Using Kinect to detect objects on the floor

Question

Let's say I have a kindex pointing to the floor.

If I place 3 or 4 objects on the floor, how can I determine the plane on which these objects are?

How can I detect bright objects on this floor?

Answer 1

Kinect returns you a matrix def card that represents the distance of any surface to the sensor and after the pinhole camera model to align each depth measure with the corresponding RGB value. I will think that you already know how to correlate each pixel of the depth matrix with it X, Y, Z in space and the value of RGB. If not, you will need to do further research and understand how stereo correlation is performed between the depth sensor and the RGB camera.

You asked two completely different questions here. The first of them is easily solvable with some basic concept of geometry, but you must first solve the second in order to find the position of the object in space.

. , Background Subsctraction. , . , , Thresholding Segmentation. RGB HSL . , , . . blobs .

3 A ', B' C ' , :

: ​​ () (). , , , , , 3 , A, B, C, . (A - B) x (C - B) - x - . , , . , , .