33 results about "Sequence graph" patented technology

Rendering an animation on a mobile device having a display screen, including: (a) storing in a memory of the mobile device a binary animation instruction set that includes a visual graph and a sequence graph, the visual graph including instructions defining visual objects that are to be displayed on the display screen and visual attributes of the visual objects, the sequence graph including instructions setting out behavioral operations to be performed on the visual objects, at least some of the behavioral operations defining changes to the visual attributes of the visual objects; and (b) rendering the visual objects on the display screen in accordance with the instructions contained in the visual graph and periodically re-rendering at least some of the visual objects in accordance with the behavioral operations set out in the sequence graph.

The invention provides an ant colony sequencing and positioning method for circular layout in cable processing, which comprises the following steps of: abstracting a sequencing process for determininga circular wire placement sequence into an optimal path problem in a graph theory, and obtaining a sequencing graph according to a pattern; abstracting a positioning process for determining the placement position of the circular wire into a position selection problem; initializing parameters; according to heuristic information in the sequencing diagram, enabling the ants to determine to-be-placedcircular wires from the to-be-placed circular wire set; according to a stimulation-response principle, enabling the ants to select one from a plurality of feasible positions to place a circular wire;updating the current pattern and the to-be-set circular wire set; enabling the ants to complete one-time search; enabling all ants to be searched for once, and updating heuristic information in the sequencing diagram; and circularly updating the radius of the circular insulating tube, and outputting a final layout result. The method can adapt to different layout environments, and the diversity ofsearch patterns is maintained; and the searching space can be reduced, the searching speed is improved, and round wires are ensured not to overlap with each other during cable processing.

The invention discloses a method for correcting sequence diagrams based on 3D try-on, which includes detecting each frame image of a video generated in 3D try-on, and generating detection data corresponding to each frame image in the video, the detection data Including the yaw angle; selecting the images of each frame with the yaw angle within the first threshold range to form an effective sequence atlas; re-detecting each frame of image in the effective sequence atlas to generate a corresponding The re-detection data of each frame image in the effective sequence atlas, the re-detection data includes the re-detection yaw angle; the re-detection yaw angle is corrected according to the order of each frame image in the effective sequence atlas; The method disclosed in the invention improves the accuracy of the identification of the try-on part through multiple detections, reduces the error when identifying the try-in part, thereby improving the accuracy of the try-on; the invention also discloses a method based on The sequence diagram correction device for 3D try-on also has the above-mentioned beneficial effects.

The present invention discloses a prostate KVCT image prostate region 3D segmentation method, which mainly aims to solve the problem of failing to perform prostate segmentation on a KVCT image. The implementation steps of the method are as follows: 1) inputting a to-be-segmented prostate KVCT three-dimensional image, and generating super pixels based on the three-dimensional image; 2) calculating a 15-dimensional texture feature of the super pixels; 3) performing primary clustering on the super pixels to obtain an initial segmentation result; 4) performing secondary clustering on the initial segmentation result to obtain two clustering results; 5) performing three-dimensional morphological processing on the two clustering results to obtain an adhesion-removing result; and 6) segmenting an image with severe adhesion at the top of a sequence graph by using registration, and then substituting an obtained part of the sequence graph by registration segmentation for the corresponding sequence graph in the adhesion-removing graph, so as to obtain a final segmentation result.

The invention discloses a method, a device, a storage medium and a processor for detecting fighting behavior in a video. Among them, the method includes: decoding the video to be detected to obtain multiple single-frame pictures; extracting and processing multiple single-frame pictures according to the preset deep learning pose estimation model to obtain the position information of key nodes of the human body in multiple single-frame pictures; Multiple human skeleton sequence diagrams; input multiple human skeleton sequence diagrams into a preset three-dimensional convolutional neural network abnormal behavior detection model, and obtain one or more preliminary detection results matching the number of multiple human skeleton sequence diagrams; One or more preliminary detection results are calculated to obtain target detection results. The invention solves the technical problems of low detection accuracy and low detection efficiency in the detection of fighting behavior in videos in the prior art.

Described is a system for an episodic memory used by an automated platform. The system acquires data from an episodic memory that comprises an event database, an event-sequence graph, and an episode list. Using the event-sequence graph, the system identifies a closest node to a current environment for the automated platform. Based on the closest node and using a hash function or key based on the hash function, the system retrieves from the event database an episode that corresponds to the closest node, the episode including a sequence of events. Behavior of the automated platform in the current environment is guided based on the data from the episodic memory.

The invention discloses a human behavior recognition method based on a structuralized characteristic pattern. The method comprises the steps that a space-time interest point is extracted from a sample, and a characteristic vector is generated; the characteristic vector is set as an initial value, parameter training of a hidden condition random field model is completed by utilizing a preset function, and an element with intermediate semantic information and a spatial connecting relation of the element are learned; the sample is divided into timing sequence units, characteristic patterns are established inside the timing sequence units, and the characteristic patterns are mapped in a characteristic space; the timing sequence units are connected through a timing sequence relation, a chain-shaped graph is established, and a timing sequence graph kernel is brought up; the timing sequence graph kernel is utilized, and to-be-recognized behavior video is classified and recognized. By adopting an HCRF to complete the learning on the element and the incidence relation of the element, by using the characteristic patterns to complete the description of a video sequence, and by using the timing sequence graph kernel to complete the matching of the characteristic patterns in space and time, behavior sequences of different lengths and velocities can be matched, and the method can be used for the behavior of an individual and also be used for the interactive behaviors of many people.