The present invention confirms whether a caregiven person, such as a solitary advanced aged person, is living a normal daily life, while respecting the privacy when the caregiven person is in a normal state. The present invention further outputs a detailed video with a warning to a caregiver when the caregiven person has fallen into an abnormal state. A human body detecting device comprises an imaging unit, a human body detecting unit for detecting a human body from an image signal obtained from the imaging unit, a state judging unit for judging a state of the human body, and a normal/abnormal signal outputting unit, a field memory for storing the image signal, a second memory for dividing a pixel data of the human body included in the image signal into blocks of a predetermined number of pixels and luminance, to be stored, and a selector for selectively performing a reading out from the field memory for storing the image signal and from the second memory in accordance with the judgement of the state judging unit, wherein the reading out from the field memory is authorized only when it is judged that abnormal states are encountered by the state judging unit.

A face image processing apparatus for use in a sleep-inhibition security system for car drivers is disclosed. The apparatus includes an input section for acquiring an input face image of a target person, an eye extraction region setter for determining an eye extraction region within the input face image, and an extractor for extracting from the eye extraction region first and second image components corresponding to an eyebrow image and an eye image respectively. A first detector is adapted to detect relative positions of the first and second image components extracted. A second detector is provided for detecting the open or closed state of at least one eye image by analyzing variations in the relative positions detected.

An apparatus for estimating a drowsiness level of a vehicle driver first prepares a frequency distribution of blink durations of the driver for a first predetermined period after the start of a driving operation, and sets a threshold value for a discrimination of slow blinks by the frequency distribution. Thereafter, the apparatus calculates, every second predetermined period, a ratio of the number of slow blinks to the total number of blinks of the driver's eyes during the second period, and discriminates a rise in the drowsiness level of the driver in accordance with the calculated ratio.

A method and apparatus for analyzing drowsiness of a subject. The monitor measures motion of the head of the subject and of one or both eyes of the subject in at least one dimension and derives at least one physiological indication such as gaze stability, saccade speed, saccade frequency, blink duration, and instrument-world scanning performance of the subject. The physiological indicator or indicators are compared with predetermined ranges of acceptable values in such a manner as to determine an onset of drowsiness in the subject.

An apparatus for determining the alertness of a person, especially a vehicle or machine operator, comprises an image pickup system for recording images of the area of at least one eye of the person, and an image evaluating system which evaluates the images detected by the image pickup system and contains means for detecting the shutting of an eye. The image evaluating system has means for determining pupil size and an evaluating apparatus which determines the alertness according to the eye closing state information obtained by the closed-eye detection means, and according to the pupil size information obtained by the pupil size determining means, with classification into one of at least three stages. The apparatus is used, for example, for determining the alertness of drivers of motor vehicles.