Vehicle external environment recognition device

1. A vehicle external environment recognition device, comprising:

a three-dimensional position deriving module that derives three-dimensional positions in real space of a plurality of subject parts in images that are obtained by imaging a detection area;

an object identifying module that groups the subject parts of which differences in the three-dimensional position are within a predetermined range to identify an object;

an edge intensity deriving module that horizontally divides an area containing the object to set a plurality of divided areas, and derives an edge average that is an average value of edge intensities based on a luminance value of each pixel within each of the divided areas; and

a floating matter identifying module that compares the edge average with a predetermined threshold, and identifies the object to be likely floating matters when the edge average is less than the threshold.

2. The vehicle external environment recognition device of claim 1 , wherein the edge intensity deriving module derives the edge average based on the luminance value of each pixel within a plurality of predetermined judgment parts that are set within the divided area, and the plurality of predetermined judgment parts are continuous in horizontal directions and offset toward a horizontal end side of the object, while being equally separated from each other in vertical directions.

3. The vehicle external environment recognition device of claim 2 , wherein each of the predetermined judgment parts is a pixel, and

wherein the edge intensity deriving module derives the edge intensity using a Laplacian filter of a pixel corresponding to the predetermined judgment part and two adjacent pixels adjacent to the predetermined judgment part on the left side and two adjacent pixels adjacent to the predetermined judgment part on the right side, the predetermined judgment parts being continuous in horizontal directions.

4. The vehicle external environment recognition device of claim 1 , wherein the edge intensity deriving module derives the edge average frame by frame, and concludes a median of the edge averages of three consecutive frames that is calculated using median filters, to be the edge average to be used by the floating matter identifying module.

5. The vehicle external environment recognition device of claim 2 , wherein the edge intensity deriving module derives the edge average frame by frame, and concludes a median of the edge averages of three consecutive frames that is calculated using median filters, to be the edge average to be used by the floating matter identifying module.

6. The vehicle external environment recognition device of claim 3 , wherein the edge intensity deriving module derives the edge average frame by frame, and concludes a median of the edge averages of three consecutive frames that is calculated using median filters, to be the edge average to be used by the floating matter identifying module.

7. A vehicle external environment recognition device comprising circuitry configured to:

drive three-dimensional positions in real space of a plurality of subject parts in images that are obtained by imaging a detection area;

group the subject parts of which differences in the three-dimensional position are within a predetermined range to identify an object;

horizontally divide an area containing the object to set a plurality of divided areas, and derive an edge average that is an average value of edge intensities based on a luminance value of each pixel within each of the divided areas; and

compare the edge average with a predetermined threshold, and identify the object to be likely floating matters when the edge average is less than the threshold.

8. The vehicle external environment recognition device of claim 7 , wherein the circuitry is further configured to derive the edge average based on the luminance value of each pixel within a plurality of predetermined judgment parts that are set within the divided area, and the plurality of predetermined judgment parts are continuous in horizontal directions and offset toward a horizontal end side of the object, while being equally separated from each other in vertical directions.

9. The vehicle external environment recognition device of claim 8 , wherein each of the predetermined judgment parts is a pixel, and

wherein the circuitry is configured to derive the edge intensity using a Laplacian filter of a pixel corresponding to the predetermined judgment part and two adjacent pixels adjacent to the predetermined judgment part on the left side and two adjacent pixels adjacent to the predetermined judgment part on the right side, the predetermined judgment parts being continuous in horizontal directions.

10. The vehicle external environment recognition device of claim 7 , wherein the circuitry is further configured to derive the edge average frame by frame, and conclude a median of the edge averages of three consecutive frames that is calculated using median filters, to be the edge average.

11. The vehicle external environment recognition device of claim 8 , wherein the circuitry is further configured to derive the edge average frame by frame, and conclude a median of the edge averages of three consecutive frames that is calculated using median filters, to be the edge average.

12. The vehicle external environment recognition device of claim 9 , wherein the circuitry is further configured to derive the edge average frame by frame, and conclude a median of the edge averages of three consecutive frames that is calculated using median filters, to be the edge average.