Intelligent interaction method and system for historic building restoration based on image feature recognition

Abstract

The invention provides an ancient building restoration intelligent interaction method and system based on image feature recognition, and the method comprises the steps: obtaining a multi-angle image of a to-be-restored target ancient building; extracting image features of the multi-angle image, and determining restoration content; performing three-dimensional reconstruction based on the multi-angle image to obtain a three-dimensional reconstruction model, and marking the repair content in the three-dimensional reconstruction model; obtaining a repairing process of a repairing person; and automatically adjusting the model angle of the three-dimensional reconstructed ancient building model according to the repair process for repair personnel to check. According to the historic building restoration intelligent interaction method and system based on image feature recognition, the image features of the multi-angle image of the target historic building are extracted, the restoration content is determined, the multi-angle image is subjected to three-dimensional reconstruction, the restoration content is marked in the three-dimensional reconstruction model, the historic building model is obtained, and the historic building restoration intelligent interaction method and system based on image feature recognition are obtained. And the model angle of the historic building model is automatically and synchronously adjusted based on the obtained repair process of the repair personnel for the repair personnel to check, which is more convenient and intuitive.

Description

Technical Field

[0001] The present invention relates to the technical field of ancient building restoration, and in particular to an intelligent interactive method and system for ancient building restoration based on image feature recognition. Background Art

[0002] As carriers of historical information and cultural memory, ancient buildings reflect the architectural art, technology and cultural level of the time. As non-renewable cultural heritage and historical physical evidence, their maintenance and management are of great significance. Ancient building restoration is an important cultural and historical protection activity for ancient buildings. At present, ancient building restoration mainly relies on experienced restorers to carry out restoration and maintenance according to experience. However, restorers need to find relevant historical materials as the basis for restoration by themselves, and cannot obtain direct restoration guidance. The process is relatively cumbersome.

[0003] In view of this, there is an urgent need for an intelligent interactive method and system for ancient building restoration based on image feature recognition to at least solve the above-mentioned deficiencies. Summary of the invention

[0004] One of the purposes of the present invention is to provide an intelligent interactive method for ancient building restoration based on image feature recognition, extract image features of multi-angle images of the target ancient building, determine the restoration content, and perform three-dimensional reconstruction of the multi-angle images, mark the restoration content in the three-dimensional reconstruction model, obtain the ancient building model, and automatically and synchronously adjust the model angle of the ancient building model based on the restoration progress of the restoration personnel for the restoration personnel to view, without the need for manual active switching of the ancient building model observation angle, which is more convenient and intuitive.

[0005] The intelligent interactive method for ancient building restoration based on image feature recognition provided by the embodiment of the present invention includes: Step 1: Acquire multi-angle images of the target ancient building to be restored; Step 2: Extract image features of multi-angle images and determine the restoration content; Step 3: Perform 3D reconstruction based on multi-angle images to obtain a 3D reconstruction model, annotate the restoration content in the 3D reconstruction model, and obtain an ancient building model; Step 4: Get the restoration process from the restorer; Step 5: Automatically adjust the model angle of the 3D reconstructed ancient building model according to the restoration progress for restoration personnel to view.

[0006] Preferably, step 1: obtaining multi-angle images of the target ancient building to be restored, including: Get the airspace range of the target ancient building; releasing the drone in an airspace range based on the flight altitude and the first flight angle; Get the drone's scan results; Based on the preset elevation feature extraction template, the elevation features are determined according to the scanning results; Based on the preset elevation difference associated feature extraction template, the elevation difference associated features are determined according to the scanning results and the elevation features, and a combination relationship between the elevation features and the elevation difference associated features is established; Get the shooting angle range of the drone and extract the shooting angle range features; According to the combination relationship and the shooting angle range characteristics, determine the second flight angle of the UAV in the local airspace range of the elevation characteristics corresponding to the combination relationship; When the UAV reaches the local airspace, the UAV is controlled to fly based on the second flight angle and take photos; When all local airspace ranges are photographed, multi-angle images are obtained.

[0007] Preferably, according to the combination relationship and the shooting angle range characteristics, determining the second flight angle of the UAV in the local airspace range of the elevation feature corresponding to the combination relationship includes: According to the combination relationship, a local elevation model of the local airspace range of the elevation features corresponding to the combination relationship is constructed; Determine the drone model in the local elevation model; Based on the model position and shooting angle range characteristics of the UAV model, determine the shooting field of view simulation area in the local elevation model; Determine the extraction basis part model of the elevation difference correlation feature corresponding to the combination relationship in the local elevation model; Determine a part-based model that meets the characteristics of the standard part-based model and use it as the standard part-based model; The acquisition standard is based on the flight angle adjustment corresponding to the part model based on the point determination rule; According to the flight angle adjustment basis point determination rule, the flight angle adjustment basis point in the local elevation model is determined; According to the flight angle adjustment, the second flight angle is determined based on the point position and the shooting field of view simulation area.

[0008] Preferably, determining the second flight angle according to the flight angle adjustment based on the point position and the shooting field of view simulation area includes: Determine whether the flight angle adjustment point is within the shooting field of view simulation area; If not, the corresponding flight angle adjustment point will be used as the target point; Determine the target point position and the target connection line of the model position of the UAV model; Determine the area boundaries on both sides of the shooting field of view simulation area, and take the area boundary on the side of the area boundary that is relatively close to the target line as the target boundary; Calculate the angle between the target line and the target boundary, and determine the maximum angle corresponding to the local elevation model; The flight angle at which the speed direction of the UAV is tilted vertically upward based on the horizontal plane with the maximum included angle is taken as the second flight angle.

[0009] Preferably, step 2: extracting image features of multi-angle images and determining restoration content includes: Determine standard image features based on multi-angle images; Perform image feature matching on the image features and the standard image features to determine the local images where the image feature matching does not meet the requirements; The restoration content is determined based on the image features corresponding to the local image and the preset ancient building knowledge graph library.

[0010] Preferably, step 3: performing three-dimensional reconstruction based on multi-angle images to obtain a three-dimensional reconstruction model, marking the restoration content in the three-dimensional reconstruction model, and obtaining an ancient building model, includes: Determine the missing model based on the repair content; Based on the preset annotation rules of the missing model, the missing model is annotated in the 3D reconstructed model; Determine the repair strategy based on the repair content; The repair strategy is displayed in the reminder box selection area, wherein the reminder box selection area has no overlapping areas with the 3D reconstructed model and the missing model.

[0011] Preferably, step 4: obtaining the restoration process of the restoration personnel includes: Obtain standard repair process according to the repair content; Obtain images of the restoration process from restorers; Determine the repair process based on the repair process image and the standard repair process.

[0012] Preferably, step 5: automatically adjusting the model angle of the three-dimensionally reconstructed ancient building model according to the restoration process for restoration personnel to view, including: Get the current model viewing angle; Determine the ideal model viewing angle for the ancient building model according to the restoration process; Determine whether the current model viewing angle is consistent with the ideal model viewing angle. If not, adjust the current model viewing angle to the ideal model viewing angle for restoration personnel to view.

[0013] Preferably, according to the restoration process, the ideal model viewing angle of the ancient building model is determined, including: Determine the current repair scope based on the repair progress; Determine the local model of the ancient building model corresponding to the current restoration scope; Obtain the angle relationship between the local model and the ancient building model; Based on the angular relationship, determine the ideal model viewing angle.

[0014] The intelligent interactive system for ancient building restoration based on image feature recognition provided by the embodiment of the present invention includes: The ancient building image acquisition subsystem is used to acquire multi-angle images of the target ancient building that needs to be restored; A restoration content determination subsystem is used to extract image features of multi-angle images and determine restoration content; The restoration content annotation subsystem is used to perform three-dimensional reconstruction based on multi-angle images, obtain a three-dimensional reconstruction model, annotate the restoration content in the three-dimensional reconstruction model, and obtain an ancient building model; The repair process acquisition subsystem is used to obtain the repair process of the repair personnel; The intelligent interactive subsystem is used to automatically adjust the model angle of the three-dimensional reconstructed ancient building model according to the restoration progress for restoration personnel to view.

[0015] The beneficial effects of the present invention are: The present invention extracts image features of multi-angle images of the target ancient building, determines the restoration content, and performs three-dimensional reconstruction of the multi-angle images, marks the restoration content in the three-dimensional reconstruction model, obtains the ancient building model, and automatically and synchronously adjusts the model angle of the ancient building model based on the restoration progress of the restoration personnel for the restoration personnel to view, without the need for manual active switching of the ancient building model observation angle, which is more convenient and intuitive.

[0016] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures specifically pointed out in the present application documents.

[0017] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 Schematic diagram of an intelligent interactive method for ancient building restoration based on image feature recognition in an embodiment of the present invention; Figure 2 Schematic diagram of an intelligent interactive system for ancient building restoration based on image feature recognition in an embodiment of the present invention. DETAILED DESCRIPTION

[0019] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0020] The embodiment of the present invention provides an intelligent interactive method for ancient building restoration based on image feature recognition, such as Figure 1 As shown, including: Step 1: Obtain multi-angle images of the target ancient building to be restored; wherein the target ancient building is the ancient building to be restored, such as: a certain ancient building tower group; the multi-angle image is: images of the target ancient building taken by a drone at different angles; Step 2: Extract image features of multi-angle images and determine the restoration content; the image features are the characteristic representation of the ancient building images taken, such as: the edges, corners, textures and shapes of the ancient buildings in the images; the restoration content is: the ancient building area that needs to be restored and the restoration method; Step 3: Perform 3D reconstruction based on the multi-angle images to obtain a 3D reconstruction model, annotate the restoration content in the 3D reconstruction model, and obtain an ancient building model; wherein the 3D reconstruction model is: a 3D model generated by fusing 2D multi-angle images; when annotating, annotate reminder information of the auxiliary restoration; Step 4: Obtain the restoration progress of the restoration personnel; wherein the restoration progress is: the current restoration progress of the restoration personnel, specifically which stage of the restoration is in, such as: restoration of the wooden structure inside the tower, or: reinforcement of the tower body; Step 5: Automatically adjust the model angle of the 3D reconstructed ancient building model according to the restoration process for restoration personnel to view. The model angle is the observation angle of the ancient building model. Specifically, the area of ​​the ancient building model observed by the automatically adjusted observation angle is consistent with the ancient building area corresponding to the real-time restoration process.

[0021] The working principle and beneficial effects of the above technical solution are: The present invention extracts image features of multi-angle images of the target ancient building, determines the restoration content, and performs three-dimensional reconstruction of the multi-angle images, marks the restoration content in the three-dimensional reconstruction model, obtains the ancient building model, and automatically and synchronously adjusts the model angle of the ancient building model based on the restoration progress of the restoration personnel for the restoration personnel to view, without the need for manual active switching of the ancient building model observation angle, which is more convenient and intuitive.

[0022] In one embodiment, step 1: obtaining multi-angle images of a target ancient building to be restored includes: Obtain the airspace range of the target ancient building; the airspace range is: the space area above the target ancient building that can be used for drone flight; The drone is released in the airspace based on the flight altitude and the first flight angle; the flight altitude is greater than the highest height of the ancient building; the flight angle is the angle between the straight line where the drone's speed direction is and the horizontal plane, and the first flight angle is 0 degrees; Obtain the scanning result of the drone; wherein the scanning result is: the laser scanning result of the laser radar preset under the drone perpendicular to the ground direction; Based on the preset elevation feature extraction template, the elevation feature is determined according to the scanning result; wherein the elevation feature extraction template is used to extract elevation information by comparing the scanning result, for example: a template for parsing the scanning result to obtain the height value and coordinate position; the elevation feature is: where is the height; Based on the preset elevation difference associated feature extraction template, the elevation difference associated feature is determined according to the scanning results and the elevation features, and a combination relationship between the elevation features and the elevation difference associated features is established; wherein the elevation difference associated feature extraction template is: a difference relationship extraction template when there is a difference in the elevation features of adjacent coordinates, and the elevation difference associated feature is: the area boundary coordinates and elevation difference value of the adjacent coordinate area with elevation difference and the coordinate area corresponding to the elevation feature, for example: the elevation value of the A coordinate area is 10 meters, and the elevation value of the B coordinate area adjacent to the A coordinate area is 15 meters, then the corresponding elevation difference associated feature is: the area boundary coordinates of the A coordinate area and the B coordinate area, -5 meters; Obtain the shooting angle range of the drone and extract the shooting angle range feature; wherein the shooting angle range is: the shooting angle range of the camera carried by the drone; the shooting angle range feature is: the shooting angle value of the drone; According to the combination relationship and the shooting angle range characteristics, determine the second flight angle of the UAV in the local airspace range of the elevation feature corresponding to the combination relationship; wherein the second flight angle is: the shooting angle of the UAV determined according to the elevation difference correlation feature; When the UAV reaches the local airspace, the UAV is controlled to fly based on the second flight angle and take photos; When all local airspace ranges are photographed, multi-angle images are obtained; Wherein, according to the combination relationship and the shooting angle range characteristics, determining the second flight angle of the UAV in the local airspace range of the elevation characteristics corresponding to the combination relationship includes: According to the combination relationship, a local elevation model of the local airspace range of the elevation feature corresponding to the combination relationship is constructed; wherein the local elevation model is: a local ancient building model constructed based on the elevation feature and the elevation difference correlation feature corresponding to the elevation feature; Determine the drone model in the local elevation model; Based on the model position and shooting angle range characteristics of the drone model, determine the shooting field of view simulation area in the local elevation model; wherein the model position of the drone model is determined according to the elevation characteristics; the simulated shooting point position of the shooting field of view simulation area is the point position of the virtual camera on the drone model, and the area boundary of the shooting field of view simulation area is determined according to the shooting angle range characteristics; Determine the extraction basis part model of the elevation difference correlation feature corresponding to the combination relationship in the local elevation model; wherein the extraction basis part model is: the simulation area corresponding to the elevation feature in the local elevation model and the simulation area boundary of the simulation area with the elevation difference; Determine a part-based model that meets the characteristics of the standard part-based model and use it as the standard part-based model; wherein the standard part-based model characteristics are: a part-based model that is higher than the local elevation model corresponding to the elevation characteristics; The flight angle adjustment corresponding to the standard based part model is based on the point determination rule; wherein the flight angle adjustment is based on the point determination rule: how to calculate the coordinates of the simulation area boundary according to the simulation area boundary; According to the flight angle adjustment basis point determination rule, the flight angle adjustment basis point in the local elevation model is determined; wherein the flight angle adjustment basis point is: the boundary coordinates of the simulation area; According to the flight angle adjustment, the simulated area based on the point position and the shooting field of view is determined to determine the second flight angle; Wherein, adjusting the reference point and the shooting field of view simulation area according to the flight angle to determine the second flight angle includes: Determine whether the flight angle adjustment point is within the shooting field of view simulation area; If not, the corresponding flight angle adjustment point will be used as the target point; Determine the target point position and the target connection line of the model position of the UAV model; Determine the area boundaries on both sides of the shooting field of view simulation area, and take the area boundary on the side of the area boundary that is relatively close to the target line as the target boundary; Calculate the angle between the target line and the target boundary, and determine the maximum angle corresponding to the local elevation model; The flight angle at which the speed direction of the UAV is tilted vertically upward based on the horizontal plane with the maximum included angle is taken as the second flight angle.

[0023] The working principle and beneficial effects of the above technical solution are: The present invention controls a drone to enter and shoot multi-angle images within the airspace range of a target ancient building, introduces an elevation feature extraction template, and extracts the elevation features of the target ancient building area; since there are shielding areas between buildings of different heights, and the shooting range of the drone in one direction is limited, an elevation difference associated feature extraction template is introduced to determine the elevation difference associated features (the region boundary coordinates and elevation difference between the adjacent coordinate region with elevation difference and the coordinate region corresponding to the elevation feature), establish a combination relationship between the elevation feature and the elevation difference associated features, and at the same time, extract the shooting angle range features of the shooting angle range of the drone, determine the second flight angle of the local airspace range of the elevation feature corresponding to the combination relationship based on the combination relationship and the shooting angle range features, when the drone arrives at the local airspace range, control the drone to fly and shoot based on the second flight angle, and when all local airspace ranges are shot, obtain multi-angle images, thereby improving the comprehensiveness of the multi-angle images and improving the construction accuracy of the subsequent three-dimensional reconstruction model.

[0024] Specifically, when determining the second flight angle of the UAV in the local airspace range of the elevation feature corresponding to the combination relationship according to the combination relationship and the shooting angle range characteristics, a local elevation model of the local airspace range of the elevation feature corresponding to the combination relationship is constructed, the UAV model is determined based on the three-dimensional parameters of the UAV, the model position of the UAV model is determined based on the elevation feature, and the shooting field of view simulation area in the local elevation model is determined based on the model position and the shooting angle range characteristics; based on the elevation difference association characteristics corresponding to the combination relationship in the local elevation model, an extraction basis part model is constructed to determine a standard basis part model with a height above the elevation feature, and based on the relative position relationship between the standard basis part model and the local elevation model, a flight angle adjustment basis point determination rule is determined, and according to the flight angle adjustment basis point determination rule, the flight angle adjustment basis point in the local elevation model is determined; It is determined whether the basis point for adjusting the flight angle is within the shooting field of view simulation area. If not, it means that the side wall image of the ancient building corresponding to the corresponding standard based on the part model cannot be fully captured, which will lead to inaccurate 3D reconstruction in the future. Therefore, the target line corresponding to the basis point for adjusting the flight angle and the model position is obtained. At the same time, the area boundary on both sides of the shooting field of view simulation area that is relatively close to the target line is determined as the target boundary, and the angle between the target line and the target boundary is calculated. Since the local elevation model may correspond to multiple target points, the maximum angle is selected to ensure that all high-rise building areas can be photographed. The flight angle with the maximum angle of the UAV speed direction vertically upward based on the horizontal plane is used as the second flight angle, which improves the suitability of the second flight angle determination process, further improves the richness of the 3D reconstruction material, and improves the reliability of the restoration basis.

[0025] In one embodiment, step 2: extracting image features of multi-angle images and determining restoration content includes: Determine standard image features based on multi-angle images; wherein the standard image features are: a characteristic representation of the standard image of the target ancient building, extracted through the recorded information (such as historical images, historical descriptions) of the target ancient building before it was damaged; Perform image feature matching on the image features and the standard image features to determine the local image where the image feature matching does not meet the requirements; wherein the local image is: the local area of ​​the multi-angle image corresponding to the non-matching features between the image features and the standard image features; The restoration content is determined based on the image features corresponding to the local image and the preset ancient building knowledge graph library; wherein the preset ancient building knowledge graph library is: a database containing ancient building knowledge, and the ancient building knowledge includes, for example: architectural style, construction technology, restoration methods, etc.

[0026] The working principle and beneficial effects of the above technical solution are: The present invention introduces standard image features to match the image features of multi-angle images, determines the local images where the image features do not match, and determines the restoration content based on the image features corresponding to the local images and the introduced ancient building knowledge graph library, so that the determination of the restoration content is more reasonable.

[0027] In one embodiment, step 3: performing three-dimensional reconstruction based on multi-angle images, obtaining a three-dimensional reconstruction model, marking the restoration content in the three-dimensional reconstruction model, and obtaining an ancient building model, includes: Determine the missing model according to the repair content; wherein the missing model is: a three-dimensional model of the area to be repaired; Based on the preset annotation rules of the missing model, the missing model is annotated in the three-dimensional reconstructed model; wherein the preset annotation rules are manually set in advance, for example: a dotted line is marked at the missing position corresponding to the ancient building model; Determine the repair strategy based on the repair content; the repair strategy is: the repair plan, including: what kind of repair materials to use, what kind of repair technology to use, and precautions, etc.; The repair strategy is displayed in the reminder box selection area, wherein the reminder box selection area has no overlapping areas with the 3D reconstructed model and the missing model.

[0028] The working principle and beneficial effects of the above technical solution are: The present invention constructs a missing model of the missing part based on the repair content, and marks the missing model in the three-dimensional reconstructed model. At the same time, the text information of the repair strategy is displayed in the reminder box selection area next to the three-dimensional reconstructed model. At the same time, the textual information of the repair strategy and the graphical results of the repair result are displayed, thereby improving the comprehensiveness of the intelligent interaction of the repair.

[0029] In one embodiment, step 4: obtaining the restoration process of the restoration personnel includes: According to the repair content, a standard repair process is obtained; wherein the standard repair process is: a result obtained by standardizing the repair process according to the repair strategy in the repair content; Acquire restoration process images of restoration personnel; wherein the restoration process images are: images of restoration personnel performing restoration of ancient buildings, which are recorded and acquired through the restoration site monitoring device; Determine the repair process based on the repair process image and the standard repair process.

[0030] The working principle and beneficial effects of the above technical solution are: The present invention determines a standard repair process corresponding to a repair strategy, determines a sub-process corresponding to the standard repair process according to a repair process image, and uses the sub-process as the repair process. The determination of the repair process is more reasonable, and the accuracy of the adjustment basis for subsequent angle adjustment is further improved.

[0031] In one embodiment, step 5: automatically adjusting the model angle of the 3D reconstructed ancient building model according to the restoration process for restoration personnel to view, includes: Get the current model viewing angle; the current model viewing angle is: the model screen displayed in real time on the ancient building model viewing terminal interface relative to the model viewing angle of the ancient building model, and the model viewing angle is: different viewing angles selected by rotating the view around the ancient building model; According to the restoration process, the current restoration scope is determined; wherein the current restoration scope is: the scope of the ancient building model that needs to be restored corresponding to the restoration process; Determine the local model of the ancient building model corresponding to the current restoration scope; wherein the local model is: the local model part of the ancient building model containing the smallest current restoration scope; Obtaining the angular relationship between the local model and the ancient building model; wherein the angular relationship is: the spatial orientation relationship between the local model and the ancient building model; According to the angle relationship, an ideal model viewing angle is determined; wherein the ideal model viewing angle is: the best viewing angle of the ancient building model that can observe the local model; Determine whether the current model viewing angle is consistent with the ideal model viewing angle. If not, adjust the current model viewing angle to the ideal model viewing angle for restoration personnel to view.

[0032] The working principle and beneficial effects of the above technical solution are: The present invention determines a local model of the current restoration range of the restoration process, and then determines the best observation angle for restoration based on the ancient building model, that is, the ideal model viewing angle, according to the angular relationship between the local model and the ancient building model; determines whether the current model viewing angle is consistent with the ideal model viewing angle. If not, the system automatically adjusts the current model viewing angle to the ideal model viewing angle for restoration personnel to view, without the need for restoration personnel to manually switch views, which is more convenient.

[0033] The embodiment of the present invention provides an intelligent interactive system for ancient building restoration based on image feature recognition, such as Figure 2 As shown, including: The ancient building image acquisition subsystem 1 is used to acquire multi-angle images of the target ancient building that needs to be restored; The restoration content determination subsystem 2 is used to extract image features of multi-angle images and determine restoration content; The restoration content annotation subsystem 3 is used to perform three-dimensional reconstruction based on multi-angle images, obtain a three-dimensional reconstruction model, annotate the restoration content in the three-dimensional reconstruction model, and obtain an ancient building model; The repair process acquisition subsystem 4 is used to obtain the repair process of the repair personnel; The intelligent interactive subsystem 5 is used to automatically adjust the model angle of the three-dimensionally reconstructed ancient building model according to the restoration process for the restoration personnel to view.

[0034] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An intelligent interactive method for ancient building restoration based on image feature recognition, characterized in that: include: Step 1: Acquire multi-angle images of the target ancient building to be restored; Step 2: Extract image features of multi-angle images and determine the restoration content; Step 3: Perform 3D reconstruction based on multi-angle images to obtain a 3D reconstruction model, annotate the restoration content in the 3D reconstruction model, and obtain an ancient building model; Step 4: Get the restoration process from the restorer; Step 5: Automatically adjust the model angle of the 3D reconstructed ancient building model according to the restoration progress for restoration personnel to view.

2. The intelligent interactive method for ancient building restoration based on image feature recognition according to claim 1, characterized in that: Step 1: Obtain multi-angle images of the target ancient building to be restored, including: Get the airspace range of the target ancient building; releasing the drone in an airspace range based on the flight altitude and the first flight angle; Get the drone's scan results; Based on the preset elevation feature extraction template, the elevation features are determined according to the scanning results; Based on the preset elevation difference associated feature extraction template, the elevation difference associated features are determined according to the scanning results and the elevation features, and a combination relationship between the elevation features and the elevation difference associated features is established; Get the shooting angle range of the drone and extract the shooting angle range features; According to the combination relationship and the shooting angle range characteristics, determine the second flight angle of the UAV in the local airspace range of the elevation characteristics corresponding to the combination relationship; When the UAV reaches the local airspace, the UAV is controlled to fly based on the second flight angle and take photos; When all local airspace ranges are photographed, multi-angle images are obtained.

3. The intelligent interactive method for ancient building restoration based on image feature recognition as claimed in claim 2, characterized in that: According to the combination relationship and the shooting angle range characteristics, the second flight angle of the UAV in the local airspace range of the elevation characteristics corresponding to the combination relationship is determined, including: According to the combination relationship, a local elevation model of the local airspace range of the elevation features corresponding to the combination relationship is constructed; Determine the drone model in the local elevation model; Based on the model position and shooting angle range characteristics of the UAV model, determine the shooting field of view simulation area in the local elevation model; Determine the extraction basis part model of the elevation difference correlation feature corresponding to the combination relationship in the local elevation model; Determine a part-based model that meets the characteristics of the standard part-based model and use it as the standard part-based model; The acquisition standard is based on the flight angle adjustment corresponding to the part model based on the point determination rule; According to the flight angle adjustment basis point determination rule, the flight angle adjustment basis point in the local elevation model is determined; According to the flight angle adjustment, the second flight angle is determined based on the point position and the shooting field of view simulation area.

4. The intelligent interactive method for ancient building restoration based on image feature recognition as claimed in claim 3, characterized in that: According to the flight angle adjustment, the second flight angle is determined based on the point position and the shooting field of view simulation area, including: Determine whether the flight angle adjustment point is within the shooting field of view simulation area; If not, the corresponding flight angle adjustment point will be used as the target point; Determine the target point position and the target connection line of the model position of the UAV model; Determine the area boundaries on both sides of the shooting field of view simulation area, and take the area boundary on the side of the area boundary that is relatively close to the target line as the target boundary; Calculate the angle between the target line and the target boundary, and determine the maximum angle corresponding to the local elevation model; The flight angle at which the speed direction of the UAV is tilted vertically upward based on the horizontal plane with the maximum included angle is taken as the second flight angle.

5. The intelligent interactive method for ancient building restoration based on image feature recognition according to claim 1, characterized in that: Step 2: Extract image features of multi-angle images and determine the repair content, including: Determine standard image features based on multi-angle images; Perform image feature matching on the image features and the standard image features to determine the local images where the image feature matching does not meet the requirements; The restoration content is determined based on the image features corresponding to the local image and the preset ancient building knowledge graph library.

6. The intelligent interactive method for ancient building restoration based on image feature recognition according to claim 1, characterized in that: Step 3: Perform 3D reconstruction based on multi-angle images to obtain a 3D reconstruction model, annotate the restoration content in the 3D reconstruction model, and obtain an ancient building model, including: Determine the missing model based on the repair content; Based on the preset annotation rules of the missing model, the missing model is annotated in the 3D reconstructed model; Determine the repair strategy based on the repair content; The repair strategy is displayed in the reminder box selection area, wherein the reminder box selection area has no overlapping areas with the 3D reconstructed model and the missing model.

7. The intelligent interactive method for ancient building restoration based on image feature recognition according to claim 1, characterized in that: Step 4: Get the restoration personnel's restoration progress, including: Obtain standard repair process according to the repair content; Obtain images of the restoration process from restorers; Determine the repair process based on the repair process image and the standard repair process.

8. The intelligent interactive method for ancient building restoration based on image feature recognition according to claim 1, characterized in that: Step 5: Automatically adjust the model angle of the 3D reconstructed ancient building model according to the restoration process for restoration personnel to view, including: Get the current model viewing angle; Determine the ideal model viewing angle for the ancient building model according to the restoration process; Determine whether the current model viewing angle is consistent with the ideal model viewing angle. If not, adjust the current model viewing angle to the ideal model viewing angle for restoration personnel to view.

9. The intelligent interactive method for ancient building restoration based on image feature recognition according to claim 8, characterized in that: According to the restoration process, determine the ideal model viewing angle of the ancient building model, including: Determine the current repair scope based on the repair progress; Determine the local model of the ancient building model corresponding to the current restoration scope; Obtain the angle relationship between the local model and the ancient building model; Based on the angular relationship, determine the ideal model viewing angle.

10. The intelligent interactive system for ancient building restoration based on image feature recognition is characterized by: include: The ancient building image acquisition subsystem is used to acquire multi-angle images of the target ancient building that needs to be restored; A restoration content determination subsystem is used to extract image features of multi-angle images and determine restoration content; The restoration content annotation subsystem is used to perform three-dimensional reconstruction based on multi-angle images, obtain a three-dimensional reconstruction model, annotate the restoration content in the three-dimensional reconstruction model, and obtain an ancient building model; The repair process acquisition subsystem is used to obtain the repair process of the repair personnel; The intelligent interactive subsystem is used to automatically adjust the model angle of the three-dimensional reconstructed ancient building model according to the restoration progress for restoration personnel to view.

Images