System and method for identifying an object in water
The invention relates to a system for identifying at least one object at least partially immerged in a water area, said system comprising a capturing module comprising at least one camera, said at least one camera being configured to generate at least one sequence of images of said water area, and a processing module being configured to receive at least one sequence of images from said at least one camera and comprising at least one artificial neural network, said at least one artificial neural network being configured to detect at least one object in said at least one received sequence of images, extract a set of features from said at least one detected object, compare said extracted set of features with at least one predetermined set of features associated with a predefined object, identify the at least one detected object when the extracted set of features matches with the at least one predetermined set of features.
1. A system for identifying at least one object at least partially immerged in a water area, said system comprising a capturing module comprising at least one camera, said at least one camera being configured to generate at least one sequence of images of said water area, an inertial measurement module configured to provide spatial data, said spatial data comprising an inclination angle, relatively to the terrestrial horizontal axis, of the support on which the capturing module is mounted, and a processing module being configured to receive at least one sequence of images from said at least one camera and comprising at least one artificial neural network, said at least one artificial neural network being configured to detect at least one object in said at least one received sequence of images, to extract a set of features from said at least one detected object, to compare said extracted set of features with at least one predetermined set of features associated with a predefined object, and to identify the at least one detected object when the extracted set of features matches with the at least one predetermined set of features, said processing module being configured to receive the inclination angle and to estimate the distance of the identified object using the at least one sequence of images, and said inclination angle, to track the at least one identified object in the at least one sequence of images to avoid the at least one identified object.
2. The system according to claim 1 , wherein the processing module is configured to detect the horizon in each image of the sequence of image and to estimate the distance of the identified object using said detected horizon.
3. The system according to claim 1 , wherein the at least one camera is a RGB camera or a thermal camera.
4. The system according to claim 1 , wherein the capturing module comprises at least one RGB camera and at least one thermal camera.
5. The system according to claim 1 , wherein the processing module is configured to generate information data related to the at least one identified object.
6. The system according to claim 1 , wherein the processing module is configured to generate navigation data that allow to avoid the at least one detected object.
7. The system according to claim 6 , wherein the navigation data comprises a new course of the boat, a new speed of the boat or a new engine power request.
8. The system according to claim 1 , wherein the processing module is configured for sending navigation data to an electronic control module of the boat in order to automatically modify the trajectory of the boat and therefore avoid colliding with the identified object.
9. The system according to claim 1 , said system comprising an application module configured to display information related to the at least one identified object.
10. The system according to claim 9 , wherein the application module is operated by a fixed or a mobile user equipment.
11. A boat comprising the system according to claim 1 .
12. The system according to claim 1 , the processing module is configured to receive the inclination angle and to compensate each image of the sequence of images using the received inclination angle.
13. A method of identifying an object at least partially immerged in a water area, said method comprising the steps of:
generating by a capturing module at least one sequence of images of said water area,
providing spatial data comprising at least an inclination angle, relatively to the terrestrial horizontal axis, of the support on which the capturing module is mounted,
identifying at least one object in said at least generated sequence of images using an artificial neural network, wherein the identification step comprises the sub-steps of detecting at least one object in the at least one generated sequence of images, of extracting a set of features from said at least one detected object, of comparing said extracted set of features with at least one predetermined set of features associated with a predefined object, and of identifying the at least one object when the extracted set of features matches with the at least one predetermined set of features,
estimating the distance, the speed and the direction of the at least one identified object using the at least one sequence of images and said inclination angle,
tracking the at least one identified object in the at least one sequence of images.