Robot for detecting human head and control method thereof

A robot comprising:

• a camera configured to acquire a depth image of a specific area;
• and
• a processor configured to:
• create an elevation map for the specific area based on the depth image;
• and
• determine whether a head of a person is in the specific area based on the elevation map,
• wherein the processor, when determining whether the head of the person is in the specific area is further configured to:
• partition pixels of the elevation map into floor pixels corresponding to a floor area and non-floor pixels corresponding to a non-floor area using elevation values of the elevation map,
• set paths through the elevation map with a subset of the non-floor pixels as starting points, and
• determine whether the head of the person is in the specific area based on whether the paths converge, based on whether a circular or elliptical curve is detected in the pixels of the depth image corresponding to the pixels on which the paths converge, and based on brightness values of the pixels included in the paths in the depth image.

A method of controlling a robot, comprising:

• acquiring a depth image of a specific area;
• creating an elevation map for the specific area based on the depth image;
• determining whether a head of a person is in the specific area based on the elevation map;
• and
• controlling an operation of the robot based on whether the head of the person is in the specific area,
• wherein determining whether the head of the person is in the specific area includes:
• partitioning pixels of the elevation map into floor pixels corresponding to a floor area and non-floor pixels corresponding to a non-floor area using elevation values of the elevation map;
• setting paths through the elevation map with a subset of the non-floor pixels as starting points;
• and
• determining whether the head of the person is in the specific area based on whether the paths converge.