10 results about "Stick figure" patented technology

The invention discloses a robot carrying method and system in a low-gravity environment and a storage medium, and the method comprises the steps: collecting a stick figure drawn by an operator and a real scene image in a current cabin, and inputting the stick figure and the real scene image into a trained dual-branch visual encoder model; a basic action sequence instruction used for controlling the robot to complete material carrying operation is generated, then the target rotation angular speed is monitored in real time in the process of executing the basic action sequence instruction to conduct target grabbing, and if the target rotation angular speed is larger than a set threshold value, a robot clamping jaw is driven to conduct rotation fine adjustment in the reverse direction. Therefore, pure visual instruction interaction is realized to adapt to the condition that voice interaction in a low-gravity scene is completely unavailable, and meanwhile, the problem that an object is easy to generate irregular rotation and is difficult to grab when being stressed under low gravity is solved.

1. Name of the product in this design: Doll (Orange Sticky Doll). 2. Purpose of this design: Primarily for play. 3. The key design features of this product are the combination of shape and pattern. 4. The image or photograph that best illustrates the design's key points: a 3D model.

1. The name of the design product: silica gel mold (strawman card). 2. The use of the design product: silica gel mold for making strawman card by dropping glue. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective view 1.

A dual video recording system and method can capture simultaneous multiple angles of exercises using a first and a second camera for recording video and a processor that compiles the video data from the first and second cameras. The compiled video may be analyzed by transmitting it to a physical health professional for analysis, transmitting it to an artificial intelligence capability for training a machine learning model and / or for analysis by a machine learning model, or may be analyzed by the processor. The analysis may include generating a stick figure model representing the exercise actions, and this model may be used to generate the graphic interpretation overlaid over video of the exercise to provide feedback.

This invention discloses a method for fitting a 3D human body model based on 2D contour interaction and semantic segmentation. The method first parses a user-drawn 2D stick figure skeleton using a JPN module and drives an SMSLX model to generate an initial 3D human body. Then, the initial model contour is rendered from multiple fixed perspectives, generating corresponding bounding voxel spaces and point cloud projections. A prior network combining UDF and positional information is introduced to guide the training of the multi-view semantic segmentation network module UPS, achieving accurate segmentation of each part of the contour image. Based on the segmentation results and voxel point cloud projections, surface constraint point clouds for each body part are calculated. Finally, using the constraint point clouds as targets, the SMSLX model parameters are optimized for each part using a CFM module, ultimately generating a 3D human body shape that matches the user's editing intent. This invention allows users to indirectly adjust complex 3D models through intuitive 2D contour editing, significantly improving interaction efficiency and avoiding direct manipulation of complex 3D data.

The embodiment of the invention discloses a drawing interaction method and device, a storage medium and electronic equipment, and the method comprises the steps: carrying out the stick figure conversion processing of an image photographed by a user through a drawing creation large model, and obtaining a reference simulated stick figure, so that the user can select a target simulated stick figure, performing drawing customization processing based on the target imitation stick figure to obtain a drawing line draft and a color filling area corresponding to the drawing line draft, displaying the drawing line draft and the color filling area to a user, obtaining first drawing operation data input by the user, generating an initial drawing work based on the first drawing operation data, and displaying the initial drawing work on the user. And performing painting detail detection processing on the initial painting work to obtain a painting detail complete area, displaying the painting detail complete area to the user, obtaining second painting operation data input by the user, and generating a target painting work based on the second painting operation data. Therefore, the drawing interaction function of the intelligent shooting equipment is enriched, and meanwhile, the user can be helped to improve the drawing ability.

The present invention discloses a method for generating stick figures based on artificial intelligence, and relates to the field of artificial intelligence technology. The present invention greatly reduces the difficulty of data collection by adopting unpaired training data as training samples for deep learning. At the same time, shared data sets or data on the Internet can be used as training samples for training, and more challenging photos can be included in the training set, thereby expanding the training set and enriching the data categories. The problem of paired training data is solved, and the effect of stick figure generation is greatly improved, which provides strong data support for the algorithm for generating stick figures. It is also one of the important reasons why the present invention finally achieves good results. The present invention enhances the generation performance of facial features. On the basis of the original network, multiple local discriminant networks are used, including local discriminant networks for eyes, nose and lips, to enhance the expression of regional information, and well preserve all important facial features in the generated portrait.

According to the robot material carrying method, the robot and the storage medium, the shape features of the operation target are extracted from the stick figures by obtaining the stick figures describing the shape of the operation target and the position information of the carrying destination; environment data in the current task scene are collected, visual features are extracted from the environment data, and the visual features and the shape features are aligned through a contrast loss function; extracting shape features of an operation target from a target area, and calculating a target pose and confirming a material type from the environmental data based on the target area; and finally, a preset control information base is inquired based on the type of the target object to obtain corresponding action constraint information, the action constraint information, the target pose and the destination position information are combined, and after a material carrying instruction is generated, all executing mechanisms are controlled to move to complete material carrying operation. Material carrying can be achieved in a noisy industrial scene only through a pure visual instruction without inputting a complex text instruction.