5results about How to "Rich texture" patented technology

The utility model relates to a fountain equipment technical field, especially a pencil type circulating fountain, including the pen point, the pen point top outer wall fixedly connected rotating base, rotating base inner wall fixedly connected first motor, first motor output fixedly connected gear, the rotating base inner wall has set up first sliding slot, the rotating base top outer wall sliding connection pen barrel outer wall, the pen barrel inner wall is fixedly provided with the toothed disc, the toothed disc is engaged with the gear, the utility model discloses through starting the first motor in rotating base, drives the gear and toothed disc engagement transmission, drives pen barrel rotation. The waterproof color light bar of pen barrel outer wall synchronous display changeable light, create the visual effect of dynamic and gorgeous multicolored, make the fountain become the visual focus, simultaneously, the atomizer and the spray head that added, let the fountain on the basis of traditional water flow injection, add the landscape level that water mist diffuses and rain curtain sprays, the form and the texture of the fountain are enriched.

This invention relates to a video object removal method based on a text-based video model and learnable negative tokens, comprising: acquiring the original video to be processed and a specified target to be removed; segmenting the target to be removed using a video segmentation model to generate a corresponding video mask sequence; preprocessing the original video and the video mask sequence to obtain masked video latent features and mask latent features; constructing an object removal model based on a text-based video model, wherein the object removal model retains the cross-attention module of the pre-trained text-based video model; setting the text prompt input to empty and introducing learnable negative tokens; inputting the masked video latent features, mask latent features, and negative tokens into the object removal model; the object removal model processes the negative tokens through the cross-attention module, suppressing object generation features within the mask region, and generating filling content based on video background information; and outputting the video after removing the specified target.

The present application relates to the field of robot environment perception, and is used for solving the problem that the existing robot environment perception system lacks a unified and efficient hierarchical fusion architecture to systematically process multi-source heterogeneous data, in particular to a robot real environment perception early warning system for multi-sensor data fusion; the present application significantly improves the comprehensiveness and accuracy of environment perception through the cooperative work of laser radar, visual camera, millimeter wave radar and ultrasonic sensor; through the progressive processing flow of space-time registration, cross-checking, feature definition to deep fusion, the multi-source information is sorted by confidence and features are extracted, and the heterogeneous feature fusion module generates an environment dynamic semantic map rich in texture, structure, motion and semantic information by means of convolutional neural network, which provides accurate and comprehensive information basis for early warning decision, and at the same time, the dynamic hierarchical early warning mechanism provides reliable guarantee for robot safety and autonomous operation.

The application belongs to the field of image processing, and proposes a multispectral image fusion framework of an optimized double-branch feature pyramid, aiming to solve the problems of unnatural color and contrast mismatch that may occur when fusing infrared and visible light images under dark light conditions. First, a multi-scale residual module is used to strengthen feature extraction, and a Canny filter is integrated to capture feature information. Second, shallow and deep fusion modules are used to realize information fusion, and a weighted loss guide process of gradient and contrast is designed. Finally, a residual connection feature reconstruction module is used to splice and reconstruct the features of the fused image. The application can effectively realize the fusion of infrared and visible light images based on low light scenes, has excellent feature extraction capability and high-quality visual fusion effect, and can ensure high contrast, rich background and other features.

The invention belongs to the technical field of unmanned driving, and particularly relates to a sensing method and device based on multi-radar and camera fusion and a vehicle, and the method comprises the steps: obtaining the original point cloud data of a plurality of radar sensors and the image data of a camera, carrying out the space-time alignment of the original point cloud data and the image data, and obtaining the image data of the camera; generating a depth map of the image by using the data after space-time alignment; the depth map is input into a wavelet DSIRes2Net module, multi-scale information is extracted, and output features are formed; the output features are sent to a feature fusion module for feature integration, and the three branches are spliced in the channel dimension when the model is output; the spliced features are sent to three task decoders, obstacle instance segmentation, drivable region segmentation and depth prediction are carried out through different encoders, and loss between different tasks is balanced in a self-adaptive manner, so that image results are obtained to present different regions of an obstacle module and a drivable region boundary. The method is used for solving the problem of poor multi-sensor fusion perception.