JP2013195185A - Object detector, object detection method, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an object detector, an object detection method, and a program which can accurately detect the existence or nonexistence of a detection object without being affected by a color of the object.SOLUTION: An object detector 102 comprises: a sensor data acquisition section 103; an image data acquisition section 104; and a correction determination section 105. The sensor data acquisition section 103 acquires sensor data from an infrared sensor 106 detecting infrared which is applied to a determination area a1 and which is reflected. The image data acquisition section 104 acquires image data of the determination area a1. The correction determination section 105 corrects the sensor data on the basis of the image data, and determines whether or not an object exists in the determination area a1 by using the corrected sensor data.

Description

  The present invention relates to an object detection apparatus, an object detection method, and a program for detecting whether or not an object exists in a predetermined determination area.

  In recent years, many electronic devices such as personal computers have a power saving function. As an example of this power saving function, there is a function of reducing power consumption when the user is not using an electronic device. For example, in the case of a personal computer, if there is no input for a certain period of time, the screen is first turned off.

  Recently, electronic devices equipped with a sensor such as an infrared sensor for detecting the presence of a user have appeared (for example, see Patent Documents 1 to 4). The electronic devices described in Patent Literatures 1 and 2 determine whether the user is in front of the device according to the detection result of the sensor. That is, whether the user is present or away is detected by the sensor. When the user is away from the seat in front of the electronic device, the electronic device shifts to the power saving mode. On the other hand, when the user is sitting on the seat in front of the electronic device, the electronic device cancels the power saving mode.

JP2011-257996A JP 2011-202987 A JP 2010-160114 A JP-A-5-164555

  The infrared sensor has, for example, a light emitting element that emits infrared rays and a light receiving element that receives infrared rays reflected by an object. This infrared sensor acquires the distance between the sensor and an object that reflects infrared rays as distance data (received light amount data). Then, the electronic device uses this distance data to determine whether the user is present or away. However, this infrared sensor has variations in distance data due to the color of the object. For example, even when the distance between the user and the electronic device is constant, the distance data of the infrared sensor is different when the user is wearing white clothes and when the user is wearing black clothes.

  Specifically, when the user wears white clothes as a color having a high light reflectance, the intensity of light incident on the light receiving element is large. For this reason, the distance between the user and the electronic device detected by the infrared sensor is close to the actual value.

  On the other hand, when the user wears black clothes having a low light reflectance, the intensity of light incident on the light receiving element is small. For this reason, the distance between the user and the electronic device detected by the infrared sensor may be larger than the actual distance. For this reason, although the user is actually present in front of the electronic device, the user may be judged to be away from the seat because he is wearing black clothes. That is, the presence / absence determination may not be performed correctly.

  In any of the configurations described in Patent Documents 1 to 4, the sensor is not configured to identify a color. For this reason, there is a limit to correct the deviation of the detection result of the sensor due to the color of the object, and there is a limit to the accuracy of the presence determination.

  An example of an object of the present invention provides an object detection device, an object detection method, and a program that can accurately detect the presence or absence of an object without the influence of the color of the object, eliminating the above problem. There is.

In order to achieve the above object, an object detection apparatus according to one aspect of the present invention includes:
A sensor data acquisition unit that acquires sensor data that identifies the detection result of the infrared ray from an infrared sensor that detects the infrared ray that is irradiated and reflected on a predetermined determination region;
An image data acquisition unit for acquiring image data of the determination region;
A correction determination unit that corrects the sensor data based on the image data, and determines whether or not an object exists in the determination region using the corrected sensor data;
It is characterized by having.

In order to achieve the above object, an object detection method according to one aspect of the present invention includes:
(A) acquiring sensor data for specifying the detection result of the infrared ray from an infrared sensor that detects the reflected infrared ray that has been irradiated and reflected on a predetermined determination region;
(B) obtaining image data of the determination area;
(C) correcting the sensor data based on the image data, and determining whether an object exists in the determination region using the corrected sensor data;
It is characterized by including.

In order to achieve the above object, a program according to one aspect of the present invention is stored in a computer.
(A) acquiring sensor data for specifying the detection result of the infrared ray from an infrared sensor that detects the reflected infrared ray that has been irradiated and reflected on a predetermined determination region;
(B) obtaining image data of the determination area;
(C) correcting the sensor data based on the image data, and determining whether an object exists in the determination region using the corrected sensor data;
Is executed.

  As described above, according to the present invention, the presence or absence of a detection target can be accurately detected without being affected by the color of the detection target.

It is a block diagram which shows the structure of the object detection system in embodiment of this invention. It is a typical side view of an object detection system, and has shown the state where a person is present in the judgment field ahead of an object detection system. It is a figure which shows an example of the image which the imaging | photography part image | photographed. It is a histogram which shows the relationship between each brightness and the number of pixels. It is a figure for demonstrating a correction value table. It is a flowchart which shows operation | movement of the object detection system in embodiment of this invention. It is a flowchart for demonstrating the flow of calculation of reference | standard lightness. It is a block diagram which shows an example of the computer which implement | achieves the object detection apparatus in embodiment of this invention.

  Hereinafter, an object detection device, an object detection method, and a program according to an embodiment of the present invention will be described with reference to the drawings.

[overall structure]
First, the configuration of an object detection system including an object detection device according to an embodiment of the present invention will be described with reference to FIG. FIG. 1 is a block diagram showing a configuration of an object detection system 101 according to an embodiment of the present invention.

  As shown in FIG. 1, the object detection system 101 includes an object detection device 102. The object detection device 102 determines whether or not a person is present around the object detection system 101, that is, whether or not a person is present. The object detection apparatus 102 includes a sensor data acquisition unit 103, an image data acquisition unit 104, and a correction determination unit 105.

  The sensor data acquisition unit 103 acquires sensor data from the infrared sensor 106 provided in the object detection system 101. The infrared sensor 106 irradiates a predetermined determination area a1 (see FIG. 2 described later) with infrared rays, and detects the reflected infrared rays, thereby generating sensor data specifying the detection result of the infrared rays. The sensor data includes distance data. The distance data is data for specifying the distance between the infrared sensor 106 and the position where the infrared ray from the infrared sensor 106 is reflected.

  The greater the value d1 (hereinafter also referred to as the distance data value d1) indicated by the distance data of the infrared sensor 106, the closer the distance from the infrared sensor 106 to the position where the infrared light is reflected from the infrared sensor 106. The distance data is data indicating the amount of light received by the infrared sensor 106.

  The image data acquisition unit 104 acquires image data obtained by shooting the determination area a1 from the shooting unit 107. The image data is color image data.

  The correction determination unit 105 corrects the sensor data based on the image data. The correction determination unit 105 determines whether or not there is a person in the determination area a1 using the corrected sensor data.

  As described above, in the present embodiment, sensor data for determining whether or not a person is present in the determination area a1 is corrected based on the image data. As described above, by using the image data, the brightness information of the determination area a1 can be obtained. Therefore, the sensor data (distance data) from the infrared sensor 106 that generates different sensor data due to the difference in color such as the color of clothes worn by a person is corrected based on the brightness data of the image data. can do. For this reason, it is possible to more accurately determine the presence or absence of a person using the infrared sensor 106. As a result, the presence or absence of a person can be accurately detected without being affected by the color.

  The above is a schematic description of the object detection apparatus 102. Next, a more specific configuration of the object detection system 101 will be described with reference to FIGS. 2 to 7 in addition to FIG. FIG. 2 is a schematic side view of the object detection system 101, and shows a state where a person H is present in the determination area a1 in front of the object detection system 101. FIG.

  As shown in FIGS. 1 and 2, in the present embodiment, a personal computer or the like can be exemplified as the object detection system 101. In the present embodiment, a case will be described in which the object detection system 101 is a notebook personal computer (notebook personal computer).

  In the present embodiment, the object detection system 101 includes an object detection device 102, an infrared sensor 106, an imaging unit 107, and a display unit 108.

  In the present embodiment, display unit 108 is a power control target and is a liquid crystal display or the like.

  In the present embodiment, the infrared sensor 106 is fixed to the housing 110 of the object detection system 101 and is disposed above the display unit 108. In the present embodiment, the infrared sensor 106 is a so-called active infrared sensor, and includes a light emitting element and a light receiving element. The light emitting element emits infrared rays to the determination area a1 in front of the object detection system 101. The light receiving element receives infrared rays.

  In the present embodiment, when the person H is present in the determination area a <b> 1, the infrared light from the light emitting element of the infrared sensor 106 is reflected by the person H and is incident on the light receiving element of the infrared sensor 106. On the other hand, when the person H is not present in the determination area a1, the infrared light from the light emitting element of the infrared sensor 106 is reflected by a chair or a wall and is incident on the light receiving element of the infrared sensor 106. The determination area a1 is set in front of the object detection system 101, and is set within a range of about 1 m from the infrared sensor 106, for example. In the present embodiment, an imaging unit 107 is arranged so as to be adjacent to the infrared sensor 106.

  Note that the infrared sensor 106 and the imaging unit 107 may each be incorporated in a computer that constitutes the object detection device 102, or may be configured as a discrete component that is retrofitted to the computer that constitutes the object detection device 102. Also good.

  In the present embodiment, the photographing unit 107 includes a semiconductor element such as a CMOS (Complementary Metal Oxide Semiconductor) and a CCD (Charge Coupled Device). In the present embodiment, the imaging unit 107 is fixed to the housing 110 of the object detection system 101 and is disposed above the display unit 108. As shown in FIG. 3, the imaging unit 107 captures the front of the object detection system 101 and generates image data of an area including at least the determination area a1.

  FIG. 3 is a diagram illustrating an example of an image photographed by the photographing unit 107. As shown in FIGS. 1 to 3, in the present embodiment, the photographing unit 107 photographs at least a part of the determination area a <b> 1. In the present embodiment, the area captured by the imaging unit 107 includes the entire determination area a1. In the present embodiment, the number of pixels of the image specified by the image data generated by the photographing unit 107 is about several hundred thousand to several million.

  In FIG. 3, an image in a state where the person H is present is shown in the determination area a <b> 1, and the person H is sitting on a chair in front of the object detection system 101. In the present embodiment, infrared rays are emitted from the infrared sensor 106 toward the center of the region where the photographing unit 107 photographs. Image data generated by the imaging unit 107 is output to the object detection device 102.

  In the present embodiment, as described above, the object detection device 102 includes the sensor data acquisition unit 103, the image data acquisition unit 104, and the correction determination unit 105, and further includes a correction value table storage unit 111, And a power control unit 112.

  In the present embodiment, the object detection device 102 detects whether or not the person H is present in the determination area a1, as described above. The image data generated by the imaging unit 107 is output to the image data acquisition unit 104 of the object detection device 102 and further output to the correction determination unit 105.

  In the present embodiment, the correction determination unit 105 includes a correction data generation unit 113 and a determination unit 114.

  In the present embodiment, the correction data generation unit 113 generates correction data for correcting the distance data. The correction data generation unit 113 is connected to the image data acquisition unit 104, and the image data acquired by the image data acquisition unit 104 is given to the correction data generation unit 113. The correction data generation unit 113 analyzes the brightness of the image in the determination area a1.

  Specifically, as shown in FIGS. 1 and 3, the correction data generation unit 113 sets a rectangular area b1 for lightness analysis. In the present embodiment, the rectangular area b1 is set to match the captured image of the determination area a1. More specifically, in the photographed image of the photographing unit 107, the upper left coordinate of the determination area a1 is set as the upper left coordinate P1 (x1, y1) of the rectangular area b1, and the lower right coordinate of the determination area a1 is the rectangular area b1. Is set as the lower right coordinate P2 (x2, y2). The coordinates described above are coordinates with the upper left corner of the captured image of the imaging unit 107 as the origin O, the horizontal direction as the x axis, and the vertical direction as the y axis. In the photographed image of the photographing unit 107, the right side of the origin O is a positive region of the x axis, and the lower side of the origin O is a positive region of the y axis. Note that P1 (x1, y1) and P2 (x2, y2) are set in the captured image. The determination area a <b> 1 is within the image photographed by the photographing unit 107.

  The correction data generation unit 113 calculates the brightness V of each pixel of the image of the rectangular area b1 (the image of the determination area a1) specified in a rectangular shape by the coordinates P1 (x1, y1) and P2 (x2, y2). . More specifically, each pixel of the image in the determination area a1 is configured by three primary colors of R (red), G (green), and B (blue). The correction data generation unit 113 specifies the lightness in the range of 0 to 255 for the primary colors of R, G, and B of each of the pixels. Then, the correction data generation unit 113 identifies the lightness V of the arbitrary pixel as the lightness V of the arbitrary pixel among the lightness of R, the lightness of G, and the lightness of B for an arbitrary pixel. That is, for each pixel, the lightness V = (the maximum value among the lightness of R, the lightness of G, and the lightness of B).

  For example, for a certain pixel, when the brightness of R is 10, the brightness of G is 50, and the brightness of B is 100, the brightness of B = 100 is specified as the brightness V of the one pixel. The correction data generation unit 113 specifies the lightness V for each pixel in the same manner as described above.

  In the present embodiment, the correction data generation unit 113 totals the number of pixels having the same brightness as shown in FIG. 4 for each brightness V of 0 to 255. FIG. 4 is a histogram showing the relationship between each brightness V and the number of pixels hist [c]. The horizontal axis of the histogram in FIG. 4 indicates the lightness V. The lightness at the origin is set to 0, and the maximum value on the horizontal axis is set to 255. The vertical axis of the graph in FIG. 4 indicates the number of pixels hist [c]. For example, when there are 500 pixels with lightness V = 100, hist [100] = 500.

  In the present embodiment, for each lightness V, the correction data generation unit 113 totals the number of pixels hist [c] with the same lightness V. Then, among each lightness V, the lightness V having the largest number of pixels hist [c] is set as the reference lightness Vb. The correction data generation unit 113 generates correction data for correcting the distance data according to the reference lightness Vb.

  More specifically, in the present embodiment, the correction data generation unit 113 generates correction data with reference to the correction value table 121 stored in advance in the correction value table storage unit 111 shown in FIG. To do. FIG. 5 is a diagram for explaining the correction value table 121. As shown in FIG. 5, in the present embodiment, the correction value table 121 is a table showing the relationship among Munsell lightness Vm, reference lightness Vb, and correction value r.

  In the present embodiment, the correction value table 121 is defined based on the relationship between Munsell brightness Vm and reflectance in JIS (Japanese Industrial Standards), Z 8721-1993 “Color Display Method-Display with Three Attributes”. ing. Munsell lightness Vm is lightness specified in the range of 0 to 10, with 10 being the lightness of white as the brightest color and 0 being the lightness of black as the darkest color. In the above JIS standard, the reflectance of light with respect to Munsell brightness Vm is defined, and the reflectance of light decreases as the value of Munsell brightness Vm decreases. In FIG. 5, Munsell brightness Vm and the reflectance are values defined in the JIS standard, and the correction value r corresponds to the reflectance.

  In the present embodiment, as shown in FIG. 5, in the correction value table 121, 10 to 1 is set as the Munsell brightness Vm. In the present embodiment, the Munsell lightness Vm is set for every 1 in the range of 1 to 4 Munsell lightness Vm. In the range where the Munsell lightness Vm is 4 to 10, the Munsell lightness Vm is set every 0.5. In the correction value table 121, a reference lightness Vb corresponding to each Munsell lightness Vm is set. In the correction value table 121, a correction value r corresponding to each Munsell lightness Vm (reference lightness Vb) is set.

In the present embodiment, the range of the reference brightness Vb is 0 to 255. Therefore, in order to use the value of the above JIS standard in the present embodiment, the correction value table 121 shows the relationship between Munsell brightness Vm and brightness V. The upper limit value of the reference lightness Vb corresponding to each Munsell lightness Vm is represented by the following formula (1), for example.
Vb = Vm × 255 ÷ 10 (1)

  The first decimal place of the result of the above formula (1) is rounded off. For example, when the Munsell lightness Vm is 8.5, the reference lightness Vb = 8.5 × 255 ÷ 10≈217. The reference lightness Vb corresponding to each Munsell lightness Vm has a predetermined width as shown in FIG. More specifically, the reference brightness Vb between the upper limit value of the reference brightness Vb corresponding to a certain Munsell brightness Vm and the upper limit value of the reference brightness Vb corresponding to the Munsell brightness Vm one step below the Munsell brightness Vm is The reference brightness Vb corresponding to the certain Munsell brightness Vm is set. For example, the reference brightness Vb 243 to 254 between the upper limit value 255 of the reference brightness Vb corresponding to a certain Munsell brightness Vm = 10 and the upper limit value 242 of the reference brightness Vb corresponding to the Munsell brightness Vm9.5 is Munsell brightness Vm = Reference brightness Vb corresponding to 10.

  The correction data generation unit 113 refers to the correction value table 121 shown in FIG. 5 and sets a correction value r corresponding to the reference brightness Vb. Then, the correction data generation unit 113 generates correction data for specifying the correction value r. For example, when the reference lightness Vb is 160, the reference lightness Vb is included in the range of 166 to 154 in the correction value table 121. Therefore, the correction data generation unit 113 sets the correction value r = 35. The correction data generation unit 113 outputs the correction data to the determination unit 114.

As illustrated in FIG. 1, the determination unit 114 uses the correction data generation unit 113 to correct the uncorrected distance data value d1 to generate corrected distance data d2. Further, the determination unit 114 determines whether or not the person H is present in the determination area a1 based on the corrected distance data value d2. Specifically, the distance data d2 is calculated using the following equation (2).
d2 = d1 × 100 / r (2)

Here, the derivation of equation (2) will be described. When correcting the distance data, the correction is performed based on the distance data when infrared rays are reflected by the object with a reflectance of 100%. If it is considered that the distance data value of the infrared ray detected by the infrared sensor 106 after being reflected by the reflectance corresponding to the correction value r on the object is the corrected distance data value d2, The value d1 can be derived from the following (2).
d1 = d2 × r / 100 (3)

  By transforming equation (3), equation (2) is obtained. As is apparent from the equation (2) and the correction value table 121, the smaller the reference brightness Vb, the smaller the correction value r and the greater the degree of correction of the distance data value d1. For example, when the distance data value d1 before correction is 10 and the reference brightness Vb is 90, as is apparent from the correction value table 121, the correction value r = 12. Therefore, the corrected distance data d2 = 10 × 100 / 12≈83, which is larger than the distance data value d1 before correction. That is, the distance data is corrected so that the distance specified by the value d2 of the distance data becomes smaller as the reference brightness Vb becomes lower. On the other hand, when the distance data value d1 is 10 and the reference brightness is 250, as is apparent from the correction value table 121, the correction value r = 100. Therefore, the corrected distance data value d2 = 10 × 100/100 = 10, which is the same as the distance data value d1 before correction. That is, when the reference lightness Vb is sufficiently large, the distance specified by the distance data value d2 is the same as the distance specified by the distance data value d1 before correction.

  As shown in FIGS. 1 and 2, the determination unit 114 determines whether the corrected distance data value d2 is equal to or greater than a predetermined threshold value dt, so that the person H is present in the determination area a1. It is determined whether or not. As described above, the greater the value d2, the shorter the distance between the infrared sensor 106 and the person H. Therefore, when the corrected distance data value d2 is equal to or greater than the threshold value dt, the determination unit 114 determines that the person H is present in the determination area a1. On the other hand, when the corrected distance data value d2 is less than the threshold value dt, the determination unit 114 determines that the person H is not present in the determination area a1. For example, when the person H is not present in the determination area a1, and the front wall of the object detection system 101 reflects infrared rays from the infrared sensor 106, the corrected distance data value d2 is: It is less than the threshold value dt. Data indicating the determination result of the determination unit 114 is output to the power control unit 112.

  In the present embodiment, the power control unit 112 controls power supply to the display unit 108. The power control unit 112 turns on the power of the display unit 108 when it is determined that a person is present in the determination area a1. On the other hand, when it is determined that the person H is not present in the determination area a1, the power control unit 112 turns off the power of the display unit 108.

[Description of operation of object detection system]
Next, the operation of the object detection system 101 in the embodiment of the present invention will be described with reference to FIG. FIG. 6 is a flowchart showing the operation of the object detection system 101 in the embodiment of the present invention. Moreover, in the following description, FIGS. 1-7 is referred suitably. In this embodiment, in the embodiment, the object detection method is implemented by operating the object detection system 101. Therefore, the description of the object detection method in the embodiment of the present invention is replaced with the following description of the operation of the object detection system 101.

[Overall processing]
The object detection system 101 executes the operation flow shown in FIG. 6 at regular intervals. In the flow shown in FIG. 6, first, the correction determination unit 105 acquires distance data (step A1). Specifically, while step A1 is being executed, the light emitting element of the infrared sensor 106 irradiates infrared rays toward the determination area a1. As a result, the infrared light is reflected by a person H or a wall and is incident on the light receiving element of the infrared sensor 106. The infrared sensor 106 generates data corresponding to the amount (intensity) of received light as distance data. This distance data is output from the infrared sensor 106 to the sensor data acquisition unit 103. The sensor data acquisition unit 103 outputs the distance data to the determination unit 114 of the correction determination unit 105.

  Next, the correction determination unit 105 acquires image data (step A2). Specifically, the image data generated by the imaging unit 107 is output from the imaging unit 107 to the image data acquisition unit 104. The image data acquisition unit 104 outputs the image data to the correction data generation unit 113 of the correction determination unit 105.

  Next, the correction data generation unit 113 calculates the reference brightness Vb of the rectangular area b1 by analyzing the brightness V of each pixel of the rectangular area b1 in the captured image (step A3). Specific processing in step A3 will be described later with reference to FIG.

  The correction data generation unit 113 refers to the correction value table 121 and sets a correction value r corresponding to the reference brightness Vb calculated in step A3 (step A4). Specifically, the correction data generation unit 113 determines which range the reference brightness Vb calculated in step A3 applies to in the reference brightness Vb of the correction value table 121, and sets the correction value r corresponding to the reference brightness Vb. get. The correction data generation unit 113 generates correction data for specifying the correction value r and outputs the correction data to the determination unit 114. For example, as described above, when the reference brightness Vb is 160, the correction data generation unit 113 refers to the correction value table 121 and sets the correction value r to 35.

  The determination unit 114 corrects the distance data value d1 to calculate the corrected distance data value d2 (step A5). Specifically, the determination unit 114 calculates the above-described formula (2) using the distance data value d1 acquired in step A1 and the correction value r acquired in step A4. Accordingly, the determination unit 114 calculates the corrected distance data value d2.

  Next, the determination unit 114 determines whether or not the corrected distance data value d2 is less than a predetermined threshold value dt (step A6). When the corrected distance data value d2 is less than the predetermined threshold value dt, the distance between the position where the infrared light is reflected and the infrared sensor 106 is sufficiently large. In this case (YES in step A6), the determination unit 114 determines that the person H is not present in the determination area a1.

  As described above, when it is determined that the person H is not present in the determination area a1, the power control unit 112 turns off the power of the display unit 108 (step A7). Note that when the power of the display unit 108 is already off, the state where the power of the display unit 108 is off is continued.

  On the other hand, when the corrected distance data value d2 is equal to or greater than the predetermined threshold value dt, the distance between the infrared reflected position and the infrared sensor 106 is small, and the person H is present in the determination area a1. Yes. In this case (NO in step A6), the determination unit 114 determines that the determination area a1 person H is present.

  As described above, when the person H is present in the determination area a1, the power control unit 112 turns on the power of the display unit 108 (step A8). Note that, when the power of the display unit 108 is already turned on, the state where the power of the display unit 108 is turned on is continued.

[Details of Standard Lightness Calculation (Step A3)]
Next, the flow of processing for calculating the reference lightness Vb in the correction data generation unit 113 of the correction determination unit 105 will be specifically described with reference to FIG. FIG. 7 is a flowchart for explaining the flow of calculating the reference brightness Vb. Moreover, in the following description, FIGS. 1-5 is referred suitably.

  First, the correction data generation unit 113 sets a rectangular area b1 in the image photographed by the photographing unit 107 (step A11). Specifically, the correction data generation unit 113 sets P1 (x1, y1) as the coordinates of the upper left corner of the determination area a1 and P2 (x2) as the coordinates of the lower right edge of the determination area a1 in the image captured by the imaging unit 107. , Y2). In the present embodiment, the correction data generation unit 113 sets a rectangular area b1 at the center of the image captured by the imaging unit 107.

  Next, the correction data generation unit 113 initializes the number of pixels hist [c] for creating a brightness histogram (step A12). The number of pixels hist [c] is set for each brightness. That is, the number of pixels hist [c] is set to 256 from 0 to 255. The correction data generation unit 113 performs initialization to set the values to zero for all the number of pixels hist [c].

  Next, the correction data generation unit 113 substitutes y1 set in step A11 for a counter y that counts the number of pixels in the vertical direction of the rectangular region b1. As a result, the correction data generation unit 113 initializes the counter y (step A13). Furthermore, the correction data generation unit 113 substitutes x1 set in step A11 for a counter x that counts the number of pixels in the horizontal direction of the rectangular region b1. As a result, the correction data generation unit 113 initializes the counter x (step A14).

  Next, the correction data generation unit 113 calculates the brightness V of the pixel P (x, y) (step A15). The correction data generation unit 113 calculates the maximum value among the brightness of R, the brightness of G, and the brightness of B in the pixel P (x, y) as the brightness V.

  Next, the correction data generation unit 113 adds one value of the number of pixels hist [c] for the same brightness as the brightness V calculated in step A15 (step A16). For example, when the brightness V calculated in step A15 is 100, the value of the counter hist [100] is incremented by one. Further, the correction data generation unit 113 creates a histogram using the number of pixels hist [c] (step A16).

  Next, the correction data generation unit 113 determines whether or not the calculation of the lightness V has been completed for all the pixels in one line aligned in the X direction with the pixels for which the lightness V has been calculated in Step A15 (Step A17). Specifically, the correction data generation unit 113 compares the value of the counter x with the x coordinate x2 of the right end of the rectangular area b1.

  When the counter x <x2, the lightness analysis of all the pixels on the same line as the pixel for which the lightness V is calculated in step A15 has not been completed (NO in step A17). In this case, the correction data generation unit 113 determines that the calculation of the brightness V has not been completed for the pixels for one line.

  In this case, the correction data generation unit 113 adds one value of the counter x (step A18). Thereafter, the correction data generation unit 113 executes steps A15 to A17 again.

  On the other hand, if the counter x = x2 in step A17, the calculation of the brightness V of all the pixels on the same line as the pixel for which the brightness V was calculated in step A15 has been completed (YES in step A17). In this case, the correction data generation unit 113 determines whether or not the calculation of the brightness V and the creation of the histogram have been completed for all the pixels of the image in the rectangular area b1 (step A19). Specifically, the correction data generation unit 113 compares the value of the counter y with the y coordinate y2 of the lower end of the rectangular area b1.

  When the counter y <y2, the calculation of the brightness V and the creation of the histogram are not completed for all the pixels of the image in the rectangular area b1 (NO in step A19). In this case, the correction data generation unit 113 adds one value to the counter y (step A20). Thereafter, the correction data generation unit 113 executes steps A14 to A19 again. That is, the brightness V is calculated for each pixel in the line immediately below the line where the brightness V was performed immediately before the determination in step A19.

  On the other hand, if the counter y = y2 in step A19, the calculation of the lightness V and the creation of the histogram have been completed for all the pixels of the image in the rectangular area b1 (YES in step A19). In this case, the correction data generation unit 113 sets the lightness V having the largest number of pixels hist [c] among the lightness V as the reference lightness Vb (step A21).

[program]
Moreover, the program in this Embodiment should just be a program which makes a computer perform step A1-A8 and A11-21 shown in FIG. 6 and FIG. By installing and executing this program on a computer, the object detection system 101 and the object detection method in the present embodiment can be realized. In this case, a CPU (Central Processing Unit) of the computer functions as a sensor data acquisition unit 103, an image data acquisition unit 104, a correction determination unit 105, and a power control unit 112 to perform processing. Further, in the present embodiment, the correction value table storage unit 111 can be realized by storing data files constituting these in a storage device such as a hard disk provided in the computer. Further, the correction value table storage unit 111 may be constructed by another computer.

  As described above, in this embodiment, the distance data from the infrared sensor 106 that outputs different distance data due to the difference in the color of the reflected object is based on the color data of the image captured by the imaging unit 107. Can be corrected. For this reason, the presence or absence of the person H using the infrared sensor 106 can be determined more accurately. For example, it is possible to reduce misjudgments such that it is determined that the person H is away from the user even though he / she is wearing black clothes and is present in the determination area a <b> 1 and shifts to a power saving state. Further, in order to correct the distance data, it is not necessary for the person H to input correction information. Therefore, it is always possible to accurately determine whether or not the user is present in the determination area a1 using the corrected distance data value d2.

  In the present embodiment, the correction data generation unit 113 of the correction determination unit 105 corrects the distance data according to the reference brightness Vb. Thus, by correcting the distance data according to the reference brightness Vb, the value d1 of the distance data can be corrected more accurately.

  In the present embodiment, the correction data generation unit 113 of the correction determination unit 105 sets the lightness V having the largest number of pixels hist [c] as the reference lightness Vb. Thus, the distance data value d1 is corrected based on the reference lightness Vb as the lightness V that greatly affects the distance data value d1 in the rectangular region b1. Therefore, the value d1 of the distance data can be corrected more accurately.

  In the present embodiment, the correction data generation unit 113 of the correction determination unit 105 corrects the distance data using a correction value r set in advance according to the reference lightness Vb. In this way, the correction data generation unit 113 can easily correct the distance data with a simple configuration using the preset correction value r.

  In the present embodiment, the correction data generation unit 113 of the correction determination unit 105 corrects the value d1 of the distance data so that the distance specified by the distance data becomes smaller as the reference brightness Vb becomes lower. Thereby, it can suppress that the distance of the person H who wears clothes with small brightness V, such as black, and the infrared sensor 106 is calculated larger than an actual distance. Thereby, the correction determination part 105 can determine more accurately whether the person H exists in the determination area | region a1.

  In the present embodiment, power control unit 112 controls power supply to display unit 108 based on the determination result of determination unit 114 of correction determination unit 105. Thereby, when the person H is present in the determination area a1, it is possible to suppress the operation of the object detection system 101 by the person H, and the person H is present in the determination area a1. When there is not, wasteful power consumption of the object detection system 101 can be suppressed.

  In the present embodiment, the infrared sensor 106 is configured to irradiate infrared rays toward the center of the area captured by the imaging unit 107. Thereby, the whole area of the determination area a1 can be more reliably imaged by the imaging unit 107.

  Here, a computer that realizes the object detection apparatus 102 by executing the program according to the present embodiment will be described with reference to FIG. FIG. 8 is a block diagram showing an example of a computer 210 that implements the object detection apparatus according to the embodiment of the present invention.

  As illustrated in FIG. 8, the computer 210 includes a CPU 211, a main memory 212, a storage device 213, an input interface 214, a display controller 215, a data reader / writer 216, and a communication interface 217. These units are connected to each other via a bus 221 so that data communication is possible.

  The CPU 211 performs various operations by expanding the program (code) in the present embodiment stored in the storage device 213 in the main memory 212 and executing them in a predetermined order. The main memory 212 is typically a volatile storage device such as a DRAM (Dynamic Random Access Memory).

  In addition, the program in the present embodiment is provided in a state stored in a computer-readable recording medium 220. Note that the program in the present embodiment may be distributed on the Internet connected via the communication interface 217.

  Specific examples of the storage device 213 include a semiconductor storage device such as a flash memory in addition to a hard disk. The input interface 214 mediates data transmission between the CPU 211 and the input device 218 such as a keyboard and a mouse. The display controller 215 is connected to the display device 219 and controls display on the display device 219.

  The data reader / writer 216 mediates data transmission between the CPU 211 and the recording medium 220, and reads a program from the recording medium 220 and writes a processing result in the computer 210 to the recording medium 220. The communication interface 217 mediates data transmission between the CPU 211 and another computer.

  Specific examples of the recording medium 220 include general-purpose semiconductor storage devices such as CF (Compact Flash (registered trademark)) and SD (Secure Digital), magnetic storage media such as a flexible disk, or CD- An optical storage medium such as ROM (Compact Disk Read Only Memory) can be used.

[Modification]
(1) In the above-described embodiment, the configuration in which the object detection system 101 is a notebook personal computer is described, but this need not be the case. For example, the object detection system may be another object detection system such as a desktop personal computer, a monitor, or a television. When the object detection system is a television, for example, when the person H is present in front of the television, the volume of the television is increased, and when the person H is not present in front of the television, The volume of the TV may be reduced. It is also possible to realize volume control such as measuring the distance between the person H and the television, increasing the volume when the measured distance is far, and decreasing the volume when the measured distance is short. Moreover, the object detection apparatus of the present invention can be used for detection of an object other than a person.

(2) In the above-described embodiment, the correction value table 121 describes a configuration in which one correction value r is set for a plurality of reference brightness values Vb. However, this need not be the case. For example, the correction value r may be set for each reference lightness Vb.

(3) In the above-described embodiment, the configuration is described in which the power of the display unit 108 is turned off when the person H is not present in the determination area a1, but this need not be the case. For example, when the person H is not present in the determination area a1, the display unit 108 may be controlled to enter a sleep state. In this case, when it is determined that the person H is present in the determination area a1, the display unit 108 is controlled to return from the sleep state.

(4) In the above embodiment, the Munsell brightness Vm is included in the correction value table 121, but the Munsell brightness Vm is not referred to by the correction data generation unit 113. Therefore, in the correction value table 121, the Munsell brightness Vm may be omitted.

(5) In the above embodiment, the entire determination area a1 is set as the rectangular area b1 in the image captured by the imaging unit 107. However, this need not be the case. For example, in the image, only a part of the determination area a1 may be set as the rectangular area b1. Further, by changing the arrangement of the infrared sensor 106 and the photographing unit 107, the rectangular area b1 may be set closer to the upper part, lower part, left side, or right side of the image.

  Part or all of the above-described embodiments can be expressed by (Appendix 1) to (Appendix 18) described below, but is not limited to the following description.

(Appendix 1)
A sensor data acquisition unit that acquires sensor data that identifies the detection result of the infrared ray from an infrared sensor that detects the reflected infrared ray that is irradiated to the predetermined determination region; and
An image data acquisition unit for acquiring image data of the determination region;
A correction determination unit that corrects the sensor data based on the image data, and determines whether or not an object exists in the determination region using the corrected sensor data;
An object detection apparatus comprising:

(Appendix 2)
The sensor data includes distance data for specifying a distance between the infrared sensor and a position where the infrared light is reflected,
The object detection apparatus according to appendix 1, wherein the correction determination unit specifies a reference lightness of an image specified by the image data, and corrects the distance data according to the reference lightness.

(Appendix 3)
The correction determination unit calculates the brightness of the image for each pixel, counts the number of pixels having the same brightness for each of the plurality of brightnesses, and among the plurality of brightnesses, the number of pixels is the largest. The object detection device according to attachment 2, wherein the lightness is set as the reference lightness.

(Appendix 4)
4. The object detection apparatus according to appendix 2 or appendix 3, wherein the correction determination unit corrects the distance data using a preset correction value according to the reference brightness.

(Appendix 5)
The object detection according to any one of appendix 2 to appendix 4, wherein the correction determination unit corrects the distance data so that a distance specified by the distance data decreases as the reference lightness decreases. apparatus.

(Appendix 6)
A power control unit that controls power supply to a power control target based on the determination result of the correction determination unit;
The object detection device according to any one of appendix 1 to appendix 5, further comprising:

(Appendix 7)
(A) obtaining sensor data specifying the detection result of the infrared rays from an infrared sensor that detects the reflected infrared rays that are irradiated and reflected on the predetermined determination region;
(B) obtaining image data of the determination area;
(C) correcting the sensor data based on the image data, and determining whether an object exists in the determination region using the corrected sensor data;
An object detection method comprising:

(Appendix 8)
The sensor data includes distance data for specifying a distance between the infrared sensor and a position where the infrared light is reflected,
The object detection method according to appendix 7, wherein, in the determining step, a reference brightness of an image specified by the image data is specified, and the distance data is corrected according to the reference brightness.

(Appendix 9)
In the determining step, the brightness of the image is calculated for each pixel, and for each of the plurality of brightnesses, the number of pixels having the same brightness is totaled, and among the plurality of brightnesses, the number of pixels is the largest. The object detection method according to appendix 8, wherein the lightness is set as the reference lightness.

(Appendix 10)
The object detection method according to appendix 8 or appendix 9, wherein, in the determining step, the distance data is corrected using a correction value set in advance according to the reference brightness.

(Appendix 11)
The object detection according to any one of appendix 8 to appendix 10, wherein in the determining step, the distance data is corrected so that the distance specified by the distance data decreases as the reference brightness decreases. Method.

(Appendix 12)
(D) controlling power supply to the power control target based on the determination result of the determining step;
The object detection method according to any one of appendix 7 to appendix 11, further comprising:

(Appendix 13)
On the computer,
(A) obtaining sensor data specifying the detection result of the infrared rays from an infrared sensor that detects the reflected infrared rays that are irradiated and reflected on the predetermined determination region;
(B) obtaining image data of the determination area;
(C) correcting the sensor data based on the image data, and determining whether an object exists in the determination region using the corrected sensor data;
A program that executes

(Appendix 14)
The sensor data includes distance data for specifying a distance between the infrared sensor and a position where the infrared light is reflected,
14. The program according to appendix 13, wherein, in the determining step, a reference brightness of an image specified by the image data is specified, and the distance data is corrected according to the reference brightness.

(Appendix 15)
In the determining step, the brightness of the image is calculated for each pixel, and for each of the plurality of brightnesses, the number of pixels having the same brightness is totaled, and among the plurality of brightnesses, the number of pixels is the largest. The program according to appendix 14, wherein the lightness is set as the reference lightness.

(Appendix 16)
The program according to appendix 14 or appendix 15, wherein in the determining step, the distance data is corrected using a preset correction value according to the reference brightness.

(Appendix 17)
The program according to any one of Supplementary Note 14 to Supplementary Note 16, wherein in the determining step, the distance data is corrected so that the distance specified by the distance data decreases as the reference lightness decreases.

(Appendix 18)
(D) controlling power supply to the power control target based on the determination result of the determining step;
The program according to any one of appendix 13 to appendix 17, further comprising:

  The present invention can be applied to an object detection device, an object detection method, and a program for detecting whether or not an object exists in a predetermined determination region.

DESCRIPTION OF SYMBOLS 102 Object detection apparatus 103 Sensor data acquisition part 104 Image data acquisition part 105 Correction determination part 106 Infrared sensor 108 Display part (power control object)
112 power control unit 210 computer a1 determination area hist [c] number of pixels r correction value Vb reference brightness V brightness

Claims (8)

A sensor data acquisition unit that acquires sensor data that identifies the detection result of the infrared ray from an infrared sensor that detects the reflected infrared ray that is irradiated to the predetermined determination region; and
An image data acquisition unit for acquiring image data of the determination region;
A correction determination unit that corrects the sensor data based on the image data, and determines whether or not an object exists in the determination region using the corrected sensor data;
An object detection apparatus comprising: The sensor data includes distance data for specifying a distance between the infrared sensor and a position where the infrared light is reflected,
The object detection apparatus according to claim 1, wherein the correction determination unit specifies a reference lightness of an image specified by the image data, and corrects the distance data according to the reference lightness.   The correction determination unit calculates the brightness of the image for each pixel, counts the number of pixels having the same brightness for each of the plurality of brightnesses, and among the plurality of brightnesses, the number of pixels is the largest. The object detection apparatus according to claim 2, wherein the lightness is set as the reference lightness.   The object detection device according to claim 2, wherein the correction determination unit corrects the distance data using a correction value set in advance according to the reference brightness.   5. The correction determination unit according to claim 2, wherein the correction determination unit corrects the distance data so that a distance specified by the distance data decreases as the reference brightness decreases. 6. Object detection device. A power control unit that controls power supply to a power control target based on the determination result of the correction determination unit;
The object detection device according to any one of claims 1 to 5, further comprising: (A) obtaining sensor data specifying the detection result of the infrared rays from an infrared sensor that detects the reflected infrared rays that are irradiated and reflected on the predetermined determination region;
(B) obtaining image data of the determination area;
(C) correcting the sensor data based on the image data, and determining whether an object exists in the determination region using the corrected sensor data;
An object detection method comprising: On the computer,
(A) obtaining sensor data specifying the detection result of the infrared rays from an infrared sensor that detects the reflected infrared rays that are irradiated and reflected on the predetermined determination region;
(B) obtaining image data of the determination area;
(C) correcting the sensor data based on the image data, and determining whether an object exists in the determination region using the corrected sensor data;
A program that executes

Images