Abstract: Subjects of the present disclosure are methods for training deep learning models, methods for predicting a map matching parameter, methods for updating a digital road map, and a computer program making it possible to implement the methods and devices for updating a digital road map. The general principle is based on the use of machine learning. Accordingly, a statistical deep learning model is trained according to a “supervised” machine learning scheme. Thereafter, the pretrained statistical deep learning model is used to predict a map matching parameter on the basis of a measurement of geographic coordinates and of an identifier of the position sensor that has performed the measurement of geographic coordinates. Finally, the map matching parameter can be used to update a digital road map.

Abstract: A method for aligning at least a first source image with a second reference image, each image including a set of three-dimensional points. The method being intended to reconstruct a common image by aligning the first source image with the second reference image. The method including at least: an association step of associating, in pairs, at least some of the points of the first source image, forming a first group of interest of points, with the corresponding points of the second reference image, using nearest neighbor criteria, a step of aligning the points associated in pairs by applying a spatial transformation. The method being noteworthy in that it includes a step of estimating the visibility of the points in order to limit point alignment errors.

Abstract: Subjects of the present disclosure are methods for training deep learning models, methods for predicting a map matching parameter, methods for updating a digital road map, and a computer program making it possible to implement the methods and devices for updating a digital road map. The general principle is based on the use of machine learning. Accordingly, a statistical deep learning model is trained according to a “supervised” machine learning scheme. Thereafter, the pretrained statistical deep learning model is used to predict a map matching parameter on the basis of a measurement of geographic coordinates and of an identifier of the position sensor that has performed the measurement of geographic coordinates. Finally, the map matching parameter can be used to update a digital road map.

Abstract: A method of processing images allowing the identification of at least one same point appearing on each image of a sequence of images, the sequence of images including a first image, a second image and a third image generated respectively at a first instant, a second instant, later than the first instant, and a third instant, later than the second instant, by a camera mounted in an automotive vehicle. The method includes detecting a plurality of identical points in each image of the sequence of images, relating to a plurality of repetitive patterns in each image of the sequence of images and of identification, in the second image and in the third image, of the identical points corresponding to the points in space for which the calculated depth is identical, these points in space representing respectively in the second image and the third image one and the same real point.

Abstract: Disclosed is a method to calibrate an on-board stereo system. The method includes correlating the depth deviation of a point of a scene observed by the system with respect to a supposedly planar scene and the corresponding yaw deviation between the cameras of the system, then deducing therefrom a yaw calibration correction for the cameras. The comparison between the scene as observed and as expected consists in determining, via spatio-temporal filtering, a depth deviation between the observed depth of at least one point of a planar scene image formed in the image plane of first camera, as positioned in the coordinate system of the other camera, and the expected depth of this point projected onto the planar scene from the first camera, then in determining the yaw calibration deviation between the cameras as a function of the deviation in depth averaged over a sufficient set of points.

Abstract: A method of processing images allowing the identification of at least one same point appearing on each image of a sequence of images, the sequence of images including a first image, a second image and a third image generated respectively at a first instant, a second instant, later than the first instant, and a third instant, later than the second instant, by a camera mounted in an automotive vehicle. The method includes detecting a plurality of identical points in each image of the sequence of images, relating to a plurality of repetitive patterns in each image of the sequence of images and of identification, in the second image and in the third image, of the identical points corresponding to the points in space for which the calculated depth is identical, these points in space representing respectively in the second image and the third image one and the same real point.

Abstract: A method, a medium (20) and a system (10) for calibrating a camera (32) of a vehicle (30). The calibration system (10) is remarkable in that it includes a calibration medium (20), including at least a first calibration reference (24) and a mirror (26), and a vehicle (30), including at least a second calibration reference (34). The method can be used to calibrate the camera (32) by determining the spatial compensation values between the camera (32) and the vehicle (30), without any need to align the vehicle (30) perfectly facing the calibration medium (20).

Abstract: The disclosed method checks the state of degradation of the suspension of a vehicle without having to carry out tests that immobilize the vehicle or to use non-objective expertise. The method processes data provided by at least one front camera in an on-board visual system. The checking method includes steps for periodically acquiring images provided by the camera or cameras, followed by storage of the positional data of the three-dimensional road in relation to a flat road and basic positional parameter data for the path of the vehicle. The error between the ideal values of the suspension parameters of a chosen suspension model and the values of these parameters corresponding to the stored path data from the positional data is then minimized. By iteration, the accuracy ? of the error reaches a predetermined value sufficient to diagnose a state of the suspension.

Abstract: Disclosed is a method to calibrate an on-board stereo system. The method includes correlating the depth deviation of a point of a scene observed by the system with respect to a supposedly planar scene and the corresponding yaw deviation between the cameras of the system, then deducing therefrom a yaw calibration correction for the cameras. The comparison between the scene as observed and as expected consists in determining, via spatio-temporal filtering, a depth deviation between the observed depth of at least one point of a planar scene image formed in the image plane of first camera, as positioned in the coordinate system of the other camera, and the expected depth of this point projected onto the planar scene from the first camera, then in determining the yaw calibration deviation between the cameras as a function of the deviation in depth averaged over a sufficient set of points.

Abstract: The disclosed method checks the state of degradation of the suspension of a vehicle without having to carry out tests that immobilize the vehicle or to use non-objective expertise. The method processes data provided by at least one front camera in an on-board visual system. The checking method includes steps for periodically acquiring images provided by the camera or cameras, followed by storage of the positional data of the three-dimensional road in relation to a flat road and basic positional parameter data for the path of the vehicle. The error between the ideal values of the suspension parameters of a chosen suspension model and the values of these parameters corresponding to the stored path data from the positional data is then minimized. By iteration, the accuracy ? of the error reaches a predetermined value sufficient to diagnose a state of the suspension.

Abstract: A method, a medium (20) and a system (10) for calibrating a camera (32) of a vehicle (30). The calibration system (10) is remarkable in that it includes a calibration medium (20), including at least a first calibration reference (24) and a mirror (26), and a vehicle (30), including at least a second calibration reference (34). The method can be used to calibrate the camera (32) by determining the spatial compensation values between the camera (32) and the vehicle (30), without any need to align the vehicle (30) perfectly facing the calibration medium (20).

Abstract: A method for measuring a period of time between a first event and a second event via a hardware counter 2 and of a software counter 3. A digital counter 1 using such a method is also described.

Abstract: A method for measuring a period of time between a first event and a second event via a hardware counter 2 and of a software counter 3. A digital counter 1 using such a method is also described.