Extraneous-matter detecting apparatus and extraneous-matter detecting method

1. An extraneous-matter detecting apparatus comprising:

a processor programmed to:

divide a captured image into a plurality of regions, the captured image being output from an image capturing device including an image sensor;

detect luminance values of pixels included in each of the plurality of divided regions, and compute, for each of target regions, an average value or a standard deviation of luminance values of the detected luminance values, the corresponding target region corresponding to one or more regions of the plurality of regions;

extract target regions having the computed average values or the computed standard deviations of the luminance values, which are within a predetermined range, and detect, when the extracted target regions are adjacent to each other, the adjacent target regions as an extraneous-matter region, the extraneous-matter region being a region of the image capturing device to which an extraneous matter is adhered; and

set each of the target regions for computing the standard deviations to be larger than each of the target regions for computing the average values.

2. The extraneous-matter detecting apparatus according to claim 1 , wherein

the processor is further programmed to compute, for each of the target regions, the average value and the standard deviation of the luminance values, and

the processor is further programmed to extract, from the target regions, a target region having the average value and the standard deviation of the luminance values that are within respective predetermined ranges so as to detect the extraneous-matter region, the computed average value and the computed standard deviation.

3. The extraneous-matter detecting apparatus according to claim 2 , wherein

the processor is further programmed to compute a standard deviation for each of movement regions obtained by moving the target region so that at least a part of the target region overlaps with the corresponding movement region, and

the processor is further programmed to extract, as a total region of the standard deviations, a region indicated by a logical disjunction between one or more target regions of the target regions and one or more movement regions of the movement regions, the one or more target regions and one or more movement regions having standard deviations within the predetermined range.

4. The extraneous-matter detecting apparatus according to claim 3 , wherein

a movement amount unit of the target region in longitudinal and lateral directions is 1/M (M is integer number) times of respective longitudinal and lateral widths of the target region, and

the processor is further programmed to take M logical disjunctions based on M standard deviations computed while moving the target region M times, so as to extract the total region.

5. The extraneous-matter detecting apparatus according to claim 1 , wherein

the processor is further programmed to compute a standard deviation for each of movement regions obtained by moving the target region so that at least a part of the target region overlaps with the corresponding movement region, and

the processor is further programmed to extract, as a total region of the standard deviations, a region indicated by a logical disjunction between one or more target regions of the target regions and one or more movement regions of the movement regions, the one or more target regions and one or more movement regions having standard deviations within the predetermined range.

6. The extraneous-matter detecting apparatus according to claim 5 , wherein

a movement amount unit of the target region in longitudinal and lateral directions is 1/M (M is integer number) times of respective longitudinal and lateral widths of the target region, and

the processor is further programmed to take M logical disjunctions based on M standard deviations computed while moving the target region M times, so as to extract the total region.

7. The extraneous-matter detecting apparatus according to claim 1 , wherein the processor is further programmed to set a connection region to be the target region for computing the standard deviation, the connection region being obtained by connecting the target regions for computing the average values.

8. The extraneous-matter detecting apparatus according to claim 7 , wherein

the processor is further programmed to compute a standard deviation of a movement region obtained by moving the connection region so that the moved connection region overlaps with at least a part of the plurality of target regions included in the connection region, and

the processor is further programmed to extract, as a total region of the standard deviations, a region indicated by a logical disjunction between the connection region and the movement region having the standard deviations within the predetermined range, and detects the extraneous-matter region based on the total region and the one or more target regions for computing the average values.

9. The extraneous-matter detecting apparatus according to claim 8 , wherein the processor is further programmed to move the movement region so that the movement region overlaps with one target region of the target regions included in the connection region.

10. An extraneous-matter detecting apparatus comprising:

a processor programmed to:

divide a captured image into a plurality of regions, the captured image being output from an image capturing device including an image sensor;

detect luminance values of pixels included in each of the plurality of divided regions, and compute, for each of target regions, an average value or a standard deviation of luminance values of the detected luminance values, the corresponding target region corresponding to one or more regions of the plurality of regions;

extract target regions having the computed average values or the computed standard deviations of the luminance values, which are within a predetermined range, and detect, when the extracted target regions are adjacent to each other, the adjacent target regions as an extraneous-matter region, the extraneous-matter region being a region of the image capturing device to which an extraneous matter is adhered;

compute a standard deviation for each of movement regions obtained by moving the target region so that at least a part of the target region overlaps with the corresponding movement region, andregion; and

extract, as a total region of the standard deviations, a region indicated by a logical disjunction between one or more target regions of the target regions and one or more movement regions of the movement regions, the one or more target regions and one or more movement regions having standard deviations within the predetermined range.

11. The extraneous-matter detecting apparatus according to claim 10 , wherein

a movement amount unit of the target region in longitudinal and lateral directions is 1/M (M is integer number) times of respective longitudinal and lateral widths of the target region, and

the processor is further programmed to take M logical disjunctions based on M standard deviations computed while moving the target region M times, so as to extract the total region.

12. An extraneous-matter detecting method comprising:

dividing a captured image into a plurality of regions, the captured image being output from an image capturing device including an image sensor;

detecting luminance values of pixels included in each of the plurality of regions divided in the dividing, and computing, for each of target regions, an average value or a standard deviation of luminance values of the detected luminance values, the corresponding target region corresponding to one or more regions of the plurality of regions; and

extracting target regions having the average values or the standard deviations of the luminance values computed in the computing, which are within a predetermined range, and detecting, when the extracted target regions are adjacent to each other, the adjacent target regions as an extraneous-matter region, the extraneous-matter region being a region of the image capturing device to which an extraneous matter is adhered; and

setting each of the target regions for computing the standard deviations to be larger than each of the target regions for computing the average values.