CN116863331B - Method and device for determining target roof area of building group and electronic equipment - Google Patents
Method and device for determining target roof area of building group and electronic equipment Download PDFInfo
- Publication number
- CN116863331B CN116863331B CN202310730878.XA CN202310730878A CN116863331B CN 116863331 B CN116863331 B CN 116863331B CN 202310730878 A CN202310730878 A CN 202310730878A CN 116863331 B CN116863331 B CN 116863331B
- Authority
- CN
- China
- Prior art keywords
- initial
- pixels
- target
- digital
- roof area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000001514 detection method Methods 0.000 claims abstract description 18
- 230000008859 change Effects 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 description 11
- 238000004891 communication Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 230000004069 differentiation Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000000712 assembly Effects 0.000 description 1
- 238000000429 assembly Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/176—Urban or other man-made structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
- G06V10/765—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects using rules for classification or partitioning the feature space
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Image Processing (AREA)
Abstract
The invention provides a method and a device for determining a target roof area of a building group and electronic equipment, wherein the method comprises the following steps: acquiring a digital orthographic image of a building group and a digital earth surface model; based on the digital orthophotos, carrying out image recognition processing to obtain a first initial roof area of the building group; extraneous pixels in the digital surface model are removed based on the first initial rooftop area, thereby determining a target rooftop area of a building group from the digital surface model. The technical problem that false detection or missing detection often occurs only through an image recognition mode in the prior art is solved.
Description
Technical Field
The invention relates to a photovoltaic power station stepping survey, in particular to a method and a device for determining a target roof area of a building group and electronic equipment.
Background
For distributed photovoltaic power plants, photovoltaic panel assemblies are often installed on roofs of industrial plants, warehouses, residences, and the like. The distributed photovoltaic power station survey refers to analyzing a building before the building is under construction to determine the roof area on which the photovoltaic panels can be installed.
In the prior art, the roof area is extracted from a building mainly through image recognition by artificial intelligence, so that the roof area in the building is recognized, but false detection or missed detection often occurs only through the image recognition.
In view of this, the present invention has been proposed.
Disclosure of Invention
The invention provides a method and a device for determining a target roof area of a building group and electronic equipment, and aims to solve the technical problem that false detection or omission detection often occurs only through an image recognition mode in the prior art.
According to a first aspect of the present invention there is provided a method of determining a target roof area of a building group, comprising: acquiring a digital orthographic image of a building group and a digital earth surface model; based on the digital orthophotos, carrying out image recognition processing to obtain a first initial roof area of the building group; extraneous pixels in the digital surface model are removed based on the first initial rooftop area, thereby determining a target rooftop area of a building group from the digital surface model.
Further, removing extraneous pixels in the digital surface model based on the first initial rooftop area, thereby determining a target rooftop area of a building group from the digital surface model, comprising: determining to remove ground pixels and ground low object pixels of the ground surface model based on the background pixels of the first initial roof area to obtain a second initial roof area; performing outer expansion on each sub-region of the first initial roof region to obtain a plurality of first sub-regions subjected to outer expansion; obtaining a plurality of second subareas corresponding to the expanded plurality of first subareas in the second initial roof area; extracting each second sub-region according to the image boundary change position in each second sub-region to obtain a plurality of target sub-regions; and merging the target subareas to obtain the target roof area of the building group.
Further, determining to remove ground pixels and ground low object pixels of the surface model based on the first initial roof area background pixels to obtain a second initial roof area, including: removing foreground pixels in the first initial roof area to obtain background pixels of the first initial roof area; determining a height average parameter corresponding to a background pixel of the first initial roof area in the digital surface model; determining a building height threshold according to the height average parameter; pixels in the digital earth model that are less than a building height threshold are removed to obtain a second initial roof region in the digital earth model.
Further, before determining the height average parameter corresponding to the background pixel of the first initial roof area in the digital surface model, the method further comprises: and expressing the elevation of each pixel in the digital surface model by adopting a positive value.
Further, before extracting each second sub-region according to the image boundary change position in each second sub-region, the method further includes: and performing second-order differential processing on each second sub-region along the x direction and the y direction to obtain the image boundary change position in each second sub-region.
Further, before merging the plurality of target subregions, the method further comprises: counting all target subareas by adopting a quantile method to obtain a statistical height value; removing pixels higher than the preset range of the statistical height values and pixels lower than the preset range of the statistical height values in each target subarea, and calculating to obtain average height values after the pixels are removed, wherein each target subarea is associated with one average height value; and removing pixels with the average height value less than or equal to the average height value associated with each target subarea.
Further, based on performing image recognition processing on the digital orthophotos, a first initial roof area of the building group is obtained, including: performing model detection on the digital orthophoto image to obtain a plurality of initial closed areas; carrying out opening and closing operation on the plurality of initial closed areas so as to communicate a plurality of densely distributed initial closed areas in the plurality of initial closed areas; removing the initial closed areas with building areas smaller than a preset area in the initial closed areas after the opening and closing operation to obtain a plurality of target initial closed areas; the plurality of target initial enclosed areas is determined to be the first initial roof area.
According to a second aspect of the present invention, there is provided a device for determining a target roof area of a building group, comprising: the acquisition unit is used for acquiring the digital orthographic image and the digital earth surface model of the building group; the identification unit is used for carrying out image identification processing on the digital orthophoto image to obtain a first initial roof area of the building group; a determining unit for removing extraneous pixels in the digital surface model based on the first initial rooftop area, thereby determining a target rooftop area of a building group from the digital surface model.
According to a third aspect of the present invention there is provided a non-transitory computer readable storage medium having stored thereon a computer program which when executed by a processor causes any of the methods described above to be performed.
According to a fourth aspect of the present invention there is provided an electronic device comprising a memory and a processor, the memory having stored thereon computer instructions, characterised in that the computer instructions, when executed by the processor, cause any of the methods described above to be performed.
The invention provides a method and a device for determining a target roof area of a building group and electronic equipment, wherein the method comprises the following steps: acquiring a digital orthographic image of a building group and a digital earth surface model; based on the digital orthophotos, carrying out image recognition processing to obtain a first initial roof area of the building group; extraneous pixels in the digital surface model are removed based on the first initial rooftop area, thereby determining a target rooftop area of a building group from the digital surface model. The technical problem that false detection or missing detection often occurs only through an image recognition mode in the prior art is solved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following description will briefly introduce the drawings that are needed in the embodiments or the prior art descriptions, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for determining a target roof area of a building group provided by the invention;
FIG. 2 is a schematic illustration of a dom image of a building group provided by the present invention;
FIG. 3 is a schematic illustration of a target roof area of a building group provided by the present invention;
FIG. 4 is a schematic illustration of the profile of a single second sub-region provided by the present invention;
FIG. 5 is a schematic view of a building extracted by removing pixels with average height values less than or equal to the average height value in a target sub-area according to the present invention;
FIG. 6 is a schematic illustration of a plurality of initial enclosed areas provided by the invention;
FIG. 7 is a schematic illustration of a second initial roof area in a digital earth model provided by the present invention.
Detailed Description
To further clarify the above and other features and advantages of the present invention, a further description of the invention will be rendered by reference to the appended drawings. It should be understood that the specific embodiments presented herein are for purposes of explanation to those skilled in the art and are intended to be illustrative only and not limiting.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. It will be apparent, however, to one skilled in the art that the specific details need not be employed to practice the present invention. In other instances, well-known steps or operations have not been described in detail in order to avoid obscuring the invention.
Example 1
The application provides a method for determining a target roof area of a building group, which comprises the following steps in combination with fig. 1:
step S11, obtaining a digital orthographic image and a digital earth surface model of the building group.
Specifically, the method can be implemented by a server or other devices with data processing function as an implementation subject of the method steps of the method, the building group can be a building group formed by buildings such as industrial plants, warehouses and houses, and the roof area of the building group can be used for paving the photovoltaic panel assembly, and the purpose of the method is to extract the roof area of the building group.
The digital orthographic image is dom (digital orthophoto map), the surface model is dsm (digital surface model), and the dom and the dsm are obtained by photographing the same building group, and have a mapping relationship. A schematic representation of a dom image of a building group is shown in fig. 2.
And step S13, performing image recognition processing on the digital orthophoto image to obtain a first initial roof area of the building group.
Specifically, the scheme can cut the digital orthophoto to be detected firstly, keep the position information of each small image in the original image, send the position information into a model for detection, then combine the detection results of all the small images to obtain the detection result of the whole dom, namely the first initial roof area, and the model is a building extraction model trained in advance by the scheme.
The training method of the building extraction model is specifically described below:
Firstly, due to the fact that the different acquisition devices and the parameter setting reasons, the resolutions of the n-shot pixels in different areas are different, in order to avoid deviation caused by data and hardware requirements, all the n-shot images are firstly downsampled, and the dom data are uniformly set to be 5cm in resolution.
Then, the orthographic images are subjected to overlapping clipping, and different types of buildings are subjected to classification marking, so that a building extraction data set is constructed and used for training a building extraction model.
Finally, using semantic segmentation UNet network as building extraction model, and enhancing the data set in brightness transformation, scaling, noise addition and other modes in training process to obtain better building extraction model.
Step S15, removing extraneous pixels in the digital surface model based on the first initial roof area, thereby determining a target roof area of a building group from the digital surface model. The extraneous pixels include at least low vegetation or other non-buildings (including cars and ground debris, which may be referred to as non-buildings in general). A schematic representation of a target roof area of a building group is shown in fig. 3.
Specifically, the method removes irrelevant pixels in the digital surface model dsm based on the recognition result of the dom image, so as to determine the target roof area of the building group from the digital surface model, and it should be noted that, here, the dsm includes elevation information of each pixel, so that the removal of the irrelevant pixels in the dsm by means of the elevation information can be more accurate, and since the dsm cannot be recognized by the image recognition model, the method firstly performs image recognition on the dom, and then performs screening of the irrelevant pixels on the dsm by the recognition result of the dom. After the roof area of the building is positioned by using a deep learning scheme, the result is optimized by means of the elevation information in the surface model dsm.
Optionally, step S15 removes extraneous pixels in the digital surface model based on the first initial roof area, thereby determining a target roof area of a building group from the digital surface model, including:
and step S151, the ground pixels and the ground low object pixels of the ground surface model are removed based on the background pixels of the first initial roof area, and a second initial roof area is obtained.
And step S152, performing outer expansion on each sub-area of the first initial roof area to obtain a plurality of outer expanded first sub-areas.
And step S153, obtaining a plurality of second subareas corresponding to the expanded first subareas in the second initial roof area.
Specifically, the first initial roof area is a preliminary building extraction result generated for dom, and the scheme needs to map the first initial roof area to the dim to find the corresponding area in the dim and the elevation information, because the preliminary building extraction result is against the building boundary, if the first initial roof area extracted by the preliminary building fails to be detected, relevant pixels are omitted in the dim, so that each sub-area of the first initial roof area is firstly expanded, thereby ensuring the integrity of the associated building area determined in the dim. The first subregion is a plurality of regions in the dom image, and the second subregion is a plurality of regions in the dim image.
In an alternative embodiment, the specific strategy for the above-described flaring is to magnify both the length and width of the first subregion by a factor of 0.1.
It should be noted that, since the present solution needs to find the corresponding pixel corresponding to the dom pixel from the dsm, the mapping relationship between each pixel of the dsm and each pixel of the dom may be determined before the step S153, so that, when the position coordinates of the pixel on the dom are obtained, the position coordinates of the pixel of the dom may be converted into the geographic coordinates through the mapping relationship, and then the dsm pixel corresponding to the dom pixel is obtained in the dsm through the geographic coordinates.
And step S154, extracting each second subarea according to the image boundary change position in each second subarea to obtain a plurality of target subareas.
Specifically, the above-mentioned multiple second sub-areas are multiple sub-areas in the dsm, where the multiple sub-areas in the dsm include these buildings and empty spaces, so this solution needs to continue to extract for each second sub-area to further extract from each second sub-area to the target sub-area, and it should be noted that, when extracting each second sub-area according to the image boundary change position in each second sub-area, the contour of a single second sub-area may be extracted, and a schematic diagram of the contour of a single second sub-area is shown in fig. 4.
And step S155, combining the target subareas to obtain the target roof area of the building group.
Optionally, step S151, determining to remove ground pixels and ground low object pixels of the surface model based on the background pixels of the first initial roof area, to obtain a second initial roof area, including:
Step S1511, removing foreground pixels in the first initial roof region, to obtain background pixels of the first initial roof region.
Step S1512, determining a height average parameter corresponding to the background pixel of the first initial roof area in the digital surface model.
And step S1513, determining a building height threshold according to the height average parameter.
And step S1514, removing pixels smaller than the building height threshold in the digital surface model to obtain a second initial roof area in the digital surface model.
Specifically, the present solution maps the background pixels in the first initial roof area into the dsm, and averages Gao Chengqiu the pixels mapped into the dsm to obtain the height-average parameter, where it should be noted that the height-average parameter is the global ground height h.
Specifically, the building height threshold s may be a height average parameter +2m, that is, s=s+2m, where in the scheme, pixels smaller than the building height threshold in the dsm are determined as the background to be removed, and the building height threshold is kept greater than or equal to the building height threshold, so that shorter vegetation and other non-buildings can be removed.
It should be noted that, in the dsm, the height of the building is greater than 2m compared with the ground and some short features, so the ground and the short features are removed in the above-mentioned manner. A schematic of a second initial roof area in a digital earth model is shown in fig. 7.
It should be further noted that, since the dim itself cannot be identified by the image identification model, the present solution first performs image identification on the dim, then maps the identification result of the dim into the dim, and then screens out irrelevant pixels of the dim in combination with the elevation information in the dim.
Optionally, before determining the height average parameter corresponding to the background pixel of the first initial roof area in the digital surface model in step S1512, the method further includes:
and expressing the elevation of each pixel in the digital surface model by adopting a positive value.
Specifically, the elevation information of all pixels in the dsm is expressed according to positive values, so that the situation that the acquired elevation information is inconsistent is avoided, because some elevation information is embodied in the form of negative number elevation, some elevation information is positive elevation value, and all elevation information is expressed according to positive values for processing convenience and considering ground elevation information.
Optionally, in step S154, before extracting each second sub-region according to the image boundary change position in each second sub-region to obtain a plurality of target sub-regions, the method further includes:
And performing second-order differential processing on each second sub-region along the x direction and the y direction to obtain the image boundary change position in each second sub-region. And then taking the place of the height change as a segmentation position, and carrying out building extraction to obtain a building area (as the second subarea is not the only building, there is some interference, here by means of second order differentiation, since the height change is obvious at the building boundary, the second order differentiation can basically extract the boundary contour, and further separate the building from the interference part, and only the building area is remained as much as possible).
Optionally, before merging the plurality of target sub-regions in step S155, the method further includes:
and step S1411, counting all target subareas by adopting a quantile method to obtain a statistical height value.
In step S1412, pixels above the preset range of the statistical height values and pixels below the preset range of the statistical height values are removed from each target sub-region, and an average height value after the pixels are removed is calculated, where each target sub-region is associated with an average height value.
Specifically, considering that some interference points may exist, such as parapet wall, roof protrusion, middle height vacancy, etc., we discard the upper and lower 10% quantiles of the statistical height value, and then calculate a new average height value of the roof, where the statistical height value is calculated by adopting quantile method according to all target subareas, and the average height value is generated by each target subarea separately, that is, there is an average height value for each target subarea.
Step S1413, removing pixels with the average height value less than or equal to the average height value associated with each target sub-region.
Specifically, since the building has obvious step in elevation with the ground near the location thereof, a method of local threshold segmentation can be selected, namely, a threshold value (i.e. an average height value) is determined according to the height of the building, whether the height value of the pixels in the dsm is greater than the threshold value is judged, if so, the pixels are marked as targets, otherwise, the pixels are marked as backgrounds, non-buildings can be further removed, and a schematic diagram of the building extracted after each target subarea removes the pixels with the average height value less than or equal to the average height value of the target subarea is shown in fig. 5.
Optionally, step S13, based on performing image recognition processing on the digital orthophotos, obtains a first initial roof area of the building group, including:
step S131, performing model detection on the digital orthophoto image to obtain a plurality of initial closed areas.
Specifically, in the present solution, a model trained by Unet may be used to perform model detection on a digital orthophoto image, so as to obtain a plurality of initial closed areas, where a schematic diagram of the plurality of initial closed areas is shown in fig. 6.
And step S132, performing opening and closing operation on the plurality of initial closed areas so as to communicate a plurality of densely distributed initial closed areas in the plurality of initial closed areas.
Specifically, the method can further extract the building area in the detection result by using morphological open-close operation, can filter isolated objects by performing open-close operation and then open-close operation on the image, and can form a communication area in the dense object area to realize the extraction of the building area.
And step S133, removing the initial closed areas with building areas smaller than the preset area in the plurality of initial closed areas after the opening and closing operation to obtain a plurality of target initial closed areas.
Specifically, since the detection result in S132 may have some false detection, for example, pixels on some building areas may be erroneously detected as vegetation and containers due to similar spectral characteristics, the present solution uses the statistical analysis of the size of the building to be detected, and the area of the individual building is larger than 60m by 60m, so that the object whose area is smaller than 60m by 60m is discarded, and the remaining result is used for the further operation in step S15.
In conclusion, the building extraction method provided by the application has important significance in the field of distributed photovoltaic roof stepping, firstly, the recognition effect is ensured, and the recognition effect of the building roof is improved only by sacrificing less post-processing time. In addition, the whole data processing and identifying process reduces personnel participation as much as possible, and the distributed photovoltaic roof investigation efficiency is improved and the distributed photovoltaic roof investigation cost is indirectly reduced.
Example two
The present application also provides a device for determining a target roof area of a building group, which can be used to perform the method of the first embodiment, including: an acquisition unit 80 for acquiring a digital orthographic image of a building group and a digital earth model; an identification unit 82, configured to obtain a first initial roof area of the building group based on performing image identification processing on the digital orthophoto; a determining unit 84 for removing extraneous pixels in the digital surface model based on the first initial roof area, thereby determining a target roof area of a building group from the digital surface model.
Specifically, the method removes irrelevant pixels in the digital surface model dsm based on the recognition result of the dom image, so as to determine the target roof area of the building group from the digital surface model, and it should be noted that, here, the dsm includes elevation information of each pixel, so that the removal of the irrelevant pixels in the dsm by means of the elevation information can be more accurate, and since the dsm cannot be recognized by the image recognition model, the method firstly performs image recognition on the dom, and then performs screening of the irrelevant pixels on the dsm by the recognition result of the dom. After the roof area of the building is positioned by using a deep learning scheme, the result is optimized by means of the elevation information in the surface model dsm.
It is to be understood that the specific features, operations and details described herein before with respect to the method of the invention may be similarly applied to the apparatus and system of the invention, or vice versa. In addition, each step of the method of the present invention described above may be performed by a corresponding component or unit of the apparatus or system of the present invention.
It is to be understood that the various modules/units of the apparatus of the invention may be implemented in whole or in part by software, hardware, firmware, or a combination thereof. The modules/units may each be embedded in a processor of the computer device in hardware or firmware or separate from the processor, or may be stored in a memory of the computer device in software for invocation by the processor to perform the operations of the modules/units. Each of the modules/units may be implemented as a separate component or module, or two or more modules/units may be implemented as a single component or module.
In one embodiment, a computer device (electronic device) is provided that includes a memory and a processor, the memory having stored thereon computer instructions executable by the processor, which when executed by the processor, instruct the processor to perform the steps of the method of embodiments of the present invention. The computer device may be broadly a server, a terminal, or any other electronic device having the necessary computing and/or processing capabilities. In one embodiment, the computer device may include a processor, memory, network interface, communication interface, etc. connected by a system bus. The processor of the computer device may be used to provide the necessary computing, processing and/or control capabilities. The memory of the computer device may include a non-volatile storage medium and an internal memory. The non-volatile storage medium may have an operating system, computer programs, etc. stored therein or thereon. The internal memory may provide an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface and communication interface of the computer device may be used to connect and communicate with external devices via a network. Which when executed by a processor performs the steps of the method of the invention.
The present invention may be implemented as a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, causes steps of a method of an embodiment of the present invention to be performed. In one embodiment, the computer program is distributed over a plurality of computer devices or processors coupled by a network such that the computer program is stored, accessed, and executed by one or more computer devices or processors in a distributed fashion. A single method step/operation, or two or more method steps/operations, may be performed by a single computer device or processor, or by two or more computer devices or processors. One or more method steps/operations may be performed by one or more computer devices or processors, and one or more other method steps/operations may be performed by one or more other computer devices or processors. One or more computer devices or processors may perform a single method step/operation or two or more method steps/operations.
Those of ordinary skill in the art will appreciate that the method steps of the present invention may be implemented by a computer program, which may be stored on a non-transitory computer readable storage medium, to instruct related hardware such as a computer device or a processor, which when executed causes the steps of the present invention to be performed. Any reference herein to memory, storage, database, or other medium may include non-volatile and/or volatile memory, as the case may be. Examples of nonvolatile memory include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), flash memory, magnetic tape, floppy disk, magneto-optical data storage, hard disk, solid state disk, and the like. Examples of volatile memory include Random Access Memory (RAM), external cache memory, and the like.
The technical features described above may be arbitrarily combined. Although not all possible combinations of features are described, any combination of features should be considered to be covered by the description provided that such combinations are not inconsistent.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.
Claims (8)
1. A method of determining a target roof area for a building group, comprising:
acquiring a digital orthographic image of a building group and a digital earth surface model;
based on the digital orthophotos, carrying out image recognition processing to obtain a first initial roof area of the building group;
Removing extraneous pixels in the digital surface model based on the first initial rooftop area to thereby determine a target rooftop area of a building group from the digital surface model, wherein removing extraneous pixels in the digital surface model based on the first initial rooftop area to thereby determine a target rooftop area of a building group from the digital surface model comprises: determining to remove ground pixels and ground low object pixels of the ground surface model based on the background pixels of the first initial roof area to obtain a second initial roof area; performing outer expansion on each sub-region of the first initial roof region to obtain a plurality of first sub-regions subjected to outer expansion; obtaining a plurality of second subareas corresponding to the expanded plurality of first subareas in the second initial roof area; performing second-order differential processing on each second sub-region along the x direction and the y direction to obtain an image boundary change position in each second sub-region; extracting each second subarea according to the image boundary change position in each second subarea to obtain a plurality of target subareas; and merging the target subareas to obtain the target roof area of the building group.
2. The method of claim 1, wherein determining to remove ground pixels and ground low object pixels of the surface model based on the first initial roof region background pixels, results in a second initial roof region, comprising:
Removing foreground pixels in the first initial roof area to obtain background pixels of the first initial roof area;
Determining a height average parameter corresponding to a background pixel of the first initial roof area in the digital surface model;
determining a building height threshold according to the height average parameter;
Pixels in the digital earth model that are less than a building height threshold are removed to obtain a second initial roof region in the digital earth model.
3. The method of claim 2, wherein prior to determining the height average parameter corresponding to the background pixel of the first initial roof area in the digital surface model, the method further comprises:
and expressing the elevation of each pixel in the digital surface model by adopting a positive value.
4. The method of claim 1, wherein prior to merging the plurality of target subregions, the method further comprises:
Counting all target subareas by adopting a quantile method to obtain a statistical height value;
removing pixels higher than the preset range of the statistical height value and pixels lower than the preset range of the statistical height value in each target subarea, and calculating to obtain an average height value after the pixels are removed, wherein each target subarea is associated with one average height value;
and removing pixels with the average height value less than or equal to the average height value associated with each target subarea.
5. The method of claim 1, wherein obtaining a first initial rooftop area of a building group based on image recognition processing of the digital orthographic image comprises:
Performing model detection on the digital orthophoto image to obtain a plurality of initial closed areas;
Carrying out opening and closing operation on the plurality of initial closed areas so as to communicate a plurality of densely distributed initial closed areas in the plurality of initial closed areas;
Removing the initial closed areas with building areas smaller than a preset area in the initial closed areas after the opening and closing operation to obtain a plurality of target initial closed areas;
the plurality of target initial enclosed areas is determined to be the first initial roof area.
6. A device for determining a target roof area of a building group, comprising:
the acquisition unit is used for acquiring the digital orthographic image and the digital earth surface model of the building group;
The identification unit is used for carrying out image identification processing on the digital orthophoto image to obtain a first initial roof area of the building group;
A determining unit for removing extraneous pixels in the digital surface model based on the first initial roof area, thereby determining a target roof area of a building group from the digital surface model, the determining unit further being for determining to remove ground pixels and ground low object pixels of the surface model based on the first initial roof area background pixels, resulting in a second initial roof area; performing outer expansion on each sub-region of the first initial roof region to obtain a plurality of first sub-regions subjected to outer expansion; obtaining a plurality of second subareas corresponding to the expanded plurality of first subareas in the second initial roof area; performing second-order differential processing on each second sub-region along the x direction and the y direction to obtain an image boundary change position in each second sub-region; extracting each second subarea according to the image boundary change position in each second subarea to obtain a plurality of target subareas; and merging the target subareas to obtain the target roof area of the building group.
7. A non-transitory computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when executed by a processor, causes the method according to any one of claims 1 to 5 to be performed.
8. An electronic device comprising a memory and a processor, the memory having stored thereon computer instructions, which when executed by the processor result in the method of any of claims 1-5 being performed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310730878.XA CN116863331B (en) | 2023-06-20 | 2023-06-20 | Method and device for determining target roof area of building group and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310730878.XA CN116863331B (en) | 2023-06-20 | 2023-06-20 | Method and device for determining target roof area of building group and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116863331A CN116863331A (en) | 2023-10-10 |
| CN116863331B true CN116863331B (en) | 2024-07-09 |
Family
ID=88225995
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310730878.XA Active CN116863331B (en) | 2023-06-20 | 2023-06-20 | Method and device for determining target roof area of building group and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116863331B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101978395A (en) * | 2008-04-23 | 2011-02-16 | 株式会社博思科 | Building roof outline recognizing device, building roof outline recognizing method, and building roof outline recognizing program |
| CN109614871A (en) * | 2018-11-13 | 2019-04-12 | 远景能源（南京）软件技术有限公司 | Photovoltaic roof and photovoltaic barrier automatic identification algorithm |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5181379B1 (en) * | 2012-03-08 | 2013-04-10 | 国際航業株式会社 | Power generation potential evaluation device and power generation potential evaluation program |
| CN107607090B (en) * | 2017-09-12 | 2020-02-21 | 中煤航测遥感集团有限公司 | Building projection correction method and device |
| CN111191500A (en) * | 2019-11-12 | 2020-05-22 | 广东融合通信股份有限公司 | Photovoltaic roof resource identification method based on deep learning image segmentation |
| WO2022125787A1 (en) * | 2020-12-09 | 2022-06-16 | Zesty.Ai, Inc. | Determining 3d structure features from dsm data |
| KR102567800B1 (en) * | 2021-06-10 | 2023-08-16 | 이재영 | Drone used 3d mapping method |
| CN114549543A (en) * | 2021-12-30 | 2022-05-27 | 浙江大华技术股份有限公司 | Building three-dimensional model construction method and device, terminal and storage medium |
| CN114912370B (en) * | 2022-06-13 | 2023-08-22 | 中国科学院空天信息创新研究院 | Building photovoltaic potential analysis available area calculation method |
| CN114758252B (en) * | 2022-06-16 | 2022-11-11 | 南开大学 | Image-based distributed photovoltaic roof resource segmentation and extraction method and system |
| CN115758769A (en) * | 2022-11-25 | 2023-03-07 | 国网江苏省电力有限公司经济技术研究院 | Power distribution network roof photovoltaic energy storage optimal configuration method based on image recognition |
| CN115564926B (en) * | 2022-12-06 | 2023-03-10 | 武汉大学 | Three-dimensional patch model construction method based on image building structure learning |
| CN115937708A (en) * | 2023-02-09 | 2023-04-07 | 国网河南省电力公司经济技术研究院 | High-definition satellite image-based roof information automatic identification method and device |
-
2023
- 2023-06-20 CN CN202310730878.XA patent/CN116863331B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101978395A (en) * | 2008-04-23 | 2011-02-16 | 株式会社博思科 | Building roof outline recognizing device, building roof outline recognizing method, and building roof outline recognizing program |
| CN109614871A (en) * | 2018-11-13 | 2019-04-12 | 远景能源（南京）软件技术有限公司 | Photovoltaic roof and photovoltaic barrier automatic identification algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116863331A (en) | 2023-10-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107735794B (en) | Condition detection using image processing | |
| CN107835997B (en) | Vegetation management for powerline corridor monitoring using computer vision | |
| CN109033950B (en) | Vehicle illegal parking detection method based on multi-feature fusion cascade depth model | |
| CN110889428A (en) | Image recognition method and device, computer equipment and storage medium | |
| CN111179232A (en) | Steel bar size detection system and method based on image processing | |
| CN109413411B (en) | Black screen identification method and device of monitoring line and server | |
| Zhou et al. | Seed-based approach for automated crack detection from pavement images | |
| CN113297946B (en) | Monitoring blind area identification method and identification system | |
| CN108847031B (en) | Traffic behavior monitoring method and device, computer equipment and storage medium | |
| CN114299457A (en) | Accumulated water depth detection method and device | |
| CN111680610A (en) | Construction scene abnormity monitoring method and device | |
| CN111832515B (en) | Intensive pedestrian detection method, medium, terminal and device | |
| CN110807765A (en) | Suspension insulator string inclination detection method and system based on image processing | |
| CN111798435A (en) | Image processing method, and method and system for monitoring invasion of engineering vehicle into power transmission line | |
| CN113963314A (en) | Rainfall monitoring method and device, computer equipment and storage medium | |
| CN112184814B (en) | Positioning method and positioning system | |
| CN108509826A (en) | A kind of roads recognition method and its system of remote sensing image | |
| CN116863331B (en) | Method and device for determining target roof area of building group and electronic equipment | |
| CN112560814A (en) | Method for identifying vehicles entering and exiting parking spaces | |
| CN110826364A (en) | Stock position identification method and device | |
| CN117541594A (en) | Double-non-maximum-suppression transverse wind ridging small target detection method and system | |
| CN114550060A (en) | Perimeter intrusion identification method and system and electronic equipment | |
| CN114529714A (en) | Unmanned aerial vehicle detection method and device, computer equipment and storage medium | |
| Bachtiar et al. | Parking management by means of computer vision | |
| Adi et al. | Parking slot detection system based on structural similarity index |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |