Abstract: A device capable of equipping a vehicle comprises: a first sensor placed on the side of the vehicle facing the entrance of the space, the sensor, which may be a lidar, makes distance and orientation measurements of said vehicle with respect to the space based on the reconstruction of a cloud of points belonging to the surface of said walls; a series of sensors placed on the lateral sides of the vehicle to measure the distance from the sides to the lateral walls of the parking space, these sensors possibly being ultrasound or optical; processing means calculating the position and the relative orientation of the vehicle with respect to the walls as a function of the measurements by the various sensors and as a function of the various parking phases.

Abstract: A device and a method for assisting security in the 3D tracking of objects of interest are provided. A proposed risk propagation module makes it possible to create kinship links between the analyzed tracks, during interactions or during disappearance/reappearance of tracks, thus making it possible to diffuse the highest risks to each track concerned.

Abstract: The invention relates to a system for adjusting the height of an agricultural implement, including an arm that can be controlled to raise and lower the implement, a height measuring sensor, and a calculator configured to provide a control set point for the height of the arm on the basis of the measurements obtained by the height measuring sensor. The height measuring sensor is an imaging system including at least one camera mounted such that the sensor can form an image of a scene located in front of the agricultural implement in the direction of travel of the vehicle equipped with the arm. A computer processing unit is configured to produce, on the basis of the images delivered by the at least one camera, a 3D reconstruction representative of the depth of the aforementioned scene.

Abstract: The invention relates to a system for adjusting the height of an agricultural implement, including an arm that can be controlled to raise and lower the implement, a height measuring sensor, and a calculator configured to provide a control set point for the height of the arm on the basis of the measurements obtained by the height measuring sensor. The height measuring sensor is an imaging system including at least one camera mounted such that the sensor can form an image of a scene located in front of the agricultural implement in the direction of travel of the vehicle equipped with the arm. A computer processing unit is configured to produce, on the basis of the images delivered by the at least one camera, a 3D reconstruction representative of the depth of the aforementioned scene.

Abstract: A device capable of equipping a vehicle comprises: a first sensor placed on the side of the vehicle facing the entrance of the space, the sensor, which may be a lidar, makes distance and orientation measurements of said vehicle with respect to the space based on the reconstruction of a cloud of points belonging to the surface of said walls; a series of sensors placed on the lateral sides of the vehicle to measure the distance from the sides to the lateral walls of the parking space, these sensors possibly being ultrasound or optical; processing means calculating the position and the relative orientation of the vehicle with respect to the walls as a function of the measurements by the various sensors and as a function of the various parking phases.

Abstract: A device and a method for assisting security in the 3D tracking of objects of interest are provided. A proposed risk propagation module makes it possible to create kinship links between the analyzed tracks, during interactions or during disappearance/reappearance of tracks, thus making it possible to diffuse the highest risks to each track concerned.

Abstract: A method for detection of a target present on at least two images of the same scene captured by separate cameras comprises a prior step for learning about targets under setup conditions and further comprises, under conditions of use, a simultaneous classification step for objects present on the images, the target being said to be detected as soon as an object is classified as being one of the targets learned during the learning step. The classification step includes a step for adapting at least one of the images to the setup conditions under which the learning step took place. Application: surveillance, assistance and safety based on stereoscopic images.

Abstract: A method for detection of a target present on at least two images of the same scene captured by separate cameras comprises a prior step for learning about targets under setup conditions and further comprises, under conditions of use, a simultaneous classification step for objects present on the images, the target being said to be detected as soon as an object is classified as being one of the targets learned during the learning step. The classification step includes a step for adapting at least one of the images to the setup conditions under which the learning step took place. Application: surveillance, assistance and safety based on stereoscopic images.

Abstract: A coded target used in photogrammetry, the target being circular and including at least two concentric coding rings with at least two equal angular sectors, arranged around a central area including a central disk with a uniform color surrounded by a ring with a complementary color, itself surrounded by a ring the same color as the central disk. A photogrammetry process automatically detects and identifies targets.

Abstract: In this system, three-dimensional objects (1, 5, 6) in an environment that may be very complex are discerned by identifying their simple contour shapes on images, and the geometric characteristics of these objects and their positions and orientations are then measured. Contours are defined by simple length, inclination, position parameters, etc. The acquired knowledge of the environment is used in each new image to refine the estimates, while introducing new object contours that have appeared, into the model.

Abstract: A coded target used in photogrammetry, the target being circular and including at least two concentric coding rings with at least two equal angular sectors, arranged around a central area including a central disk with a uniform color surrounded by a ring with a complementary color, itself surrounded by a ring the same color as the central disk. A photogrammetry process automatically detects and identifies targets.

Abstract: In this system, three-dimensional objects (1, 5, 6) in an environment that may be very complex are discerned by identifying their simple contour shapes on images, and the geometric characteristics of these objects and their positions and orientations are then measured. Contours are defined by simple length, inclination, position parameters, etc. The acquired knowledge of the environment is used in each new image to refine the estimates, while introducing new object contours that have appeared, into the model.