System and method for quantifying and calculating window field of view opening index
By generating window field image and calculating the far-field layer proportion and close-range field layer distance, and combining the two to calculate the width adjustment factor, the problem of insufficient calculation of window field width in the prior art is solved, and more accurate quantization and It says it is suitable for real estate and urban planning.
Patent Information
- Application Number
- CN202380029205.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2022-03-24
- Filing Date
- 2023-02-23
- Publication Date
- 2024-12-31
AI Technical Summary
The prior art is difficult to accurately quantify the window field of view widening, especially due to the lack of quantitative distances of the field of view objects, resulting in insufficient fine and accurate calculation results.
By generating window field images, calculate the far-field layer ratio and close-field field layer distance, combine the two to calculate the width adjustment factor, and then calculate the window field of view widening index (WVOI) to more accurately quantify and represent the width of window field of view widening more accurately .
It realizes a more refined and accurate quantification of the window view width, can distinguish views with the same proportion but different distances, and is suitable for real estate valuation and urban planning, reducing the cost of three-dimensional data processing.
Smart Images
Figure CN119234216A_ABST
Abstract
Description
Background Art
[0001] The Importance and Application of Window Vision
[0002] Window view width is a key attribute of living and working spaces such as residences and offices, and it significantly affects the quality of human life in terms of physical and mental health and satisfaction. Generally, windows with more distant view elements (e.g., buildings, greenery, water bodies, and sky) have greater width than windows with close-up scenes. It has been found that the human brain has specific areas of environmental width that recognize and detect, which generally lead to feelings of relaxation and comfort. Urban residents are willing to pay a premium for an open distant view compared to a close-up window view. Urban residences with low window view width can lead to urban diseases such as depression and mood disorders. Therefore, quantification of window view width is very important in real estate valuation and in the planning and design of comfortable, healthy and sustainable urban environments.
[0003] Window field of view width and width index
[0004] Window view openness is determined by the distance from the window to visible elements such as the sky, buildings, greenery, and water bodies. Window views with a greater proportion of sky and distant landscape layers tend to provide greater openness. Compared with other view openness (such as street view openness), the quantification of window view openness has not received enough attention due to the previous difficulties in large-scale window view data collection. Generally, the window view openness index (WVOI) can be calculated as a percentage of the sky view or the volume of the visible space. More visible sky elements and larger visible space indicate greater openness of the window view.
[0005] Previous studies and their limitations
[0006] Visibility analysis and view photography are two ways to quantify and calculate the openness of a window's view.
[0007] Visibility analysis of window view openness aims to measure the visibility of predefined landscape objects. For example, Fisher-Gewirtzman (2018) measured human-perceived window view openness on manual 3D models used for urban planning and design. However, the calculation results are inaccurate due to simplified simulations of the outside world. In order to achieve a highly detailed scale representation of the real world, the data preparation and large-scale 3D mutual visibility calculation process is often very complex and costly.
[0008] In contrast, field of view photography can capture a realistic window view of the outside world at low cost thanks to mature technologies (e.g., portable camera sensors and lightweight 3D visualization on geospatial platforms).
[0009] Calculation of the ratio of the sky and landscape layers of a view image has become a mainstream technique for representing view openness. Gong et al. (2018) extracted the ratio of the sky layer in street view photos to calculate street openness. Xia et al. (2021) further improved the accuracy and efficiency of street view openness using photography. Chang (2021) calculated the ratio of the sky layer and the landscape layer of window view photos to represent the window view openness. However, the quantitative distance to the view object that affects the window view openness has not been involved to enrich the view openness calculation. Window views with the same ratio of the sky layer but different distances to the landscape layer cannot be distinguished. Therefore, there is a lack of research on using window view images with distance information for more accurate window view openness calculation. Summary of the invention
[0010] There is a continuing need in the art for improved designs and techniques for systems and methods for quantifying and calculating a window view openness index (WVOI) based on a window view image and view distance.
[0011] Embodiments of the present invention relate to a system and method for quantifying and calculating a window field of view openness index. The method includes: generating a window field of view image by an image capture device; calculating a far field of view layer ratio; measuring and calculating a near field of view layer distance; calculating an openness adjustment factor (OAF) based on the field of view distance; and calculating a window field of view openness index. Generating a window field of view image includes defining multiple groups of settings for window field of view image generation. The multiple groups of settings may include a group of settings, the group of settings including orientation attributes, the orientation attributes including heading, pitch, and tilt. The multiple groups of settings may include a group of settings, the group of settings including cone attributes, the cone attributes including a field of view (FoV). The multiple groups of settings may include a group of settings, the group of settings including a position of the image capture device in an (x, y, z) coordinate system. In addition, calculating a far field of view layer ratio includes extracting a ratio of a far layer of the window field of view image as a basic factor for measuring the field of view openness. Measuring and calculating the near field of view layer distance is performed by a user or by a computing system. The OAF is summarized according to the field of view distance calculated in the steps of measuring and calculating the near field of view layer distance. Furthermore, the window view openness index (WVOI) was calculated based on the far view layer ratio and the OAF from the near view layer distance. BRIEF DESCRIPTION OF THE DRAWINGS
[0012] Figure 1 A flow chart showing the steps of a method for quantifying and calculating a window field of view openness index according to an embodiment of the present invention.
[0013] Figure 2 is a schematic diagram of the steps of generating a window field of view image according to an embodiment of the present invention.
[0014] Figure 34 is a schematic diagram of the steps of calculating the ratio of the far-view layer according to an embodiment of the present invention.
[0015] Figure 4 is a schematic diagram of steps for measuring and calculating a near-field vision layer distance according to an embodiment of the present invention.
[0016] Figure 5 4 is a schematic diagram of the steps of calculating the openness adjustment factor based on the field of view distance according to an embodiment of the present invention.
[0017] Figure 6 4 is a schematic diagram of the steps of calculating the window field of view openness index according to an embodiment of the present invention.
[0018] Figure 7A- Fig. 7E An image showing an example of a method for quantifying and calculating a window field of view openness index according to an embodiment of the present invention.
[0019] Figure 8A- Figure 8C 8A shows an image of a window view width index for an exemplary pair of window views with the same sky layer ratio but different non-sky view distances according to an embodiment of the present invention, wherein FIG. 8A shows a view with two high sky layer ratios, FIG. 8B shows a view without a sky layer, and Figure 8C A similar field of view is shown. DETAILED DESCRIPTION
[0020] The embodiment of the present invention shows a method and system for quantifying and calculating WVOI using window field of view images and field of view distance, aiming to quantify the window field of view width, so as to facilitate housing selection by buyers, housing evaluation by developers, and sustainable planning and design by urban planners. The method and system are based on both semantic and distance information of window field of view images, and are used to more accurately quantify and calculate WVOI.
[0021] The terms used herein are only used for the purpose of describing specific embodiments and are not intended to limit the present invention. As used herein, the term "and / or" includes any and all combinations of one or more associated listed items. As used herein, the singular forms "one", "an" and "the" are intended to include plural forms as well as singular forms, unless the context clearly states otherwise. It will be further understood that when used in this specification, the terms "include" and / or "comprise" specify the presence of the features, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, elements, components and / or groups thereof.
[0022] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the invention belongs. It will be further understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted in an idealized or overly formal sense unless explicitly so defined herein.
[0023] When the term "about" is used in conjunction with a numerical value herein, it is understood that the value may be within the range of 90% to 110% of the value, i.e., the value may be + / -10% of the value. For example, "about 1 kg" means 0.90 kg to 1.1 kg.
[0024] In describing the present invention, it should be understood that many techniques and steps are disclosed. Each of these has a separate benefit, and each can also be used in combination with one or more or in some cases with all other disclosed techniques. Therefore, for the sake of clarity, this description will avoid repeating each possible combination of the various steps in an unnecessary manner. However, the specification and claims should be read with the understanding that such a combination is fully within the scope of the present invention and claims.
[0025] refer to Figure 1 , the method for quantifying and calculating the window field of view openness index of the present invention includes five steps. In the first step M1, an image of the window field of view close to the window is captured by a physical camera in the real world or by a virtual camera of a computing system. Then, in the second step M2, the distant field layer ratio is calculated by extracting distant layer elements (e.g., the sky) through manual work of the user or computer vision technology. Next, in the third step M3, the field of view distance to the remaining elements (e.g., non-sky elements) is measured by manual surveying with the aid of a ranging sensor or an automatic method (such as distance calculation performed by a computing system with a geographic module). Then, in the fourth step M4, the openness adjustment factor (OAF) is calculated based on the obtained field of view distance. Next, the field of view openness index is calculated based on the obtained distant layer ratio and OAF. These steps of the method for quantifying and calculating the window field of view openness index of the present invention are described in more detail below.
[0026] Step 1: Window field of view image generation
[0027] refer to Figure 2, the window field of view image is captured by an image capture device such as a real camera or a virtual camera. Multiple groups of settings are defined for image generation. A first group of settings may include orientation attributes, such as pitch, tilt, and heading. A second group of settings may include cone attributes, such as field of view (FoV). A third group of settings may include a position of the image capture device in an (x, y, z) coordinate system. In addition, orientation attributes and cone attributes are defined to represent the evaluated window field of view range. In addition, the position (x, y, z) and heading of the image capture device are determined by the window location information. In addition, as Figure 2 As shown, a window view image is captured at a target window position in a real world or virtual environment.
[0028] Step 2: Calculation of the ratio of the far horizon layer
[0029] refer to Figure 3 , extract the proportion of the distant layer of the window field of view image as the basic factor for measuring the openness of the field of view. The distant layer can be defined as the sky layer or the layer including the sky and landscape elements, such as very distant buildings, greenery and water bodies. Taking the sky layer as an example, the following procedure describes how to calculate the distant field of view layer proportion.
[0030] Given an image i with M×N pixels, the proportion of the sky layer Defined as the ratio by equation (1),
[0031]
[0032] where λ(p)=sky is the semantic label of pixel p, and |·| is a cardinality operator indicating the total number of pixels. As a result, is a scalar value between 0 and 1.
[0033] The scale of the background layer, such as the sky scale It can be extracted from the window field of view image by manual methods such as labeling or automatic methods such as computer vision techniques.
[0034] If the extraction is based on a manual approach, the pixels of the elements in the far layer can be directly identified, labeled and summarized by the user. On the other hand, if the extraction is based on an automatic approach, for example, machine learning, which is one of the popular computer vision techniques, the window field of view image can be initially segmented by a deep learning model based on predefined field of view element labels (such as sky, water, buildings and greenery). Then, the pixels of the labeled field of view elements in the far field of view layer (e.g., sky layer) are summarized for area calculation. Finally, It is calculated based on the area of the sky layer over the total area of the entire image i.
[0035] Step 3: Close-range visual layer distance measurement and calculation
[0036] refer to Figure 4 , the distance to the remaining view elements on the image (i.e., target near-view layer elements, such as buildings, greenery, and water bodies) can be measured in the real world or calculated by the computing system. In the real world, the distance between the target view element and the window position is measured by a surveying instrument (e.g., a ranging sensor such as LiDAR). On the other hand, in the case of a computing system, the distance is calculated based on the position of the window and the target view element based on a geographic location database. The distance information is then saved as a distance map and associated with the window view image.
[0037] Step 4: Calculate the openness adjustment factor (OAF) based on the field of view distance
[0038] refer to Figure 5 , summarize the OAF according to the view distance calculated in step 3. OAF can be any representative statistical value from the near-distance view layer distance. Set the average distance of non-sky elements (e.g., buildings, greenery, and water bodies in the near-distance layer) as an example, the OAF calculation steps are described as follows.
[0039] Given a set D of non-sky average distances of n collected window view images, OAF is defined by equation (2) as the ratio,
[0040]
[0041] Where D i is the average view distance of m non-sky pixels in image i, and max and dist are two functions that calculate the maximum value of D and the view distance to the element at pixel j, respectively. is a scalar value between 0 and 1. The higher it is, the more it increases openness.
[0042] The view distance information collected from step 3 is assigned and matched with non-sky pixels to calculate
[0043] Step 5: Calculate the window field of view index
[0044] Compared with the conventional image-based openness index which only involves the view layer ratio (e.g., sky ratio) and cannot fully reflect the degree of window view openness, the openness index calculation of the embodiment of the present invention is based on the far view layer ratio and the OAF from the near view layer distance, such as Figure 6 shown.
[0045] By defining different equations, the window view openness index based on the view ratio and distance can have various forms. Using the sky ratio P mentioned in step 2 and step 4sky and OAF, non-sky element I non-sky As an example, the example WVOI is defined by equation (3),
[0046] WVOI=P sky +(1-P sky )×I non-sky . (3)
[0047] Therefore, all examples of WVOI are scalars between 0 and 1. The higher the WVOI, the greater the openness of the window. For example, the openness of a window with a 50% sky view and a 20% OAF can be calculated as 50% + (1-50%) x 20% = 60%.
[0048] Materials and methods
[0049] The key technology of the embodiment of the present invention is illustrated by the example case described below. It should be noted that this case only illustrates the general concept of the present invention and should not be considered to limit its scope. Similar data and methods can also be used according to the example Figure 1 The general workflow shown calculates the window field of view.
[0050] Example of Step 1: Window Field of View Image Generation
[0051] A window view image is generated by a virtual camera on a 3D photo-realistic city information model (CIM) platform to demonstrate the present invention as shown in FIG7A. For horizontal view capture, the camera orientation attributes including tilt and pitch are all set to 0, and the FoV is set to 60°. Then, the camera position (x, y, z) and heading are set based on the target window location position (longitude, latitude, altitude) and heading information. Next, two types of window information are extracted from a geographic database. Then, the window view is captured at the target window position and saved as an image.
[0052] Example of Step 2: Far Horizon Scale Calculation
[0053] The sky layer is selected to calculate the basic openness ratio of the window field of view. The sky layer is detected by the deep learning model DeepLabV3. As shown in Figure 7B, P mentioned in equation (1) is calculated by finding the area of the sky layer over the entire area of the image. sky .
[0054] Example of Step 3: Close Field of View Distance Measurement and Calculation
[0055] The distance between the window position and the remaining view elements (i.e., non-sky elements) on the view is calculated by the computing system. First, the geographic location of the non-sky elements at the target pixel position of the image is returned from the rendered 3D CIM by setting the virtual camera at the window position (longitude, latitude, altitude) with the same parameters (such as the orientation and FoV parameters of reference step 1). Then, the distance between the window and the view object is calculated. Next, the distance information is saved as a distance map and associated with the view image, as shown in Figure 7C.
[0056] Example of step 4: Calculation of the openness adjustment factor based on the field of view distance
[0057] I mentioned in equation (2) non-sky It is used to represent OAF. First, the average distance between the window position and the non-sky elements is calculated and added to D. Then, the maximum value of the set D is determined as the benchmark. Next, I is calculated using the ratio of the image average field of view distance of the non-sky elements to the benchmark. non-sky , as shown in Figure 7D.
[0058] Example of Step 5: Window View Index Calculation
[0059] The example WVOI mentioned by equation (3) is used to quantify Fig. 7E Window field of view shown. Figure 8A- Figure 8C Three typical window field of view pairs and quantified WVOIs are shown respectively to test the feasibility of the embodiments of the present invention respectively. According to the legend, the numbers in the blue and yellow rectangles indicate the sky ratio and OAF of the field of view image, respectively, and the WVOI calculated by equation (3) is shown in the gray rectangle. It is found that the field of view in group #1 has the same sky layer ratio as the field of view in group #2, but the field of view distance to the non-sky elements is larger. And therefore the WVOI of the field of view in group #1 is greater than that in group #2. The calculation results confirm that even for fields of view with the same proportion of sky elements, the system and method of the present invention can further quantify the fine-scale field of view openness difference by adding the field of view distance.
[0060] The present invention uses the semantic and distance information of the window field of view image to effectively calculate a more accurate WVOI. Compared with the traditional field of view openness measurement method based on visibility analysis, the use of the window field of view image with distance information not only achieves more accurate quantification, but also avoids the high cost of three-dimensional data processing and mutual visibility calculation. Compared with the traditional field of view-image-content openness estimation method, the use of the window field of view image with distance information can achieve more accurate quantification, especially for fields of view with the same distant layer ratio.
[0061] Comparison with conventional techniques
[0062] In an existing technology ("A method for calculating the openness of urban sky using Internet street view photos", Chinese patent number CN202010146662.5A), the sky openness of the street is calculated, the openness is calculated based on skyline analysis, and the sky ratio of the street view photo is used to calculate the sky openness, which does not involve the calculation of the field of view distance.
[0063] In contrast, in the present invention, the window view width involving the ratio of sky and landscape layers and the viewing distance of the residence is calculated from multiple levels, and the window view of high-rise residences cannot be represented by street view photos.
[0064] In another prior art (“Information processing method for architectural space openness based on three-dimensional model”, Chinese patent number CN201911126596.9A), a method for estimating the spatial openness of different building designs through 3D models is provided. The openness of different interior layout designs is measured. The model focuses on the level of a single building and uses traditional visibility analysis to measure spatial openness.
[0065] In contrast, in the present invention, the window view width to the outside world is measured, the window view width at the city scale is measured, and view photography with view distance information is used.
[0066] In yet another prior art (“method and apparatus for automating observer-centered analysis of viewing area in urban center using 3D sensor data”, Korean Patent No. KR1019739030000*), a method and apparatus for measuring the viewing area in the urban center from an observer-centered perspective is provided. The area of the urban center exposed to the sky is measured and a conventional visibility analysis is used.
[0067] In contrast, in the present invention, the multi-level window field of view width is analyzed, and the window field of view image with field of view distance information is used.
[0068] Therefore, compared with the traditional quantification of view openness, the system and method of the present invention can more accurately calculate the openness index to distinguish various window views, thereby benefiting many related disciplines and fields including real estate valuation and sustainable urban planning and design.
[0069] All patents, patent applications, provisional applications, and publications mentioned or cited herein are incorporated by reference in their entirety, including all figures and tables, to the extent they are not inconsistent with the explicit teachings of this specification.
[0070] It should be understood that the examples and embodiments described herein are for illustrative purposes only, and those skilled in the art are suggested various modifications or changes of these examples and embodiments, and these modifications or changes are included in the spirit and scope of the present application. In addition, any element or limitation of any invention disclosed herein or its embodiment can be combined with any and / or all other elements or limitations disclosed herein (alone or in any combination) or any other invention or its embodiment, and all these combinations are within the scope of the present invention, without limitation thereto.
[0071] References
[0072] 1. Chang, CY (2021): Window view quality: investigation of measurement method and proposed view attributes (PhD thesis, University of Sheffield).
[0073] 2.Fisher-Gewirtzman, D. (2018): "Integrating'weighted views'toquantitative 3D visibility analysis as a predictive tool for perception of space.Environment and planning B: Urban Analytics and City Science, 45(2),345-366.doi:10.1177 / 0265813516676486
[0074] 3. Gong, F.-Y., Zeng, Z.-C., Zhang, F., Li, X., Ng, E., and Norford, LK (2018): Mapping sky, tree, and building view factors of street canyons in a high-density urban environment.Building and Environment,134,155-167.doi:10.1016 / j.buildenv.2018.02.042
[0075] 4. Xia, Y., Yabuki, N. & Fukuda, T. (2021): Sky view factor estimation from street view images based on semantic segmentation. Urban Climate, 40, 100999. doi: 10.1016 / j.uclim.2021.100999.
Claims
1. A method for quantifying and calculating a window field of view width index based on a window field of view photograph and field of view distance, the method comprising: generating a window field of view image by an image capture device; Calculate the proportion of distant horizon layer; Measure and calculate the near-field distance; Calculate the openness adjustment factor OAF based on the field of view distance; as well as Calculate the window field of view openness index.
2. The method according to claim 1, wherein: Generating the window view image includes defining a plurality of sets of settings for generating the window view image.
3. The method according to claim 1, wherein: The plurality of groups of settings include a group of settings including orientation attributes including heading, pitch, and roll.
4. The method according to claim 1, wherein: The plurality of groups of settings include a group of settings including frustum properties including a field of view FoV.
5. The method according to claim 1, wherein: The plurality of sets of settings include a set of settings including a position of the image capture device in an (x, y, z) coordinate system.
6. The method according to claim 1, wherein: Quantifying and calculating the proportion of the far-view layer includes extracting the proportion of the far layer of the window-view image as a basic factor for measuring the openness of the view.
7. The method according to claim 1, wherein: The measuring and calculating of the near-field vision layer distance are performed by a user or by a computing system.
8. The method according to claim 1, wherein: The OAF is summarized according to the field of view distance calculated in the step of measuring and calculating the near field of view layer distance.
9. The method according to claim 1, wherein: The window field of view openness index WVOI is calculated based on the far field of view ratio and the OAF from the near field of view distance.
10. A computer-readable storage medium having program instructions stored therein, wherein the program instructions, when executed by a processor of a computing system, cause the processor to perform a method for quantifying and calculating a window view width index based on a window view image and a view distance, the method comprising: generating a window field of view image by an image capture device; Calculate the proportion of distant horizon layer; Measure and calculate the near-field distance; Calculate the openness adjustment factor OAF based on the field of view distance; as well as Calculate the window field of view openness index.
11. The computer-readable storage medium of claim 10, wherein: Generating the window view image includes defining a plurality of sets of settings for generating the window view image.
12. The computer-readable storage medium of claim 10, wherein: The plurality of groups of settings include a group of settings including orientation attributes including heading, pitch, and roll.
13. The computer-readable storage medium of claim 10, wherein: The plurality of groups of settings include a group of settings including frustum properties including a field of view FoV.
14. The computer-readable storage medium of claim 10, wherein: The plurality of sets of settings include a set of settings including a position of the image capture device in an (x, y, z) coordinate system.
15. The computer-readable storage medium of claim 10, wherein: Calculating the far-view layer ratio includes extracting the ratio of the far layer of the window view image as a basic factor for measuring the openness of the view.
16. The computer-readable storage medium of claim 10, wherein: Measuring and calculating the near field of view distance is performed by a user or by a computing system.
17. The computer-readable storage medium of claim 10, wherein: The OAF is summarized according to the field of view distance calculated in the step of measuring and calculating the near field of view layer distance.
18. The computer-readable storage medium of claim 10, wherein: The window field of view openness index WVOI is calculated based on the far field of view ratio and the OAF from the near field of view distance.
19. A system for quantifying and calculating window field of view index, comprising: An image generator generates a window field of view image; as well as The processor is configured as: Calculate the proportion of distant horizon layer; Measure and calculate the near-field distance; Calculate the openness adjustment factor OAF based on the field of view distance; as well as Calculate the window field of view openness index.