PROBLEM TO BE SOLVED: To detect drowsiness of a subject more accurately than ever before even in the case of a subject who tries not to blink intentionally when he or she becomes drowsier in a device to detect drowsiness based on a person's eyelid opening/closing movement.SOLUTION: A drowsiness detection device includes means to detect an opening/closing state of a subject's eyelids, means to sequentially detect a time interval of the transition between an open state and a closed state of the eyelids, means to calculate an eyelid opening/closing feature amount from data on the time interval of the transition between the open state and the closed state of the eyelids over the time width corresponding to the length of the time when the subject's eyes are open, and drowsiness determination means to determine that the subject is feeling drowsiness when the eyelid opening/closing feature amount falls below a first threshold, and when it exceeds a second threshold which is higher than the first threshold.SELECTED DRAWING: Figure 2【課題】人の瞼の開閉運動に基づいて眠気を検知する装置に於いて、眠気が増加した際に意図的に瞬きをしないようにする被検者の場合にも、被検者の眠気の発生を従前よりも精度よく検知できるようにする。【解決手段】眠気検知装置は、被検者の瞼の開閉状態を検出する手段と、瞼の開状態と閉状態との間の遷移の時間間隔を逐次的に検出する手段と、被験者の開眼時間の長短に応じた時間幅に亙る瞼の開状態と閉状態との間の遷移の時間間隔のデータから瞼開閉特徴量を算出する手段と、瞼開閉特徴量が第一の閾値を下回ったとき、及び、第一の閾値よりも高い第二の閾値を上回ったときに、被検者が眠気を感じていると判定する眠気判定手段とを含む。【選択図】図２
