Night vision apparatus
AssigneeFujitsu Limited
InventorSeiya Shimizu
Life of this patent
Estimating the term…
Abstract
A night vision image processing unit (night vision apparatus) separates an input field image that a field separating unit has acquired from a near-infrared camera into an odd-numbered field image and an even-numbered field image. A region segmenting unit segments an image into a plurality of regions (a luminous region, a high-reflection region, a low-luminance region) based on luminance value of each pixel included in the odd-numbered field image and the even-numbered field image. A luminous region processing unit, a high-reflection region processing unit, and a low-luminance region processing unit correct the luminance value according to characteristics of the regions.
Claims4
A night vision apparatus for taking an image of a subject by using reflected light of infrared light emitted, the night vision apparatus comprising:
- an image segmenting unit configured to segment said image into a plurality of regions based on a luminance value of a lighting image taken when the infrared light is emitted and a luminance value of a non-lighting image taken when the infrared light is not emitted;
- and
- a luminance value correcting unit configured to correct luminance values of the regions based on characteristics of the regions segmented by the image segmenting unit, wherein
- the image segmenting unit is further configured to segment a first region in said image whose luminance value of the non-lighting image is smaller than a first threshold, and whose luminance value of the lighting image is larger than a second threshold as a high-reflection region, and
- the luminance value correcting unit is further configured to correct the luminance values of the first region based on the luminance values of the corresponding region of the non-lighting image.
A computer readable non-transitory storage medium having stored therein a night vision image processing program, the night vision image processing program causing a computer to execute a process comprising:
- segmenting an image into a plurality of regions based on a luminance value of a lighting image taken by an infrared camera when infrared light is emitted and a luminance value of a non-lighting image taken by the infrared camera when the infrared light is not emitted;
- and
- correcting luminance values of the regions based on characteristics of the regions segmented at the segmenting, wherein
- the segmenting includes segmenting a first region in said image whose luminance value of the non-lighting image is smaller than a first threshold, and whose luminance value of the lighting image is larger than a second threshold as a high-reflection region, and
- the correcting includes correcting the luminance values of the first region based on the luminance values of the corresponding region of the non-lighting image.
Dependencies are inferred from the claim text.