Real-time multi-view detection of objects in multi-camera environments

1. An apparatus comprising:

one or more processors coupled to memory, the one or more processors to:

map first lines associated with one or more objects to a ground plane based on group centers corresponding to object groups; and

form clusters of second lines corresponding to the first lines such that an intersection point between a first line and a second line in a cluster represents a position of an object on the ground plane, wherein the clusters represent the object groups, wherein an object group is created as represented by the cluster if the second line is detected as an isolated second line such that the isolated second line is assigned to the object group.

2. The apparatus of claim 1 , wherein the one or more processors are further to facilitate one or more cameras to capture one or more scenes having one or more images of the one or more objects, wherein a camera offers an input based on its capture of a scene of the one or more objects, wherein the input represents a view of the one or more objects from a perspective of the camera.

3. The apparatus of claim 1 , wherein the one or more processors are further to:

detect whether the second lines include an isolated second line; and

if the isolated second line is not detected, assign the second lines to the object groups wherein the first line runs vertically with respect to the object, and wherein the object includes one or more of a living being or a non-living thing.

4. The apparatus of claim 1 , wherein the one or more processors are further to:

compute group centers for the object groups; and

output positions of the one or more objects associated with the group plane based on the group centers.

5. The apparatus of claim 1 , wherein the one or more processors comprise one or more graphics processor or one or more application processors, wherein the one or more graphics processors are co-located with the one or more application processors on a common semiconductor package.

6. A method comprising:

mapping, by one or more processors of a computing device, first lines associated with one or more objects to a ground plane based on group centers corresponding to object groups; and

forming clusters of second lines corresponding to the first lines such that an intersection point between a first line and a second line in a cluster represents a position of an object on the ground plane, wherein the clusters represent the object groups, wherein an object group is created as represented by the cluster if the second line is detected as an isolated second line such that the isolated second line is assigned to the object group.

7. The method of claim 6 , further comprising facilitating one or more cameras to capture one or more scenes having one or more images of the one or more objects, wherein a camera offers an input based on its capture of a scene of the one or more objects, wherein the input represents a view of the one or more objects from the a perspective of the camera.

8. The method of claim 6 , further comprising:

detecting whether the second lines include an isolated second line; and

if the isolated second line is not detected, assigning the second lines to the object groups wherein the first line runs vertically with respect to the object, and wherein the object includes one or more of a living being or a non-living thing.

9. The method of claim 6 , further comprising:

computing group centers for the object groups; and

outputting positions of the one or more objects associated with the group plane based on the group centers.

10. The method of claim 6 , wherein the one or more processors comprise one or more graphics processor or one or more application processors, wherein the one or more graphics processors are co-located with the one or more application processors on a common semiconductor package.

11. A non-transitory computer-readable medium having stored thereon instructions which, when executed, cause a computing device to perform operations comprising:

mapping first lines associated with one or more objects to a ground plane based on group centers corresponding to object groups; and

forming clusters of second lines corresponding to the first lines such that an intersection point between a first line and a second line in a cluster represents a position of an object on the ground plane, wherein the clusters represent the object groups, wherein an object group is created as represented by the cluster if the second line is detected as an isolated second line such that the isolated second line is assigned to the object group.

12. The non-transitory computer-readable medium of claim 11 , wherein the operations further comprise facilitating one or more cameras to capture one or more scenes having one or more images of the one or more objects, wherein a camera offers an input based on its capture of a scene of the one or more objects, wherein the input represents a view of the one or more objects from the a perspective of the camera.

13. The non-transitory computer-readable medium of claim 11 , wherein the operations further comprise:

detecting whether the second lines include an isolated second line; and

if the isolated second line is not detected, assigning the second lines to the object groups wherein the first line runs vertically with respect to the object, and wherein the object includes one or more of a living being or a non-living thing.

14. The non-transitory computer-readable medium of claim 11 , wherein the operations further comprise:

computing group centers for the object groups; and

outputting positions of the one or more objects associated with the group plane based on the group centers.

15. The non-transitory computer-readable medium of claim 11 , wherein the computing device comprises one or more processors having one or more graphics processor or one or more application processors, wherein the one or more graphics processors are co-located with the one or more application processors on a common semiconductor package.