253 results about "Material classification" patented technology

Systems and methods are provided for displaying data, such as 3D models, having spatial coordinates. In one aspect, a height map and color map are generated from the data. In another aspect, material classification is applied to surfaces within a 3D model. Based on the 3D model, the height map, the color map, and the material classification, haptic responses are generated on a haptic device. In another aspect, a 3D user interface (UI) data model comprising model definitions is derived from the 3D models. The 3D model is updated with video data. In another aspect, user controls are provided to navigate a point of view through the 3D model to determine which portions of the 3D model are displayed.

The present disclosure relates to systems and methods for classifying videos based on video content. For a given video file including a plurality of frames, a subset of frames is extracted for processing. Frames that are too dark, blurry, or otherwise poor classification candidates are discarded from the subset. Generally, material classification scores that describe type of material content likely included in each frame are calculated for the remaining frames in the subset. The material classification scores are used to generate material arrangement vectors that represent the spatial arrangement of material content in each frame. The material arrangement vectors are subsequently classified to generate a scene classification score vector for each frame. The scene classification results are averaged (or otherwise processed) across all frames in the subset to associate the video file with one or more predefined scene categories related to overall types of scene content of the video file.

The present disclosure relates to systems and methods for classifying videos based on video content. For a given video file including a plurality of frames, a subset of frames is extracted for processing. Frames that are too dark, blurry, or otherwise poor classification candidates are discarded from the subset. Generally, material classification scores that describe type of material content likely included in each frame are calculated for the remaining frames in the subset. The material classification scores are used to generate material arrangement vectors that represent the spatial arrangement of material content in each frame. The material arrangement vectors are subsequently classified to generate a scene classification score vector for each frame. The scene classification results are averaged (or otherwise processed) across all frames in the subset to associate the video file with one or more predefined scene categories related to overall types of scene content of the video file.

A system and method for controlling navigation of a vehicle carrying hazardous materials includes a control module carried on-board the vehicle storing an information matrix containing hazardous material classifications associated with the identity and location of restricted sites. Each site and material pair has associated with it a control zone around it from which the hazardous material is restricted. The control module includes a positioning device that produces a signal indicating the vehicle's current position, which is compared to the coordinates for the control zones. If the vehicle crosses into a control zone, the system generates a warning to the operator. Further penetration causes the system to order a shutdown of the vehicle engine to prevent further movement.

The present disclosure relates to systems and methods for classifying videos based on video content. For a given video file including a plurality of frames, a subset of frames is extracted for processing. Frames that are too dark, blurry, or otherwise poor classification candidates are discarded from the subset. Generally, material classification scores that describe type of material content likely included in each frame are calculated for the remaining frames in the subset. The material classification scores are used to generate material arrangement vectors that represent the spatial arrangement of material content in each frame. The material arrangement vectors are subsequently classified to generate a scene classification score vector for each frame. The scene classification results are averaged (or otherwise processed) across all frames in the subset to associate the video file with one or more predefined scene categories related to overall types of scene content of the video file.

The present invention relates to a system and methodology facilitating material class processing and quality controls in an industrial controller environment. One or more classes are provided that generically describe materials or components of a recipe. The classes are associated with the recipe and resolved or determined before or during runtime of automated processes producing the recipe. If a class designation is encountered during recipe execution, an operator can be queried for which material or materials from the detected class is desired for the recipe currently being produced. After a material is selected from the class, the recipe is then processed according to the selected material from the respective class. In another aspect, automatic selections can be made to resolve members of class-based recipes. In yet another aspect of the present invention, quality phase processes and procedures are associated with a recipe and can be automatically initiated during various phases or stages of recipe production. Such processes include quality tests, quality recording / documentation, corrective actions, maintenance procedures, serving embedded files or documentation, initiating training procedures, and / or providing other automated procedures.

A method and system for enhancing predictive accuracy of planet surface characteristics from orbit using an extended approach of Pan-Sharpening by using multiple high resolution bands to reconstruct high resolution hyperspectral image is disclosed. Sparsity based classification algorithm is applied to rock type classification. An Extended Yale B face database is used for performance evaluation; and utilizing deep Neural Networks for pixel classification. The present invention presents a system that can significantly enhance the predictive accuracy of surface characteristics from the orbit. The system utilizes complementary images collected from imagers onboard satellites. The present system and method generates high spatial high spectral resolution images; accurate detection of anomalous regions on Mars, Earth, or other planet surfaces; accurate rock / material classification using orbital data and the surface characterization performance will be comparable to in-situ results; and accurate chemical concentration estimation of rocks.

The invention relates to an object material classification method based on multimodal fusion deep learning and belongs to the technical field of computer vision, artificial intelligence and material classification. The object material classification method based on multimodal fusion deep learning is a multimodal fusion method of an extreme learning machine based on multi-scale local reception fields. The method achieves accurate classification of object materials through fusion of perceptual information (including visual images, tactile acceleration signals and tactile sound signals) of different modes of object materials. The method not only can perform high-representativeness feature extraction on complex materials by using multi-scale local reception fields but also can fuse information of all modes effectively to achieve information complementation between modes. The method can improve the robustness and accuracy of complex material classification, thereby having greater applicability and universality.

Imagery is used to identify architectural elements that have known architectural patterns. Feature sets associated with a surface and architectural elements in a building model image are compared with known architectural standards of materials to determine the surface building materials and architectural details of a textured building model. In addition, specific texture patterns can assist final material selections for a repair / replacement.

The present invention presents four fusion approaches, which can be directly applied to Worldview-3 (WV-3) images. Moreover, they can also be applied to other current or future satellite images that have similar characteristics of WV-3. The present invention also presents data processing methods, including image fusion method, anomaly detection method, material classification method, and concentration estimation method that utilize the high-resolution images generated by the mentioned fusion methods. There are four fusion approaches disclosed in the present invention, e.g. Parallel one-step fusion approach; Sequential fusion of various bands; Sequential-Parallel fusion; and Parallel-Sequential fusion.

The invention relates to a linguistic data classifying method, a linguistic data classifying device and a terminal. The linguistic data classifying method comprises the following steps: performing word classification on training linguistic data and to-be-classified linguistic data; extracting feature words of each category from the result after the training linguistic data is subjected to word classification; according to the feature words of each category and a training linguistic data training classifier, determining a probability threshold value in the classifier; classifying the to-be-classified linguistic data by utilizing the classifier after training is finished to obtain the classification result. According to the technical scheme of the invention, the accuracy of linguistic material classification is improved.

The invention relates to a product material code management method and system. Product data can be extracted automatically from a design drawing which satisfies product material classification rules,a product material is identified, product material information is compared with that stored in a database server, and a code is matched or a new code is generated for the product material via an automatic code generation system. A computer cloud platform information technology is used, the product material code is managed scientifically, efficiently and conveniently via a simple flow control method, the problem that that a product cannot be delivered timely due to the fact that enterprise product data and product materials cannot be provided timely is solved, and the working efficiency of an enterprise is improved.

The present invention relates to a system and methodology facilitating material class processing and quality controls in an industrial controller environment. One or more classes are provided that generically describe materials or components of a recipe. The classes are associated with the recipe and resolved or determined before or during runtime of automated processes producing the recipe. If a class designation is encountered during recipe execution, an operator can be queried for which material or materials from the detected class is desired for the recipe currently being produced. After a material is selected from the class, the recipe is then processed according to the selected material from the respective class. In another aspect, automatic selections can be made to resolve members of class-based recipes. In yet another aspect of the present invention, quality phase processes and procedures are associated with a recipe and can be automatically initiated during various phases or stages of recipe production. Such processes include quality tests, quality recording / documentation, corrective actions, maintenance procedures, serving embedded files or documentation, initiating training procedures, and / or providing other automated procedures.

The invention discloses an electric power field warehouse material management system, comprising a basic data module, a stock management module and a material taking management module. The basic data module comprises material information, material classification and system management. The stock management module comprises stock, material warehousing and checking, wherein the stock comprises stock gathering and itemizing stock; the checking comprises inventory profits and inventory losses. The material taking management module comprises warehouse-out recording, material taking application form filling, reservoir area navigation, application list details configuration, material taking navigation and warehouse-out completion. On the premise of meeting operation and use requirements, the electric power field warehouse material management system can rapidly and efficiently realize in-out stock management of electric power field warehouse materials, timely and accurately connect to a stock database system, greatly improve electric power field material running efficiency, possess better safe performance, and meet real use requirements.

The invention discloses a character string similarity calculation method and device as well as a material classification method and device. The similarity calculation method includes: calculating the initial similarity between the character string X and the character string di; obtaining the character string X and the character string di; The longest common prefix and the longest common suffix between di; determine the weight of the longest common prefix and the weight of the longest common suffix; and calculate the similarity between the string X and the string di. Through the above technical scheme, aiming at the characteristics of Chinese material names, the present invention provides a method for calculating the similarity of Chinese character strings oriented to material classification (that is, the dynamic weight method (DynamicWeight)), which can dynamically estimate the material name characters The weight of the prefix and suffix of the string makes the material names of the same category have a higher similarity, which improves the accuracy of automatic material classification.

The present invention discloses a shadow removal method and apparatus. The method includes the following steps that: an inputted image to be detected is pre-segmented through using a super pixel algorithm, and seed points are allocated for pre-segmented super pixels; the distance measure of each pixel point in the pre-segmented super pixels and the seed points of adjacent pre-segmented super pixels is obtained, the minimum value of the distance measure is adopted as the class label of the pixels, and the coordinate mean values of pixels in each class label are obtained, and the coordinate mean values are adopted as new seed points; the distance measure is iteratively calculated by using the weights of color distance and spatial distance until new seed points no longer change, and the new seed points are determined as final seed points and are adopted as super pixels; material classification is performed on the super pixels, and a shadow material is removed. According to the method, the complexity of background information is not considered, the material in the image is directly decomposed into the super pixels; and the super pixels are described based on the fusion of various features, the super pixels containing shadow are removed from pixel classes; and therefore, the accurate coordinate position of a target can be obtained.

The invention discloses an electric power material classification method based on a self-organizing characteristic mapping network. The method comprises the following steps of material data acquisition: selecting material data and constructing the selected material data into an electric power material index system; material data analysis: according to a nonlinear principal component analysis method, selecting an electric power material principal component analysis index in the electric power material index system; and material classification: using a self-organizing characteristic mapping network (SOFM) algorithm to carry out index subdivision on the selected electric power material principal component analysis index, according to a subdivision index, carrying out clustering, and establishing electric power material classification.

The invention provides a material classification screening method and device and belongs to the field of nut processing. According to the material classification screening method, a plurality of vibration screening parts are used for screening materials in sequence. The device for achieving the material classification screening method comprises a rack, a vibration screening device and a storage device, wherein the vibration screening device is arranged on the rack, and the storage device comprises a plurality of material storage chambers. The method and device overcome the defects that an existing screening method is not high in screening precision, efficiency is low through screening measures, the production cost is high, and environment protection is not facilitated.

The present invention solves the problems with the prior-art environmentally friendly design. That is, in order to achieve continual improvement, it is necessary to make a detailed evaluation based on the parts configuration. If a method of setting a basic unit for each individual part is used, a large number of process steps are required, and it is impossible to conduct accurate life cycle assessments (LCAs) frequently. The present invention provides an environmental impact assessment support and design support system incorporating a database in which information about the basic unit is associated with information about product classifications, parts classifications, and materials classifications. The system manages the information about the parts configuration and the basic unit while associating their histories of creation with each other.

The invention discloses a material identification method and device based on laser speckle and modal fusion, and the method comprises the following steps: carrying out the data collection of a measured object through a structured light camera of a projection laser speckle structure, and obtaining a color modal image, a depth modal image and an infrared modal image; preprocessing the color modal image, the depth modal image and the infrared modal image; inputting the preprocessed color modal image, depth modal image and infrared modal image into a preset depth neural network; training an acquired data set, learning material-level features from corresponding speckle structures and color and depth modal coupling relationships, and generating an object material classification model for material classification, so as to generate a material prediction result through the object material classification model in a test stage. According to the method, material identification can be realized by utilizing interaction of laser speckles and materials and modal fusion of the laser speckles and visible light vision, and the method is simple and easy to realize.

The invention provides a building decoration material selecting and matching device and method, belongs to the technical field of computer information and particularly relates to the technical field of building decoration computer information based on computers and relevant to an information network. A decoration style positioning system, a function positioning system, a decoration material classification information database (material category selection), a customer (user) service system, a theme style matching index information database, a function classification information database and a material attribute selection information system are input and contained, are stored in a computer storage device and can be displayed on a display device. The building decoration material selecting and matching device is characterized in that the style positioning system, the function positioning system, the decoration material classification information database (material category selection), the customer (user) service system, a customer relationship management system (digital home system), the style theme style matching index information database, the function classification information database and the material attribute selection information system are relevant to each other.

The invention discloses an optimal material classification and recognition method based on hyperspectral data information maximization. The optimal material classification and recognition method comprises the following steps: (1) selecting training data from acquired hyperspectral data; (2) successively carrying out zero-mean, energy-keeping dimensionality reduction and unit normalizing pretreatment on the training data; (3) estimating a dimension matrix of line dimensionality reduction according to pretreatment data; (4) carrying out information maximizing row dimensionality reduction characteristic matrix calculation according to line-by-line dimensionality reduction dimension arrays; (5) carrying out classifier training according to a row-by-row dimensionality reduction characteristic matrix; (6) selecting an optimal characteristic matrix and an optimal classifier according to a training result; and (7) carrying out material classification and recognition on to-be-classified hyperspectral data according to the optimal characteristic matrix and the optimal classifier. The method provided by the invention has the advantages that the reduction of the hyperspectral data can be performed from a high-order statistics angle, and thus the high classification efficiency is achieved; a new classifier is easy to expand and add, so that the classifier with the excellent property is convenient to generate, and the material classification and recognition are well performed.

The invention provides a material classification device comprising a fan, a granulometric-class declining chamber, an airflow effuser and a feeding port. The airflow effuser is connected with the fan. The straight line of the airflow effuser intersects with the straight line of the feeding port; and the straight line of an airflow effuser opening is horizontal. A plurality of hoppers are arranged at the bottom of the granulometric class declining chamber. The diameter of the airflow effuser opening is 8-30 times of the average diameter of material granules. By the aid of high-speed airflow can be adjusted by the aid of the airflow effuser, according to the specific surface area difference of materials dropping from the feeding port, granules with different diameters are given with different horizontal moving speeds, so that different horizontal distances are obtained, and the granules optionally drop with gravity into the corresponding hoppers at the bottom of the granulometric-class declining chamber to realize the purpose of classification. Besides, the materials do not contact with any screening device bodies, relative friction force is avoided, and loss of devices is low.

A method and apparatus are provided for identifying a material with a sample-specific reference spectral list or library. A sequential approach to SEM-EDS automated mineralogy classification is carried out by performing two or more material classification analyses. A pre-classification step restricts the processing of spectra deconvolution algorithms to a subset of spectra that pass a dominant mineral criteria resulting in a significantly reduced subset of reference spectra that occur within the measured sample in pure enough form at a given minimum quantity. The following complex classification stages involving deconvolution of multiple constituents within measured spectra is based on this sample relevant subset.

The invention provides an automatic material classification warehouse-in and warehouse-out system which comprises a conveying device, a lifting device, a goods shelf, material trays and a control unit. The control unit is connected with the conveying device and the lifting device through signals, the goods shelf is of a multilayer structure, and each layer of the goods shelf is provided with a conveying chain for conveying and arranging the material trays. Materials are classified and then placed into the corresponding material trays, identification codes are set on the material trays, and thecontrol unit distinguishes material types through the identification codes and controls the conveying device to convey the material trays to a lifting station corresponding to the goods shelf. When the lifting device receives lifting signals transmitted by the control unit, the material trays are lifted and placed onto the conveying chains of corresponding containers, the control unit controls rotation of the conveying chains, and the material trays are conveyed to corresponding positions of the good shelf. Manpower cost can be reduced, and automation and intelligence of material management are improved.

Belonging to the technical field of silicon recycle and purification, the invention discloses a method for extraction of high-purity silicon from waste liquid. The method comprises the steps of: precursor material preparation; material classification and flotation; high temperature smelting and separation of an ingot. According to the preparation method for recycled silicon, a high-purity silicon ingot can be acquired by few processing steps. The preparation process does not involve toxic and harmful substances, and acid-base, so that treatment of the ''three wastes'' can be simple. The whole process is continuous, easy to control, and is easy to realize large scale and automation.

The present disclosure relates to systems and methods for classifying videos based on video content. For a given video file including a plurality of frames, a subset of frames is extracted for processing. Frames that are too dark, blurry, or otherwise poor classification candidates are discarded from the subset. Generally, material classification scores that describe type of material content likely included in each frame are calculated for the remaining frames in the subset. The material classification scores are used to generate material arrangement vectors that represent the spatial arrangement of material content in each frame. The material arrangement vectors are subsequently classified to generate a scene classification score vector for each frame. The scene classification results are averaged (or otherwise processed) across all frames in the subset to associate the video file with one or more predefined scene categories related to overall types of scene content of the video file.