128 results about "Body identification" patented technology

The invention comprises a processor capable of receiving, storing and processing waveform signals generated in the body and generating waveform signals that substantially correspond to waveform signals that are generated in the body and are operative in the control of a body organ function. The invention also includes a computerized system having a sensor for capturing at least one waveform signal that is generated in a subject's body and is operative in the regulation of body organ function, a processor that is capable of receiving, storing and processing the captured waveform signals and generating a waveform signal that is recognized by the body as a modulation signal, and a transmitter for delivering the generated waveform signal to the body.

The present invention provides a method for generating a three-dimensional (3D) building model based on photographed house type image identification. The method is used for solving the problem conventional house-type-image-based 3D reconstruction methods are not suitable for photographing-version house type images. Aiming at characteristics of a photographing- version house type image, correction treatment is first carried out on the photographing- version house type image, thus to enable the quality of the corrected image to be similar to that of an electronic-version house type image, thereby bringing convenience for follow-up house type image identification; carrying out wall body identification according to the characteristics of the photographing-version house type image, and carrying out size correction and closing of wall bodies, and generating a cross-platform JSON file; and ultimately using wall body information of the JSON file by Unity3D to carry out 3D reconstruction. With adoption of the method provided by the present invention, identification of photographed house type images is realized, the 3D building model is generated, the problem that the photographed house type image is inclined can be effectively solved, a wall body calculating method based on wall body intersecting anchor points is provided, and thus the following generated 3D wall bodies can be conveniently freely pulled and stretched based on the anchor points.

An interrogator with an antenna that allows information exchanges with multiple transponders in a shorter distance of communication, by securing an intensified and uniform electromagnetic energy concentrated on areas near antenna elements. The interrogator is furnished with a sleeve antenna that includes a monopole conductor of ¼ wavelength (free space wavelength) continuously connected to a core wire of a coaxial cable on one end thereof, and a feed point on the other end, in which the sleeve antenna is grounded at the feed point. The interrogator has a plurality of the transponders arrayed near the antenna, and a plurality of the antennas selected by RF signal selectors. The interrogator antenna allows movable body identification such as in a goods management system for identifying multiply arrayed goods.

The invention discloses a focusing processing method and apparatus, a device and a storage medium. The method comprises the following steps: performing main body identification on a picture collectedby a camera module at present by using a preset neural network to determine a target main body contained in the currently collected picture and the position information of the target main body; determining a current corresponding target shooting mode of the camera module according to the type to which the target main body belongs; and controlling the camera module to perform focusing on the targetmain body according to the position information of the target main body, and shooting an image containing the target main body in the target shooting mode, wherein the preset neural network is trained by using all types of shooting main bodies as samples. By adoption of the method, the target main body in the collected picture is identified by using the neural network and automatic focusing is performed on the target main body according to the position of the target main body, thereby not only improving the quality of the shot pictures and effectively avoiding the phenomenon that the shot pictures are fuzzy, but also reducing manual operations, facilitating the use of users and improving the user experience.

The invention relates to a three-dimensional model retrieval method used for mixed contour line views. The method comprises the steps of extracting algorithm training based on an optimal viewpoint and obtaining a three-dimensional model preferable viewpoint set; rendering three-dimensional model mixed contour line views under the preferable viewpoint set, extracting Gabor edge response features for the mixed contour line views of the viewpoints and establishing a feature library; extracting the same edge response features for input natural images, retrieving similar models from the feature library by using the visual word bag method, and performing ordering according to the similarity degrees. Experimental results show that the method realizes three-dimensional model retrieval through the edge similarity of natural images and model feature line views, reduces the interference of degradation views and the texture of natural images on the three-dimensional model retrieval, accords with the mechanism of three-dimensional body identification of human vision, and achieves a good retrieval effect.

The invention discloses a method for assisting in identifying a wall body in CAD based on deep learning. The method comprises the following steps of acquiring and analyzing CAD file data correspondingto a house type image; acquiring a first wall body obtained by identifying the CAD file data; identifying the house type image corresponding to the CAD file data by utilizing a wall body identification model to obtain a second wall body; and carrying out cross verification on the first wall body by utilizing the second wall body to obtain a final wall body, wherein the wall body identification model is obtained by training based on a deep learning network. The invention further discloses a device for assisting in identifying the wall body in the CAD based on the deep learning. According to the method and the device, the accuracy of wall body identification can be improved.

The invention discloses a star-map matching autonomous navigation positioning system which comprises a star sensor, a tilt angle sensor, a data acquisition device and a terminal computer, wherein the star sensor is used for obtaining a star map; the tilt angle sensor is used for obtaining tilt angle information of the x axis and the y axis of a platform; the data acquisition device is used for acquiring data detected by the star sensor and the tilt angle sensor and sending the data to the terminal computer; a time sequence control circuit is used for controlling acquisition frequency and synchronization; the terminal computer is in charge of sending an instruction and making a final calculation, and comprises a star map image processing and barycentric coordinate extracting module, an image space coordinate conversion module, a star body identification module, an apparent position calculation module and an optimal calculation module.

The invention provides a method and a device for calculating a passenger vehicle passenger flow congestion degree. The method comprises steps that images respectively acquired by at least two cameras in a passenger vehicle are acquired, the acquired images are spliced to form a panorama image in the passenger vehicle, body identification and counting are carried out on the basis of the panorama image, and the counting result is used for carrying out passenger vehicle passenger flow analysis. The method is advantaged in that the images acquired by the multiple cameras are spliced according to an image coordinate transformation matrix, the panorama image in the vehicle is determined, body detection of the panorama image in the vehicle is carried out to determined the quantity of passengers in the vehicle, the passenger vehicle passenger flow congestion degree is analyzed according to the passenger quantity detected from the panorama image but not according to statistics on the basis of accumulation difference of passengers getting on and off of vehicle gates, an accumulation error is avoided, and statistics precision is improved.

The invention discloses an image body identification, correction and registration method comprising the following steps: target detection: performing threshold segmentation by observing the features of an image, and roughly distinguishing between the foreground and the background; binarization: getting a black-and-white binary image, removing noise points through expansion, and retaining a compartment part in the original image; image feature extraction: positioning the four corners of the compartment based on the mathematical properties of trapezoid; perspective transformation: stretching an irregular convex quadrilateral to a regular rectangle through a transformation matrix; and registration and splicing: combining multiple box body images, and for the images with common image features, registering and splicing multiple box body images on the side by use of an Opencv open-source library Stitcher class or augmenting the images based on the properties of the matrix. The image body identification, correction and registration method is beneficial to eliminating background interference, reducing the sample set of box body identification and improving the efficiency of identification.

The invention discloses a non-maximum suppression, dynamic threshold calculation and image edge detection method. The detection method comprises the following steps: eliminating Gaussian noise in an original image by Gaussian filtering; obtaining the gradient of each pixel point of the image obtained after Gaussian filtering; carrying out non-maximum suppression processing by utilizing the gradient amplitude and the gradient direction of each pixel point to obtain a candidate edge image, marking pixel points serving as candidate edge points in the candidate edge image, calculating a dynamic threshold value of a target body contour edge point in the image, and screening the candidate edge points by using the dynamic threshold value to obtain an edge image. According to the invention, the gradient direction is determined by comparing the gradient amplitudes in the horizontal direction and the vertical direction; Therefore, the calculation of the gradient direction angle is avoided, the calculation complexity of edge detection is simplified, the dynamic threshold calculation method can effectively distinguish the pseudo edge and the contour edge of the target body caused by the surface texture of the target body in the image, and more accurate edge information is provided for target body identification.

The invention which relates to the field of the geological modeling technology, provides a method for refined modeling and block recognition of a rock slope structure. The method comprises: (1), obtaining a triangular element grid and a structural plane geometric parameter of a slope free face by using a laser scanning technique; (2) transforming a triangular face unit into a body unit by a projection method; (3) realizing spatial distribution of a structural surface by using a three-dimensional network simulation technology; (4) with a plane where the structural plane is located, cutting an intersected body unit completely; and (5) carrying out blanking on a side surface of a cylindrical unit inside a rock mass, carrying out fusion with the cut body unit, and thus forming block body merging between structural surfaces, thereby realizing block body identification. Therefore, the field measurement data and the block identification are combined; the precision is high and the speed is fast; and the identified block form and number are not limited.

The invention discloses a result competition automatic reporting method and system and a computer readable storage medium. the method comprises: identifying a competition live video by utilizing a keyframe, a key event detection model and an event main body identification engine; obtaining the type, time and event main body corresponding to the key event in the event process; and automatically forming reports and competition collection. The live broadcast of each event does not need to be manually watched, edited or formed into news reports, so that on one hand, the coverage of the news reports is increased under the condition of saving the labor cost, the live broadcast video of the event can be directly processed, and the timeliness of the formed news reports and event collection is higher.

The invention provides a method for detecting a deep sand body of a low-resistance coverage area. The method comprises the following steps of in a uranium metallogenesis prospective area, arranging measuring lines according to an outstanding tectonic direction, wherein the number of drilling holes is higher than or equal with 1, at least one measuring line passes through one known drilling hole, and performing measuring point positioning by means of high-precision GPS and a forest compass; performing wide-frequency magnetotelluric method measurement by means of a continuous tensor observing device according to a platform type electrode arranging method; performing impedance calculation on the acquired data, obtaining visual resistivity and phase information, performing two-dimensional datainversion, drawing an inversion resistivity section view according to an inversion result; according to a known drilling hole exposure result, performing fine layering on the inversion resistivity section view, and extracting an electric characteristic of the sand-containing sand body; and according to the electric characteristic of the sand body, predicating the distribution range of the deep sand body by means of artificial intelligence technology such as neural network method. The method settles problems such as low depth measuring resolution and high sand body identification difficulty inthe low-resistance coverage area, and realizes an excellent effect in sand body prediction.

The invention relates to a video processing method and device, an electronic device and a storage medium, and relates to the technical field of multimedia. The method comprises steps of obtaining at least one to-be-detected image from a to-be-processed video, carrying out object identification on each to-be-detected image, determining at least one first object included in the to-be-detected image,wherein the object identification comprises at least one of face identification and body identification; for any first object in the at least one first object, adding a first object identifier of thefirst object to the to-be-detected image; and synthesizing the video images with the same object identifier into a target video. According to the technical scheme, the video images in the to-be-processed video can be automatically synthesized into the independent videos again according to different objects, and the video processing accuracy and efficiency are high.

The invention relates to an image processing method and device and electronic equipment and a computer readable storage medium. The method comprises the steps of obtaining a visible light graph; inputting the visible light image into a main body identification layer of a main body detection model to obtain a main body identification image, wherein the main body detection model is a model obtainedby training according to preset conditions of the same scene; inputting the visible light image into a depth prediction layer of the main body detection model to obtain a depth prediction image; fusing the main body identification map and the depth prediction map to obtain a main body region confidence map; and determining a target main body in the visible light image according to the main body region confidence map. The target main body in the image can be accurately identified.

The present invention provides an electric power business hall dressing normalization identification method based on color and Hu moment matching. The method comprises: extracting a dressing color analysis area, wherein the process comprises the capture of fact identification, human body upper body identification and rectangle dressing color analysis area; performing color matching analysis of the captured rectangle area, and performing matching analysis through extraction of the maximum color of the identification area and the maximum color of the clothes in the frock picture base; extracting the identified upper body clothes outline and calculating the Hu moment, and performing Hu moment matching of the Hu moment and the outline Hu moment of the clothes in the frock picture base; and finally weighing and synthesizing the color matching result and the Hu moment matching result to obtain a clothing analysis result. The electric power business hall dressing normalization identification method based on the color and Hu moment matching solves the phenomenon that it is easy to generate errors in the traditional clothing identification process caused by single identification factor, and realizes the intelligence of the electric power business hall dressing management so as to reduce the work of the manual supervision management and improve the validity and the normalization of the work of the power electric business hall.

The invention discloses a data dynamic anti-leakage and warning method and system. The method comprises the following steps of binding user authentication information and a user biological characteristic image; integrating user behavior data, integrating a user behavior identification result, an operation body identification result and a body behavior identification result, and converting the results into user behavior characteristic data; calculating a user behavior, on the basis of a machine learning technology, calculating a user behavior abnormal index by taking the user behavior characteristic data as input and taking a user behavior model as a reference; warning the user behavior, comparing the user behavior abnormal index with a set warning threshold value, and if the user behavior abnormal index is greater than the warning threshold value, generating warning information to a manager. Through application of the scheme provided by the invention, under the condition that a user has no sense, real-time audit is carried out on the terminal user behavior, a potential suspicious user behavior is identified and warned timely, and a control method over the whole data anti-leakage system is perfected.

The invention discloses a regional development evaluation method based on image identification. The method comprises steps that a satellite picture of a to-be-identified region is acquired; the satellite picture is divided into corresponding multiple block pictures according to color clustering; characteristic extraction of each block picture is carried out to acquire a corresponding characteristic vector, and a body corresponding to each block picture is acquired according to the corresponding characteristic vector of each block picture and an established body identification model; the blockpictures of the adjacent similar bodies are merged, and the satellite picture is divided into multiple types of regions; according to the latitude and longitude data of the map, the geographic location of each region type of the satellite picture is acquired, and the area size of each region type is calculated according to the area of each region type. The invention further discloses electronic equipment, a storage medium and a regional development evaluation device. The method is advantaged in that through identifying the satellite map of the region, the corresponding body and area change ofthe body are acquired, and thereby regional development status evaluation is realized.

The invention discloses a depth detection-based body identification control device, which comprises an ultrasonic sensing module, a depth image module and a data control module. The ultrasonic sensing module emits coded narrow-beam ultrasonic wave limited by a certain beam range, and receives reflected sound wave of an object through a receiving transducer; the depth image module comprises a depth reconstruction unit for receiving data transmitted by the ultrasonic receiving transducer and generating a depth image; and the data control module comprises a target identification unit, a target positioning unit, a data conversion unit and a data transmission unit and is used for identifying and positioning the target body part of the beam range or the whole body, converting the image into data capable of being identified, and transmitting the date capable of being identified to the corresponding equipment. The device can be applied in the field of multimedia teaching equipment and the field of game equipment.

The invention relates to a superimposed sand body identification method based on seismic forward modeling, and belongs to the technical field of oilfield reservoir prediction. The method comprises the following steps: first, acquiring the spectral range and main spectrum of earthquake in an exploration area and the petro-physical parameters of sand bodies in the exploration area according to the seismic data of the exploration area; then, establishing geological forward models of different superimposed sand body structures according to the petro-physical parameters of the sand bodies in the exploration area; performing seismic forward modeling for different geological forward models based on the acquired spectral range and main spectrum; and finally, comparing the seismic forward modeling results with actual seismic reflection, determining a forward modeling result which can completely separate the waveforms of the superimposed parts of the sand bodies, and identifying superimposed sand bodies according to the forward modeling result. According to the invention, by simulating the seismic reflection characteristics of different superimposed sand body structures through the seismic forward modeling technology and comparing the seismic reflection characteristics with those of an actual seismic reflection profile, superimposed sand bodies are identified, and the connectivity of sand bodies is worked out. A basis is provided for overall evaluation and deployment of exploration and development.

The invention provides an automatic adjusting method for an emission line angle of a puncture needle probe. The method comprises the following steps: primarily adjusting a scanning line emission angle of the probe; emitting and obtaining puncture echo data; carrying out needle body identification on the puncture echo data, and calculating an inclined angle of a needle body; calculating an optimal scanning line emission angle of the probe according to the inclined angle of the identified needle body; and adjusting the scanning line emission angle according to the calculated optimal scanning line emission angle condition. The invention further provides corresponding device and system. By the aid of the method, the scanning line emission angle can be automatically adjusted according to the position of a puncture needle.

The embodiment of the invention discloses a system and a method for video recording and processing. The method for video recording and processing comprises the steps of carrying out video recording for a scene where a target display device is by utilizing a camera device so as to obtain a recorded video, wherein the target display device is used for enabling a specific video frame to have a periodic display characteristic, and the recorded video comprises a picture of the specific video frame displayed on the screen of the target display device; and, by utilizing a screen body identification and content replacement device, identifying the picture of the specific video frame on the screen of the target display device based on a preset characteristic and a periodic display characteristic of the specific video frame and replacing the picture of the specific video frame of the recorded video displayed on the screen of the target display device into target content so as to obtain a target video signal serving as an output. Therefore, according to the embodiment, different content can be displayed at the screen region of the display device when live broadcast is carried out at different areas.

The invention discloses a compact sandstone reservoir refined description method and system; the method comprises the following steps: using known geology rules and drilling and logging data as constraints according to post-stack three dimensional earthquake data, and carrying out wave impedance inversion so as to obtain a wave impedance inversion data body; determining lithology division standards of the wave impedance inversion data body according to logging lithology and wave impedance inversion data body intersections; using the geologic body identification technology to automatically identify the geologic body according to deposition microfacies and the lithology division standards; using a high resolution sequence stratum division result as a hierarchy interface so as to analyze thegeologic body configurations according to the geologic body, thus obtaining reservoir configuration parameters; using the geologic body as constraints and combining the reservoir configuration parameters so as to carry out three dimensional geology modeling, thus finishing reservoir refined descriptions.

The present invention relates to a data communication based fish body identification method. The method comprises: 1 ) providing a data communication based fish body identification system specially used for a diver, wherein the identification system comprises a head top fixing platform, an image identification device and a waterborne processing device, the image identification device is located on the head top fixing platform and used for detecting whether a fish body exists in water, and the waterborne processing device is connected with the image identification device and used for receiving an identification result of the image identification device; and 2) performing identification by using the identification system. According to the method, the diver can be helped to identify the type of the fish body accurately and automatically catch the fish body, thereby improving working efficiency.

The invention discloses a security industry-oriented intelligent public opinion monitoring method and system, and the method comprises the steps: collecting news public opinion data for issuing a maindimension in the security industry, carrying out the data duplication removal, and obtaining news public opinion information; carrying out abstract extraction and sentiment classification on the newspublic opinion information, generating a chapter abstract and a chapter sentiment label, and carrying out main body identification on the news public opinion data to obtain corresponding main body information, a main body industry label and a main body area label; performing main event identification on the main body information according to the event tag system and an event classification algorithm to obtain a main body event tag and a corresponding emotion tag; and forming a triple according to the main body information, the main body event tags and the emotion tags, and summarizing the triple corresponding to all the main bodies to generate a chapter-level triple. The public opinion information can be extracted in multiple dimensions, the accuracy and efficiency of system classification are improved through the event label system and the fusion algorithm, and the effect of accurate and efficient public opinion monitoring is achieved.

The invention belongs to the technical fields of uranium prospecting and geophysical exploration, particularly to an interlayer oxidation zone sandstone type uranium deposit favorable target area space location method. The interlayer oxidation zone sandstone type uranium deposit favorable target area space location method comprises the following steps of in key working areas, determining favorable metallogenic sections through telluric electromagnetic sounding; for the favorable metallogenic sections, outlining a redox transitional zone range through high-accuracy ground magnetic survey scanning; outlining the front line of a redox zone; primarily determining a favorable metallogenic area, performing electromagnetic measurement and fine sand body identification to outline target sand bodies in a longitudinal direction; according to the outlined redox transitional zone range and the longitudinal distribution of the target sand bodies, outlining a favorable metallogenic target area. The interlayer oxidation zone sandstone type uranium deposit favorable target area space location method solves the technical problem that the prior art cannot achieve accurate space location of uranium deposit, and by combining with the redox transitional zone range and the longitudinal distribution of the target sand bodies, can achieve accurate space location of interlayer oxidation zone sandstone type uranium deposit, thereby being significant sandstone type uranium deposit prospecting.

A method, server and computer storage medium for logging in, the method includes: receiving a login request including user's identification; assigning a body identification corresponding to the user's identification according to the login request, and generating a success login message that includes the body identification; returning the success login message including the body identification. The method distributes a corresponding body identification after receiving a login request that includes user's identifications, then returns a success login message containing the body identification to the client. When a same user's identification logs in different terminal clients, corresponding body identifications are distributed to every client, thereby the same user's identification can log in different terminal clients simultaneously without forcing other user's identifications which have logged in other terminals to be logged out.

The invention provides a local map displaying method, comprising the steps of firstly displaying a body identification point of a current position at any position of a display screen, through the acquisition of coordinates of other positions and a local coordinate, computing the distances and orientations of the other positions relative to the local position, and mapping them to the display screen; therefore, communication between groups and display within the signal coverage are achieved, and the map judgment is achieved; meanwhile, through the displaying manner, provided is an orientation judgment method which is applicable to be used when the orientation judgment cannot completely rely on other devices; a device capable of achieving the displaying method has the displaying function and position acquiring function, can be existing devices such as mobile phones and interphones, and is provided with an orientation acquiring module for displaying a location map better, thus the orientation can be directly displayed on the location map, and the usability of the location map is improved.

The invention belongs to the technical field of artificial intelligence, and discloses a house type graph intelligent identification method, which comprises the steps of obtaining a two-dimensional house type graph to be identified; identifying the two-dimensional house type image based on a preset wall body identification model, and outputting the wall body information in the two-dimensional house type image; and generating a three-dimensional house type model graph corresponding to the two-dimensional house type graph based on the wall body information, and outputting the three-dimensional house type model graph. The invention also discloses a house type graph intelligent identification device, an apparatus and a computer readable storage medium. According to the invention, the accuracyof wall body identification in the house type graph is improved.