A smart city-oriented actual residence big data detection method and system for owners

Abstract

The application discloses a kind of owner actual residence big data detection method and system for smart city, it is related to data processing technical field.The method includes: collecting image to be detected;Obtain target building window area image;Significance detection is carried out, and it is judged whether it is bright window;If yes, then the target building window area image is marked;Otherwise, then obtain bright window template image and dark window template image;The similarity of target building window area image and bright window template image and dark window template image is calculated, and then it is judged whether it is bright window, if yes, then mark;Otherwise, then the corresponding target building window area image is handled using low-light image enhancement method, and then it is judged again.The application combines multiscale target detection method, multiple significance detection model and multiple region color histogram comparison method, and combines low-light image enhancement method, to realize the accurate discrimination of window area image.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and more specifically, to a method and system for detecting the actual residence of homeowners in smart cities. Background Technology

[0002] With societal development, more and more residential communities have been built in cities, effectively improving the living environment for residents. This, in turn, necessitates effective management of these communities. Accurately collecting big data on the actual occupancy of residents in a community allows for a more rational allocation of resources such as property management, thus providing direct support for the construction of smart cities.

[0003] Previously, the main method for collecting statistics on residents' actual occupancy was through door-to-door verification by staff. This not only wasted significant human resources but also caused considerable inconvenience to residents. Although existing technologies employ methods such as target recognition and detection to detect the actual occupancy of residents in residential communities, they still suffer from significant detection errors and cannot obtain highly accurate data. Therefore, how to achieve accurate detection of residents' actual occupancy data for smart cities has become an urgent problem to be solved. Summary of the Invention

[0004] To overcome or at least partially solve the above problems, embodiments of the present invention provide a method and system for detecting actual residential big data of property owners in smart cities. This method combines a multi-scale target detection method, a multi-saliency detection model, and a multi-region color histogram comparison method, along with a low-light image enhancement method, to achieve accurate identification of window area images.

[0005] The embodiments of the present invention are implemented as follows:

[0006] In a first aspect, embodiments of the present invention provide a method for detecting the actual occupancy of property owners using big data in smart cities, comprising the following steps:

[0007] Take photos of the target community buildings at preset times to obtain the images to be detected;

[0008] A multi-scale target detection method is used to detect the image to obtain the window area image of the target building;

[0009] The depth test method of the multisaliency detection model is used to detect the window area images of each target building in order to obtain and determine whether the corresponding target building window is a bright window based on the corresponding saliency detection results;

[0010] If the corresponding target building window is a bright window, it is determined that there are actual residents in the target building, and the image of the window area of ​​the target building is marked, and the process ends; otherwise, the template images of bright windows and dark windows are obtained.

[0011] The similarity between the target building window area image and the bright window template image is calculated using a multi-region color histogram comparison method to obtain the first similarity result; and the similarity between the target building window area image and the dark window template image is calculated using a multi-region color histogram comparison method to obtain the second similarity result.

[0012] Based on the first and second similarity results, it is determined whether the windows of the corresponding target building are bright or dark. If they are determined to be bright or dark, it is determined whether there are actual residents in the corresponding target building, and the window area image of the target building with bright windows is marked, and the process ends. Otherwise, the low-light image enhancement method is used to process the window area image of the corresponding target building to obtain an enhanced window area image.

[0013] Using a multi-region color histogram comparison method, the similarity between the enhanced window region image and the bright window template image is used to determine whether the corresponding target building window is a bright window. If the corresponding target building window is a bright window, it is determined that there are actual residents in the target building, and the corresponding target building window region image is marked, and the process ends. Otherwise, the corresponding target building window is determined to be a dark window, and there are no actual residents in the target building.

[0014] To address the problems in existing technologies, this invention utilizes a multi-scale object detection method to detect windows in the image to be detected, enabling more accurate detection of all windows in a building. Then, a multi-saliency detection model depth testing method is used to detect window areas, allowing for the early detection of some bright windows and significantly reducing computational resource consumption while maintaining detection accuracy. Furthermore, a multi-region color histogram comparison method is employed to more accurately identify window areas in the image. For window areas whose identification is not yet complete, a low-light image enhancement method is used for optimization, followed by further identification, further improving the accuracy of window area image identification. This invention combines multi-scale object detection, a multi-saliency detection model, and a multi-region color histogram comparison method, along with a low-light image enhancement method, to achieve accurate identification of window areas in the image.

[0015] Based on the first aspect, in some embodiments of the present invention, the method for detecting the actual residence of homeowners in smart cities further includes the following steps:

[0016] The target community buildings are photographed according to a preset collection cycle to obtain multiple images to be detected.

[0017] Based on the first aspect, in some embodiments of the present invention, the method for detecting the image to be detected using a multi-scale target detection method to obtain an image of the window area of ​​the target building includes the following steps:

[0018] The image to be detected is divided into multiple scales to obtain images to be detected at multiple scales;

[0019] The target detection method is used to detect the image at various scales to obtain and determine the window area image of the target building based on multiple detection results.

[0020] Based on the first aspect, in some embodiments of the present invention, the method for detecting window areas of various target buildings using the multisaliency detection model depth test method includes the following steps:

[0021] Multiple saliency detection methods were used to detect the window areas of each target building to obtain multiple saliency detection results for the corresponding window areas of the target buildings.

[0022] Based on the first aspect, in some embodiments of the present invention, the method for calculating the similarity between a target building window area image and a bright window template image using the multi-region color histogram comparison method includes the following steps:

[0023] The target building window area image and the bright window template image are divided into multiple equal regions, and color histograms are constructed in each equal region to obtain the corresponding color histograms of the target window equal region and the template equal region.

[0024] The color histograms of the target window regions and the template regions under each corresponding equal division are compared to generate and determine the similarity between the target building window region image and the bright window template image based on the corresponding comparison results.

[0025] Based on the first aspect, in some embodiments of the present invention, the method for comparing the color histograms of the target window's equally divided regions and the color histograms of the template's equally divided regions under corresponding equally divided regions includes the following steps:

[0026] Calculate the similarity between the color histograms of the target window's divided regions and the color histograms of the template's divided regions under each equally divided region to obtain the corresponding similarity results for multiple equally divided regions.

[0027] Secondly, embodiments of the present invention provide a big data detection system for actual resident status in smart cities, comprising: an image acquisition module, a target detection module, a saliency detection module, a first determination module, a similarity comparison module, a second determination module, and a third determination module, wherein:

[0028] The image acquisition module is used to take pictures of the buildings in the target community at preset times to obtain the images to be detected;

[0029] The target detection module is used to detect the target image using a multi-scale target detection method to obtain the image of the target building window area;

[0030] The saliency detection module is used to detect the window area images of each target building using the depth test method of the multi-saliency detection model, so as to obtain and determine whether the corresponding target building window is a bright window based on the corresponding saliency detection results;

[0031] The first determination module is used to determine that there are actual residents in the target building if the corresponding target building window is a bright window, and to mark the window area image of the target building and end the process; otherwise, it obtains the bright window template image and the dark window template image.

[0032] The similarity comparison module is used to calculate the similarity between the target building window area image and the bright window template image using a multi-region color histogram comparison method to obtain a first similarity result; and to calculate the similarity between the target building window area image and the dark window template image using a multi-region color histogram comparison method to obtain a second similarity result.

[0033] The second determination module is used to determine whether the windows of the corresponding target building are bright windows or dark windows based on the first similarity result and the second similarity result. If they are determined to be bright windows or dark windows, it is determined whether there are actual residents in the corresponding target building, and the window area image of the target building with bright windows is marked and the process ends. Otherwise, the window area image of the corresponding target building is processed using a low-light image enhancement method to obtain an enhanced window area image.

[0034] The third determination module is used to calculate and determine whether the corresponding target building window is a bright window based on the similarity between the enhanced window area image and the bright window template image using a multi-region color histogram comparison method. If the corresponding target building window is a bright window, it is determined that there are actual residents in the target building, and the corresponding target building window area image is marked, and the process ends; otherwise, it is determined that the corresponding target building window is a dark window, and there are no actual residents in the target building.

[0035] To address the problems in existing technologies, this system utilizes the cooperation of multiple modules, including an image acquisition module, a target detection module, a saliency detection module, a first judgment module, a similarity comparison module, a second judgment module, and a third judgment module. It employs a multi-scale target detection method to detect windows in the image to be tested, achieving more accurate detection of all windows in a building. Then, it uses a multi-saliency detection model depth testing method to detect window areas, enabling the early detection of some bright windows and significantly reducing the system's computational resource consumption while maintaining detection accuracy. Finally, it uses a multi-region color histogram comparison method to more accurately identify window areas in the image. For window areas whose identification is not yet complete, a low-light image enhancement method is used for optimization, followed by further identification, further improving the accuracy of window area image identification. This invention combines multi-scale target detection methods, multi-saliency detection models, and multi-region color histogram comparison methods, along with low-light image enhancement methods, to achieve accurate identification of window areas in images.

[0036] Based on the second aspect, in some embodiments of the present invention, the smart city-oriented big data detection system for actual residence of homeowners further includes a periodic collection module for taking pictures of target community buildings according to a preset collection cycle to obtain multiple images to be detected.

[0037] Thirdly, embodiments of this application provide an electronic device including a memory for storing one or more programs; and a processor. When the one or more programs are executed by the processor, they implement the methods described in any of the first aspects above.

[0038] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method as described in any of the first aspects above.

[0039] The embodiments of the present invention have at least the following advantages or beneficial effects:

[0040] This invention provides a method and system for detecting real-time residential data of property owners in smart cities. It combines multi-scale target detection methods, multi-saliency detection models, and multi-region color histogram comparison methods with low-light image enhancement methods to achieve accurate identification of window area images. Attached Figure Description

[0041] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 This is a flowchart of a method for detecting the actual residence of property owners in smart cities, according to an embodiment of the present invention.

[0043] Figure 2 This is a flowchart illustrating the detection of an image using a multi-scale target detection method in a big data detection method for real-world residential properties in smart cities, as described in an embodiment of the present invention.

[0044] Figure 3 This is a flowchart illustrating the process of calculating the similarity between a target building window area image and a bright window template image using a multi-region color histogram comparison method in a big data detection method for actual resident status in smart cities according to an embodiment of the present invention.

[0045] Figure 4 This is a schematic diagram of a big data detection system for actual occupancy of homeowners in smart cities, according to an embodiment of the present invention.

[0046] Figure 5 This is a structural block diagram of an electronic device provided in an embodiment of the present invention.

[0047] Explanation of reference numerals in the attached figures: 100, image acquisition module; 200, target detection module; 300, saliency detection module; 400, first determination module; 500, similarity comparison module; 600, second determination module; 700, third determination module; 101, memory; 102, processor; 103, communication interface. Detailed Implementation

[0048] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0049] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0050] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0051] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the term "comprising" or any other variations thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0052] In the description of the embodiments of the present invention, "multiple" means at least two.

[0053] Example:

[0054] like Figures 1-3 As shown, in a first aspect, embodiments of the present invention provide a method for detecting the actual occupancy of property owners in smart cities using big data, comprising the following steps:

[0055] S1. Take photos of the target community buildings at a preset time to obtain the images to be detected; take photos of specific buildings in the community at a specific time (usually after 8:00 pm) and use the photos as the images to be detected.

[0056] S2. Use a multi-scale target detection method to detect the image to obtain the image of the window area of ​​the target building;

[0057] Furthermore, such as Figure 2 As shown, it includes:

[0058] S21. Divide the image to be detected into multiple scales to obtain the image to be detected at multiple scales;

[0059] S22. Use target detection methods to detect the images to be detected at various scales, so as to obtain and determine the window area images of the target building based on multiple detection results.

[0060] In some embodiments of the present invention, a multi-scale target detection method is used to detect all windows of a building in the image to be detected. For a region in the image to be detected, if windows can be detected very stably at most scales, the region is identified as a window region; if windows can only be detected at a few scales, the region is identified as a non-window region.

[0061] S3. Use the multi-saliency detection model depth test method to detect the window area images of each target building, so as to obtain and determine whether the corresponding target building window is a bright window based on the corresponding saliency detection results;

[0062] Furthermore, multiple saliency detection methods are used to detect the window area images of each target building to obtain multiple saliency detection results for the corresponding target building window area images.

[0063] In some embodiments of the present invention, a multisaliency detection model depth test method is used to detect all window regions. If, for any given window region, multiple saliency detection methods can detect that the window region contains a large salient area, the window is directly identified as a bright window; otherwise, the next step is performed. Window regions already identified as bright windows in this step do not need to undergo further discrimination in subsequent steps, greatly saving computational resources.

[0064] S4. If the corresponding target building window is a bright window, it is determined that there are actual residents in the target building, and the image of the window area of ​​the target building is marked, and the process ends; otherwise, obtain the template image of the bright window and the template image of the dark window; manually select a representative image of the bright window (downloaded from the Internet or taken by the individual) as the template image of the bright window; manually select a representative image of the dark window (downloaded from the Internet or taken by the individual) as the template image of the dark window.

[0065] S5. Using the multi-region color histogram comparison method, calculate the similarity between the target building window area image and the bright window template image to obtain the first similarity result; and using the multi-region color histogram comparison method, calculate the similarity between the target building window area image and the dark window template image to obtain the second similarity result.

[0066] Furthermore, such as Figure 3 As shown, it includes:

[0067] S51. Divide the target building window area image and the bright window template image into multiple equal regions, and construct color histograms in each equal region to obtain the corresponding target window equal region color histogram and template equal region color histogram.

[0068] S52. Compare the color histograms of the target window regions and the template regions under each corresponding equal division area, generate and determine the similarity between the target building window region image and the bright window template image based on the corresponding comparison results.

[0069] Furthermore, the similarity between the color histograms of the target window's divided regions and the color histograms of the template's divided regions under each equally divided region is calculated to obtain the corresponding similarity results for multiple equally divided regions.

[0070] S6. Based on the first similarity result and the second similarity result, determine whether the corresponding target building window is a bright window or a dark window. If it is determined to be a bright window or a dark window, then determine whether there are actual residents in the corresponding target building, and mark the window area image of the target building with bright windows, and end; otherwise, use the low light image enhancement method to process the window area image of the corresponding target building to obtain the enhanced window area image.

[0071] In some embodiments of the present invention, a multi-region color histogram comparison method is used to calculate the similarity between the target building window region image (detected in step S2 but not identified as a bright window in step S3) and the bright window template image, and the similarity between the target building window region image (detected in step S2 but not identified as a bright window in step S3) and the dark window template image. If a target building window region image has a high similarity to the bright window template image (greater than a preset similarity threshold), it is directly identified as a bright window; if a target building window region image has a high similarity to the dark window template image (greater than a preset similarity threshold), it is directly identified as a dark window. If a window region image has no significant similarity to either of the two, the next step of calculation is performed, and the corresponding target building window region image is processed using a low-light image enhancement method.

[0072] S7. Using the multi-region color histogram comparison method, calculate and determine whether the corresponding target building window is a bright window based on the similarity between the enhanced window region image and the bright window template image. If the corresponding target building window is a bright window, it is determined that there are actual residents in the target building, and the corresponding target building window region image is marked, and the process ends; otherwise, it is determined that the corresponding target building window is a dark window, and there are no actual residents in the target building.

[0073] In some embodiments of the present invention, the window region image (for which no result was determined in step S6) is processed using a low-light image enhancement method, and the similarity with the bright window template image and the dark window template image is calculated again using a multi-region color histogram comparison method. If the enhanced window region image and the bright window template image have a high similarity, it is still directly identified as a bright window; otherwise, it is identified as a dark window.

[0074] The above steps were used to test all buildings in the community, thereby obtaining big data on the actual living conditions of the community's residents.

[0075] To address the problems in existing technologies, this invention utilizes a multi-scale object detection method to detect windows in the image to be detected, enabling more accurate detection of all windows in a building. Then, a multi-saliency detection model depth testing method is used to detect window areas, allowing for the early detection of some bright windows and significantly reducing computational resource consumption while maintaining detection accuracy. Furthermore, a multi-region color histogram comparison method is employed to more accurately identify window areas in the image. For window areas whose identification is not yet complete, a low-light image enhancement method is used for optimization, followed by further identification, further improving the accuracy of window area image identification. This invention combines multi-scale object detection, a multi-saliency detection model, and a multi-region color histogram comparison method, along with a low-light image enhancement method, to achieve accurate identification of window areas in the image.

[0076] Based on the first aspect, in some embodiments of the present invention, the method for detecting the actual residence of homeowners in smart cities further includes the following steps:

[0077] The target community buildings are photographed according to a preset collection cycle to obtain multiple images to be detected.

[0078] To further ensure the accuracy and completeness of the detection, photos are taken at regular intervals for assessment. The building is photographed every half hour, and all the above detection and assessment steps are completed. All bright windows are marked (as long as one bright window is detected), to determine which household is occupied (each household may have multiple windows, and as long as one window is detected as bright, it can be determined that the household is actually occupied).

[0079] like Figure 4 As shown, in a second aspect, embodiments of the present invention provide a big data detection system for actual occupancy of property owners in smart cities, comprising: an image acquisition module 100, a target detection module 200, a saliency detection module 300, a first determination module 400, a similarity comparison module 500, a second determination module 600, and a third determination module 700, wherein:

[0080] The image acquisition module 100 is used to take pictures of the target community buildings at preset times to obtain the image to be detected;

[0081] The target detection module 200 is used to detect the image to be detected using a multi-scale target detection method to obtain the image of the window area of ​​the target building;

[0082] The saliency detection module 300 is used to detect the window area images of each target building using the multi-saliency detection model depth test method, so as to obtain and determine whether the corresponding target building window is a bright window based on the corresponding saliency detection results.

[0083] The first determination module 400 is used to determine that there are actual residents in the target building if the corresponding target building window is a bright window, and to mark the window area image of the target building and end the process; otherwise, it obtains the bright window template image and the dark window template image.

[0084] The similarity comparison module 500 is used to calculate the similarity between the target building window area image and the bright window template image using a multi-region color histogram comparison method to obtain a first similarity result; and to calculate the similarity between the target building window area image and the dark window template image using a multi-region color histogram comparison method to obtain a second similarity result.

[0085] The second determination module 600 is used to determine whether the corresponding target building window is a bright window or a dark window based on the first similarity result and the second similarity result. If it is determined to be a bright window or a dark window, it is determined whether there are actual residents in the corresponding target building, and the window area image of the target building with bright windows is marked and the process ends. Otherwise, the window area image of the corresponding target building is processed using a low-light image enhancement method to obtain an enhanced window area image.

[0086] The third determination module 700 is used to calculate and determine whether the corresponding target building window is a bright window based on the similarity between the enhanced window area image and the bright window template image using a multi-region color histogram comparison method. If the corresponding target building window is a bright window, it is determined that there are actual residents in the target building, and the corresponding target building window area image is marked, and the process ends. Otherwise, it is determined that the corresponding target building window is a dark window, and there are no actual residents in the target building.

[0087] To address the problems in existing technologies, this system utilizes the cooperation of multiple modules, including an image acquisition module 100, a target detection module 200, a saliency detection module 300, a first judgment module 400, a similarity comparison module 500, a second judgment module 600, and a third judgment module 700. It employs a multi-scale target detection method to detect windows in the image to be detected, achieving more accurate detection of all windows in a building. Then, it uses a multi-saliency detection model depth testing method to detect window areas, enabling the early detection of some bright windows and significantly reducing the system's computational resource consumption while maintaining detection accuracy. Finally, it uses a multi-region color histogram comparison method to more accurately distinguish window areas in the image. For window areas whose results are not yet available, a low-light image enhancement method is used for optimization, followed by further judgment to improve the accuracy of window area image discrimination. This invention combines multi-scale target detection, multi-saliency detection models, and multi-region color histogram comparison methods with a low-light image enhancement method to achieve accurate discrimination of window area images.

[0088] Based on the second aspect, in some embodiments of the present invention, the smart city-oriented big data detection system for actual residence of homeowners further includes a periodic collection module for taking pictures of target community buildings according to a preset collection cycle to obtain multiple images to be detected.

[0089] To further ensure the accuracy and completeness of the detection, the periodic acquisition module takes pictures at regular intervals and then makes a judgment. The building is photographed every half hour, and all the above detection and judgment steps are completed. All bright windows are marked (as long as a bright window is detected once), to determine which household in the building is occupied (each household may have multiple windows, as long as a bright window is detected, it can be determined that the household is actually occupied).

[0090] like Figure 5 As shown, in a third aspect, embodiments of this application provide an electronic device including a memory 101 for storing one or more programs; and a processor 102. When the one or more programs are executed by the processor 102, they implement the methods described in any of the first aspects above.

[0091] The system also includes a communication interface 103. The memory 101, processor 102, and communication interface 103 are electrically connected directly or indirectly to each other to enable data transmission or interaction. For example, these components can be electrically connected to each other via one or more communication buses or signal lines. The memory 101 can be used to store software programs and modules, and the processor 102 executes various functional applications and data processing by executing the software programs and modules stored in the memory 101. The communication interface 103 can be used for signaling or data communication with other node devices.

[0092] The memory 101 may be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc.

[0093] The processor 102 can be an integrated circuit chip with signal processing capabilities. The processor 102 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0094] In the embodiments provided in this application, it should be understood that the disclosed methods, systems, and approaches can also be implemented in other ways. The method and system embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of methods, systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0095] In addition, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0096] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program thereon. When executed by processor 102, the computer program implements the methods described in any of the first aspects above. If the functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0097] The above are merely preferred embodiments of the present invention and are not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

[0098] It will be apparent to those skilled in the art that this application is not limited to the details of the exemplary embodiments described above, and that this application can be implemented in other specific forms without departing from the spirit or essential characteristics of this application. Therefore, the embodiments should be considered illustrative and non-limiting in all respects, and the scope of this application is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within this application. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A smart city-oriented actual residence big data detection method for owners, characterized in that, Includes the following steps: Take photos of the target community buildings at preset times to obtain the images to be detected; A multi-scale target detection method is used to detect the image to obtain the window area image of the target building; The depth test method of the multisaliency detection model is used to detect the window area images of each target building in order to obtain and determine whether the corresponding target building window is a bright window based on the corresponding saliency detection results; If the corresponding target building window is a bright window, it is determined that there are actual residents in the target building, and the image of the window area of ​​the target building is marked, and the process ends; Conversely, it retrieves the bright window template image and the dark window template image; The similarity between the target building window area image and the bright window template image is calculated using a multi-region color histogram comparison method to obtain the first similarity result; Furthermore, by using a multi-region color histogram comparison method, the similarity between the target building window area image and the dark window template image is calculated to obtain a second similarity result; Based on the first similarity result and the second similarity result, determine whether the corresponding target building window is a bright window or a dark window. If it is determined to be a bright window or a dark window, it is determined whether there are actual residents in the corresponding target building, and the window area image of the target building with bright windows is marked, and the process ends. Conversely, low-light image enhancement methods are used to process the corresponding target building window area image to obtain an enhanced window area image. Using a multi-region color histogram comparison method, the similarity between the enhanced window region image and the bright window template image is used to determine whether the corresponding target building window is a bright window. If the corresponding target building window is a bright window, it is determined that there are actual residents in the corresponding target building, and the corresponding target building window region image is marked, and the process ends. Conversely, if the windows of the target building are dark, it is determined that there are no actual residents in the target building. 2.The owner actual residence big data detection method for smart city according to claim 1, characterized in that, It also includes the following steps: The target community buildings are photographed according to a preset collection cycle to obtain multiple images to be detected. 3.The method of claim 1, wherein, The method for detecting the target image using a multi-scale target detection method to obtain an image of the target building's window area includes the following steps: The image to be detected is divided into multiple scales to obtain images to be detected at multiple scales; The target detection method is used to detect the image at various scales to obtain and determine the window area image of the target building based on multiple detection results.

4. The method for detecting actual occupancy data of property owners in smart cities according to claim 1, characterized in that, The method for detecting window areas of various target buildings using the multi-significance detection model depth test method includes the following steps: Multiple saliency detection methods were used to detect the window areas of each target building to obtain multiple saliency detection results for the corresponding window areas of the target buildings.

5. The method for detecting actual occupancy data of property owners in smart cities according to claim 1, characterized in that, The method for calculating the similarity between a target building window area image and a bright window template image using a multi-region color histogram comparison method includes the following steps: The target building window area image and the bright window template image are divided into multiple equal regions, and color histograms are constructed in each equal region to obtain the corresponding color histograms of the target window equal region and the template equal region. The color histograms of the target window regions and the template regions under each corresponding equal division are compared to generate and determine the similarity between the target building window region image and the bright window template image based on the corresponding comparison results.

6. The method for detecting actual occupancy data of property owners in smart cities according to claim 5, characterized in that, The method for comparing the color histograms of the target window's equally divided regions and the color histograms of the template's equally divided regions includes the following steps: Calculate the similarity between the color histograms of the target window's divided regions and the color histograms of the template's divided regions under each equally divided region to obtain the corresponding similarity results for multiple equally divided regions.

7. A big data detection system for actual occupancy of property owners in smart cities, characterized in that: include: The system comprises an image acquisition module, a target detection module, a saliency detection module, a first determination module, a similarity comparison module, a second determination module, and a third determination module, wherein: The image acquisition module is used to take pictures of the buildings in the target community at preset times to obtain the images to be detected; The target detection module is used to detect the target image using a multi-scale target detection method to obtain the image of the target building window area; The saliency detection module is used to detect the window area images of each target building using the depth test method of the multi-saliency detection model, so as to obtain and determine whether the corresponding target building window is a bright window based on the corresponding saliency detection results; The first determination module is used to determine that there are actual residents in the target building if the corresponding target building window is a bright window, and to mark the window area image of the target building and end the process; otherwise, it obtains the bright window template image and the dark window template image. The similarity comparison module is used to calculate the similarity between the target building window area image and the bright window template image using a multi-region color histogram comparison method to obtain a first similarity result; and to calculate the similarity between the target building window area image and the dark window template image using a multi-region color histogram comparison method to obtain a second similarity result. The second determination module is used to determine whether the windows of the corresponding target building are bright windows or dark windows based on the first similarity result and the second similarity result. If they are determined to be bright windows or dark windows, it is determined whether there are actual residents in the corresponding target building, and the window area image of the target building with bright windows is marked and the process ends. Otherwise, the window area image of the corresponding target building is processed using a low-light image enhancement method to obtain an enhanced window area image. The third determination module is used to calculate and determine whether the corresponding target building window is a bright window based on the similarity between the enhanced window area image and the bright window template image using a multi-region color histogram comparison method. If the corresponding target building window is a bright window, it is determined that there are actual residents in the target building, and the corresponding target building window area image is marked, and the process ends; otherwise, it is determined that the corresponding target building window is a dark window, and there are no actual residents in the target building.

8. A big data detection system for actual occupancy of property owners in smart cities according to claim 7, characterized in that, It also includes a periodic acquisition module, which is used to take pictures of the target community buildings according to a preset acquisition cycle to obtain multiple images to be detected.

9. An electronic device, characterized in that, include: Memory, used to store one or more programs; processor; When the one or more programs are executed by the processor, the method as described in any one of claims 1-6 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-6.

Images