84 results about "Visual computing" patented technology

The invention relates to the technical field of computer vision, computer aided design and artificial intelligence, and discloses a geometric feature recognition method based on a large language model, which comprises the steps of three-dimensional model natural linguistization, large language model feature reasoning, incremental learning and optimization, and feature verification and output. According to the geometric feature recognition method based on the large language model, three-dimensional geometric data are converted into structured text description, and a joint representation space of'geometric parameter-topological relation 'is constructed, so that the large language model can better understand the meaning of geometric features and the structure of parts; the method comprises the following steps: analyzing topological association among geometric features by utilizing long context understanding ability of a large language model, capturing dependency among the features through an attention mechanism, realizing hierarchical recognition of the features in a complex assembly, dynamically updating a geometric feature knowledge base of the large language model by continuously learning new geometric cases and engineering specifications, and realizing hierarchical recognition of the features in the complex assembly. Adaptive recognition of novel features is supported, and the model does not need to be retrained.

The present invention discloses a method for robot-assisted flame visual recognition and positioning, which relates to the field of computer vision and includes the following steps: using a calibrated camera to obtain a video image; obtaining a suspected flame dynamic target based on an improved background difference method based on a flame color model; calculating and extracting a series of static features of the target; inputting the fused model into a trained support vector machine (SVM); if it is determined to be a flame, then calculating the rough positioning of the suspected flame based on the monocular, binocular, or multi-camera vision that identified the flame, and guiding the robot to a specified position; the robot's pan / tilt platform is aligned with the suspected flame position, and dynamic and temperature features are extracted respectively. After the features are fused, they are input into another SVM; if the result of the second recognition is still a flame, fine positioning is performed. The present invention has high recognition accuracy and strong applicability, and can minimize the hazards of fire by providing early warning and precise spatial positioning of flame targets.

The invention discloses a concrete wall full-section deformation monitoring device and method, and relates to the technical field of engineering structure health monitoring, and the device comprises an integrated measurement unit, a passive stable characteristic target group and a processing unit. The integrated measuring unit is composed of an area array solid-state laser radar and a high-resolution binocular vision camera which are rigidly and fixedly connected, and is used for synchronously collecting three-dimensional point cloud and two-dimensional images of a wall and an environment. The target group is arranged on an independent stable object near the wall body; the processing unit identifies coordinates of the target group based on laser radar data, establishes a world coordinate system, calculates self pose drift of the measuring unit by periodically detecting position change of the target, and performs coordinate correction on a wall surface relative displacement field obtained by visual calculation by using the drift distance; and finally, outputting a full-section absolute deformation field under a world coordinate system. According to the invention, high-precision monitoring of full-field continuous deformation of the concrete wall is realized, and the reliability and comprehensiveness of structural health monitoring data are improved.

The proposed technique introduces embodiments of a computer-implemented method for interpreting image delineations as vector objects and topological extraction from segmentation by visual computational methods applied to sections (slices) of seismic volumes, in order to aid geological interpretation and sampling of parameters originating from the fracture network and its topology. Embodiments of a developed method integrates a software / application that allows the loading and generation of statistical data related to the fracture network while maintaining georeferencing and scale of the two-dimensional input data. In addition, a fracture segmentation method is shown that uses pyramid image smoothing (decomposition into hierarchical levels of resolution) in order to reduce the amount of details and aid the identification of main faults or fractures. The segmentation after this smoothing is based on adaptive thresholding segmentation.

A system within a vehicle for communicating with a person in the vicinity of the vehicle comprises a perception system connected to a control unit of the system and adapted to detect the presence of a person, a monitoring system adapted to monitor the position of the person's head and eyes, a holographic image generator comprising a visual computing engine adapted to compute a holographic image and encode the holographic image onto a spatial light modulator of an image generation unit, and a beam steering device, wherein the beam steering device is adapted to receive information regarding a position of the person's head and eyes from the monitoring system, and the display is adapted to project the holographic image onto the beam steering device, and the beam steering device is adaptedto redirect the projected holographic image to the person's eyes.

The invention discloses a quick classification method and system for human scars through visual calculation, and relates to the technical field of artificial intelligence, and the method comprises the following steps: S1, scar image collection and preprocessing: obtaining a human scar region image and shooting parameters, and carrying out the noise removal, illumination correction and scar region segmentation of an original image; s2, multi-modal scar feature extraction: based on the segmented scar region, extracting color features, texture features, morphological features and depth features; s3, feature fusion and dimension reduction; s4, constructing and training a lightweight scar classification model; s5, outputting a classification result and dynamically optimizing the model; according to the rapid classification method and system for the human body scars through visual calculation, through multi-modal feature fusion and improvement of a lightweight model, the classification accuracy is better than that of a traditional manual classification and single feature machine learning method, subjective differences of doctors are eliminated, and the classification objectivity is guaranteed.

The invention provides a rapid dust removal system and method for engineering machinery welding, and the system comprises a rack, an air suction cover which is movably arranged on the rack and is used for capturing welding smoke dust; the dust removal purifier is arranged on the rack along with the suction hood and is used for purifying welding fume; the visual detection device comprises a camera and a visual calculation unit in communication connection with the camera, and the camera is arranged on the air suction cover and used for recognizing the welding point position in real time; the visual calculation unit is used for calculating the relative position of the welding point position and the suction hood and outputting a control signal; the servo driving mechanism is used for driving the dust removal purifier and the air suction cover to move along the rack, the servo driving mechanism is in communication connection with the visual inspection device, and the air suction cover is driven to move to the position over the welding point position according to the control signal; the dust removal efficiency can be improved, the energy consumption can be reduced, and the welding gun can be accurately tracked to collect smoke dust.

The invention relates to the technical field of computer aided design and visual computing, and provides a visual communication design evaluation system and method based on data analysis. The method comprises the following steps: acquiring original design data, and extracting a spatial layout feature matrix, a color distribution feature vector and a semantic content feature set; calling a design specification knowledge base based on the design purpose information; performing simulated attention distribution analysis and design compliance analysis to generate corresponding features; constructing a transmission efficiency prediction model to generate a comprehensive transmission efficiency score and an initial design evaluation report; performing interference effect joint analysis to obtain a comprehensive interference effect quantitative evaluation result; and performing efficiency optimization correction on the initial design evaluation report based on the result, and outputting a final design evaluation report integrating spatial layout and visual attribute optimization suggestions. According to the method, the interference effect is accurately quantified through conjoint analysis of spatial layout and semantic attributes, and the accuracy and reliability of design conveying efficiency evaluation are improved.

Presented are apparatus, systems and methods for creating tuned color emissions, from lighting and displays, that can be electronically controlled to select a desirable spectrum of wavelengths safer for human vision, for optimal color reproduction, for energy / brightness efficiency, and more. Apparatus including light emitting chips, materials, package design, electronic control devices and circuits, lights, light-fixtures, display panels, visual computing devices and systems, are disclosed. An embodiment is described which is capable of operating in modes, where eye-safe colors are rendered with minimal harmful wavelengths, as well as at least one mode of operation favoring color rendering, and brightness configurations. An embodiment is operable to deliver a paper-like black-on-white viewing experience, in both night-time and day-time operating modes, with reduced high-energy blue-wavelength light spectra. In one embodiment, the light-emitter, controller, display and system are operable to switch between these modes of operation.

The invention provides a multi-modal data real-time analysis and feedback method and system, and the method comprises the steps: collecting a video frame and an audio frame, reading a count value of the same monotonic timer when the collection of the video frame and the audio frame is completed, and generating an audio and video sequence; calculating the behavior popularity of each region in each time slice based on the sequence, and generating a region set for multi-modal event analysis in combination with a preset threshold and a quantity upper limit; scheduling the corresponding video sub-blocks to a visual computing power unit for target positioning and action classification, and executing voice activity detection and keyword category judgment on the time-aligned audio clips at the same time; visual and audio results are fused, and a structured event sequence is generated according to time slice and region compression; and constructing a classroom teaching chain through the sequence, identifying a key event, and finally generating a teaching event description. According to the invention, under the condition of domestic chip combination, cost, time delay, multi-modal consistency and data security controllability are considered, and real-time perception and feedback of teaching behaviors are effectively supported.

The invention relates to the technical field of crossing of computer vision, computer graphics and digital fashion, and discloses a three-dimensional digital clothing stylization method, which comprises the following steps of: firstly, constructing a double-encoder color mapping network to realize color alignment of a clothing image and a style image; the problem that training data is difficult to obtain is solved through a self-supervision strategy; then extracting depth features of the multi-view garment image and the style image by using a pre-trained VGG network, and embedding the style features into a garment feature space by means of an edge enhancement nearest neighbor feature matching algorithm; secondly, introducing an attention-guided edge enhancement feature extraction network, extracting edge features, and performing alignment optimization; finally, a stylized three-dimensional digital clothing image which has high style fidelity and clear structure details and supports rendering at any viewing angle is generated, the problems of color distortion, fuzzy details, inconsistent styles and the like in the prior art are effectively solved, and the method is suitable for the fields of virtual fitting, digital fashion design and the like.

The application belongs to the field of artificial intelligence, computer vision and computer graphics, and discloses a gaze point prediction method and system for VR large space immersive tour, which comprises the following steps: acquiring an eye image transmitted by a near-eye camera; constructing a gaze point prediction network model; inputting the eye image into the gaze point prediction network model to output a predicted line-of-sight direction. The application provides a method for accurately predicting a gaze point in real time, and through the method of eliminating 80% irrelevant pixels in the input image and the method of outputting a prediction value by a multi-level neural network, the calculation complexity is reduced in multiple dimensions, thereby reducing the system delay and improving the rendering quality.

The invention relates to the technical field of dangerous building troubleshooting, in particular to a dangerous building troubleshooting method and system based on AI visual computing video image acquisition and analysis, and the system comprises a video acquisition module, a preprocessing module, a target detection module, a feature extraction module, a state analysis module, a data transmission module and a remote monitoring center module. According to the invention, the video image is analyzed and processed in real time through edge calculation, the time delay of data transmission and central server processing is reduced, and the troubleshooting efficiency of dangerous buildings is remarkably improved. The house target in the video image is detected by using the deep learning algorithm, information such as the position, the contour and the structure of the house is identified, and the accuracy of target detection is improved. And multi-feature extraction is carried out on the detected house target, and state analysis is carried out by integrating feature information, so that the accuracy and reliability of dangerous house troubleshooting are improved. The problem that an existing dangerous building checking system is low in efficiency is solved.

The invention relates to the technical field of visual computing, and particularly provides an overlapping activity area detection method, medium, equipment and product, and the method can comprise the steps: projecting a plane polygon area which is in a world calibration coordinate system and is parallel to the ground plane into images collected by each camera in a multi-camera stereoscopic vision system, obtaining each projection polygon area; obtaining each overlapping area of each projection polygon area and the image acquired by each camera; performing back projection mapping on each overlapping region to the world calibration coordinate system to obtain each mapping polygon region; and performing fusion calculation on each mapping polygon region to obtain an overlapping activity region which is used for providing a standing reference for the motion capture actor. According to some embodiments of the invention, efficient and accurate detection of the overlapping area of the multi-camera stereoscopic vision system can be realized.

Presented are apparatus, systems and methods for creating tuned color emissions, from lighting and displays, that can be electronically controlled to select a desirable spectrum of wavelengths safer for human vision, for optimal color reproduction, for energy / brightness efficiency, and more. Apparatus including light emitting chips, materials, package design, electronic control devices and circuits, lights, light-fixtures, display panels, visual computing devices and systems, are disclosed. An embodiment is described which is capable of operating in modes, where eye-safe colors are rendered with minimal harmful wavelengths, as well as at least one mode of operation favoring color rendering, and brightness configurations. An embodiment is operable to deliver a paper-like black-on-white viewing experience, in both night-time and day-time operating modes, with reduced high-energy blue-wavelength light spectra. In one embodiment, the light-emitter, controller, display and system are operable to switch between these modes of operation.

The invention discloses a dynamic scene image domain adaptation system and method based on four-dimensional Gaussian sputtering and a computer storage medium, and relates to the field of computer vision and computer graphics, and the method comprises the steps: obtaining dynamic images captured at different time points from a plurality of visual angles; generating a four-dimensional Gaussian model based on the dynamic image; decomposing the four-dimensional Gaussian model into a conditional three-dimensional Gaussian model and an edge one-dimensional time component; extracting a target domain embedding vector; based on the extracted target domain embedding vector and the embedding vector of the three-dimensional Gaussian model, performing affine transformation on each Gaussian point, and mapping the Gaussian representation to the distribution of the target domain; and the multi-view consistency is maintained by predicting the corresponding relationship between different training views. According to the dynamic scene image domain adaptation method based on four-dimensional Gaussian sputtering provided by the embodiment of the invention, the four-dimensional Gaussian is decomposed into the conditional three-dimensional Gaussian and the one-dimensional Gaussian based on time distribution by utilizing extension, so that the multi-view visual consistency can be ensured.

The invention discloses a soil cation exchange capacity detection method based on color developing solution image recognition, and relates to the technical field of soil physicochemical property detection. Comprising the following steps: acquiring a supernatant image after a soil sample of to-be-detected soil reacts with a methylene blue solution under a multi-light-source condition; zero-sample semantic segmentation is carried out on color blocks in the supernatant image to extract position information of different color developing areas in the color blocks, and color partitions are obtained; performing color correction on the color subareas to eliminate color deviation of the color subareas under different light source conditions to obtain RGB parameters of the methylene blue circular color development area; and inputting the RGB parameters into an extreme gradient lifting algorithm so as to fit a numerical relationship between the color concentration of the color developing area and the soil cation exchange capacity, thereby obtaining the soil cation exchange capacity of the soil to be detected. According to the method, a complex chemical detection process is converted into a visual calculation task, and an artificial chemical process depending on multiple ion exchange, washing and titration is simplified.

This invention discloses a method and system for synchronous monitoring of bridge structural displacement based on wireless intelligent vision, belonging to the field of bridge health monitoring technology. The method involves acquiring images of the bridge monitoring area and performing format standardization processing; synchronizing the clock and frame acquisition timing of multiple monitoring nodes, achieving microsecond-level synchronization through linear drift compensation, hardware-triggered synchronization, and frame buffering technology; calculating sub-pixel displacement data using either target-independent or improved marker tracking modes, the former based on frequency domain phase correlation analysis, and the latter using a constrained attitude decomposition algorithm to improve accuracy; performing localized visual calculations on the displacement data and outputting displacement time-series data; and wirelessly transmitting the data to achieve real-time visualization and data interaction with downstream systems. The system includes modules for image acquisition, node synchronization, displacement calculation, local calculation, wireless transmission, and data interaction. This invention achieves non-contact, high-precision displacement monitoring, improves multi-node synchronization and data real-time performance, and is adaptable to various inspection scenarios.

The application relates to a kind of complex fusion network training system and method based on blockchain, including target visual computing network and target feature chain;Target visual computing network is based on public data set and adaptive loss function, and pre-training is carried out for different task types to the target frame in the target monitoring video collected, and target feature information related to the current specific task is calculated;Target feature chain is used to store the target feature information after encryption.The application can process the identification of multiple tasks of pedestrians and vehicles in parallel, while introducing blockchain technology to effectively guarantee the security and non-tamperability of data, greatly improving the usability and practicality of the system, achieving the effect of enhancing system robustness, promoting multi-source data security fusion and improving complex scene perception ability.

The present application belongs to the field of augmented reality, computer vision, computer graphics, and relates to a kind of garment three-dimensional reconstruction method based on geometric prior and generated image auxiliary, comprising: obtaining image, inputting image into trained garment three-dimensional reconstruction model, and obtaining detailed three-dimensional garment grid;Garment three-dimensional reconstruction model includes: multi-modal prior information extraction module, garment generation network and geometry enhancement module;The present application extracts prior information that can reflect geometric structure from synthetic image, i.e.semantic segmentation map and surface normal map, which is jointly trained with real data set, and combined with real data set to construct garment statistical model, and according to garment statistical model, principal component coefficient is restored to garment grid, to make up for the problem of insufficient three-dimensional supervision signal, without relying on additional three-dimensional scanning grid data, improve the representation ability of model to complex garment shape, thereby improve the precision and generalization performance of three-dimensional garment reconstruction.

A method for realizing tapping or touch functionality with realistic touch sensation, applied in a system with XR augmented reality wearables and head-mounted displays. Preset points are marked on the joint lines of the palm. The user can see the functional areas bound to these preset points through the glasses. Two trigger points WL and WR are set. The system acquires N image video streams with parallax information. For the N images of the same time sequence, the position of the trigger fingertip P in each image is tracked and evaluated to determine whether it lies between the two trigger points WL and WR of any functional area. The x-coordinate values ​​of the three target points WL, P, and WR are acquired. The differences between WL and P, and between P and WR, are calculated, and their ratios are determined.Only when all ratios in the N images match is it determined that the trigger fingertip P has touched the functional area, and the corresponding content of the functional area is output or activated. This invention makes it possible to precisely determine whether a real touch has occurred through purely visual calculations. This involves touching the palm of the hand or an object surface, providing a realistic touch sensation when typing or using touch functions.

The invention discloses a ship-end sailing berthing and departing active safety intelligent prevention and control system, which comprises a ship visual perception module, navigation equipment, a video storage module, a visual computing server, a terminal host, a network switch, a serial port server and a wireless module, and is characterized in that the ship visual perception module comprises a berthing visual perception module and a sailing visual perception module; the acquisition module is used for acquiring berthing environment video data and navigation video data of a ship; the wireless module is used for transmitting the berthing environment video data and the navigation video data to the management platform in real time; the system can provide the functions of situation awareness, sailing collision prevention and bridge collision prevention early warning in the sailing process, provide ship side images, berthing and leaving data and early warning information for a driver in the ship berthing process, reduce the berthing blind area of the driver, provide berthing safety guarantee and reduce the collision risk of the ship in the berthing and leaving period to the maximum extent.

The invention belongs to the field of artificial intelligence, computer vision and computer graphics, and discloses a VR real-time rendering method and system for low-bit-rate cloud rendering plug flow, and the method comprises the steps: obtaining a rendering frame image; a lightweight super-resolution model is constructed; inputting the rendered frame image into the lightweight super-resolution model to obtain a reconstructed 4K-resolution image; and performing real-time rendering and display on the VR equipment based on the reconstructed 4K-resolution image. According to the invention, high bandwidth pressure caused by direct transmission of the 4K video is avoided, and the hardware limitation that low configuration equipment cannot carry out complex rendering tasks is overcome. Through the combination of a scene customization model and video coding, high-quality and low-delay visual experience under limited resources is realized, and the method is suitable for various application scenes with relatively high requirements on image quality and real-time performance, such as large-scale cloud simulation, VR tourism and intelligent power grid monitoring.

The present application relates to a dance posture and movement recognition and interaction method and system based on visual computing, comprising the following steps: upon receiving a recognition start command, obtaining a student's dance movement information and dance music rhythm information through a camera device; extracting the student's posture profile information at several preset moments from the dance movement information based on the dance music rhythm information; comparing the extracted posture profile information with pre-stored standard posture profile information and outputting the comparison results; based on the comparison results, screening out posture profile information with a degree of overlap with the standard posture profile information below a preset threshold, extracting the standard posture profile information corresponding to the posture profile information, generating a movement correction data packet; and sending the movement correction data packet to an interactive terminal. The present application has the effect of accurately determining whether a student's dance posture movement is standard and providing timely feedback to the student.

The invention belongs to the field of artificial intelligence, computer vision and computer graphics, and discloses a fixation point prediction method and system for VR large-space immersive sightseeing, and the method comprises the steps: obtaining an eye image transmitted by a near-eye camera; constructing a fixation point prediction network model; and inputting the eye image into the fixation point prediction network model, and outputting a predicted sight line direction. The invention provides a method for accurately predicting the fixation point in real time, and the calculation complexity is reduced in multiple dimensions by eliminating 80% of irrelevant pixels in the input image and outputting the predicted value in multiple levels by the neural network, so that the system delay is reduced, and the rendering quality is improved.

A method for detecting beef cattle body size parameters based on machine vision, which relates to the fields of image processing and breeding technology, and particularly relates to a method for detecting beef cattle body size parameters. Aiming at the measurement of beef cattle body size, this paper proposes a detection algorithm combining image processing and deep learning. This method first preprocesses the beef cattle images under a specific scale, and uses image feature calculation and deep learning methods, combined with visual computing technology to measure the following parameters of beef cattle: body height, body straight length, cannon circumference, chest width, chest depth, hip angle width, cross height, body diagonal length, hip width, etc. This method provides a convenient, simple and low-cost method for detecting beef cattle body size parameters, which is convenient for small and medium-sized farmers.

The invention provides a rescue vehicle, a rescue method and a storage medium. The rescue vehicle comprises a visual computing device, a vehicle control device and a vehicle replacement layer. The visual computing device is used for collecting depth image data of the vehicle in the advancing direction of the rescue vehicle; based on the depth image data, the distance between the rescue vehicles and the attitude parameters of the vehicles are determined; the vehicle control device is used for determining driving parameters of the rescue vehicle based on the vehicle distance and the attitude parameters when the vehicle comprises the vehicle in front of the blocking state; based on the driving parameters, the rescue vehicle is controlled to advance to the first position of the vehicle in front of the blocking state, and the vehicle in front of the blocking state is placed on a vehicle replacement layer and runs to the initial position of the vehicle in front of the blocking state; and the vehicle replacement layer is controlled to sequentially replace the vehicle in the blocking state between the rescue vehicle and the to-be-rescued vehicle to the position in the opposite direction of the advancing direction of the rescue vehicle, so that the to-be-rescued vehicle is rescued.

The invention belongs to the field of artificial intelligence, computer vision and computer graphics, and discloses a large space positioning method and system adaptive to an adversarial unsupervised domain, and the method comprises the steps: obtaining multi-modal data of an indoor large space environment, carrying out the normalization of the multi-modal data, and forming domain data, the multi-modal data comprises Wi-FI RSSI, Wi-Fi CSI, BLE, RFID, magnetometer data, accelerometer data and ultra-bandwidth signals, and the domain data is divided into source domain data and target domain data; constructing a positioning prediction network model; and inputting the source domain data and the target domain data into the trained positioning prediction network model to complete positioning prediction on the target domain. According to the method, high positioning precision can be kept in complex environments such as poor light conditions, changeable obstacles and dense crowds, and smoother, safer and more personalized immersive experience is provided.

The invention discloses a multi-page screen display data automatic traversal method and system based on visual computing, mainly solves the problems that manual information input in a screen display is easy to make mistakes and low in efficiency, and overcomes the defect that the existing optical character recognition technology is difficult to competent to screen display complex scenes. The method comprises the following steps: firstly, preprocessing collected multi-page screen display optical character image data, and improving the recognizability of optical characters in an image through a character information enhancement method; then, analyzing the highlighted character image set by using a combined scanning method, obtaining a specific region with optical character sub-images, constructing a character sub-image set, and further extracting sub-image information and obtaining a character set; finally, a text proofreading and correcting algorithm is used for proofreading and correcting the extracted character information, the recognition accuracy and the output result quality are improved, more complete and smooth character information can be output, multi-page screen display data can be processed in real time, and the method is suitable for real scenes where characters need to be extracted.

The invention provides an industrial part assembling device based on visual identification and a method thereof, and belongs to the technical field of industrial automation. According to the industrial part assembling device based on visual identification, a structure supporting base, a human-computer interaction interface module and a visual computing host are arranged in an automatic assembling station in a layered mode, and a rotary working assembly and an assembling mechanical arm are arranged on an assembling reference platform. The modularized assembling carrier is provided with an annular indexing positioning rotary disc, a servo steering actuator and a visual sensing module are integrated on the central bearing base, and the side edge error compensation mechanism is provided with a deviation rectifying mechanical arm. During working, part images are collected in real time through the visual sensing module, deviation data are generated through analysis of the visual computing host, the error compensation mechanism drives the deviation correction mechanical arm to conduct fine adjustment compensation, and the assembling mechanical arm completes final assembling. According to the device, visual guidance is matched with servo compensation to execute double-closed-loop control, the assembly precision can be remarkably improved, and the device is suitable for automatic assembly scenes of high-precision and various parts.