Detection method and system for detecting a building part on a construction site

Abstract

The invention relates to a system and detection method for detecting a building part (9) on a construction site (2), comprising the following steps: i) acquiring at least one camera image of the construction site (2) at an acquisition position (P1, P2); ii) generating data points (19) in a three-dimensional coordinate system (20), the data points (19) representing the construction site (2); iii) recognizing data points (19) belonging to a formwork element (7) which is arranged in a forming position; iv) determining, in a stored building model (23), the visible area (22) of a building part (9) to be erected that is visible from the acquisition position (P1, P2) according to a current construction progress; v) assigning the data points (19) belonging to the formwork element (7) to the visible area (22) of the building part (9) to be erected when the formwork element is arranged in the forming position for erecting the building part (9); and vi) detecting the building part (9) when a specified number of data points (19) belonging to the formwork element (7) are assigned to the visible area (22) of the building part (9) to be erected.

Description

[0001] Detection method and system for detecting a building component on a construction site

[0002] The invention relates to a detection method and a system for detecting a building component on a construction site, particularly during the shell construction phase. Furthermore, the invention relates to a method for monitoring the construction progress of a building, particularly during the shell construction phase.

[0003] With the help of technical monitoring of a structure, it is possible to determine during the construction phase whether a specified construction schedule is being adhered to or whether construction errors have occurred. The actual structure can be recorded using cameras or other sensors and compared with a plan or model of the structure. Based on this comparison, the construction progress can be determined and potential construction errors can be identified.

[0004] Adhering to the construction schedule and identifying and avoiding construction errors are essential for the successful construction of buildings. Construction errors lead to increased costs due to the need to correct them and can, in turn, cause delays, which can further negatively impact costs due to delayed acceptance and commissioning of the building. Until now, construction errors and construction progress have usually been identified during inspections and documentation by specialists, which takes time and personnel. Therefore, many companies need to be able to identify construction errors and construction progress automatically and without human intervention.

[0005] One way to obtain information about a building during construction is to use wireless sensor units that are attached directly to the work equipment on the construction site. Such sensor units are known, for example, from WO 2020 / 038949 A1. Depending on the design, the sensor units can, for example, transmit the spatial position of the work equipment or measured values ​​such as temperature, humidity and pressure via a radio system. The disadvantage is that the sensor units are directly exposed to the harsh environmental conditions on the construction site, which can lead to failures of the sensor units and corrupted measurement data. Furthermore, in addition to a stable radio connection, a reliable power supply for the sensor units must also be guaranteed. A further disadvantage of wireless sensor units is the effort required to attach, dismantle and maintain the sensor units.Furthermore, theft is a problem on construction sites. Another disadvantage is that systems with wireless sensor units are usually developed and optimized for specific applications. Adapting the sensor units for other applications is usually very complex.

[0006] When it comes to recording the construction progress of a building, camera-based systems are considerably more flexible and easier to handle. While these systems are not capable of directly providing measurement data such as temperature, humidity, or pressure on structural components, they do provide a holistic overview of a building during its construction phase, particularly during the shell construction phase. With the help of image processing software, the recorded structure can be analyzed and compared with a model, allowing the construction progress to be determined. With the help of training data, the systems can be flexibly adapted to new conditions and structures.

[0007] WO 2019 / 137814 A1 and DE 10 2018 200 221 A1 disclose a method for construction site monitoring, in which a building object is imaged using imaging sensors, and a feature of a structural part of the building object is recognized from the acquired image data. This feature can be, for example, an electrical installation box of a prefabricated reinforced concrete wall. The imaging sensors can be arranged on a construction machine or on a crane.

[0008] Further methods for construction site monitoring are known from JP 2021026281 A and JP 2020181241 A. In YANG JUN ET AL: "Image-Based 3D Semantic Modeling of Building Facade", September 15, 2014 (2014-09-15), SAT 2015 18TH INTERNATIONAL CONFERENCE, AUSTIN, TX, USA, SEPTEMBER 24-27, 2015; [LECTURE NOTES IN COMPUTER SCIENCE; LECT. NOTES COMPUTER], SPRINGER, BERLIN, HEIDELBERG, PAGE (S) 661-671, a modeling method is described using the example of a building facade, which is based on a 3D model. In this process, a point cloud is obtained from stereo images.

[0009] A typical problem that arises when monitoring buildings with the help of imaging sensors is the possible obscuration of building parts by other building parts. If, for example, a wall is built behind another wall or a pillar, it may only be partially visible to the camera and therefore cannot be reliably detected. Another problem is that concrete walls in particular are difficult to distinguish from other concrete walls or ceilings because of their similar colors and textures. If the transitions between the individual walls and floors are not detected correctly, construction errors cannot be identified and the construction progress cannot be correctly determined.

[0010] In light of these statements, the present invention is based on the object of alleviating or even completely eliminating the disadvantages of the prior art. Preferably, the object of the present invention is to provide a method and a system with which building components such as walls or floors can be reliably detected. Furthermore, the object of the invention is to provide a method with which construction progress can be reliably monitored.

[0011] These objects are achieved by a detection method for detecting a building part according to claim 1, a method for monitoring construction progress according to claim 12 and a system for detecting a building part according to claim 13. Preferred embodiments are specified in the dependent claims.

[0012] According to the invention, the detection method according to claim 1 comprises the following steps: i) capturing one or more camera images of the construction site with at least one, preferably at least two spaced-apart digital cameras at a capture position; ii) generating data points in a three-dimensional coordinate system, preferably in the form of a point cloud, the data points depicting the construction site; iii) detecting data points in the three-dimensional coordinate system which belong to a formwork element on the construction site which is arranged in a formwork position; iv) determining that field of view of a building part to be erected, for example a wall or ceiling element, in a stored building model which is visible from the capture position according to a current construction progress;v) assigning the data points belonging to the formwork element to the field of view of the building part to be erected when the formwork element is arranged in the formwork position for erection of the building part on the construction site; and vi) detecting the building part on the construction site when a predetermined number of data points belonging to the formwork element are assigned to the field of view of the building part to be erected.

[0013] The invention is based on the realization that formwork elements on construction sites are in many situations more visible and can be identified more easily than concrete walls or concrete ceilings, which merge into one another in terms of color and structure and are sometimes difficult to distinguish from one another. Due to their size, color, structure and shape, formwork elements, in particular frame formwork elements, stand out from the building and can therefore be more easily identified and distinguished from other objects using image processing software. Frame formwork in particular typically has easily identifiable structures such as cross braces on the back and, depending on the manufacturer, has a characteristic color and frame contour on the front. In the case of frame formwork for walls, characteristic holes for anchor rods are also provided.If a formwork element is now present on the construction site in a formwork position, it can be assumed that a building component to be erected with the formwork element is present, even if the poured concrete may not yet have fully hardened. One advantage of the invention is that building components that are partially hidden by other building components can also be detected, because when assigning the data points belonging to the formwork element, only the areas of the building components to be erected that are visible from the recording position are taken into account. For this purpose, a stored 3D model of the building is used. The model can be in the form of a BIM model (BIM = Building Information Modeling) or derived from one. The model can be stored in a memory. In step i), one or more camera images of the construction site are recorded.The construction site comprises the structure to be erected, for example a building, a bridge or a tunnel, and any construction site facilities, in particular the work equipment. The recording position at which the at least one digital camera is located is preferably a position at which the at least one digital camera can capture an image of the entire structure to be erected from one viewing angle. Of course, however, it is also possible to provide a plurality of digital cameras, each of which captures a part of the structure, wherein their camera images can be combined to display an image of the entire structure. It is preferred if the recording position is essentially static, i.e. unchanging. However, it can also be provided that the recording position changes over time. If the recording position changes, its position is (re)determined.This can be done manually or with the help of a GNSS unit (Global Navigation Satellite System), for example. The recording position is preferably determined using control points on the construction site. The control points can be (reference) markers located on the construction site and whose position is known or has been measured. White boards with a black symbol can be used as markers. The control points can also be prominent points on the construction site, such as the edge of an existing building. The position of the prominent points is also known, for example from surveying. One advantage of the control points is that movements of the crane due to wind or load lifting are compensated for, as is a change in the camera position. If several digital cameras are planned, each digital camera is arranged at its own recording position.The at least one digital camera can be designed as a stereo camera. However, it can also be provided that two digital cameras spaced apart from one another form a stereo camera. In such a case, the two digital cameras can be arranged on a common support frame, for example. In step ii), data points are generated which map the construction site in a three-dimensional coordinate system. The data points are preferably in the form of a point cloud. The data points can be generated from the previously recorded, in particular two-dimensional camera images. However, it is also possible for the data points to be generated with the aid of a distance measuring device, in particular a LIDAR system (LIDAR: Light Imaging, Detection and Ranging). Each data point can be assigned a position in three-dimensional space. The position is determined by coordinates.In step iii), data points are detected that belong to a formwork element on the construction site that is arranged in a formwork position. The formwork position of a formwork is the position in which concrete can be poured into the space between formwork elements in order to produce the building component. The formwork position can be detected, for example, in the case of vertical walls to be erected by the fact that the formwork element is aligned vertically. Data points that belong to the formwork element can be detected by classification and the associated segmentation. Classification algorithms are known from the state of the art. Image analysis libraries and / or a classifier trained with training examples, for example a neural network, can be used to classify the individual pixels.Algorithms for segmenting and classifying objects in images are known in the art. Training data can be used to classify formwork elements. The classification or segmentation can take place in the recorded camera images or in the data points generated in three-dimensional space. If the segmentation and classification takes place in the individual camera images, the data points in the three-dimensional coordinate system are linked to the pixels of the camera images in order to determine those data points that belong to the formwork element. If the data points are generated from the pixels of the camera images, this link is already given. It can also be provided that in step iii) other formwork elements that are not in a formwork position are also detected. These formwork elements are then not taken into account when detecting the building component.In step iv), the field of view of a building part to be erected in a stored building model is determined which is visible from the recording position according to a current construction progress. The field of view of a building part can be understood as those areas which, for example, as viewed from the recording position, are not obscured by other building parts (to be erected). The current construction progress is taken into account here. The construction progress indicates which building parts have already been erected and which have not. The field of view can be determined by determining which areas of a building part are hit by lines of sight from the recording position where a digital camera is located. The orientation, i.e. the alignment, and intrinsic camera parameters of the digital camera are also taken into account.The building component to be erected can be a wall, a floor or a ceiling, for example. In step v), the data points belonging to the formwork element are assigned to the field of view of the building component to be erected when the formwork element is arranged in the formwork position for erecting the building component on the construction site. The formwork element is particularly arranged for erecting the building component when it is in a formwork position and adjacent to the position of the building component to be erected and is preferably oriented parallel to its surface. Finally, in step vi), the building component is detected on the construction site when a predetermined number of data points belonging to the formwork element are assigned to the field of view of the building component to be erected. As long as the formwork element is present, the building component can be classified as “in progress”.It is advantageous that only the field of vision of the building part to be erected is taken into account, which can reduce the error rate in the assignment. In summary, the method according to the invention makes it possible to detect a building part, for example a wall, a ceiling or a floor, with the aid of a formwork element in a formwork position if the formwork element can be assigned, depending on the construction progress, to a building part to be erected which is at least partially visible from a detection position. Steps i) - vi) can, but do not have to, be carried out in the specified order. For example, step iv) can also be carried out before step i). Individual steps can, if technically possible, at least partially also be carried out in an overlapping manner.

[0014] According to a preferred embodiment, the field of view of the building part to be erected is divided into virtual cells and the data points belonging to the formwork element are assigned to the cells of the building part according to their position in the three-dimensional coordinate system, wherein the building part is detected on the construction site when at least one data point is assigned to a predetermined number of cells of the building part. The field of view can be determined by dividing all building parts in the building model into cells and taking into account cells that are hit by a line of sight from the detection position of a digital camera. A data point is preferably assigned to a cell when a data point lies within a cell. The cells can, for example, be spherical, cylindrical, cuboid or cubic.In one embodiment, the structure to be erected is divided into cuboid cells, the edges of the cube being 5 cm to 20 cm, in particular substantially 10 cm long. The cells can extend beyond the boundaries of the structural part to be erected. In this way, the data points of the formwork elements arranged on a structural part to be erected can lie within the cells. Additional cells can also be provided outside the structural part 9 to be erected.

[0015] In step iii), the recognition of data points in the three-dimensional coordinate system that belong to the formwork element can be carried out on the basis of a segmentation and classification of segmented components of the one or more camera images. Segmentation and classification methods are known from the prior art. For example, specially adapted image processing algorithms or trained networks can be used. In particular, image analysis libraries in a database and / or models trained with training examples can be used for segmentation, for example neural networks. With the help of the segmentation and classification in the camera images, formwork elements can be recognized. By assigning data points in three-dimensional space to pixels in the camera images, those data points that belong to a formwork element can be identified.The assignment of data points to image points can be done in particular by generating the data points from the camera images.

[0016] In one embodiment it can be provided that, on the basis of an orientation and a formwork type of the formwork element, a distinction is made as to whether the formwork element is arranged in a formwork position or a storage position and the formwork element is only taken into account in step iii) if it is arranged in the formwork position. This means that the formwork element is no longer taken into account if it is in a storage position. Whether a formwork element is in a formwork position or in a storage position depends on the formwork type and its orientation. If it is a formwork element for a vertical wall, it is in a formwork position if the formwork element is aligned vertically adjacent to the wall.If formwork elements are arranged parallel and opposite one another so that a receiving space is formed between them, it can also be assumed that they are in a formwork position. If, on the other hand, the formwork element is leaning against a wall that has already been erected, is arranged outside the building or is lying on the ground, the formwork element is in a storage position. If it is a formwork element for a slab, it is in a formwork position if the formwork element is aligned horizontally adjacent to a slab to be erected. If, on the other hand, the formwork element for a slab is leaning against a wall, it is in a storage position.

[0017] It is preferred if at least two digital cameras are provided at each capture position, wherein the at least two digital cameras form a stereo camera and the digital cameras each record camera images essentially simultaneously. The at least two digital cameras can be fastened to a holding frame and connected to one another via a connecting element, for example a rod. The holding frame can have joints in order to align the digital cameras in the vertical and / or horizontal direction. Furthermore, the holding frame can have a fastening element, in particular a holding clamp, for fastening the holding frame to an object, for example a crane. In view of the size of the structures to be captured, it is advantageous if the at least two digital cameras are at a distance of at least 50 cm, preferably of at least 80 cm or at least 100 cm, from one another.Preferably, the two digital cameras are spaced approximately 120 cm apart. The digital cameras each capture only two-dimensional images.

[0018] Consequently, in step ii), the data points in the three-dimensional coordinate system can be generated from two simultaneously captured camera images of the at least two digital cameras. The position of the data points in three-dimensional space can be derived from the geometric properties of the digital cameras and the distance between the digital cameras.

[0019] For image recording of the construction site, it is advantageous if the recording position is arranged on a construction site facility, in particular on a crane or a post, or on another building. If a plurality of digital cameras are provided, the recording positions of these digital cameras can also be arranged on the construction site facility or the other building. In a particularly preferred embodiment, two digital cameras forming a stereo camera are provided and the recording positions of these digital cameras are arranged on the construction site facility, in particular a crane, or another building. Advantageously, the at least one digital camera is protected against damage and theft if it is arranged at an elevated location, such as on a crane or a post.

[0020] In order to be able to compare the data points more easily with the model of the building, it is advantageous if one or more control points, in particular one or more markers, are provided on the construction site and the data points are oriented and / or scaled in step ii) according to the one or more control points. The control points can in particular be formed by signs or posters. Alternatively, the control points can be formed by characteristic features on the construction site. The control points have a pattern that is easily identifiable. With the help of at least one control point, the orientation, i.e. the alignment, and the scaling of the data points in the three-dimensional coordinate system is simplified.

[0021] For efficient data processing, it is advantageous to discard data points that do not belong to a formwork element. In other words, only data points that belong to a formwork element are used in step v).

[0022] For the purpose of data protection, it is advantageous if people are detected in the camera images and / or in the data points in the three-dimensional coordinate system and at least the people’s faces are anonymized, for example by pixelation. The detection of people and faces can be achieved by segmenting the camera images and classifying segmented image components. Segmentation and classification methods are known from the prior art. For example, specially adapted image processing algorithms or trained networks can be used. In particular, image analysis libraries in a database and / or models trained with training examples can be used for segmentation, for example neural networks. A neural network is preferably used for segmentation. Anonymization can also be achieved by placing an area over the recognized faces.What is important is that people are no longer clearly identifiable for human observers.

[0023] It is advantageous if the formwork element is a frame formwork element or a slab formwork element. These types of formwork elements are particularly easy to recognize due to their shape, structure and color. Frame formwork consists of a frame, in particular a steel frame, into which a formwork panel is inserted and fixed. Due to this characteristic, frame formwork is particularly easy to recognize. Slab formwork elements are supported by formwork props and usually have end or edge stop ends that prevent the concrete from running out. Slab formwork elements are therefore also easy to recognize.

[0024] According to the invention, a method for monitoring the construction progress of a building, in particular in the shell construction phase, is also provided. The method has the following steps: a) repeatedly carrying out a detection method for detecting a building part on a construction site of the type described above; b) marking a building part as completed when the building part has been detected according to step vi) of the detection method and the data points belonging to the formwork element that was arranged on the construction site for erecting the building part are no longer assigned to the field of view of the building part when the detection method is carried out again in step v).

[0025] If a formwork element has been removed from the structural component and therefore the data points belonging to the formwork element are no longer assigned to the structural component in step v) of the detection process, it can be assumed that the poured concrete has hardened and that the structural component is therefore completed. As long as data points of a formwork element are assigned to a structural component, the structural component can be marked as "in progress." Thus, the construction progress can also be updated when a structural component is completed.

[0026] The invention further relates to a system for detecting a building component on a construction site, in particular during the shell construction phase. The system comprises the following: at least one, preferably two, digital cameras for capturing camera images of the construction site, wherein the at least one digital camera can be arranged at a capturing position; and a processing unit which is configured to carry out the following steps: i) controlling the at least one digital camera to capture one or more camera images of the construction site; ii) generating data points in a three-dimensional coordinate system, preferably in the form of a point cloud, wherein the data points depict the construction site; iii) detecting data points in the three-dimensional coordinate system which belong to a formwork element on the construction site;iv) determining that field of view of a building part to be erected, for example a wall or a ceiling element, in a stored building model which is visible from the detection position according to a current construction progress, wherein the building model is stored in a memory; v) assigning the data points belonging to the formwork element to the field of view of the building part to be erected when the formwork element is arranged in a formwork position for erecting the building part on the construction site; and vi) detecting the building part on the construction site when a predetermined number of data points belonging to the formwork element are assigned to the field of view of the building part to be erected.

[0027] The system is therefore set up to carry out the method described above. All advantages, developments and features of the method can therefore be transferred to the system. The processing unit can, but does not have to, be formed by a single unit. The processing unit can also be present as a distributed processing unit made up of several spatially separate (sub-)units or modules. Steps i) - vi) can, but do not have to, be carried out in the specified order. For example, step iv) can also be carried out before step i). The steps can also be carried out at an overlap in time.

[0028] In a preferred embodiment, at least two digital cameras are provided, which are arranged on a support frame, wherein the digital cameras are spaced apart by at least 50 cm, preferably at least 100 cm. The support frame can have a rod connecting the at least two digital cameras. The two digital cameras form a stereo camera for generating three-dimensional images.

[0029] The invention is described in more detail below with reference to figures, to which it is not intended to be limited. They show:

[0030] Fig. 1 shows a construction site where the system according to the invention is used to detect a building component;

[0031] Fig. 2 shows in detail a support frame for digital cameras which together form a stereo camera;

[0032] Fig. 3A and Fig. 3B schematically illustrate a field of view and data points of a structural component;

[0033] Fig. 4 shows schematically data points that are assigned to a building component; and

[0034] Fig. 5 shows schematically the sequence of a detection method according to the invention for detecting a building part on a construction site;

[0035] Fig. 6 shows schematically the sequence of a method according to the invention for monitoring the construction progress of a building; and

[0036] Fig . 7 shows schematically the exchange of data in a system for detecting a building component on a construction site .

[0037] Fig. 1 shows an unfinished building 1 in the shell construction phase on a construction site 2. The building 1 is a multi-story building 1a in the form of a house. In the shell construction phase, the shell is not yet finished. This means that not all walls 3, floors 4 and ceilings 5 ​​of the building 1 have been erected yet.

[0038] In the illustration shown, a crane 6 is transporting a formwork element 7, in particular a frame formwork element 8, to the top floor of the as yet unfinished building 1. The formwork element 7, like the other formwork elements 7 already located on the building 1, is used to produce a building part 9 that is still to be erected, in this case a wall 3. For this purpose, a plurality of formwork elements 7 are arranged opposite one another and, if necessary, next to one another, so that a receiving space 10 is formed into which concrete (not shown) can be poured. This position of the formwork elements is referred to as the formwork position. While the concrete is hardening, the building part 9 is being worked on. Once the concrete has hardened, the formwork elements 7 are removed again and the building part 2 is completed. In Fig.1, a formwork element 7 is not in the formwork position and is leaning against a wall 3 of the lowest floor of the building 1. This formwork element 7 is in a storage position.

[0039] For the successful construction of a building 1, it is essential to adhere to a specified construction schedule. To this end, construction errors should be identified early and construction progress regularly recorded. To determine construction errors and construction progress, individual building components 9, i.e., walls 3, floors 4, and ceilings 5, must be detected during the construction phase.

[0040] According to the invention, a system 11 for detecting a building component 9 is provided for this purpose. In the embodiment shown, the system 11 has two digital cameras 12 which are fastened to a holding frame 13. The holding frame 13 is in turn mounted on the crane 6, from where the digital cameras 12 can image the building 1 currently under construction. The two digital cameras 12 together form a stereo camera 14. The two digital cameras 12 are each arranged at a separate detection position Pi, P2. The digital cameras 12 are each configured to record two-dimensional camera images.

[0041] The holding frame 13 is shown enlarged in Fig. 2 and has a connecting element 15, preferably a rod 16 or a profile element, to which the digital cameras 12 can be fastened. The holding frame 13 further has at least two joints 17a, b, one of the joints 17a enabling the connecting element 15 to be pivoted in the vertical direction and one of the joints 17b enabling the connecting element 15 to be pivoted in the horizontal direction. The joints 17 can each be locked, for example with the aid of locking pins which engage in locking holes in order to prevent the connecting element 15 from pivoting. The mounting points 50 for mounting the digital cameras 12 are preferably arranged at the ends of the connecting element 15 and are in particular spaced apart by at least 50 cm.The holding frame 13 can be releasably fastened to an object, in particular the crane 6, by means of a fastening element 51, for example a holding clamp 52.

[0042] The system 11 further comprises a processing unit 18 (see Fig. 7), which does not necessarily have to be a single centralized unit. It can also be provided that the processing unit 15 is a distributed processing unit 18, divided into several distributed (sub-)units or modules that are spatially separated from one another. Thus, the processing steps performed by the processing unit 15 can also take place at different locations.

[0043] The system 11 is designed to carry out the method described below, whereby the specified steps do not necessarily have to be performed in the described order. Individual steps can also be interchanged or at least partially or completely overlapped.

[0044] In a first step i), at least one two-dimensional camera image of the not-yet-completed structure 1 is recorded with the aid of each of the digital cameras 12. It is preferred if the camera images of the two digital cameras 12 are recorded essentially simultaneously.

[0045] In a second step ii), data points 19 are generated in a three-dimensional coordinate system 20 from at least two camera images, each of which was recorded essentially simultaneously by the digital cameras 12. These data points 19 depict the construction site 2, i.e. the structure 1 and any work equipment such as formwork elements 7 (see Fig. 3A, B and Fig. 4). Each data point 19 is assigned a unique position in the form of coordinates in the three-dimensional coordinate system 20. The set of data points 19 can also be referred to as a point cloud 21. Each data point 19 belongs to an object or a person on the construction site 2. In order to align and scale the point cloud 21, control points 53 can be placed on the construction site. The control points 53 facilitate the determination of distances and orientations.

[0046] In a third step iii), data points 19 in the three-dimensional coordinate system 20 that belong to a formwork element 7 in a formwork position on the construction site 2 are recognized. The invention is based on the knowledge that formwork elements 7 can be recognized more easily because their shape, color and structure make them easier to distinguish from other objects on the construction site 2. The recognition of formwork elements 7 can be carried out in particular on the basis of a segmentation and subsequent classification of the segmented image components. Those data points 19 that emerged in step ii) from image points that belong to formwork elements 7 can be declared as data points 19 that belong to a formwork element 7. The formwork position of a formwork for a wall is, for example, the position in which concrete can be poured into the receiving space 10 in order to produce the building part 9.The formwork position can be recognized, for example, in the case of walls 3 to be erected, by the fact that the formwork element 7 is aligned vertically.

[0047] In a fourth step iv), the field of view 22 of a building component 9 to be erected is determined in a stored building model 23, in particular a digital BIM model (see Fig. 7), which is visible from the recording positions P1, P2 according to a current construction progress. The field of view depends on the recording position P2, P2 and the orientation of the digital camera 12. In this step, the building component 9 is not yet classified as completed. The aim is to detect the building component 9 on the construction site 2. This should be done with the help of the existing formwork elements 7.

[0048] The determination of a field of view 22 from a detection position P2, P2 is shown in Fig. 3A. Fig. 3A schematically shows two walls 3a, b arranged one behind the other and a digital camera 12 which is located at a detection position P2. From the perspective of the digital camera 12, the rear wall 3b is at least partially obscured by the front wall 3a, i.e. some lines of sight 24 strike the front wall 3a, but not the rear wall 3b or the formwork element 7 which is also shown. The lines of sight 24 are shown schematically in Fig. 3A. The area onto which lines of sight 24 from the detection position P2 of the digital camera 12 strike represents the field of view 22 of a building part 9.Based on knowledge of the acquisition position P2 and the orientation of the digital camera 12, as well as intrinsic parameters, the field of view 22 visible from the acquisition position P2 can be determined in a building model 23. The field of view 22 can be determined depending on the construction progress, since at a later point in time, the field of view 22 may be restricted due to the addition of building components 9.

[0049] In a fifth step v), those data points 19 belonging to the formwork element 7 in the formwork position are assigned to the field of view 22 of the structural part 9 to be erected when the formwork element 7 is arranged in a formwork position for the erection of the structural part 9 on the construction site 2. The formwork element 7 is arranged in particular for the erection of the structural part 9 when it is in a formwork position and borders on the position of the structural part 9 to be erected and is preferably oriented parallel to its surface.

[0050] In Fig. 3B, data points 19 are entered that belong to a formwork element 7, which is arranged in a formwork position for the construction of the wall 3b. The data points 19 can therefore be assigned to the wall 3b.

[0051] The assignment of the data points 19 is shown schematically in Fig. 4 and can be carried out by dividing the visible area 22 of a building part 9 to be erected into cells 25 and assigning those data points 19 that lie within the cells 25 to the corresponding cells 25. The cells 25 can project beyond the boundaries of the building part 9 to be erected, so that the data points 19 of the formwork element 7 lie in the cells 25. In the illustration shown, the cells have the shape of cubes. The edge lengths can be, for example, 10 cm.

[0052] In step vi), the structural component is detected when a predetermined number of data points 19 belonging to the formwork element 7 are assigned to the field of view 22 of the structural component 9 to be erected. This can be achieved, in particular, by having a certain number of cells 25 filled with data points 19. Thus, when a certain number of filled cells 25 are present, the structural component 9 to be erected can be declared as present.

[0053] Fig. 5 shows schematically the sequence of the detection method described so far.

[0054] Fig. 6 shows the sequence of a method for monitoring the construction progress of a building 1. The method described above for detecting a building part 9 is carried out several times (step a)). If a building part 9 is detected, it is classified as "in progress" as long as the data points 19 of the formwork element 7 that was arranged for the erection of the building part 9 are assigned to the field of view 22 of the building part 9. As soon as the data points 19 of the formwork element 7 that was arranged for the erection of the building part 9 are no longer assigned to the field of view 22 of the building part 9, i.e. the formwork element 7 is no longer required for the building part 9, the building part 9 is classified as "completed" (step b).

[0055] Fig. 7 shows a schematic view of the structure of the system 11 for detecting a building part 9. As already mentioned above, the processing unit 18 does not have to be a single unit, but can also consist of several decentralized (sub-)units that are geographically separate from one another. In the present case, the processing unit 18 has a central computing unit 26 which carries out or initiates steps i) - vi) of the method. The building model 23, which is used in step iv), is stored in a memory 27, which in the embodiment shown forms a component of the processing unit 18 or, alternatively, can be arranged in a server 28. Further data, such as training data for segmenting and classifying formwork elements 7, can also be stored in the memory 27. On a screen 29 of a computer 30 (see also Fig.1 ), detected building components 9 and the determined construction progress can be displayed. In addition, detected persons, preferably anonymously, and detected construction equipment, such as concrete buckets or trucks, can be displayed on the screen 29. The processing unit 18 has a data transmission unit 31 for connection to the server 28. The processing unit 18 can be fastened to the crane 6 by means of a mounting bracket 32. The processing unit 18 is supplied with electrical energy 33 via a line. The energy can originate from a supply network or an energy storage device. The digital cameras 12 are connected to the processing unit 18 via data and power connections 34. In the illustration shown, the processing unit 18 is connected to the server 28 by means of a data connection 35.The computer 30 can also be connected to the server 28 and thereby control the processing unit 18 and the digital cameras 12 or retrieve data from them.

Claims

Claims:

1. Detection method for detecting a structural element (9) on a construction site (2), particularly during the structural work phase, comprising the following steps: i) capturing one or more camera images of the construction site (2) with at least one, preferably at least two spaced-apart, digital camera(s) (12) at a capture position (Pi, P2); ii) generating data points (19) in a three-dimensional coordinate system (20), preferably in the form of a point cloud (21), wherein the data points (19) represent the construction site (2); iii) recognizing data points (19) in the three-dimensional coordinate system (20) that belong to a formwork element (7) on the construction site (2) that is arranged in a formwork position;iv) Determining the viewing area (22) of a building component (9) to be erected, for example a wall (3) or a ceiling element (5), in a stored building model (23) that is visible from the detection position (P2, P2) according to a current construction progress; v) Assigning the data points (19) belonging to the formwork element (7) to the viewing area (22) of the building component (9) to be erected when the formwork element (7) is in the formwork position for the erection of the building component (9) on the construction site (2); and vi) Detecting the building component (9) on the construction site (2) when a predetermined number of data points (19) belonging to the formwork element (7) are assigned to the viewing area (22) of the building component (9) to be erected.

2. Detection method according to claim 1, characterized in that the viewing area (22) of the building component (9) to be erected is divided into virtual cells (25) and the data points (19) belonging to the formwork element (7) are assigned to the cells (25) of the building component (9) according to their position in the three-dimensional coordinate system (20), wherein the building component (9) is detected on the construction site (2) when a predetermined number of cells (25) of the building component (9) at least one data point (19) is assigned.

3. Detection method according to claim 1 or 2, characterized in that in step iii) the detection of data points (19) in the three-dimensional coordinate system (20) belonging to the formwork element (7) is carried out on the basis of a segmentation and classification of segmented components of the one camera image or the several camera images.

4. Detection method according to one of claims 1 to 3, characterized in that, based on an orientation and a formwork type of the formwork element (7), a distinction is made as to whether the formwork element (7) is arranged in a formwork position or a storage position, and the formwork element (7) is only taken into account in step iii) if it is arranged in the formwork position.

5. Detection method according to one of claims 1 to 4, characterized in that at least two digital cameras (12) are provided at each of a detection position (Pi, P2), wherein the at least two digital cameras (12) form a stereo camera (14) and the digital cameras (12) each simultaneously record camera images.

6. Detection method according to claim 5, characterized in that in step ii) the data points (19) in the three-dimensional coordinate system (20) are generated from two simultaneously captured camera images of the at least two digital cameras (12).

7. Detection method according to one of claims 1 to 6, characterized in that the detection position (P2, P2) is arranged on a construction site facility, in particular on a crane (6) or a post, or on another structure (1).

8. Detection method according to one of claims 1 to 7, characterized in that one or more control points (53) , in particular one or more markers , are provided on the construction site (2) and the data points (19) are oriented and / or scaled in step ii) according to the one or more control points (53 .

9. Detection method according to one of claims 1 to 8, characterized in that data points (19) that do not belong to any formwork element (7) are discarded.

10. Detection method according to one of claims 1 to 9, characterized in that persons are detected in the camera image or the multiple camera images and / or in the data points (19) in the three-dimensional coordinate system (20) and at least the faces of the persons are anonymized, in particular by pixelation.

11. Detection method according to one of claims 1 to 10, characterized in that the formwork element (7) is a frame formwork element (8) or a slab formwork element.

12. Method for monitoring the construction progress of a structure (1), in particular during the structural work phase, comprising the following steps: a) Repeatedly performing a detection method to detect a structural component on a construction site according to one of claims 1 to 11; b) Marking a structural component (9) as completed when the structural component (9) has been detected according to step vi) of the detection method and the data points (19) belonging to the formwork element (7) arranged for the erection of the structural component (9) on the construction site (2) are no longer assigned to the field of view (22) of the structural component (9) when the detection method is performed again in step v).

13. System (11) for detecting a building component (9) on a construction site (2), in particular during the structural work phase, comprising: at least one, preferably two, digital camera(s) (12) for capturing camera images from the construction site (2), wherein the at least one digital camera (12) can be arranged at a capture position (Pi, P2); and a processing unit (18) configured to perform the following steps: i) Controlling the at least one digital camera (12) for capturing one or more camera images of the construction site (2); ii) Generating data points (19) in a three-dimensional coordinate system (20), preferably in the form of a point cloud (21), wherein the data points (19) represent the construction site (2); iii) Recognizing data points (19) in the three-dimensional coordinate system (20) that belong to a formwork element (7) on the construction site (2) which is arranged in a formwork position; iv) Determining that viewing area (22) of a building component (9) to be erected, for example a wall (3) or a ceiling element (5), in a stored building model (23) that is visible from the acquisition position (Pi, P2) according to a current construction progress, wherein the building model (23) is stored in a memory (27);v) Assigning the data points (19) belonging to the formwork element (7) to the line of sight (22) of the building component (9) to be erected when the formwork element (7) is in the formwork position for the erection of the building component (9) on the construction site (2); and vi) Detecting the building component (9) on the construction site (2) when a predetermined number of data points (19) belonging to the formwork element are assigned to the line of sight of the building component (9) to be erected.

14. System (11) according to claim 13, characterized in that at least two digital cameras (12) are provided which are arranged on a support frame (13), wherein the digital cameras (12) have a distance of at least 50 cm, preferably at least 100 cm, from each other.

Images