Image monitoring device, image monitoring method, and recording medium

Patent metadata

Field	Value
Publication number	US-10791252-B2
Application number	US-201916683311-A
Country	US
Kind code	B2
Filing date	Nov 14, 2019
Priority date	Aug 1, 2017
Publication date	Sep 29, 2020
Grant date	Sep 29, 2020

Abstract

An image monitoring device includes a luminance calculator and a darkness determiner. The luminance calculator calculates a first average luminance value of an illuminated region which is illuminated with a lamp and a second average luminance value of a non-illuminated region which is not illuminated with the lamp. The illuminated region and the non-illuminated region are included in a video signal generated by capturing with a lens. The darkness determiner determines whether or not the video signal is captured in dark by comparing a difference between the first average luminance value and the second average luminance value with a first threshold value.

First claim

What is claimed is:

1. An image monitoring device comprising:
a luminance calculator configured to calculate a first average luminance value of an illuminated region which is illuminated with a lamp and a second average luminance value of a non-illuminated region which is not illuminated with the lamp, the illuminated region and the non-illuminated region being included in a video signal generated by capturing with a lens;
a darkness determiner configured to determine whether or not the video signal is captured in dark by comparing a difference between the first average luminance value and the second average luminance value with a first threshold value; and
a dirt adherence detector configured to detect whether or not dirt is adherent to the lens, based on the video signal,
wherein when the darkness determiner determines the video signal is captured in dark, the image monitoring device determines that an accuracy of detection of dirt adherence of the dirt adherence detector is lower than an accuracy of detection of dirt adherence of the dirt adherence detector when the darkness determiner determines the video signal is not captured in the dark.

2. The image monitoring device according to claim 1 ,
wherein a detection result detected by the dirt adherence detector and a determination result determined by the darkness determiner are separately output.

3. The image monitoring device according to claim 1 ,
wherein the dirt adherence detector reflects a determination result determined by the darkness determiner on detection of dirt adherence.

4. An image monitoring device comprising:
a luminance calculator configured to calculate a first average luminance value of an illuminated region which is illuminated with a lamp and a second average luminance value of a non-illuminated region which is not illuminated with the lamp, the illuminated region and the non-illuminated region being included in a video signal generated by capturing with a lens; and
a darkness determiner configured to determine whether or not the video signal is captured in dark by comparing a difference between the first average luminance value and the second average luminance value with a first threshold value,
wherein the darkness determiner determines whether or not the video signal is captured in dark by comparing the difference between the first average luminance value and the second average luminance value with the first threshold value, and by comparing the first average luminance value with a second threshold value.

5. An image monitoring method comprising:
calculating a first average luminance value of an illuminated region which is illuminated with a lamp and a second average luminance value of a non-illuminated region which is not illuminated with the lamp, the illuminated region and the non-illuminated region being included in a video signal generated by capturing with a lens;
determining whether or not the video signal is captured in dark by comparing a difference between the first average luminance value and the second average luminance value with a first threshold value; and
detecting whether or not dirt is adherent to the lens, based on the video signal,
wherein an accuracy of detection of dirt adherence when it is determined that the video signal is captured in dark is determined to be lower than an accuracy of detection of dirt adherence when it is determined that the video signal is not captured in the dark.

6. The image monitoring method according to claim 5 ,
wherein a detection result of whether or not dirt is adherent to the lens and a determination result of whether or not the video signal is captured in the dark are separately output.

7. The image monitoring method according to claim 5 ,
wherein a determination result of whether or not the video signal is captured in the dark is reflected on the detecting of whether or not dirt is adherent to the lens.

Assignees

• Panasonic Ip Man Co Ltd

Inventors

• Tsurube Tomoyuki
• Hirose Nobuyuki
• Yamaguchi Kohei

Classifications

• H04N23/71

  Circuitry for evaluating the brightness variation · CPC title

• H04N23/56

  provided with illuminating means · CPC title

• H04N23/74

  by influencing the scene brightness using illuminating means · CPC title

• H04N23/52 Primary

  Elements optimising image sensor operation, e.g. for electromagnetic interference [EMI] protection or temperature control by heat transfer or cooling elements · CPC title

• H04N23/811 Primary

  by dust removal, e.g. from surfaces of the image sensor or processing of the image signal output by the electronic image sensor · CPC title