JP4442472B2 - Device part identification device - Google Patents

Description

  The present invention relates to a region determination device for an object, and in particular, distinguishes and determines a region such as skin, hair, and eyeball of an object such as a driver's head without being affected by ambient light such as sunlight. The present invention relates to a part discriminating apparatus for an object that can be used.

  Patent Document 1 discloses a camouflage detector that detects a person camouflaged with artificial material using light in the upper band of the near-infrared spectrum. This camouflaged detector uses light having a wavelength range of at least 1400 nm, which is the upper band of the near infrared spectrum. However, since an image sensor made up of a silicon semiconductor that is usually used does not have a sensitivity of 1400 nm or more, it is necessary to use an image sensor made up of another material (for example, gallium arsenide). Therefore, two cameras, a near-infrared upper band camera using gallium arsenide and a near-infrared lower band camera using silicon, are required. There's a problem.

  In Patent Document 2, a biological object is detected by measuring the intensity of a partial wavelength band whose center wavelength is around 970 nm from an object illuminated by a light source and comparing it with the characteristic of spectral intensity of a detection target object obtained in advance. A living body detection device is described. In Patent Document 2, since the intensity of a partial wavelength band in which the center wavelength included in the sensitivity of an imaging element made of a silicon semiconductor is around 970 nm is measured, it is possible to solve the problem that occurs in Patent Document 1. .

Patent Document 3 discloses the properties of the near-infrared region of the first and second inks, which are metallic inks, by transmitting near-infrared light of wavelength 1 and wavelength 2 to the metallic pair printed matter, receiving reflected light by a photodiode. A discrimination method for discriminating whether or not it is a genuine metallic pair printed matter is described. In Patent Document 3, a light source having two types of wavelengths is used, but special inks having different reflectances at the respective wavelengths are targeted, and thus cannot be used for detection of a passenger such as a vehicle driver. The object that can be discriminated is limited.
Special table 2003-536303 gazette Japanese Patent No. 2823564 JP 2000-293729 A

  However, none of the above Patent Documents 1 to 3 takes measures against disturbance light, and in an environment affected by disturbance light, the material of the object is determined to determine each part of the object. There is a problem that is difficult. For example, automobile windshields and side windows have infrared transmission characteristics that allow a considerable amount of near-infrared light to pass through in the region of 1000 nm (1.0 micron) or less. Infrared rays act as disturbance light. In situations where ambient light with unknown intensity is present, the spectral intensity from the object cannot be stored in advance in the storage area, and sunlight or the like is used to determine each part of the object in an in-vehicle environment. It is necessary to devise a method for removing the influence of ambient light.

  The present invention has been made to solve the above problem, and an object of the present invention is to provide an object discriminating apparatus that can discriminate each part of an object without being affected by ambient light.

To accomplish the above object, irradiated with light of a first wavelength band different from a second wavelength range of the light and near-infrared region of the first wavelength range in the near infrared region to the human head An illuminating means, a control means for controlling on / off of the illuminating means, an imaging means for photographing the head of the person in synchronization with the on / off control of the control means, and a state illuminated with light in the first wavelength range the difference between the pixel values of the captured the person's head of an image pixel value and the lighting means from the person's head light taken in a state of not being irradiated image, and the second wavelength region light calculating means for light pixel values of the image of the person's head taken in the illuminated state from the illumination means for calculating a difference between the pixel values of the image of the person's head taken in a state of not being irradiated , the magnitude relation of the calculated difference by the calculating means, or the magnitude relationship and the difference between the calculated difference Min based, and is configured to include a discriminating means for discriminating each site including skin of the person's head, eye, and at least one of the hair.

In the present invention, the person's head where the light from the illumination means is captured in a state of not being irradiated the head to disturbance light person corresponding to the pixel values of the image of the head of the person photographed while being irradiated image of using the pixel values, the first person light from the pixel value and the illumination means human head images taken while illuminated with light in a wavelength range were taken in a state of not being irradiated in the head of the image the difference between the pixel value, and the second wavelength region who light from the pixel value and the illumination means human head images taken while illuminated with light was taken in a state of not being irradiated in the head of the image Since each part of the human head is discriminated based on the difference from the pixel value, each part of the human head can be discriminated without being affected by ambient light .
If the person's head is not illuminated by ambient light, since disturbance light into the human's head pixel values of the image of the head of the person photographed while being irradiated it is less need, in the present invention For example, it is possible to prevent a state in which no light is emitted from the illumination unit from occurring, so that the frequency in which the state in which the illumination unit is not irradiated with light is equal to or less than a predetermined value.

In the present invention, as a pixel value corresponding to pixel values of the image of the head of the person photographed in a state where disturbance light is irradiated on the human head, the pixels of the image when the spectral reflectance was taken known object Lighting means for irradiating a human head with light in a first wavelength region in the near infrared region and light in a second wavelength region different from the first wavelength region in the near infrared region , using the value, and the illumination Control means for on / off control of the means , and the spectral reflectance of each of the human head and the light in the first wavelength range and the light in the second wavelength range in synchronization with the on / off control of the control means Is taken with a photographing means for photographing a known object, a pixel value of an image of the human head photographed with light in the first wavelength range, and illuminated with light in the first wavelength range pixel values of the image of the object, pixel values of the second of the person of the head of the image photographed in a state of being illuminated with light in the wavelength range, and A calculating means for calculating a pixel value of an image of the object taken in a state of being illuminated by a second wavelength region light, the calculated calculation result in the calculating means, and the light of the first wavelength region of the object Based on the ratio of the spectral reflectance in the first wavelength region and the second wavelength region of the human head, which is calculated based on the spectral reflectance of each of the light in the second wavelength region. And discriminating means for discriminating each part including at least one of the skin, eyeball, and hair of the human head .

In this case, the discriminating means is photographed with the pixel value of the image of the object photographed in the state illuminated with the light of the first wavelength range calculated by the computing means and the light illuminated with the light of the second wavelength range. The illumination means is adjusted so that the pixel values of the image of the object are the same, and the head of a person photographed in a state illuminated with light of the first wavelength band obtained after adjusting the illumination means Each part of the person's head can be determined based on the pixel value of the image and the pixel value of the image of the person's head photographed in a state illuminated with light in the second wavelength range. .

Further, instead of the illumination means for irradiating the light in the first wavelength range and the light in the second wavelength range, an illumination means for irradiating light in the wavelength range including the first wavelength range and the second wavelength range is used. Illuminating means for irradiating a person's head with light including the first wavelength region and the second wavelength region in the near-infrared region, control means for controlling on / off of the illumination means, and on / off control of the control means In synchronism, the human head is divided into light having a first wavelength range and a second wavelength range different from the first wavelength range, and an imaging unit that divides the head into light of the first wavelength range. the difference between the pixel values of the captured the person's head of an image pixel value and said illuminating means off state in the person's head divided for shooting the first wavelength region light image, and the in a state in which the pixel value of the person's head of an image divided and photographed to light of the second wavelength region and to turn off the illuminating means divided into a second wavelength region light A calculating means for calculating a difference between the pixel value of the person's head images captured Te, magnitude relation of the calculated difference by the arithmetic unit, or to the difference of the magnitude relationship and the difference between the calculated difference And a discriminating means for discriminating each part including at least one of the skin, eyeball, and hair of the person's head .

Further, illumination means for irradiating a human head with light including the first wavelength region and the second wavelength region in the near infrared region, control means for controlling on / off of the illumination means, and on / off control of the control means In synchronization with the human head, an object having a known spectral reflectance of each of the light in the first wavelength range and the light in the first wavelength range is changed to the first wavelength range and the first wavelength. The photographing means for dividing and photographing the light in the second wavelength range different from the region, the pixel value of the human head image photographed by dividing the light in the first wavelength range, the illumination means turned off The pixel value of the image of the object taken by dividing into light of the first wavelength region in the state, the pixel value of the image of the human head taken by dividing into light of the second wavelength region, and the illumination Computing means for computing a pixel value of the image of the object taken by dividing the light into the second wavelength region with the means turned off; The calculated operation result in stages, and is calculated based on each of the spectral reflectance of the light of the light with the second wavelength band of the first wavelength region of the object, said of the person's head Discrimination means for discriminating each part including at least one of skin, eyeballs, and hair of the human head based on a ratio of spectral reflectances in the first wavelength range and the second wavelength range; It is also possible to include it.

  It is effective to irradiate light in the near infrared region of 800 nm to 1100 nm from the illumination means of the present invention. In this case, the first wavelength region is set to a wavelength region between 800 nm to 970 nm, The wavelength range of 2 is preferably a wavelength range between 970 nm and 1100 nm.

As described above, according to the present invention, it is possible to determine each part of the human head without being affected by disturbance light.

  Hereinafter, an embodiment in which the present invention is applied to a vehicle discriminating device that discriminates each part of a driver's head will be described in detail with reference to the drawings. In the first embodiment, as shown in FIG. 1, the first light source 10 that is an illuminating means composed of an LED or the like that irradiates light in the first wavelength λ1 region, and the light in the second wavelength λ2 region. There is provided a lighting device composed of a second light source 12 which is a lighting means composed of LEDs and the like, and a camera 14 composed of a CCD camera for photographing an object illuminated by the lighting device. .

  The first light source 10, the second light source 12, and the camera 14 are connected to a light source / camera control 16 that controls opening and closing of the shutter of the camera in synchronization with the on / off control of the first light source 10 and the second light source 12.

  Further, the camera 14 includes a pixel value storage device 18 configured by a memory that stores a pixel value such as an image density value of each pixel of an image captured by the camera, and a pixel calculated according to a processing routine described below. It is connected to the arithmetic / determination device 20 that determines what each part of the object is based on the difference in values and the reflectance data stored in the database 22.

  Note that the light source / camera control device 16 and the calculation / determination device 20 can each be configured by a computer, but may be configured by one computer.

  As the CCD, XC-E150 (trade name, manufactured by Sony Corporation) having sensitivity in the near infrared region is used. As shown in FIG. 2, the CCD has sensitivity in a wavelength range of 400 nm to 1000 nm.

  In the present embodiment, a case will be described as an example in which each part of the driver's skin, hair, and eyeball is detected using the object as the head of the driver of the vehicle. 3 shows the spectral reflectance of the skin, FIG. 4 shows the spectral reflectance of the hair, and FIG. 5 shows the spectral transmittance distribution of the eyeball. Reference numeral 33 in FIG. 3 is the spectral reflectance of a person with light skin, and 34 is the spectral reflectance of a person with dark skin. The spectral reflectance of skin and the spectral reflectance of hair are compared as follows when the spectral reflectances at wavelengths of 880 nm and 970 nm are compared.

-Skin: reflectivity at 880 nm> reflectivity at 970 nm-Hair: reflectivity at 880 nm <reflectance at 970 nm For spectral transmittance, spectral reflectance = 1.0-(spectral transmittance) For this reason, the spectral reflectance of the eyeballs at wavelengths of 880 nm and 970 nm has the following relationship.

Eyeball: reflectivity at 880 nm <reflectance at 970 nm
(Transmittance at 880 nm> Transmittance at 970 nm)
Therefore, the head region of the driver is extracted as an object by image processing such as template matching, and the pixel value of the captured image is compared at each wavelength of 880 nm and 970 nm, so that the skin and hair in the head region can be compared. And each part of the eyeball can be discriminated.

  The wavelength need not be limited to 880 nm and 970 nm, but the following conditions must be satisfied.

  The first is to use light in the near infrared region. The reason for this is that when used while driving in a vehicle, the driver's face is illuminated with invisible light in order not to distract the driver, but using ultraviolet light will harm the eyes. This is because there is a fear and it is not desirable.

  Secondly, light having a wavelength of 1100 nm or less is used. The reason for this is that an imaging device made of a silicon semiconductor that is excellent in terms of cost, reliability, and responsiveness has sensitivity only to wavelengths up to 1107 nm as illustrated in FIG.

  Third, the reflectance at the two wavelengths λ1 and λ2 is different for each of skin, hair, and eyeball. In addition, when an illumination device that irradiates light having a wavelength in the vicinity of the visible region is used, it is necessary to consider that light may leak into the visible region and that the sensitivity of the image sensor is almost not 1000 nm or more.

  In particular, since the reflectance of the eyeball changes abruptly around 970 nm, in order to detect the eyeball, it is preferable to irradiate light of 970 nm or more and light of less than 970 nm. In this embodiment, 970 nm Two illumination devices are used: a first light source that emits the above light (light with a wavelength λ1) and a second light source that emits light with a wavelength less than 970 nm (light with a wavelength λ2).

  In the present embodiment, the database 22 stores in advance the spectral reflectance distribution data shown in FIGS. 3 and 4 and the data obtained by converting the spectral transmittance distribution of FIG. 5 into the spectral reflectance distribution. .

  Next, processing for determining each part of the head executed by the calculation / determination device of the present embodiment will be described.

  First, in the light source / camera control device 16, as shown in FIG. 6, the first light source 10 and the second light source 12 are alternately turned on and lit (the first light source is on and the second light source is off). A, and the state where the first light source is off and the second light source is on (state B), and after alternately turning on, the first light source 10 and the second light source 12 are turned off and turned off (state C). To control. Accordingly, the two light sources are irradiated with only light of the first wavelength λ1 (state A), irradiated only with light of the second wavelength λ2 (state B), and both the first light source and the second light source are off (state C). Take.

  Further, the camera shutter is synchronized with the on / off control of the first light source 10 and the second light source 12 so that the head of the driver as the object is photographed by the camera in each of the state A, the state B, and the state C. Open and close to shoot the object. Thereby, an image of the object is captured in each of the state A, the state B, and the state C.

  FIG. 7 is a flowchart showing the processing in the calculation / determination device 20, and it is determined in each of steps 100 to 104 whether the state is C, A or B. If it is determined in step 100 that the state is C, the pixel value Vn of the image captured by the camera in state C is calculated in step 106 and stored in the pixel value storage device 18.

  If it is determined in step 102 that the state is A, the pixel value V (λ1) of each pixel of the image captured by the camera in step A is calculated and stored in the pixel value storage device 18 in step. In the next step 110, a difference (V (λ1) −Vn) obtained by subtracting the pixel value of each corresponding pixel of the state C image from the pixel value of each pixel in the state A is calculated and stored for each pixel. Thus, by subtracting the pixel value in state C from the pixel value in state A, the pixel value (V (λ1) −Vn) based on the spectral intensity of only the first wavelength can be obtained, and the influence of disturbance light Can be removed.

  If the state B is determined in step 104, the pixel value V (λ2) of each pixel of the image photographed by the camera in step B is calculated and stored in the pixel value storage device 18 in step 112. In the next step 114, a difference (V (λ2) −Vn) obtained by subtracting the pixel value of each corresponding pixel of the state C image from the pixel value of each pixel in the state B is calculated and stored for each pixel. Similarly to the above, by subtracting the pixel value in the state C from the pixel value in the state B, a pixel value (V (λ2) −Vn) based on the spectral intensity of only the second wavelength can be obtained. Can be removed.

  By performing the above processing, the pixel value of each pixel is calculated on the basis of the state where the object is not illuminated with the light source.

  Since the brightness of the light source is known in advance, the magnitude relationship among the pixel values of the skin, hair, and eyes in the state A and the state B can be stored in the database. By comparing the difference between the database and each pixel (V (λ1) −Vn) and the difference (V (λ2) −Vn), it is determined whether each pixel belongs to hair, skin, or eyeball. can do.

  In step 116, the spectral reflectance distribution stored in the database for each pixel is compared with the difference (V (λ1) −Vn) and the difference (V (λ2) −Vn). And which part of the skin it belongs to. For example, if the difference (V (λ1) −Vn) <difference (V (λ2) −Vn) and the difference between the difference (V (λ1) −Vn) and the difference (V (λ2) −Vn) is small, it belongs to the skin. If it is larger, it can be determined that it belongs to the eyeball, and if the difference (V (λ1) −Vn)> difference (V (λ2) −Vn), it can be determined that it belongs to the hair, and the determined attribute is given to each pixel. In step 118, the attribute given for each pixel is output.

  As described above, since it is determined which part of the target object belongs to each pixel, each part of the target object can be determined.

  In the above description, the example in which the light source / camera control device 16 opens and closes the shutter of the camera in synchronization with the on / off of the light source has been described. However, as shown in FIG. The first light source and the second light source may be controlled on and off.

  Next, a second embodiment will be described. In the present embodiment, each state of the object is generated by generating two states of only the first light source (state A) and only the second light source (state B) without causing the state C of the two light sources. Is determined. The first light source and the second light source open or close the shutter of the camera in synchronization with the two light sources alternately emitted as shown in FIG. 9, or the camera shutter by the control means 16 as shown in FIG. The two light sources are caused to emit light at a timing synchronized with each other.

  In the second embodiment, a standard white plate having a known spectral reflectance is used, and the ratio of spectral reflectances O (λ1) and O (λ2) of the object at wavelengths λ1 and λ2 to the database is O (λ1) / Although the point that the data of O (λ2) is stored is different from that of the first embodiment, the other points are the same as those of the first embodiment, and the description of the same parts is omitted.

  Next, a processing routine for determining each part of the object according to the second embodiment will be described with reference to FIG.

  The standard white plate and the object are photographed while the on / off control of the first light source and the second light source and the opening / closing of the shutter of the camera are controlled at the timing shown in FIG. In step 122, the second light source is turned on to illuminate the standard white plate and the target object. It is determined whether or not shooting is performed in the state (state B).

  In the case of the state A, the area of the standard white plate is determined in step 121, and the pixel value Vs (λ1) of the image obtained by photographing the standard white plate using the data of the area of the standard white plate in step 124 is obtained. Since the area other than the area of the standard white plate corresponds to the object, the pixel value of the image obtained by photographing the object using the data of the area other than the area of the standard white plate in Step 134 is calculated and stored. V (λ1) is calculated and stored.

  In the case of state B, the standard white plate region is determined in step 123, and the pixel value Vs (λ2) of the image obtained by photographing the standard white plate using the standard white plate region data in step 126 is obtained. In step 136, the pixel value V (λ2) of the image obtained by photographing the object is calculated and stored using the data of the area other than the area of the standard white plate.

  The ratio (E (λ1): E (λ2)) of the spectral intensity between the first wavelength light and the second wavelength light at this time is expressed by the following equation (1).

E (λ1): E (λ2)
= Vs (λ1) / Os (λ1): Vs (λ2) / Os (λ2)
... (1)
Where E (λ1) and E (λ2) are the spectral intensities at wavelengths λ1 and λ2, respectively, Vs (λ1) and Vs (λ2) are the pixel values of the standard reflector at the wavelengths λ1 and λ2, respectively, and Os (Λ1) and Os (λ2) are reference reflectances at λ1 and λ2, respectively.

Further, the spectral reflectance ratio O (λ1): O (λ2) of the object is expressed by the following equation (2) using the pixel values V (λ1) and V (λ2) at the wavelengths λ1 and λ2 of the object. Can be expressed as
O (λ1): O (λ2)
= Vs (λ1) / Os (λ1): Vs (λ2) / Os (λ2) / V (λ1) × V (λ2)
... (2)
Accordingly, in step 138, the pixel values V (λ1) and V (λ2) at the wavelengths λ1 and λ2 of the object according to the above equation (2), the pixel values Vs (λ1) and Vs (λ2) of the standard white plate, and the reference Using the reflectances Os (λ1) and Os (λ2), a ratio of spectral reflectances at different wavelengths of the object is calculated, and the ratio calculated in step 140 and each of the known objects stored in the database are calculated. By comparing with the spectral reflectance data of the part, any attribute of hair, eyeball, and skin can be given to each pixel, whereby each part of the object is any of hair, eyeball, and skin Can be determined.

  In addition, although the example which image | photographs a standard white board and a target object simultaneously was demonstrated above, you may make it image | photograph separately.

  Next, a third embodiment will be described. In the present embodiment, as shown in FIG. 12, a light source adjustment device 26 that adjusts the amount of illumination light of the first light source and the second light source is provided in the second embodiment. In the present embodiment, the pixel values Vs (λ1) and Vs (λ2) of the pixels obtained by photographing the standard white plate 24 immediately before the subject is illuminated and photographed with the respective light sources are made equal. Further, the intensity of at least one of the first light source and the second light source is adjusted by the illumination adjusting means 26.

  As a result, the pixel values Vs (λ1) and Vs (λ2) on the standard white plate having the same reflectance at the wavelengths λ1 and λ2 are equal, and the reflectance is different for the wavelengths λ1 and λ2. Two classifications of Vs (λ1)> Vs (λ2) or Vs (λ1) <Vs (λ2) can be easily performed.

  Then, by examining the magnitude relationship between the pixel values V (λ1) and V (λ2) at each wavelength of the target obtained by photographing the target, each part of the target is hair, eyeball, or skin. Is determined.

  Next, a fourth embodiment will be described. In the present embodiment, a single light source is used, and the camera side divides and shoots light in the first wavelength λ1 region and light in the second wavelength λ2 region.

  In the present embodiment, as shown in FIG. 13, a camera 14 having a bandpass filter 14A that transmits light in the first wavelength λ1 region and a bandpass filter 14B that transmits light in the second wavelength λ2 region is provided. Is provided. As shown in FIG. 14, the band-pass filter 14A and the band-pass filter 14B are arranged in a lattice pattern by alternately arranging them in a two-dimensional manner.

  As a light source, a single light source 28 that emits light in a wavelength region including the first wavelength λ1 and the second wavelength λ2 is used. The light source 28 is connected to illumination control means 30 that controls on / off of the light source.

  Next, a processing routine for determining each part of the object according to the present embodiment will be described with reference to FIG. The light source 28 is turned on and off by the light source / camera control means, and the shutter of the camera is opened and closed in synchronization with the on / off of the light source, and an image of the object when the light source is on and an image of the object when the light source is off are taken. .

  In step 150, it is determined whether or not the light source is turned on. If the light source is turned on, the pixel value of the image obtained by the light passing through the bandpass filter 14A of the first wavelength when the light source is turned on is calculated in step 152. The pixel value of the image obtained by the light that has passed through the bandpass filter 14B of the second wavelength is calculated and stored, and if the light source is off, the bandpass filter of the first wavelength when the light source is off in step 154 The pixel value of the image obtained by the light passing through 14A is calculated and stored, and the pixel value of the image obtained by the light passing through the bandpass filter 14B having the second wavelength is calculated and stored.

  In the next step 156, with respect to the pixel value obtained from the light of the first wavelength, the pixel value when the light source is turned off is subtracted from the pixel value when the light source is turned on for each pixel. The pixel value V (λ1) −Vn (λ1) based on the intensity is obtained, and the pixel value obtained when the light source is turned off is subtracted from the pixel value obtained when the light source is turned on for each pixel. Thus, the pixel value V (λ2) −Vn (λ2) based on the spectral intensity of only the light of the second wavelength is obtained.

  Since the spectral intensity of the light source is known in advance, the pixel value of skin, hair, and eyeball obtained from the light that has passed through the bandpass filter of the first wavelength and the light that has passed through the bandpass filter of the second wavelength are obtained in the database. The relationship between the pixel values of skin, hair, and eyeballs is stored, and the data stored in the database and the pixel values V (λ1) −Vn (λ1) and V (λ2) −Vn (λ2) of each pixel are stored. , It can be determined whether the part of the object is hair, skin, or eyeball.

  Next, a fifth embodiment will be described. In the fourth embodiment, a standard white plate is used in the fourth embodiment, and the hair, skin, and eyeball of the object are determined in the same manner as in the second embodiment.

  A routine for determining the hair, skin, and eyeballs of the object of the present embodiment will be described with reference to FIG. In step 162, the standard white plate is photographed by the camera while the standard white plate is illuminated by the light source, and the pixel value Vs (λ1) of the image obtained by the light passing through the bandpass filter of the first wavelength is calculated and stored. At the same time, the pixel value Vs (λ2) of the image obtained by the light passing through the bandpass filter of the second wavelength is calculated and stored.

  In the next step 166, the light source is turned on to illuminate the object, and in step 168, the pixel value V (λ1) of the image obtained by the light that has passed through the bandpass filter of the first wavelength is obtained and stored. The pixel value V (λ2) of the image obtained by the light passing through the two-wavelength bandpass filter is obtained and stored.

  In the next step 170, the spectral reflectance ratio O (λ1) / O (λ2) of the object is calculated based on the above equation (2), and in step 172, the spectral reflectance ratio of the object is stored in the database. Each part of the target is discriminated by comparing the spectral reflectance data of each part of the known target.

  Next, a sixth embodiment of the present invention will be described. In the present embodiment, the frequency of occurrence of the state C is changed according to the brightness of the environment in the first embodiment. As shown in FIG. 18, the present embodiment includes a sunlight sensor 36 that detects sunlight and an interior light sensor 38 that detects whether or not the interior light is lit, and controls the brightness of the outside world. An external environment detection device for detection is provided.

  In addition, although the example which judges brightness using an interior light sensor was demonstrated above, you may make it detect the brightness of the external field from the image image | photographed with the camera, without using an interior light sensor. In order to detect the brightness of the external environment from the image, for example, the brightness is determined from the pixel value of a specific region (for example, a region where the side window is captured) of the image captured when the light source is turned off in the first embodiment. The brightness may be determined based on the average pixel value in the peripheral area of the image captured when the light source is turned off in the first embodiment.

  In the present embodiment, when it is determined that the outside light (sunlight) has not been detected by the sunlight sensor 36 and the interior light sensor 38 determines that the interior of the vehicle is off, disturbance light is applied to the object. As shown in FIG. 19, the frequency of occurrence of the state C is reduced as compared with the case where the external environment is bright. In this case, the occurrence frequency of the state C may be 0 and the state C may not be generated.

  In the present embodiment, a clock for measuring time may be provided in place of the sunlight sensor 36, and day / night may be determined based on the time to determine whether sunlight is radiated in the vehicle interior. . Further, a GPS sensor may be provided to determine whether or not the vehicle is traveling in a tunnel, and it may be determined that sunlight is not being irradiated into the vehicle interior when traveling in the tunnel.

  As described above, according to each of the above embodiments, it is possible to accurately determine each part of the driver's hair, skin, and eyeball without being affected by ambient light. In each of the above embodiments, the example of determining each part of the driver's face has been described. For example, for determining the material of each part of other objects such as sheet cloth, plastic, clothes, glasses, etc. It can also be used.

It is a block diagram which shows the 1st Embodiment of this invention. It is a diagram which shows the spectral sensitivity characteristic of CCD of the camera used for embodiment of this invention. It is a diagram which shows the spectral reflectance characteristic of human skin. It is a diagram which shows the spectral reflectance characteristic of human hair. It is a diagram which shows the spectral transmittance characteristic of a human eyeball. It is a flowchart which shows the routine which discriminate | determines each site | part of the target object of 1st Embodiment. It is a diagram which shows the example of the on-off state of the light source of 1st Embodiment, and the opening / closing timing of the shutter of a camera. It is a diagram which shows the other example of the on-off state of the light source of 1st Embodiment, and the opening / closing timing of the shutter of a camera. It is a diagram which shows the example of the on-off state of the light source of 2nd Embodiment, and the opening / closing timing of the shutter of a camera. It is a diagram which shows the other example of the on-off state of the light source of 2nd Embodiment, and the opening / closing timing of the shutter of a camera. It is a flowchart which shows the routine which discriminate | determines each site | part of the target object of 2nd Embodiment. It is a block diagram which shows 3rd Embodiment. It is a block diagram which shows 4th Embodiment. It is a top view of the filter of a 4th embodiment. It is a flowchart which shows the routine which discriminate | determines each site | part of the target object of 4th Embodiment. It is a block diagram which shows 5th Embodiment. It is a flowchart which shows the routine which discriminate | determines each site | part of the target object of 5th Embodiment. It is a block diagram which shows 6th Embodiment. It is a diagram which shows the example of the on-off state of the light source of 6th Embodiment, and the opening / closing timing of the shutter of a camera.

Explanation of symbols

10 First light source 12 Second light source 14 Camera 16 Light source / camera control device 18 Storage device

Claims (8)

Illuminating means for irradiating light of a first wavelength band different from a second wavelength range of the light and near-infrared region of the first wavelength range in the near infrared region to the human head,
Control means for on / off controlling the illumination means;
Photographing means for photographing the head of the person in synchronization with on / off control of the control means;
The pixel value of the first of the person of the head of the image light from the pixel value and the illumination means of the person's head images taken while illuminated with light in a wavelength range were taken in a state of not being irradiated differences, and the second of the person of the head of the image light from the pixel value and the illumination means of the person's head images taken while illuminated with light in a wavelength range were taken in a state of not being irradiated Computing means for computing the difference between the pixel value of
Each part including at least one of the skin of the human head , the eyeball, and the hair based on the magnitude relation of the difference computed by the computing means , or the magnitude relation of the computed difference and the difference of the difference Discrimination means for discriminating;
Discriminating device for an object including Providing detection means for detecting whether or not the human head is illuminated by ambient light;
When the human head is not illuminated by ambient light, the control means turns the illumination means on and off so that the frequency of occurrence of no light from the illumination means is less than or equal to a predetermined value. The object part discrimination | determination apparatus of Claim 1 to control Illuminating means for irradiating light of a first wavelength band different from a second wavelength range of the light and near-infrared region of the first wavelength range in the near infrared region to the human head,
Control means for on / off controlling the illumination means;
Imaging means for imaging the human head and an object with known spectral reflectances of the light in the first wavelength range and the light in the second wavelength range in synchronization with the on / off control of the control means When,
A pixel value of an image of the human head imaged in a state illuminated with light of a first wavelength range, a pixel value of an image of the object imaged in a state illuminated with light of a first wavelength range, a second A calculation means for calculating a pixel value of the human head image captured in a state illuminated with light in a wavelength range and a pixel value of the image of the object captured in a state illuminated with light in a second wavelength range; ,
The human head that is calculated based on the calculation result calculated by the calculation means and the spectral reflectance of each of the light in the first wavelength region and the light in the second wavelength region of the object. Discrimination means for discriminating each part including at least one of skin, eyeball, and hair of the human head based on a ratio of spectral reflectances in the first wavelength range and the second wavelength range of ,
Discriminating device for an object including Illumination means for irradiating the human head with light including the first wavelength region and the second wavelength region in the near infrared region ;
Control means for on / off controlling the illumination means;
An imaging unit that divides and images the human head in a second wavelength range different from the first wavelength range and the first wavelength range in synchronization with the on / off control of the control unit,
The person's head taken is divided into a first wavelength region light while turning off the first pixel value and the illumination means of the person's head of an image divided and taken light in a wavelength range And the pixel value of the human head image taken by dividing into the light of the second wavelength region and the light of the second wavelength region with the illumination means turned off. A calculation means for calculating a difference between the pixel value of the image of the person's head taken by dividing;
Each part including at least one of the skin of the human head , the eyeball, and the hair based on the magnitude relation of the difference computed by the computing means , or the magnitude relation of the computed difference and the difference of the difference Discriminating means for discriminating;
Discriminating device for an object including Illumination means for irradiating the human head with light including the first wavelength region and the second wavelength region in the near infrared region ;
Control means for on / off controlling the illumination means;
Synchronizing with the on / off control of the control means, the human head and an object having a known spectral reflectance of each of the light in the first wavelength range and the light in the second wavelength range are set to the first wavelength. An imaging unit that divides and shoots light in a second wavelength region different from the first wavelength region;
The pixel value of the human head image captured by dividing the light into the first wavelength range, and the image of the object captured by dividing the light into the first wavelength range with the illumination means turned off. The pixel value, the pixel value of the human head image taken by dividing the light into the second wavelength band, and the light divided into the second wavelength band with the illumination means turned off. A computing means for computing the pixel value of the image of the object;
The human head that is calculated based on the calculation result calculated by the calculation means and the spectral reflectance of each of the light in the first wavelength region and the light in the second wavelength region of the object. Discrimination means for discriminating each part including at least one of skin, eyeball, and hair of the human head based on a ratio of spectral reflectances in the first wavelength range and the second wavelength range of ,
Discriminating device for an object including The discrimination means includes the pixel value of the image of the object photographed in a state illuminated with light in the first wavelength range calculated by the computing means and the object photographed in a state illuminated with light in the second wavelength range. Adjusting the illumination means so that the pixel value of the image of
The shot while illuminated with light of a first pixel value and the second wavelength region of the person's head images taken while illuminated with light in a wavelength range obtained after adjusting the illumination means based on the pixel values of the human head image, the region determining apparatus according to claim 3 object, wherein determining the respective portions of said person's head.   The target part discrimination | determination apparatus of any one of Claims 1-6 which irradiates the light of a 800 nm-1100 nm near-infrared area | region from the said illumination means.   The object according to any one of claims 1 to 7, wherein the first wavelength range is a wavelength range between 800 nm and 970 nm, and the second wavelength range is a wavelength range between 970 nm and 1100 nm. Site identification device.

Images