3 results about "Fuzzy object" patented technology

The application belongs to the technical field of simultaneous localization and mapping, and particularly relates to a SLAM algorithm based on feature reinforcement and motion judgment in a dynamic scene, which applies a feature reinforcement instance segmentation network FENET and comprises the following steps: step S1, collecting image information and realizing feature recovery of a dynamic fuzzy object through a fuzzy feature recovery module; step S2, guiding a model to focus on key features of an object based on a reinforced feature recognition mechanism, and recognizing potential dynamic objects; and step S3, jointly estimating the pose of a camera itself and judging the motion of an object to remove a dynamic object. The application can reconstruct and recover lost feature information from a fuzzy image, greatly improves the recognition accuracy of a system for a dynamic object, greatly improves the recognition accuracy of a dynamic object, and avoids misjudgment of static features.

The methods presented herein are used to de-duplicate object representations in a three-dimensional (3D) scene. One or more features may be extracted from an object in a three-dimensional (3D) scene to compute an individual object signature, which may be a representation of an appearance of the object. The object signatures may then be compared using one or more similarity metrics in order to determine whether the object is duplicated and / or nearly duplicated. For duplicated objects, the common representation may be used for each duplicated object rendered at a given location and orientation within the scene, thereby rendering objects within the scene using less memory and computing resources.

Approaches presented herein provide for deduplication of object representations in three-dimensional (3D) scenes. One or more features may be extracted from objects in a 3D scene to compute an individual object signature, which may be a representation of an appearance of the object. Object signatures may then be compared using one or more similarity metrics in order to determine whether or not objects are duplicates and / or near-duplicates. For duplicate objects, a common representation may be used for each duplicate object that may be rendered within the scene at a given location and orientation, thereby using less memory and compute resources to render objects within the scene.