Image processing device of person detection system

1 . An image processing device of a person detection system mounted on a moving body, wherein

the image processing device is configured to:

detect, in image data obtained from a camera, an area in which an obstacle appears, wherein the area detected by the camera in which the obstacle appears is a rectangular area and the rectangular area is based on a detectable range of the camera;

detect a height of a lower end of the area from a road surface and a height of an upper end of the area from the road surface;

determine whether the area meets an upper body detection process condition, wherein the upper body detection process condition is met when a distance from the camera to the obstacle is within a predetermined range and the height of the lower end of the area is within a predetermined distance from the road surface;

perform an upper body detection process in which the area of the image data is compared with upper body comparison data to determine whether the obstacle in the area is a person, for the area that meets the upper body detection process condition,

wherein the upper body detection process includes:

detect an area ratio corresponding to a ratio of a dimension of the area from the lower end to the upper end of the area to a height of a top of the obstacle based on the height of the lower end of the area from the road surface and the height of the upper end of the area from the road surface; and

obtain the upper body comparison data by applying the area ratio to whole-body comparison data; and

perform a whole-body detection process in which the area of the image data is compared with the whole-body comparison data to determine whether the obstacle in the area is a person, for the area that does not meet the upper body detection process condition.

2 . The image processing device of the person detection system according to claim 1 , wherein

the upper body detection process includes:

a process in which a part of the area is taken out by a predetermined length from an upper end toward a lower end of the area of the image data and the part of the area that is taken out is defined as a post-correction area; and

a process in which the post-correction area is compared with the upper body comparison data to determine whether the obstacle in the area is a person.

3 . The image processing device of the person detection system according to claim 1 , wherein

the whole-body comparison data corresponds to whole-body dictionary data of features extracted from image data in which a whole body of the person appears, and

the upper body comparison data corresponds to upper body dictionary data of features extracted from image data in which an upper body of the person appears.

4 . An image processing device of a person detection system mounted on a moving body, comprising:

at least one memory configured to store computer program code; and

at least one processor configured to access the at least one memory and operate as instructed by the computer program code, wherein

the computer program code is configured to cause the at least one processor to:

detect, in image data obtained from a camera, an area in which an obstacle appears, wherein the area detected by the camera in which the obstacle appears is a rectangular area and the rectangular area is based on a detectable range of the camera;

detect a height of a lower end of the area from a road surface and a height of an upper end of the area from the road surface;

determine whether the area meets an upper body detection process condition, wherein the upper body detection process condition is met when a distance from the camera to the obstacle is within a predetermined range and the height of the lower end of the area is within a predetermined distance from the road surface;

perform an upper body detection process in which the area of the image data is compared with upper body comparison data to determine whether the obstacle in the area is a person, for the area that meets the upper body detection process condition,

wherein the upper body detection process includes:

detect an area ratio corresponding to a ratio of a dimension of the area from the lower end to the upper end of the area to a height of a top of the obstacle based on the height of the lower end of the area from the road surface and the height of the upper end of the area from the road surface; and

obtain the upper body comparison data by applying the area ratio to whole-body comparison data; and

perform a whole-body detection process in which the area of the image data is compared with the whole-body comparison data to determine whether the obstacle in the area is a person, for the area that does not meet the upper body detection process condition.