IMAGE PROCESSING APPARATUS
PROBLEM TO BE SOLVED: To reduce influences of reflection lights from eyeglasses or the like while preventing an entire image from becoming dark, and to obtain a continuous natural image through simple arithmetic processing.SOLUTION: A driver monitor 100 (image processing apparatus) comprises an imag...
Gespeichert in:
1. Verfasser: | |
---|---|
Format: | Patent |
Sprache: | eng ; jpn |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | PROBLEM TO BE SOLVED: To reduce influences of reflection lights from eyeglasses or the like while preventing an entire image from becoming dark, and to obtain a continuous natural image through simple arithmetic processing.SOLUTION: A driver monitor 100 (image processing apparatus) comprises an imaging part 1, a first illumination part 21, a second illumination part 22 and an image correction part 4. The image correction part 4 compares a first luminance value Q1 of a first pixel in a first image of a subject that is imaged by the imaging part 1, with a second luminance value Q2 of a second pixel in a second image for each corresponding pixel and calculates a differential ΔQ between the luminance values Q1 and Q2. A differential logarithm value A=log|ΔQ| that is a logarithm of an absolute value of the differential ΔQ is then calculated and for each corresponding pixel, a corrected luminance value Qs=Min(Q1, Q2)+A is calculated by adding the differential logarithm value A to a lower luminance value Min (Q1, Q2) that is a luminance value of a pixel having lower luminance. The corrected luminance value Qs is used to perform correction processing on a synthetic image of the first image and the second image, thereby generating a corrected image.SELECTED DRAWING: Figure 1
【課題】画像全体が暗くならないようにしつつ、眼鏡等からの反射光の影響を軽減するとともに、簡単な演算処理によって連続性のある自然な画像が得られるようにする。【解決手段】ドライバーモニタ100(画像処理装置)は、撮像部1、第1照明部21、第2照明部22、画像補正部4を備えている。画像補正部4は、撮像部1が撮像した被写体の第1画像の第1画素の第1輝度値Q1と、第2画像の第2画素の第2輝度値Q2とを対応する画素ごとに比較し、輝度値Q1、Q2の差分ΔQを算出する。そして、この差分ΔQの絶対値の対数である差分対数値A=log2|ΔQ|を算出し、各対応画素ごとに、輝度の低い方の画素の輝度値である低輝度値Min(Q1,Q2)に差分対数値Aを加算した補正輝度値Qs=Min(Q1,Q2)+Aを算出し、この補正輝度値Qsを用いて第1画像と第2画像の合成画像に対し補正処理を行い、補正画像を生成する。【選択図】図1 |
---|