Camera environment mapping
Systems and methods may be used to map an environment visible in an image captured by a camera. The mapping may include a floor map (e.g., locations within the environment where a floor is present). A method may include receiving images from a camera. The method may include using an object that moved from a first image to a second image to identify floor points within the environment. The method may include mapping a floor plane of the environment using the floor points.
1. A device for mapping an environment observable via a camera, the device comprising:
a processor; and
memory, communicatively coupled to the processor, the memory including instructions, which when executed, cause the processor to:
receive a series of frames of video data captured by the camera;
identify a person within the series of frames;
based on a determined skeletal structure for the person in each of the series of frames, calculate a primary axis of the person, the primary axis including a foot endpoint; and
map a 3D floor plane of an area captured in the series of frames based on identified locations of the foot endpoint in each of the series of frames.
2. The device of claim 1 , wherein the camera lacks any hardware-based depth sensing capabilities.
3. The device of claim 1 , wherein the primary axis is a line segment extending from a head of the person to a midpoint between two feet of the person.
4. The device of claim 1 , wherein the camera is a single camera, the 3D floor plane mapped based solely on data received from the single camera.
5. The device of claim 1 , wherein the 3D floor plane is mapped based on an assumption that the primary axis of the person varies based on distance from the camera while a height of the person remains constant.
6. The device of claim 1 , wherein the 3D floor plane is mapped based on an assumption that the primary axis is parallel to a gravity vector.
7. The device of claim 1 , wherein the instructions further cause the processor to determine an angle of orientation of the camera with respect to the 3D floor plane of the area.
8. A method for mapping an environment observable via a camera, the method comprising:
receive, at a processor, a series of frames of video data captured by a camera;
identify, using the processor, a person within the series of frames;
based on a determined skeletal structure for the person in each of the series of frames, calculate a primary axis of the person, the primary axis including a foot endpoint;
generating, using the processor, a map of a 3D floor plane of an area captured in the series of frames based on identified locations of the foot endpoint in each of the series of frames; and
outputting the map.
9. The method of claim 8 , wherein the camera lacks any hardware-based depth sensing capabilities.
10. The method of claim 8 , wherein the primary axis is a line segment extending from a head of the person to a midpoint of two feet of the person.
11. The method of claim 8 , wherein the camera is a single camera, the 3D floor plane mapped based solely on data received from the single camera.
12. The method of claim 8 , wherein the 3D floor plane is mapped based on an assumption that the primary axis of the person varies based on distance from the camera while a height of the person remains constant.
13. The method of claim 8 , wherein the 3D floor plane is mapped based on an assumption that the primary axis is parallel to a gravity vector.
14. The method of claim 8 , further comprising determining an angle of orientation of the camera with respect to the 3D floor plane of the area.
15. An apparatus for mapping an environment observable via a camera, the apparatus comprising:
means for receiving a series of frames of video data captured by a camera;
means for identifying a person within the series of frames;
means for, based on a determined skeletal structure for the person in each of the series of frames, calculating a primary axis of the person, the primary axis including a foot endpoint;
means for mapping a 3D floor plane of an area captured in the series of frames based on identified locations of the foot endpoint in each of the series of frames; and
means for outputting the 3D floor plane for display.
16. The apparatus of claim 15 , wherein the camera is a single camera, the 3D floor plane mapped based solely on data received from the single camera.
17. The apparatus of claim 15 , wherein the camera lacks any hardware-based depth sensing capabilities.
18. The apparatus of claim 15 , wherein the primary axis is a line segment extending from a head of the person to a midpoint of two feet of the person.
19. The apparatus of claim 15 , wherein the 3D floor plane is mapped based on an assumption that the primary axis of the person varies based on distance from the camera while a height of the person remains constant.
20. A device for mapping an environment observable via a camera, the device comprising:
a processor; and
memory, communicatively coupled to the processor, the memory including instructions, which when executed, cause the processor to:
receive a series of frames of video data captured by the camera;
identify an object within the series of frames;
based on a determined structure for the object in each of the series of frames, calculate a primary axis of the object, the primary axis including an endpoint; and
map a 3D floor plane of an area captured in the series of frames based on identified locations of the endpoint in each of the series of frames.