| CPC G06V 20/69 (2022.01) [G01B 11/02 (2013.01); G01B 11/2408 (2013.01); G06F 18/24 (2023.01); G06V 10/141 (2022.01); G06V 10/42 (2022.01); G06V 10/454 (2022.01); G06V 10/60 (2022.01); G06V 10/70 (2022.01); G06V 10/82 (2022.01)] | 8 Claims |

|
1. A method for representation learning for classifying a scene into at least one geometrical shape, static or dynamic, quantified by an adequate set of parameters, each geometrical shape modeling a luminous object, the method comprising:
a. projecting a singular distribution of light onto a scene;
b. detecting a light distribution, reemitted by the scene upon illumination by the singular light distribution that has interacted with each luminous object and that impinges upon a detector, the light detected constituting detected light;
c. measuring at least one projection of the singular distribution at a given position to obtain a set of coded image measurements with respect to a scene based on the detected light; and
d. employing a neural network layer, using the coded image measurements based on the detected light as direct input of the neural network layer, adapted to classify the scene, as a plurality of shapes, static or dynamic, the shapes being part of a set of shapes predetermined or acquired by learning.
|