JP2022014146A - Brightness feeling prediction device and brightness feeling prediction program - Google Patents

Abstract

To predict a brightness feeling in an object space with high accuracy.SOLUTION: A screen type setting part 26 defines each image region corresponding to each screen contained in a luminance image 20 representing an object space, and sets a screen type in a plurality of image regions defined. A brightness feeling prediction part 28 refers to weight information 22 to which a weight indicating a contribution level to a brightness feeling is related for each screen type which can be defined in the luminance image 20 to predict the brightness feeling of the object space represented by the luminance image 20 on the basis of a representative value of a luminance value of a plurality of pixels contained in each image region 40 set by the screen type setting part 26 and the weight of the screen type of each image region 40.SELECTED DRAWING: Figure 1

Description

The present invention relates to a brightness prediction device and a brightness prediction program.

In recent years, an index called a sense of brightness, which indicates the amount of brightness that humans perceive in space, has been proposed. The sense of brightness is the amount of brightness that humans perceive, and is an index different from the illuminance, which is a physical quantity that represents the brightness of light that illuminates the surface of an object. Therefore, for example, even if the illuminance of the lighting installed in the space is large, the feeling of brightness for the space is not always large.

Conventionally, devices or programs that predict the feeling of brightness in space have been proposed. For example, Patent Document 1 discloses a brightness feeling predicting device that predicts the brightness feeling of the space based on the brightness of each pixel included in the image of the target space that is the object for predicting the brightness feeling. Has been done. Further, Patent Document 2 discloses a brightness feeling predicting device that predicts the brightness feeling of the space based on the illuminance at a point on a vertical surface in the target space.

Japanese Patent No. 3995201 International Publication No. 2012/046840 Pamphlet

Conventionally, when predicting the feeling of brightness of the target space by a device or a program, there is a case where a feeling of brightness different from the feeling of brightness actually felt by a human being from the target space is predicted. That is, there are cases where it is not possible to properly predict the feeling of brightness with respect to the target space.

An object of the present invention is to predict the feeling of brightness of a target space with high accuracy.

In the present invention, the surface type setting unit that sets the surface type of each image area corresponding to each surface included in the luminance image representing the target space, and the weight indicating the degree of contribution to the feeling of brightness for each surface type are used. With reference to the associated weight information, the brightness feeling of the target space is based on the luminance values of the plurality of pixels included in the image region and the weights of the surface types of the image region for each of the plurality of image regions. It is a brightness feeling prediction device characterized by including a brightness feeling prediction unit for predicting.

Desirably, the brightness prediction unit is located in the vicinity of the representative value of the luminance values of the plurality of pixels included in the first image region and the vicinity of the first image region in the luminance image among the plurality of image regions. It is characterized in that the feeling of brightness of the target space is predicted based on the ratio of the luminance values of the plurality of pixels included in the second image region to the representative values.

Desirably, the brightness prediction unit includes a representative value of the luminance values of a plurality of pixels included in the image region whose surface type is the floor surface among the plurality of image regions, and a plurality of brightness values included in the other image regions. It is characterized in that the feeling of brightness of the target space is predicted without considering the ratio of the brightness value of the pixel to the representative value.

Desirably, the brightness feeling predicting unit intermittently predicts the brightness feeling of the target space, and the brightness feeling of the target space predicted immediately before and the brightness feeling of the target space predicted this time. It is characterized in that the brightness feeling of the target space predicted this time is corrected based on the difference between the above.

Further, the present invention comprises a surface type setting unit for setting a surface type of each image area corresponding to each surface included in a luminance image representing a target space, and a contribution to a sense of brightness for each surface type. With reference to the weight information associated with the weight indicating the degree, the target is based on the brightness values of the plurality of pixels included in the image region and the weight of the surface type of the image region for each of the plurality of image regions. It is a brightness prediction program characterized by functioning as a brightness prediction unit that predicts the brightness of a space.

According to the present invention, it is possible to predict the feeling of brightness of the target space with high accuracy.

It is a block diagram of the brightness feeling prediction apparatus which concerns on this embodiment. It is a figure which shows the example of the luminance image. It is a conceptual diagram which shows an example of weight information. It is a figure which shows the image area defined in the luminance image.

FIG. 1 is a schematic configuration diagram of a brightness feeling prediction device 10 according to the present embodiment. The brightness feeling prediction device 10 is, for example, a server computer, a personal computer, a tablet terminal, or the like, but may be any device as long as the functions described below can be exhibited. Further, although the brightness feeling prediction device 10 according to the present embodiment exerts each function described below in one device, each function of the brightness feeling prediction device 10 may be exerted by a plurality of devices.

The communication unit 12 includes, for example, a network adapter and the like. The communication unit 12 exhibits a function of communicating with another device (for example, a camera or an image processing device that processes an image captured by the camera) via a communication line such as a LAN or the Internet. For example, the communication unit 12 receives the luminance image 20 described later from another device. Further, the communication unit 12 may transmit the prediction result by the brightness feeling prediction unit 28, which will be described later, to another device.

The display unit 14 includes, for example, a liquid crystal display, an organic EL display, and the like. The display unit 14 displays various screens. For example, the display unit 14 can display the luminance image 20 and the prediction result by the brightness feeling prediction unit 28.

The input unit 16 includes, for example, a mouse, a keyboard, a touch panel, a microphone, and the like. The input unit 16 is used to input an instruction from the user to the brightness feeling prediction device 10.

The storage unit 18 includes, for example, a hard disk, SSD, ROM, RAM, or the like. The storage unit 18 stores a brightness prediction program for operating each unit of the brightness prediction device 10. Further, as shown in FIG. 1, the luminance image 20 and the weight information 22 are stored in the storage unit 18.

The luminance image 20 is an image representing a target space, which is a space for which a brightness feeling is predicted by the brightness feeling prediction device 10. The target space in the present specification is a space including a plurality of types of surfaces (for example, a wall surface, a ceiling surface, a floor surface, etc.). For example, the target space is an indoor space.

FIG. 2 shows an example of the luminance image 20. The luminance image 20 is a two-dimensional array of a plurality of pixels. Each pixel included in the luminance image 20 may have at least a luminance value as a pixel value. The luminance image 20 may be a camera image obtained by photographing the target space with a camera. Further, in the camera image, the range (range) of the brightness value of each pixel is relatively narrow (for example, 0 to 255), whereas in the brightness image 20, the brightness is processed to expand the brightness range of each pixel of the camera image. It is preferable that it is an extended image. The luminance image 20 may be an image formed by a computer program, for example, a CG image, instead of an image based on a camera image. The brightness feeling prediction device 10 receives the luminance image 20 from another device by the communication unit 12 described above and stores it in the storage unit 18. Alternatively, the brightness feeling prediction device 10 may form the luminance image 20.

Returning to FIG. 1, the weight information 22 is information in which weights indicating the degree of contribution to the feeling of brightness are associated with each surface type that can be defined in the luminance image 20. As described above, the target space includes a plurality of types of surfaces, but the inventor of the present invention has a surface according to the surface type included in the target space based on the results of a survey such as a questionnaire. It was found that the influence of the brightness value of each pixel included in the subject space on the feeling of brightness of the target space, that is, the degree of contribution to the feeling of brightness is different. Therefore, the weight indicating the degree of contribution to the feeling of brightness for each surface type based on the survey result is stored in the storage unit 18 in advance as the weight information 22.

FIG. 3 shows an example of the weight information 22. FIG. 3 shows a ceiling surface, a front wall surface, a side wall surface, and a floor surface as surface types. The ceiling surface is a surface corresponding to the ceiling of the target space, the front wall surface is a surface corresponding to the wall extending in the left-right direction of the brightness image 20 in the field of view of the brightness image 20, and the side wall surface is the surface corresponding to the brightness. In the field of view of the image 20, the surface corresponding to the wall extending in the depth direction, and the floor surface is the surface corresponding to the floor of the target space. Of course, the surface type is not limited to these, and other types of surfaces (for example, window surfaces) may be included.

Of the four surface types shown in FIG. 3, the invention of the present invention states that the degree of contribution to the sense of brightness of the target space is in the order of front wall surface, ceiling surface, side wall surface, and floor surface from the largest. Found. Therefore, among the four surface types, the weight of the front wall surface is the largest, the weight of the ceiling surface is the next largest, the weight of the side wall surface is the next largest, and the weight of the floor surface is the smallest. The actual value of the weight is an example, and may be appropriately changed according to an equation for calculating the feeling of brightness.

Returning to FIG. 1, the control unit 24 includes, for example, various control devices such as a CPU, GPU, ASIC, and FPGA. The control unit 24 controls each unit of the brightness sensation prediction device 10 based on the brightness sensation prediction program stored in the storage unit 18. In particular, as shown in FIG. 1, the control unit 24 functions as a surface type setting unit 26 and a brightness feeling prediction unit 28.

The surface type setting unit 26 first defines each image area corresponding to each surface included in the luminance image 20. In the present embodiment, the surface type setting unit 26 defines a plurality of image regions by performing image analysis on the luminance image 20. Specifically, the surface type setting unit 26 performs edge detection processing on the luminance image 20, and sets the region surrounded by the detected edge or the region surrounded by the detected edge and the side of the luminance image 20 as 1. Defined as one image area. At this time, the area below the predetermined area (number of pixels) may be ignored without being defined as an image area. As a result, objects other than the surface included in the luminance image 20 (for example, furniture, pillars, etc.) can be excluded. Further, the surface type setting unit 26 may define a plurality of image areas in the luminance image 20 according to an instruction from the user without performing image processing on the luminance image 20.

Next, the surface type setting unit 26 sets the surface types of a plurality of defined image areas. In the present embodiment, the surface type setting unit 26 sets the surface type based on the shape of the defined image area and the position in the luminance image 20. For example, the surface type setting unit 26 is a trapezoidal image region in which the upper base and the lower base are parallel to each other, the upper base is longer than the lower base, and the image region is located on the upper side in the luminance image 20. Set the surface type of to ceiling surface. Further, the surface type setting unit 26 is a quadrangular image region, and the surface type of the image region in which at least one side on the left and right sides is vertical (extended in the vertical direction in the luminance image 20) is referred to as a side wall surface. Set. Further, the surface type setting unit 26 may specify the surface type of each image area according to an instruction from the user, regardless of the shape of the defined image area or the position in the luminance image 20.

FIG. 4 shows a plurality of image regions 40 defined in the luminance image 20 shown in FIG. 2 and surface types of each image region 40. In FIG. 4, the ceiling surface 40a, the front wall surface 40b, the side wall surface 40c, and the floor surface 40d are set in the luminance image 20.

The brightness feeling prediction unit 28 predicts the brightness feeling of the target space represented by the luminance image 20. It is known that the sense of brightness felt by humans with respect to the target space is proportional to the logarithm of the brightness of each part of the target space. Therefore, the brightness feeling prediction unit 28 basically uses the brightness feeling of the target space as a numerical value based on the geometric mean brightness value which is the geometric mean value of the brightness values of the plurality of pixels constituting the luminance image 20. Predict. Since various methods have been conventionally proposed for calculating the predicted value of the feeling of brightness, detailed description thereof will be omitted here. Since it is known that the light source (for example, a light bulb) included in the luminance image 20 has a considerably small influence on the brightness feeling, the brightness feeling prediction unit 28 has the brightness of the pixel corresponding to the light source. Not used to predict the feeling. Specifically, the brightness prediction unit 28 considers a pixel having a brightness value of a predetermined value or more as a pixel corresponding to a light source, and the brightness is based on the geometric mean value of the brightness values of other pixels excluding the pixel. Predict the feeling.

In particular, in the present embodiment, the brightness prediction unit 28 refers to the weight information 22, and is a representative value (for example, geometric average) of the luminance values of a plurality of pixels included in each image area 40 set by the surface type setting unit 26. The brightness feeling of the target space represented by the luminance image 20 is predicted based on the luminance value (hereinafter referred to as “luminance representative value”) and the weight of each surface type of the image region 40. Specifically, the brightness feeling prediction unit 28 changes the degree of influence of the brightness representative value of each image area 40 on the brightness feeling of the target space according to the weight of each surface type indicated by the weight information 22. , Predict the feeling of brightness in the target area. In an extreme example, when there is an image region 40 having a weight of 0, the brightness feeling prediction unit 28 predicts the brightness feeling of the target space by ignoring the brightness representative value of the image region 40.

Various methods can be adopted as the method, and as an example thereof, the brightness feeling prediction unit 28 first obtains a luminance representative value of the image domain 40, for example, a geometric mean luminance value for each image domain 40. On top of that, the luminance representative value of the image region 40 having a larger weight is more important, in other words, the luminance representative value of the image region 40 having a smaller weight is more neglected to predict the brightness feeling of the target space.

For example, assuming that the weight information 22 is as shown in FIG. 3, since the weight of the front wall surface 40b is large, when the representative brightness value of the front wall surface 40b is large, the feeling of brightness of the target space becomes large (feels bright). ), And when the representative brightness value of the front wall surface 40b is small, it acts greatly in the direction in which the feeling of brightness of the target space becomes small (feels dark). On the other hand, since the weight of the floor surface 40d is small, even when the brightness representative value of the floor surface 40d is large, it does not act much in the direction of increasing the brightness feeling of the target space, and the brightness representative of the floor surface 40d. Even if the value is small, it does not work so much in the direction that the feeling of brightness of the target space becomes small.

Further, the brightness prediction unit 28 has a luminance representative value of the first image region 40 in the luminance image 20 and a luminance representative value of the second image region 40 located in the vicinity of the first image region 40 in the luminance image 20. It is preferable to predict the feeling of brightness of the target space based on the ratio of. Here, the second image area 40 located in the vicinity of the first image area 40 is typically an image area 40 adjacent to the first image area 40, but is located in the vicinity of the first image area 40. If so, the second image area 40 does not necessarily have to be adjacent to the first image area 40.

The inventor of the present invention feels that in the luminance image 20, the larger the ratio of the luminance representative values of the two image regions 40 in the vicinity is, the darker the human being is with respect to the target space, that is, the smaller the sense of brightness. I found that. The large ratio of the luminance representative values of the two image regions 40 means that the difference between the luminance representative values of the two image regions 40 is large. With reference to FIG. 2, for example, when the ratio of the brightness representative value between the central ceiling surface and the side wall adjacent to the central ceiling surface is large, the ratio of the brightness representative value between the ceiling surface and the side wall is large. Humans feel that the target space is darker than when it is small.

Therefore, the brightness feeling prediction unit 28 has, for each image area 40 (each first image area 40) included in the luminance image 20, with each of the other plurality of image areas 40 (second image area 40) in the vicinity thereof. Calculate the ratio of the representative brightness values between. Then, the feeling of brightness of the target space is predicted in consideration of the sum or the average value of the calculated plurality of ratios. Specifically, the larger the total or average value of the calculated ratios, the smaller the brightness of the target space, and the smaller the total or average value of the calculated ratios, the smaller the brightness of the target space. Enlarge.

In general, the floor surface 40d tends to have a considerably low representative luminance value. Therefore, even if a person feels relatively bright with respect to the target space, the image area 40 corresponding to the floor surface 40d and another image area 40 in the vicinity thereof (for example, the front wall surface 40b or the side wall surface 40c). The ratio of the representative luminance value to the image region 40) corresponding to the above tends to be large. Therefore, when calculating the ratio of the representative luminance values between the two image regions 40, it is preferable that the brightness prediction unit 28 does not consider the image region 40 corresponding to the floor surface 40d set by the surface type setting unit 26. Is. In other words, the brightness prediction unit 28 does not consider the ratio between the luminance representative value of the image region 40 corresponding to the floor surface 40d and the luminance representative value of the other image region 40, and the brightness of the target space. It is preferable to predict the feeling.

Further, the brightness feeling prediction unit 28 intermittently predicts the brightness feeling of the same target space at a plurality of different times. For example, the brightness prediction unit 28 periodically predicts the brightness of the target space, such as every 30 minutes or every 5 minutes. This is because the feeling of brightness of the target space may change depending on the time of day. For example, since sunlight is the light source in the daytime, the position of the sun changes depending on the time of day, which changes the way the light hits the target space and the feeling of brightness may change. Moreover, since the main light source is a lighting fixture at night, the feeling of brightness in the same target space may be completely different from that in the daytime.

The brightness feeling prediction unit 28 intermittently predicts the brightness feeling of the target space based on the plurality of luminance images 20 acquired intermittently. For example, a camera that captures an image of a certain target space is fixedly installed, and the camera intermittently photographs the target space to acquire a plurality of camera images. The plurality of camera images may be a plurality of luminance images 20, and a plurality of luminance expanded images processed to expand the luminance range of each camera image may be a plurality of luminance images 20.

When the space changes from a bright space to a dark space, humans (eyes) are not accustomed to the darkness at first and it is quite difficult to see the surroundings, but as time goes by, the eyes gradually become accustomed to the surroundings. It becomes easier to see (dark adaptation). Also, when the space changes from a dark space to a bright space, humans (eyes) are not accustomed to the brightness at first and it is quite difficult to see the surroundings, but the eyes gradually become accustomed to it over time. It becomes easier to see the surroundings (light adaptation).

When predicting the feeling of brightness of the target space intermittently, the feeling of brightness prediction unit 28 may predict the feeling of brightness of the target space in consideration of the above-mentioned dark adaptation or light adaptation. Specifically, the brightness prediction unit 28 predicts the brightness of the target space this time based on the difference between the brightness feeling of the target space predicted immediately before and the brightness feeling of the target space predicted this time. You may try to correct the feeling.

Specifically, the brightness prediction unit 28 increases the difference between the brightness feeling of the target space predicted immediately before and the brightness feeling of the target space predicted this time, the larger the difference is, the brightness of the target space predicted this time. Correct so that the feeling of touch is reduced. In other words, the brightness prediction unit 28 has the smaller the difference between the brightness feeling of the target space predicted immediately before and the brightness feeling of the target space predicted this time, the smaller the difference is, the more the target space predicted this time. Correct so that the feeling of brightness becomes large.

For example, it is assumed that the feeling of brightness is expressed by a numerical value from 0 to 20, and the brightness of the target space predicted this time is 5 (that is, it is predicted to be relatively dark). At this time, the brightness feeling prediction unit 28 predicts immediately before the case where the brightness feeling of the target space predicted immediately before is 6, that is, the difference in the brightness feeling is 1. When the brightness feeling of the target space is 12, that is, when the difference in brightness feeling is 7, that is, when the difference is large, the correction is made so that the predicted value of the brightness feeling this time becomes smaller. do.

Further, it is assumed that the brightness of the target space predicted this time is 15 (that is, it is predicted to be relatively bright). At this time, the brightness feeling prediction unit 28 predicts immediately before the case where the brightness feeling of the target space predicted immediately before is 14, that is, the difference in the brightness feeling is -1. When the brightness feeling of the target space is 9, that is, when the difference in brightness feeling is -6, that is, when the difference is small, the predicted value of the brightness feeling this time becomes larger. Make corrections.

The outline of the configuration of the brightness feeling prediction device 10 according to the present embodiment is as described above. According to the brightness feeling prediction device 10, weights are set according to a plurality of surface types defined in the brightness image 20, and the weights are taken into consideration to give a feeling of brightness in the target space based on the brightness image 20. is expected. As a result, it is possible to predict the feeling of brightness with higher accuracy, that is, the feeling of brightness closer to the actual feeling of human beings, as compared with the case where the feeling of brightness is predicted at least without considering the surface type included in the luminance image 20.

Although the embodiments according to the present invention have been described above, the present invention is not limited to the above-described embodiments, and various modifications can be made without departing from the spirit of the present invention.

10 Brightness prediction device, 12 Communication unit, 14 Display unit, 16 Input unit, 18 Storage unit, 20 Luminance image, 22 Weight information, 24 Control unit, 26 Surface type setting unit, 28 Brightness prediction unit, 40 images Area, 40a ceiling surface, 40b front wall surface, 40c side wall surface, 40d floor surface.

Claims (5)

A surface type setting unit that sets the surface type of each image area corresponding to each surface included in the luminance image representing the target space, and a surface type setting unit.
With reference to the weight information associated with the weight indicating the degree of contribution to the feeling of brightness for each surface type, the brightness values of the plurality of pixels included in the image area and the image for each of the plurality of image areas. A brightness prediction unit that predicts the brightness of the target space based on the weight of the surface type of the region,
A brightness prediction device characterized by being equipped with. The brightness prediction unit has a representative value of the luminance values of a plurality of pixels included in the first image region among the plurality of image regions, and a second image region located in the vicinity of the first image region in the luminance image. Further, the brightness feeling of the target space is predicted based on the ratio of the luminance values of the plurality of pixels included in the image region to the representative values.
The brightness feeling prediction device according to claim 1. The brightness prediction unit is a representative value of the brightness values of a plurality of pixels included in the image region whose surface type is the floor surface among the plurality of image regions, and the brightness of the plurality of pixels included in the other image regions. Predicting the feeling of brightness in the target space without considering the ratio of the value to the representative value.
The brightness feeling prediction device according to claim 2. The brightness prediction unit is
Intermittently predict the brightness of the target space,
The brightness feeling of the target space predicted this time is corrected based on the difference between the brightness feeling of the target space predicted immediately before and the brightness feeling of the target space predicted this time.
The brightness feeling prediction device according to any one of claims 1 to 3, wherein the brightness feeling predicting device is characterized. Computer,
A surface type setting unit that sets the surface type of each image area corresponding to each surface included in the luminance image representing the target space, and a surface type setting unit.
With reference to the weight information associated with the weight indicating the degree of contribution to the feeling of brightness for each surface type, the brightness values of the plurality of pixels included in the image area and the image for each of the plurality of image areas. A brightness prediction unit that predicts the brightness of the target space based on the weight of the surface type of the region,
Brightness prediction program characterized by functioning as.

Images