JP4074791B2 - House floor plan search program and house exterior search program - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to a technique for searching for a house layout using a computer.
[0002]
[Prior art]
Currently, housing design using CAD (Computer-Aided Design) is generally performed. Drawings created by CAD can be stored in a storage device as electronic data. The accumulated drawing data is generally managed by a relational database together with related house information. Further, when the floor plan is described by CAD data, the correspondence between the closed area in the drawing and the elements (parts) constituting the floor plan, such as the entrance, the water area, and the Japanese-style room, is defined.
[0003]
[Problems to be solved by the invention]
It is possible to search with an interest in how the elements that constitute the floor plan of the entrance, water surround, Japanese-style room (hereinafter simply referred to as “components”) are arranged in the drawing. If it becomes a method that can be handled by ordinary users, the housing information service can be greatly improved.
[0004]
When searching for the arrangement of components, that is, when searching based on the similarity of the floor plan, at present, the attribute value is a propositional representation of the state in the form of “entrance on the north side”. It is possible to search by registering in a relational database.
[0005]
However, it is actually impossible to comprehensively register the shape of multiple components and their spatial arrangement, the spatial relationship between components, and the magnitude relationship between components in such a propositional expression. Impossible.
[0006]
On the other hand, the overall shape of the floor plan is also important information when considering the similarity between the floor plans. It is also difficult to express this propositionally and register it in the relational database.
[0007]
In addition, if there is no attribute that is acceptable to the search user, the search cannot be performed.
[0008]
Therefore, it is difficult to respond to various needs of users only by searching with propositional attributes.
[0009]
An object of the present invention is to provide a house layout search program and a house floor search apparatus that allow a computer to perform a house layout search accurately based on the similarity of the shape of the floor plan.
[0010]
[Means for Solving the Problems]
In order to achieve the above object, the house floor plan search device of the present invention converts a drawing into a color image by assigning different colors to the closed region for each component in the floor plan, depending on the type of component, Divide the color image into multiple areas, calculate the color distribution feature value for each divided area, find the set of all the areas, and find the house layout that has high similarity between the house layout as the search key and the color distribution feature quantity set It is characterized by searching.
[0011]
When the color distribution histogram is adopted as the color distribution feature amount, the search is performed by storing a set of color distribution histograms of a plurality of floor plans in a feature amount data file, and from the same file, a floor plan similar to the home layout of the search key. This is done by extracting a sample.
[0012]
The color distribution histogram set becomes a feature vector, and similarity is defined by the distance between the feature vectors. Then, by calculating the color distribution histogram set, information on the arrangement, size, and shape of the components in the floor plan is expressed as a color distribution of pixel values in the color image.
[0013]
It should be noted that, when the color distribution in the image is converted into a feature vector, in addition to the above color distribution histogram, statistics such as average and variance of the color distribution can be used.
[0014]
In order to achieve the above object, another housing layout search apparatus according to the present invention generates a binary image by designating different colors for the house layout portion and other portions in the floor plan, and generates a binary image from the binary image. A luminance gradient vector image is created by calculating a luminance gradient vector, the luminance gradient vector image is divided into a plurality of regions, a histogram of the luminance gradient vector distribution is calculated for each divided region, a set of all the regions is obtained, and a search key It is characterized by searching a house floor plan having a high similarity between the house floor plan and the luminance gradient vector distribution histogram set.
[0015]
The search is executed by storing a set of brightness gradient vector distribution histograms of a plurality of floor plans in a feature data file and extracting a floor plan similar to the home layout of the search key from the file.
[0016]
The luminance gradient vector distribution histogram set is a feature vector reflecting the outline shape of the house layout, and similarity is defined by the distance between the feature vectors.
[0017]
As described above, it is possible to accurately perform a house floor search based on the similarity of the shape of the floor plan, either by the similarity of the color distribution histogram set or the similarity of the luminance gradient vector distribution histogram set. By combining these, more accurate search becomes possible.
[0018]
Also, the house layout as a search key can be freely created by the user. Therefore, according to the present invention, the propositional attribute selection such as using a drawing drawn by the user as the search key data is used. It is possible to specify a search condition with a high degree of freedom, which cannot be achieved by a search by.
[0019]
DETAILED DESCRIPTION OF THE INVENTION
DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, a house layout search program and a house floor search apparatus according to the present invention will be described in more detail with reference to embodiments of the invention shown in the drawings.
[0020]
FIG. 1 shows the configuration of the house floor search apparatus according to the present invention. In FIG. 1, 11 is a program file storing the house floor search program 21 of the present invention, 12 is a CPU (central processing unit) that executes data creation and search processing based on the house floor search program 21, and 2120 is , A CAD data file 111 which is a drawing depicting a floor plan of a house to be searched, a file 130 of image data for calculating a feature vector, and a feature data file 142 used for search, 14 is a CPU 12 Memory used during processing, 15 is a display device for displaying the screen being processed and the contents of various data, 16 is an input device for inputting a floor plan of the house, 17 is an external process A communication connection device 18 for connecting to the device 2200 via the communication path 2300, 18 is an internal bus for connecting these components to each other. It is a residential floor plan search apparatus consisting of a computer.
[0021]
The house floor space search device 2100 is accessed from an external processing device 2200 at various locations and performs search processing. The external processing device 2200 sends data and requests from the input device 26 to the home floor plan search device 2100 according to the instructions of the floor plan search program 21, and displays the search results on the display device 25. Data and requests from the input device 26 are sent from the communication connection device 27 via the communication path 2300. The house layout search device 2100 is a server device, and the external processing device 2200 is a client device (personal computer) used by a general user.
[0022]
FIG. 2 shows a procedure of search processing executed by the computer based on the shape and arrangement of the components in accordance with the house floor plan search program 21. First, in the floor plan drawing stored in the CAD data file 111, the drawing is converted into a color image by assigning different colors depending on the type of component to the closed region for each component in the drawing (step S101), this is stored in the image file 130. Next, the color image is divided into a plurality of regions independently of the floor plan (step S102). Subsequently, a histogram of the color distribution is calculated for each divided area, a set of all the areas is obtained (step S103), and the obtained set is used as a feature quantity vector and the data is stored in the feature quantity data file 142. Furthermore, a set of color distribution histograms of a plurality of house samples to be searched is stored in the feature data file 142 (step S104).
[0023]
Next, by operating the input device 26 of the external processing device 2200, a layout color image as a search key is created using components defined in mutually different colors, and a color distribution histogram set is calculated (step S1). S105). A floor plan sample having a high similarity between the floor plan used as a search key and the color distribution histogram set is searched in the feature data file 142 (step S106), and the result is displayed on the display device 25 (step S107).
[0024]
As described above, when the color distribution in an image is converted into a feature vector, in addition to the above color distribution histogram, statistics such as the average and variance of the color distribution can be used. The color feature histogram is a color distribution histogram, a color distribution statistic, and the like.
[0025]
Next, FIG. 3 shows a procedure of search processing executed by the computer based on the overall shape of the floor plan according to the house floor plan search program 21. First, in the floor plan stored in the CAD data file 111, a binary image is generated by designating different colors for the house floor portion and other portions in the drawing (step S111). Next, a luminance gradient vector is obtained from the binary image, a luminance gradient vector image having the luminance gradient vector as a pixel is created (step S112), and this is stored in the image file 130. Next, the brightness gradient vector image is divided into a plurality of regions independently of the floor plan (step S113). Subsequently, a histogram of the luminance gradient vector distribution is calculated for each divided region, a set of all the regions is obtained (step S114), and the obtained set is used as a feature vector to store the data in the feature data file 142. . Further, the brightness gradient vector distribution histogram set of the plurality of house layout samples to be searched is stored in the feature data file 142 (step S115).
[0026]
Next, by operating the input device 26 of the external processing device 2200, a luminance gradient vector image is created from the binary image of the floor plan used as a search key, and the luminance gradient vector distribution histogram set is calculated (step S116). A floor plan sample having a high similarity between the floor plan used as a search key and the luminance gradient vector distribution histogram set is searched in the feature data file 142 (step S117), and the result is displayed on the display device 25 (step S118).
[0027]
Instead of using the above binary image for grasping the overall shape, information on the shape of the boundary line included in the CAD data is used, a feature amount vector is obtained from the boundary line information, and the feature amount vector has a small distance. It is also possible to perform a search by extracting a house layout.
[0028]
Here, the flow of data when constructing the feature amount from the floor plan drawing data in steps S101 to S104 will be further described with reference to FIG. The input data file 110 includes a CAD data file 111 of a floor plan and a file 112 of bibliographic attribute data held by a house corresponding to the floor plan.
[0029]
CAD data from the CAD data file 111 is converted into image data by the image converter 120 and stored in the image file 130. The image converter 120 refers to the layout component and color association defined on the color table file 121, and fills the closed area in the drawing. Note that the feature values used in the present embodiment directly refer to the RGB values of the image. Accordingly, the image file 130 is uncompressed or an image compression format using index colors.
[0030]
The image data stored in the image file 130 is registered in the similar image search server 140 as new data. The similar image search server 140 reads image data from the image file 130, calculates an image feature amount, and stores the feature amount in the feature amount data file 142. Information such as feature parameter settings is described in the setting file 141 for the similar image search server 140.
[0031]
In the present embodiment, the feature amount reflecting the arrangement and size of the floor plan components in the drawing is calculated as follows.
[0032]
First, by defining a fixed number of divisions for each of the vertical and horizontal directions of the image, the entire image is divided into rectangular regions having a fixed size. For each rectangular area, a histogram is constructed by counting up pixels having a color corresponding to each floor plan component. A set of histograms obtained by collecting histograms for each rectangular area is defined as an image feature vector.
[0033]
Next, the feature amount that reflects the overall shape of the floor plan calculated in steps S111 to S115 is specifically calculated as follows.
[0034]
First, a binary image is constructed by assigning “1” to an area in which the floor plan component is defined in the drawing data and “0” to an area in which the floor plan component is not defined. In this example, black and white images are formed by specifying white for allocation “1” and black for “0”. However, the present invention is not limited to this, and different colors are used for allocation “1” and “0”. Can be specified.
[0035]
A black-and-white grayscale image reduced by reducing the resolution as necessary for the binary image is constructed. By lowering the resolution, it is possible to reduce the influence of unnecessary data as floor plan data in the drawing.
[0036]
An image having a luminance gradient vector as a pixel is formed by performing a two-dimensional differentiation process on the binary image or the black and white image. By defining a certain number of divisions for each of the luminance gradient vector images in the vertical and horizontal directions, the entire luminance gradient vector image is divided into rectangular regions having a constant size. The intensity distribution in the vector direction in each rectangular area is converted into histogram-like data by discretizing the direction of the luminance gradient vector and adding the vector norm of each pixel for each discretized direction for each rectangular area. Express. An example of the intensity distribution histogram in the vector direction is shown in FIG.
[0037]
A set of data obtained by collecting data for each rectangular area is defined as an image feature vector.
[0038]
Note that some numerical data provided as the bibliographic attribute data 112 in the input data is separately registered as a feature amount in the similar image search server 140 as necessary. The bibliographic attribute data 112 is used in both a search process executed based on the shape and arrangement of the constituent elements and a search process executed based on the overall shape of the floor plan. The similar image search server 140 handles this numerical data in the same manner as other image feature amounts at the time of search.
[0039]
In the above, the image converter 120 and the similar image search server 140 are functional units formed by the CPU 12 when the CPU 12 executes processing based on the floor plan search program 21 in FIG.
[0040]
In addition, it is possible to perform a highly accurate search by any of the search for the shape and arrangement of the above-described components and the search for the overall shape of the floor plan. Accurate search is possible.
[0041]
Next, the flow of processing at the time of searching in steps S105 to S107 and S116 to S118 will be further described with reference to FIG. The search apparatus according to the present embodiment is the server side 2100, and the search process proceeds based on the input from the client side 2200.
[0042]
The server side 2100 on which the similar image search server 140 operates is provided with an image file set (data file) 2120 for all data. The image file set 2120 includes two types of data groups: actual data 2121 corresponding to an actual house, and handwritten data 2122 created by a client (user) as search data.
[0043]
When the client program 2210 issues a search request, the similar image search server 140 executes a search, reads an image corresponding to the search result, and sends the image to the program 2210 via the communication path 2300.
[0044]
When performing a search using drawing data created on a client program 2210 described later as a key, the program 2210 sends the corresponding data to the similar search server 140 as image data for new registration. The similarity search server 140 extracts feature amounts from the sent data, stores the feature amount data in the feature amount data file 142, and stores image data corresponding to the feature amount data in the image file set 2120. The program 2210, after confirming the registration of the send data, issues a search request using that data as a key. The program 2210 has a file 2220 for storing the created screen data and the like.
[0045]
FIG. 7 is a display example of a screen for creating a drawing for a search key on the client program 2210. The search is performed on the shape and arrangement of the constituent elements. The display unit 310 is a part that performs drawing. In the background lattice formed by the vertical and horizontal lattice lines, one base corresponds to the size of a tatami mat. What is displayed on the display unit 320 is a list of floor plan components. After selecting a floor plan component to be designated from the list, when a mouse is dragged on the display unit 310, a rectangular area filled with the corresponding color is drawn. The size, aspect ratio, and position of the rectangular area can be changed by operating the mouse. In the display example, the shared part 321 is selected, the rough shape 311 of the house is drawn, and the entrance portion 312 and the water 313 are drawn thereon.
[0046]
By pressing the button 330, a floor plan similar to the drawn drawing is searched. A button 340 designates a search target. In this display example, the drawing for the first floor portion is a search target. The button 350 is a check box for designating whether or not to enable the size of the drawn drawing as a search feature amount. In this display example, the setting does not take into account the difference in size when searching. The button 360 is a check box for designating whether or not to enable the price of the house as a search feature amount. When this check box is checked, the price setting that can be entered on the right is valid as a search condition.
[0047]
FIG. 8 is a display example of the search result displayed on the display device 25. The top 20 floor plans 400 are displayed in descending order of similarity to the drawn drawings.
[0048]
In the search key of this example, only the entrance and the water area are specified. Therefore, when calculating the similarity between the drawn drawing and the stored house floor plan, the features obtained from the coincidence of the entrance and the surroundings and the shape of the whole floor plan are used.
[0049]
FIG. 9 is a panel for displaying an actually effective feature amount and changing the effective feature amount. Display unit 510 displays whether or not the similarity of each layout component (part) is valid as a search condition. Further, in this display example, the check boxes corresponding to the entrance and the area around the water are checked. That is, on display unit 510, a component is selected.
[0050]
The button 511 is a button for enabling the similarity of all floor plan parts. When this button is pressed, all the check boxes on the display unit 510 are checked. A button 512 is a button for invalidating the similarity of all floor plan parts. When this button is pressed, all the check boxes on the display unit 510 are not checked.
[0051]
A button 521 is a check box indicating whether similarity of the shape of the entire floor plan is valid as a search condition. A button 522 is a check box indicating whether similarity in the aspect ratio of the drawing is valid as a search condition. A button 523 is a check box indicating whether or not the similarity of the drawing size values is valid as a search condition. A button 524 is a check box indicating whether or not the similarity of the house price is valid as a search condition.
[0052]
When the search condition is changed by changing the state of the check box on the panel of FIG. 9 and then the button 530 is pressed, the changed search condition is transmitted to the similar image search server 140.
[0053]
Each component of the display unit 510 is provided with a slider 513 for designating a weight as necessary. The designated weight is used as one of the search conditions. In FIG. 9, the weight is selected in the range of 0-10. When the weight is specified, the influence on the search result changes according to the size.
[0054]
Note that the weight 0 is equivalent to selecting no component and the weight 10 is equivalent to selecting the component. Therefore, the selection non-selection of the component on the display unit 510 can be represented by 0 and 10 of the weight. .
[0055]
The panel in FIG. 10 is the same as the panel in FIG. 9, but the check box 610 corresponding to the Japanese-style room is checked, and the Japanese-style room is additionally selected.
[0056]
FIG. 11 shows a result of searching under the conditions of FIG. 10 using the drawing 700 displayed at the top as key data. Since the search key drawing itself always has the maximum similarity, it is displayed at the top. An area 710 in the drawing 700 is a water area, an area 720 is a Japanese-style room, and an area 730 is an entrance. Residential floor samples that are close in arrangement with respect to the three floor plan components are searched.
[0057]
Now, regarding the exterior of the house, each component such as the entire house layout (building), gates, trees, ponds, roads, etc. is regarded as a component of the house layout, and the exterior of the house is regarded as the entire house layout. Then, it becomes possible to search for a housing exterior using the same method and apparatus as for searching for a house layout.
[0058]
FIG. 12 is a display example of a search condition input screen in a site plan search performed from such a viewpoint. Display unit 810 is a screen for inputting a site plan. In FIG. 12, 811 is the site outline, 812 is the building part, 813 is the tree, 814 is the pond, 815 is the entrance, and 816 is the surrounding road. As in the case shown in FIG. 7, a component to be drawn is selected from the external component list of the display unit 820, and its shape and position are input on the display unit 810. Further, in FIG. 12, 830 is a search execution button, 840 is a check box for specifying whether or not the absolute size of the drawing is enabled as a search condition, and 850 is whether or not the price is enabled as a search condition. It is a check box that specifies whether or not.
[0059]
In the above description, the road is added to the component and the search is performed. However, the present invention is not limited to such a search, and the search is performed for the range in the residential premises without including the road. Also good.
[0060]
【The invention's effect】
According to the present invention, it is possible to perform a search based on the similarity of the shape and spatial arrangement of elements constituting the house floor plan, and the similarity of the overall shape of the house floor plan, thereby enabling an accurate search of the house floor plan.
[Brief description of the drawings]
FIG. 1 is a configuration diagram for explaining an embodiment of a house layout search device according to the present invention.
FIG. 2 is a flowchart for explaining an embodiment of the house layout search program according to the present invention.
FIG. 3 is a flowchart for explaining another embodiment of the house layout search program of the present invention.
4 is a diagram for explaining a procedure for constructing floor plan data to be searched in FIG. 2;
FIG. 5 is a diagram for explaining an example of a vector direction intensity distribution histogram;
6 is a configuration diagram for explaining a system that executes search processing in FIGS. 2 and 3. FIG.
FIG. 7 is a view for explaining creation of a drawing serving as a search key.
FIG. 8 is a diagram showing a display example of search results.
FIG. 9 is a diagram for explaining setting of a search condition.
FIG. 10 is a diagram for explaining how search conditions are changed.
FIG. 11 is a diagram showing another display example of search results.
FIG. 12 is a diagram for explaining the creation of a drawing serving as a search key in a housing exterior search according to the present invention.
[Explanation of symbols]
11 ... Storage device, 12 ... CPU, 17, 27 ... Communication connection device, 21 ... Residential layout search program, 25 ... Display device, 110 ... Input data file, 111 ... CAD data file, 112 ... Bibliographic data file, 120 ... Image converter, 130 ... image file, 140 ... similar image search server, 142 ... feature data file, 2100 ... home layout search device, 2120 ... data file, 2200 ... external processing device, 2210 ... client program, 2300 ... communication path.

Claims (4)

A home layout search program for searching for a home floor plan by a computer, the program comprising:
A procedure for converting a drawing into a color image by assigning different colors depending on the type of component to a closed region for each component in the drawing depicting the house layout;
Dividing the color image into a plurality of regions;
A procedure for calculating a color distribution feature amount for each divided area and obtaining a set of all the areas;
And a procedure for searching for a house floor plan having a high similarity between the color distribution feature quantity set and the house floor plan as a search key ,
A housing layout search program characterized in that a weight is specified for the component of the house floor plan, and the similarity of the color distribution feature quantity set is obtained in consideration of the weight . After causing the computer to execute the above-described procedure for searching for a house floor plan having a high similarity in the color distribution feature amount set obtained by adding the weights ,
A procedure for generating a binary image by canceling the above color assignment and designating different colors for the house layout part and other parts in the drawing depicting the house layout anew .
A procedure for obtaining a luminance gradient vector from the binary image and creating a luminance gradient vector image;
Dividing the luminance gradient vector image into a plurality of regions;
A procedure for calculating a histogram of luminance gradient vector distribution for each divided area and obtaining a set of all the areas;
The home floor plan search program according to claim 1, wherein a home floor plan as a search key and a procedure for searching for a home floor plan having a high similarity between the brightness gradient vector distribution histogram sets are executed. The high similarity house floor plans further residential floor plan search program according to claim 1, wherein the high degree of coincidence between bibliographic attributes residential floor plan to the search key has. A housing exterior search program for retrieving a housing exterior by a computer, the program being stored in the computer,
A procedure for converting a drawing into a color image by assigning different colors to the closed region for each component in the drawing depicting the exterior of the house, depending on the type of component,
Dividing the color image into a plurality of regions;
A procedure for calculating a color distribution feature amount for each divided area and obtaining a set of all the areas;
And executing a procedure for searching for a housing exterior with a high similarity between the color distribution feature quantity set and the housing exterior as a search key ,
A housing exterior search program characterized in that weights are specified for the component parts of the housing exterior, and the similarity of the color distribution feature quantity set is obtained in consideration of the weights .

Images