5 results about "Disjoint-set" patented technology

This invention relates to the field of computer vision technology, specifically disclosing a disparity detection method based on synchronous filtering. The method comprises the following steps: S1: feature extraction and cross-view point pair construction; S2: constructing a disjoint-set data structure with dynamic member tracking capabilities; S3: constructing a synchronous filtering sequence based on global ranking; S4: dynamic topological consistency analysis and disparity suspect point marking; S5: filtering to obtain highly robust final disparity feature points and outputting them. The technical solution of this invention can accurately identify and retain disparity feature points that have physical consistency but violate the global geometric model in scenarios with large disparity and complex depth, without pre-setting a global geometric model or relying on fixed parameters.

Systems and methods for detecting a presentation attack. Datasets of original images and attack samples are used to train a model that creates in a feature space of samples of original images a set of elements corresponding to each sample. Elements form a limited set normalized to a disjoint set so that the boundary of the disjoint set divides the space of all possible collections of features into “legitimate” and “all others.”“All others” include signs of known attacks, anomalies and signs of unknown attacks.

The application discloses a kind of based on adaptive boundary perception's spare part point cloud hierarchical super voxel segmentation method, it is related to three-dimensional point cloud super voxel segmentation technical field, this method calculates the multidimensional geometry feature of each point of point cloud first, constructs point cloud boundary weight model by weighted fusion and nonlinear transformation;Again, complete point cloud voxelization based on octree space division mechanism, according to boundary weight value, voxel is divided into boundary voxel and seed voxel, and the initial super voxel is generated by merging the point set in voxel through union-find set data structure;Then, relying on global energy optimization framework, combined with distance measurement function containing boundary weight difference item, hierarchical iterative fusion is carried out on the representative point of initial super voxel;Finally, the super voxel after fusion is corrected and the spatial connectivity is corrected, and the multi-resolution super voxel segmentation result is output.The application can solve the problem that traditional method is easy to over-segmentation, under-segmentation, and enhance the adaptive level of complex equipment spare part structure.

The application provides an interval event matching method and system of a content-based publish / subscribe system, through constructing a predicate disjoint set and an optimized partition model thereof, and integrating a learning index of a range query recursive model index in each partition, high-speed, stable and verifiable matching of events to a subscription set under multi-attribute interval predicates is realized; in particular, the traditional memory-intensive matching is reconstructed into a calculation-intensive process mainly based on model reasoning, while correctness and completeness are ensured, average latency is reduced and long tail delay is inhibited, and key modules such as partition and coverage optimization, model training and online reasoning, error boundary control and limited correction, and accurate back matching of residual set subscription are included.

The application discloses a satellite video dense vehicle tracking method and system, comprising: extracting vehicle target features in continuous video frames based on a space-time target detector, outputting an initial detection frame and confidence, and correcting low-confidence targets caused by motion blur through a motion offset loss function guided by optical flow; extracting a road mask and constructing a distance transform field by using superpixel segmentation, and performing confidence soft attenuation on the detection frame of a non-road area; processing high and low detection sets through cascaded data association, and performing physical occlusion diagnosis and kinematic state correction on unmatched trajectories, and dynamically adjusting the trajectory life cycle in combination with topological perception; regarding online trajectory segments as graph nodes to construct a multi-modal space-time position graph, fusing time attenuation apparent consistency, spatial distance and motion direction consistency penalty calculation edge weight with time attenuation, and realizing global merging of cross-frame trajectory segments by using the Hungarian algorithm and a union-find set, and repairing trajectory fractures through linear interpolation.