10 results about "Sobel edge detection" patented technology

The invention discloses an AI-based child story video generation method and system, and relates to the technical field of artificial intelligence and multimedia crossing, and the method comprises the steps: generating a script from an original text input by a user through constructing an AI model fusing an emotion modeling capability; constructing an image generation combination model, defining a joint loss function, calculating an edge intensity graph of the contour image by using a Sobel edge detection algorithm, calculating an optical flow field of frame change by using a block matching algorithm, and performing color image dynamic frame alignment; a fine tuning WaveNet model is used to generate audio; through constructing an image generation combination model, combining a StyleGAN3-T model and an LDM model, defining a joint loss function, and using a Sobel edge detection algorithm and a block matching algorithm to calculate an edge intensity graph and an optical flow field, dynamic frame alignment of a color image is realized, and inter-frame continuity of a generated video is improved.

The application discloses an AI-based children's story video generation method and system, relates to the field of artificial intelligence and multimedia cross technology, and comprises the following steps: constructing an AI model integrating emotion modeling capability to generate a script from original text input by a user; constructing an image generation combined model, defining a joint loss function, using a Sobel edge detection algorithm to calculate an edge intensity map of a contour image, using a block matching algorithm to calculate an optical flow field of frame changes, and performing dynamic frame alignment of a color image; using a fine-tuning WaveNet model to generate audio; constructing an image generation combined model, combining a StyleGAN3-T model and an LDM model, defining a joint loss function, using a Sobel edge detection algorithm and a block matching algorithm to calculate an edge intensity map and an optical flow field, realizing dynamic frame alignment of a color image, and improving interframe continuity of a generated video.

The application discloses a binocular stereo matching FPGA accelerator architecture, method and device, belongs to the binocular stereo vision field, and comprises a line buffer module, an initial cost calculation module, a Sobel edge detection module, a cost aggregation module, a right view cost matrix construction module, a uniqueness detection module, a left-right consistency detection module, a hole filling module and a sub-pixel interpolation module. The application solves the problems of low precision, poor efficiency and low resource utilization rate of binocular stereo matching, improves the precision, and guarantees the real-time performance and the efficiency of operation resources.

The invention discloses a skylight mounting plate welding quality detection method based on a convolutional neural network, and the method comprises the following steps: obtaining image data of a detected part through an industrial camera, and inputting the image data into a model based on the convolutional neural network; the convolutional neural network is combined with a Sobe l edge detection operator, local texture and edge features of the welding surface are extracted, and the similarity between the features is calculated based on cosine similarity and used for recognizing fine texture changes of the welding surface; and extracting the shape of the welding spot and the geometric structure characteristics of the rivet nut through a region proposal network for identifying the dimensional deviation. A template matching method based on small sample learning is adopted. The model firstly extracts key features in input data, maps the key features to a unified feature space, and then performs similarity comparison by means of a pre-constructed template library to realize rapid defect type identification.

This invention discloses a UAV-based shield tunnel inspection system and method, applied in the field of tunnel inspection technology. By manually specifying the three-dimensional coordinate axes of the shield tunnel profile and combining this with UAV automatic navigation and computational vision, the system automates UAV tunnel inspection. The invention utilizes an onboard microcomputer to reproduce the manually set coordinate system. Simultaneously, it uses the tunnel environment and the distance from the tunnel wall to calculate the coordinates of the UAV's position within the tunnel cross-section coordinate system. Furthermore, it uses the Sobel edge detection 3D method to identify the standard lining rings of the shield tunnel, thereby calculating the axial distance, establishing a 3D model of the tunnel, and determining the UAV's travel distance within the tunnel. Finally, it uses Gaussian filtering and computational vision algorithms such as the Sobel edge detection algorithm to analyze and identify tunnel damage in the image information. This invention has advantages such as low cost, high efficiency, and high automation, and can be widely applied to tunnel inspection.

The invention relates to an intelligent order making method and system based on natural language processing, and belongs to the technical field of artificial intelligence. The method comprises the following steps: acquiring a document data set and a document template set, and sequentially performing gray conversion, Sobel edge detection, binarization processing, VGH histogram calculation, non-text region elimination and noise reduction on image data to obtain text region data after noise reduction; performing character correction on the noise reduction data, segmenting characters through a standard character segmentation technology, extracting stroke direction density characteristics after normalization processing, and finally generating a character extraction document through an OCR technology; using a PyMuPDF library to convert the PDF type data into text data, calculating classified data through a text classification model in combination with a text document extracted by OCR, and retrieving a document template set to obtain a filling template; and converting the converted text data and the OCR text extraction document into plain texts, extracting key entities through an entity extraction model, and filling the key entities into a template to generate a form. And automatic filling of the receipts is realized.

The present application relates to the technical field of visual detection, and particularly relates to an online visual detection method and system for quality of iron-on picture finished products based on industrial vision, which comprises the following steps: obtaining an initial image matrix, triggering Gaussian filter denoising through brightness variance analysis to eliminate noise interference caused by light changes; adopting a Sobel edge detection algorithm to extract pattern gradient change characteristics, generating a preliminary pattern mask based on color difference distribution analysis; combining local entropy value analysis to identify edge blur risk areas, expanding the mask boundary to contain the blurred edges, and realizing the optimization of the pattern mask; superimposing the mask to separate the main body area and verify the proportion to obtain the complete pattern area; and adopting a watershed algorithm to refine the boundary details to determine the quality result. Through the double verification mechanism of color difference distribution analysis and local entropy value analysis, the present application can adapt to complex backgrounds such as dark cloth, complex texture and color gradient, effectively improving the accuracy of pattern main body area extraction and the edge recognition precision.

The application discloses a kind of multi-modal pipeline detection data acquisition systems based on FPGA architecture, ultrasonic detection module is used to generate 8 40kHz pulse excitation signal produces ultrasonic wave, and AD9226 analog-digital converter is controlled to collect echo data, and after being internally cached, original sampling data is output through high-speed interface;Image detection module is used to collect the image data output by high-definition image sensor, executes gray scale conversion, filtering, sobel edge detection and morphological operation preprocessing, and outputs the processed image data through fiber interface, and displays on HDMI display after being cached;Two kinds of modal data are accurately time-aligned and uniformly transmitted in the system interior.This application integrates ultrasonic detection and image detection processing, transmission functions in one system, realizes the synchronous acquisition and processing of multi-dimensional information of pipeline inner wall, significantly improves the integration and data consistency of detection system, and is suitable for high-precision, low-delay acquisition and transmission of multi-modal sensing data in industrial pipeline detection equipment.

The invention discloses a point cloud image identification-based ship berthing identification anti-collision early warning monitoring method and system. The method comprises the following steps of: carrying out initial segmentation on a preprocessed image by adopting a Sobel edge detection operator; edge pixel point extraction operation is carried out on the first fine segmentation processing image, and third edge pixel points are obtained by screening pixel points which do not accord with target object identification detection conditions; based on the third edge pixel points and the second edge pixel points, ship feature angular points and a ship frame are formed through intersection point fusion, and the ship feature angular points and the ship frame are connected to obtain a third ship image; obtaining a laser point cloud image of the current ship, and secondarily verifying whether the current target object is of the same ship type or not; determining the minimum safety early warning distance of the current target object according to the current ship type; according to the method, two detection means are complementary and parallel through a visual identification processing method and three-dimensional point cloud data identification, and the accuracy of ship identification is remarkably improved.

This invention relates to the field of target detection and localization, and particularly to an image enhancement-based target detection and localization method for mobile phone assembly scenarios. This method enhances the original image acquired by a visual sensor, specifically enhancing both the input image for target detection and the input image for target edge calculation. For target detection, overall brightness enhancement, histogram equalization, and Laplace sharpening are applied to enhance brightness and contrast. The enhanced image is then input into a deep learning network for target detection. For edge detection, the input RGB image is linearly enhanced using a single R-channel, the grayscale image is enhanced using the Sigmoid function, and finally, Sobel edge detection is performed, thereby achieving the target localization process.