Abstract: A projection unit projects light to a predetermined projection region in which a user's face is supposed to be located. An imaging unit images a region including the projection region projected with light from the projection unit. A proximity detection unit detects that the user's face approaches the projection unit. A first projection control unit causes the projection unit to stop or dim projection of light when the proximity detection unit detects the approach of the user's face.

Abstract: An object determining device includes imaging means for obtaining an image of the object, likelihood value calculating means for calculating a first likelihood value for the object shown in the image by use of the image obtained by the imaging means and a machine learning system and for calculating a second likelihood value for the object shown in the image by use of the image obtained by the imaging means and another machine learning system, the first likelihood value indicating a level of likelihood that the object is wearing the covering and the second likelihood value indicating a level of likelihood that the object is not wearing the covering, and determining means for determining whether or not the object, shown in the image obtained by the imaging means, is wearing a covering, on the basis of a ratio between the first likelihood value and the second likelihood value.

Abstract: An in-vehicle face image detection apparatus operates as follows. A projector projects light. A capture controller settles a capturing condition to capture a predetermined region including a face of an occupant. A capturing portion captures the predetermined region based on the capturing condition. An environment light detection portion detects environment light radiated to the vehicle or occupant. An operation mode determination portion determines a first mode where intensity of the environment light is greater than a threshold or a second mode where the intensity is not greater than the threshold. A light emission pattern setup portion settles a light emission pattern for a light source of the projector based on the operation mode. A projector controller controls the projector to activate the light source based on the light emission pattern.

Abstract: Detecting with good precision an eye inside corner position and an eye outside corner position as face feature points even when the eye inside corner and/or the eye outside corner portions are obscured by noise. First eyelid profile modeling is performed with a Bezier curve expressed by a fixed control point P3 indicating an eye inside corner first position detected in an image, a fixed control point P4 indicating an eye outside corner first position, a control point P1 corresponding to an upper eyelid position candidate (first parameter), and a control point P2 corresponding to a lower eyelid position candidate (second parameter).

Abstract: Local maxima values and local minima values are derived from eyelid openness time series data in a segment in which a continuous closed eye period of extracted blinks is a specific time duration (for example 1 second) or longer. When plural local minima values are present in the segment of continuous closed eye period of 1 second or longer, blinks are extracted passing over and back through each variable closed eye threshold value of a variable closed eye threshold that is slid in a direction from the derived local maxima value towards the local minima value in set steps to a low value, and a inter-blink interval derived. Determination is made that a blink burst has occurred when the derived inter-blink interval is 1 second or less, and say greater than 0.2 seconds, thereby detecting a blink burst. Blink bursts can be detected with good precision, and the state of drowsiness can be assessed with good precision.

Abstract: A projection unit projects light to a predetermined projection region in which a user's face is supposed to be located. An imaging unit images a region including the projection region projected with light from the projection unit. A proximity detection unit detects that the user's face approaches the projection unit. A first projection control unit causes the projection unit to stop or dim projection of light when the proximity detection unit detects the approach of the user's face.

Abstract: In a driver management apparatus for managing the driver of a vehicle, a state estimating means estimates a state of the driver based on the sensing information from a sensing means Based on an estimation result, an extracting means extracts, as a capture region, part of the sensing information. The capture information storing means extracts the sensing information associated with the extracted capture region and stores the extracted sensing information as capture information. The determining means determines whether the estimation result satisfies a reporting condition. When it is determined that the estimation result satisfies the reporting condition, the controlling means retrieves the capture information associated with the estimation result and causes the retrieved capture information to be transmitted with the estimation result to the external center.

Abstract: Detecting with good precision an eye inside corner position and an eye outside corner position as face feature points even when the eye inside corner and/or the eye outside corner portions are obscured by noise. First eyelid profile modeling is performed with a Bezier curve expressed by a fixed control point P3 indicating an eye inside corner first position detected in an image, a fixed control point P4 indicating an eye outside corner first position, a control point P1 corresponding to an upper eyelid position candidate (first parameter), and a control point P2 corresponding to a lower eyelid position candidate (second parameter).

Abstract: A sleepiness level determination device includes: a detector processing a face image of an user and for detecting an eye image of the user based on the face image; a characteristic value calculating unit calculating a characteristic value regarding the eye based on the eye image; a sleepiness level determining unit determining a sleepiness level based on the characteristic value; and a reliability calculating unit calculating reliability of the sleepiness level based on the characteristic value.

Abstract: Local maxima values and local minima values are derived from eyelid openness time series data in a segment in which a continuous closed eye period of extracted blinks is a specific time duration (for example 1 second) or longer. When plural local minima values are present in the segment of continuous closed eye period of 1 second or longer, blinks are extracted passing over and back through each variable closed eye threshold value of a variable closed eye threshold that is slid in a direction from the derived local maxima value towards the local minima value in set steps to a low value, and a inter-blink interval derived. Determination is made that a blink burst has occurred when the derived inter-blink interval is 1 second or less, and say greater than 0.2 seconds, thereby detecting a blink burst. Blink bursts can be detected with good precision, and the state of drowsiness can be assessed with good precision.

Abstract: An image is captured of a region including an eye of a driver using an image capture device 12, and the degree of eye openness is detected with a degree of eye openness detection section 24. A standard closed eye threshold value, a large value closed eye threshold value and a small closed eye threshold value stored in the threshold value storage section 28 are employed by the feature amount extraction section 30 to extract plural types of blinking feature amount from the detected degree of eye openness time series data. Threshold value determination is performed for each of the plural types of blinking feature amount by the threshold value determination section 32, and determination of the state of drowsiness of the driver is made by the drowsiness determination section 34 based on the threshold value determination results for the plural types of blinking feature amount.

Abstract: A sleep warning apparatus includes a stimulation generating portion, a reaction detecting portion, a warning determining portion, and a warning generating portion. The stimulation generating portion generates stimulation to a person before a warning is given to the person. The stimulation is used to take reaction of the person. The reaction detecting portion detects the reaction of the person to the stimulation when the stimulation generated by the stimulation generating portion is given to the person. The warning determining portion determines whether or not the warning is required to be given to the person depending on whether or not the reaction detecting portion detects the reaction of the person to the stimulation. The warning generating portion gives the warning to the person when the warning determining portion determines that the warning is required to be given to the person.

Abstract: An open-eye or closed-eye determination apparatus is provided with: an image capture section 11 for capturing an image of a region including the eye of an investigation subject; a width of eye opening measurement section 12 for detecting top and bottom eyelids of an investigation subject from the image captured by the image capture section 11 and measuring the width of eye opening between the edges of the top and bottom eyelids; a filter section 13 for subjecting the width of eye opening measured by the width of eye opening measurement section 12 to filter processing; and an open-eye or closed-eye determination section 14 for determining closed-eye when a value of the width of eye opening obtained by the filter section 13 minus the width of eye opening measured by width of eye opening measurement means is greater than a threshold value, and determining open-eye when this difference is a threshold value or less.

Abstract: A wakefulness maintaining apparatus includes an event detecting part, a drowsiness level determining part, a threshold setting part, and a stimulus supplying part. The event detecting part detects an event related to a drowsiness of a person. The drowsiness level determining part determines a drowsiness level that changes in accordance with a strength of the drowsiness. The threshold setting part sets a threshold value to divide the drowsiness level into a first level range and a second level range in such a manner that the first level range is equal to or lower than the threshold value and the second level range is higher than the threshold value. The stimulus supplying part supplies a stimulus having an awaking effect to the person when the drowsiness level is in the second level range and the event is detected.

Abstract: Light generated at a specific wavelength corresponding to a particular color or color range that is distracting or disruptive to a driver during a normal operation is blocked through an inexpensive construction without blocking light in a required range of wavelengths. A projector is constructed such that a plurality of LEDs are arranged in an array configuration. The LEDs can include a tinge of red reduction LED and near-infrared LEDs. The projector can be installed in a vehicle and disposed in proximity to the camera. In some embodiments, the projector can be controlled by a control circuit to be turned on in conjunction with the shutter of a camera.

Abstract: A face image capture apparatus for a vehicle repeatedly performs an output of a difference image to an image ECU. When the number of times of outputs reaches a predetermined number of times, a bright face image from which an influence of disturbance light is not removed is outputted to the image ECU. Thereby, the image ECU can determine an environment (daytime, nighttime, etc.) outside the vehicle based on the bright face image outputted in addition to the difference image.

Abstract: A face image capturing apparatus includes a camera, an on-axis illuminator, an off-axis illuminator, an illumination control device, an image capturing control device, and a luminance calculation process device. The camera repeatedly captures an image of a face of an occupant of a vehicle. The illumination control device is configured to adjust an illumination condition of light applied to the face of the occupant. The image capturing control device is configured to control the camera 10 to capture the image of the face at an image capturing timing that is synchronized with a timing for adjusting the illumination condition. The luminance calculation process device is configured to perform a luminance calculation process by using a bright pupil face image, a dark pupil face image, and an ambient light face image.

Abstract: An object determining device includes imaging means for obtaining an image of the object, likelihood value calculating means for calculating a first likelihood value for the object shown in the image by use of the image obtained by the imaging means and a machine learning system and for calculating a second likelihood value for the object shown in the image by use of the image obtained by the imaging means and another machine learning system, the first likelihood value indicating a level of likelihood that the object is wearing the covering and the second likelihood value indicating a level of likelihood that the object is not wearing the covering, and determining means for determining whether or not the object, shown in the image obtained by the imaging means, is wearing a covering, on the basis of a ratio between the first likelihood value and the second likelihood value.

Abstract: In a driver management apparatus for managing the driver of a vehicle, a state estimating means (14) estimates a state of the driver based on the sensing information from a sensing means (11, 12, 25). Based on an estimation result, an extracting means (11) extracts, as a capture region, part of the sensing information. The capture information storing means (16) extracts the sensing information associated with the extracted capture region and stores the extracted sensing information as capture information. The determining means (11) determines whether the estimation result satisfies a reporting condition. When it is determined that the estimation result satisfies the reporting condition, the controlling means (23, 21) retrieves the capture information associated with the estimation result and causes the retrieved capture information to be transmitted with the estimation result to the external center (30).

Abstract: A wakefulness level estimation apparatus includes: an estimation portion that estimates a level of wakefulness of a subject person based on one of a wakefulness level estimation function, of which a variable is a wakefulness level correlation value of the subject person, and a difference between the wakefulness level correlation value of the subject person and a reference value of the wakefulness level correlation value; a stimulation detection portion that detects whether an awakening stimulation is externally applied to the subject person; and a correction portion that, when the stimulation detection portion detects that the awakening stimulation is applied to the subject person, performs a correction of one of the reference value of the wakefulness level correlation value and the wakefulness level estimation function, which is used for estimating the level of wakefulness of the subject person.