two-dimensional radar data (128).

4. The method (300) according to claim 3, wherein: Two spatial dimensions of the classified and / or unclassified two-dimensional radar data (126, 128) are defined by first and second directions (X, Y) pointing perpendicular to each other and parallel to the surface of the wall (105) mapped by the radar data (126, 128), wherein a third spatial dimension is given by a third direction (Z) perpendicular to the first and second directions (X, Y) and pointing toward the wall (105), wherein the classified and / or unclassified radar data (126, 128) describe data of a plurality of scanning processes (140) of the measuring device (100) performed side by side along the second direction (Y) and along the first direction (X), wherein during the scanning processes (140), the measuring device (100) moves relative to the wall (105) along the first direction (X) and records radar data (103), wherein the radar data (103) include information about signal strength along the third direction (Z) toward the wall (105).

5. The method (300) according to any one of the preceding claims, wherein: The classification (303) comprises determining (307) the position of the object (115) along the first direction (X) based on information about the signal strength along the third direction (Z), wherein the object position (115) is defined as a position along the first direction (X) having a maximum signal strength along the third direction (Z).

6. The method (300) according to any one of the preceding claims 2 to 5, wherein: The classification additional information (130) includes information related to the signal strength along the third direction (Z).

7. The method (300) according to any one of the preceding claims, wherein: The classified and / or unclassified radar data (126, 128) are displayed as two-dimensional plots (142), into which the data of a plurality of scanning processes (140) are combined, wherein the determination of the object position (115) is carried out jointly for the plurality of scanning processes (140).

8. The method (300) according to any one of the preceding claims, wherein: The unclassified sensor data (172) are also classified with respect to the object depth (119) and / or the object extent (121) of the object (113).

9. The method (300) according to any one of the preceding claims, wherein: The object categories of the object type (117) of the object (113) include: metal / non-metal objects, cables for low voltage, cables with single-phase AC signals, cables with multi-phase AC signals, wooden brackets, metal brackets, plastic pipes, plastic pipes filled with water, such as tap water pipes, plastic pipes not filled with water, such as sewage pipes, and / or wherein the wall type categories of the wall type (123) of the wall (105) include: concrete walls, light structure / dry structure walls, brick walls and / or brick and stone walls, floor heating facilities, wall heating facilities.

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

11. A computing unit (151) configured to implement a method (300) for generating a training data set (143) according to any one of claims 1 to 9 for training 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 a method (300) for generating a training data set (143) according to any one of claims 1 to 9 for training an artificial intelligence (125) for operating a measuring device (100).

Images