Method and device for determining the depth of a pixel of an image by a neural network associated with a vision system on board a vehicle

Abstract

Method or device for determining a depth of a pixel of an image by a neural network associated with a vision system embedded in a vehicle (10) comprising two cameras (11, 12). Indeed, the neural network is learned by minimizing errors determined by comparing two images generated from images acquired by the vision system via the implementation of the neural network to other images acquired by the vision system. An image generated from an image acquired by a camera at a time instant is compared to an image acquired by the other camera at the same time instant to determine a first error while an image generated from an image acquired by a camera at a time instant is compared to an image acquired by this camera at another time instant to determine a second error. Figure for the abstract: Figure 1

Claims

5. Method according to claim 4, for which the data representative of the first displacement and the extrinsic parameters of the stereoscopic vision system each comprise three coefficients representative of a translation and three coefficients representative of a rotation in a reference frame associated with the first camera (11), said third error being equal to an average of the differences of the coefficients associated with the first displacement and the extrinsic parameters compared two by two.

6. Method according to one of claims 1 to 5, for which the camera (11) is a wide-angle camera.

7. Method according to one of claims 1 to 6, wherein a field of view of the second camera (12) covers at least half of a field of view of the first camera (11).

8. Computer program comprising instructions for implementing the method according to any one of the preceding claims, when these instructions are executed by a processor.

9. Device (4) for determining a depth by a vision system on board a vehicle (10), said device (4) comprising a memory (41) associated with at least one processor (40) configured for implementing the steps of the method according to any one of claims 1 to 7.

10. Vehicle (10) comprising the device (4) according to claim 9. [Fig. 1] [Fig. 2]

Images