741 results about "Location detection" patented technology

The invention discloses a power distribution network line fault positioning detection system, and relates to the technical field of power distribution network fault detection. The system comprises a mixed information acquisition layer, a fault feature extraction layer, an intelligent diagnosis layer and a fault positioning layer. The mixed signal acquisition layer comprises a high-frequency transient wave recording unit, a power frequency measurement unit, a wireless pulse sensor and a distributed optical fiber temperature measurement unit; the fault feature extraction layer comprises a time-frequency analysis module, a preprocessing module and a three-dimensional feature vector module; the intelligent diagnosis layer comprises a convolutional attention network, a space-time diagram neural network and a transfer learning module; the fault positioning layer comprises a particle swarm module and a fuzzy reasoning module. According to the invention, data information of the cable is acquired through the mixed information acquisition layer, a video analysis window function is dynamically matched with signal characteristics, a time domain graph scale, a frequency domain resonance component and a space field intensity gradient are constructed, fault diagnosis and positioning are carried out by using the intelligent diagnosis layer, and the fault positioning detection efficiency of the power distribution network is improved.

Methods and apparatus for determining a position of an intracardiac blood pump in a patient are described. The method includes receiving from at least one capacitive sensor associated with a cannula of the intracardiac blood pump, at least one capacitive signal, determining a position of the intracardiac blood pump in the patient based, at least in part, on the at least one capacitive signal, and providing an indication of the position of the intracardiac blood pump on a user interface of the circulatory support device.

The invention relates to a ship berthing position detection method and system based on shore end laser radars, and the method comprises the steps: deploying a plurality of laser radars at a shore end, and collecting original point clouds in parallel through an asynchronous thread model; constructing a rigid transformation matrix based on the radar installation attitude parameters, and further generating fusion point cloud data under a unified world coordinate system; then extracting 3D geometric edge points in a preset range of the front edge of the wharf as near-shore point cloud data, and further calculating the minimum ship-shore distance; based on the ship bow direction and a preset segmentation threshold value, the coastal point cloud data are segmented into ship bow area point cloud and ship stern area point cloud in the x-axis direction, the coordinate mean value of the ship bow area point cloud and the ship stern area point cloud is calculated and compared with an expected position in a wharf operation system, and berthing accuracy is judged; and the drift distance is calculated in real time, the drift distance, the attitude angle and the change rate of the attitude angle are compared with corresponding preset threshold values respectively for graded early warning and drift alarm, and high-precision ship berthing position dynamic detection is achieved.

The invention belongs to the field of robot and computer vision, and particularly relates to a visual SLAM (Simultaneous Localization and Mapping) back-end optimization technology based on a data self-adaptive iterative reweighted robust kernel. Comprising the following steps: S1, a front-end data reading and processing module: a robot carries a camera to collect an image, performs feature extraction and feature matching on the image, and generates an initial camera pose and map points; s2, a rear-end optimization module: according to the initial camera pose and map point generated at the front end, calculating a median absolute deviation in an adaptive strategy, calculating a robustness parameter, then substituting the median absolute deviation and the robustness parameter into a target function, simplifying the target function by using an iterative reweighting strategy, and finally solving the optimal camera pose and map point by using an L-M algorithm; s3, the loopback detection module detects loopback according to whether the robot reaches a previous position or not, and transmits information to a rear end for processing; and S4, constructing a map module: constructing an environment map according to the optimized camera pose and map points.

The invention discloses an engineering drawing label automatic identification method and system based on template matching. According to the method, an existing drawing is utilized to make a drawing label template library, and a drawing label position detection model, a drawing label classification model and a drawing label text recognition model are trained respectively; for the target drawing, using the drawing label position detection model to position the coordinate position of the drawing label, and cutting to obtain a to-be-identified drawing label; determining a picture label template style to which a to-be-recognized picture label belongs by using the picture label classification model, and acquiring text content and position coordinates of a textbox in the to-be-recognized picture label by using the picture label text recognition model; and acquiring an attribute value of the corresponding textbox in the to-be-identified signature by utilizing the position information and the structural relationship between the template signature attribute and the attribute value textbox and the drop point position of the central point of the attribute value textbox in the to-be-identified signature, and realizing the correspondence between the attribute and the attribute value. According to the invention, accurate identification of the drawing label is realized in a more intelligent and efficient manner, and manpower and time costs are reduced while the precision is ensured.

Systems and methods for tracking inventory items in an area of real space are disclosed. The method includes receiving a signal generated in dependence on sensors. The signal indicates a change to a portion of an image of an area of real space. The method includes, in response to receiving the signal, implementing a trained location detection model to determine, based on inputs, whether an inventory item identified in the portion of the image has changed a position in the area of real space. The method includes implementing a trained item classification model to determine a classification of the inventory item. The method includes updating an inventory database with inventory item data determined in dependence on the classification of the inventory item to provide an updated map of the area of real space as a result of the received signal indicating the change to the portion of the image.

The invention provides a multi-source information fusion unmanned aerial vehicle marine target tracking method and system, and relates to the technical field of data processing, and the method comprises the steps: obtaining image data, and extracting the features of a target region; unmanned aerial vehicle attitude data, radar position detection data and AIS identification data are obtained, attitude disturbance correction is executed, and time axis alignment is performed on the data; calculating the visual feature matching offset of the adjacent frames, and comparing the visual feature matching offset with the radar azimuth change trend; constructing a candidate target spatial position set, and executing distance convergence screening and spatial overlapping constraint processing of a geometric projection range on the candidate target spatial position set; motion direction continuity comparison is executed, and target position data is generated; generating a track control instruction for controlling the flight direction and speed of the unmanned aerial vehicle according to the target position data, and adjusting the subsequent flight path of the unmanned aerial vehicle according to the track control instruction; according to the invention, autonomy and accuracy of unmanned aerial vehicle marine target tracking are improved.

The invention provides a target position detection method, system and device and a storage medium, and the method comprises the steps: obtaining a conversion relation between a camera coordinate system of a monocular camera and a calibration plate coordinate system, the calibration plate coordinate system being a three-dimensional coordinate system established based on a calibration plate placed on a specified plane; acquiring a detection image shot by the monocular camera; performing depth estimation and target identification on the detection image, and obtaining a three-dimensional coordinate of a target in a camera coordinate system; converting the three-dimensional coordinate of the target in the camera coordinate system into the three-dimensional coordinate of the target in the calibration plate coordinate system based on the conversion relation between the camera coordinate system and the calibration plate coordinate system; and performing target position detection according to the three-dimensional coordinates of the target in the calibration plate coordinate system. According to the method and the device, the target three-dimensional coordinates in the camera coordinate system are converted into the calibration plate coordinate system, so that the visual angle can be converted into the visual angle perpendicular to the specified plane, errors caused by the visual angle are reduced, and the target position detection accuracy is improved.

This description describes a system for identifying individuals within a digital file. The system accesses a digital file describing the movement of unidentified individuals and detects a face for an unidentified individual at a plurality of locations in the video. The system divides the digital file into a set of segments and detects a face of an unidentified individual by applying a detection algorithm to each segment. For each detected face, the system applies a recognition algorithm to extract feature vectors representative of the identity of the detected faces which are stored in computer memory. The system applies a recognition algorithm to query the extracted feature vectors for target individuals by matching unidentified individuals to target individuals, determining a confidence level describing the likelihood that the match is correct, and generating a report to be presented to a user of the system.

The present invention relates to the field of new generation information technology, and discloses a method and system for improving the content recognition capability of physical real estate certificates. The method comprises S1: marking the position of real estate images to obtain a position data set; S2: constructing a training set, a verification set and a test set; S3: constructing a table position detection model, and sequentially building a position feature extraction network, a position feature fusion network, a position detection network and a non-maximum suppression network; S4: training, verifying and evaluating the detection capability of the detection model; S5: using the detection model to perform table position detection and text content recognition to obtain table position and text; S6: performing variable matching according to the position, content and the form template of real estate certification materials in various regions to obtain the recognition result of the real estate content. The system comprises a real estate image input module, a model training module, a text recognition module, a variable matching module and a real estate form content output module. The present invention can realize automatic and accurate recognition of the content of real estate certification materials.

The invention relates to the technical field of single-phase disconnection detection of an ungrounded system, in particular to a single-phase disconnection fault detection method and system based on wavelet transform. A plurality of detection points are arranged on a distribution line of the power distribution network; line voltage amplitude signals of all the detection points are collected, and a data set is formed; performing wavelet transform processing on the data set to obtain a detail coefficient corresponding to each detection point; comparing the absolute value of the detail coefficient with a preset threshold value to judge a broken line fault; and determining the position of the fault section according to the detail coefficients exceeding the preset threshold. The detection points comprise a main line detection point, a branch line detection point and an end point detection point, and the detection point spacing distance is set according to the line importance degree and load distribution; and performing signal processing by adopting Haar wavelet transform to obtain a threshold value based on a detail coefficient in a normal operation state. Through a method of combining wavelet transform and adaptive threshold determination, quick and accurate detection of a broken line fault is realized without traversing a network topology structure, and the calculation complexity is greatly reduced.

An end effector of a surgical instrument may be equipped with a limited (e.g., minimal) number of electrical pads that provides useful tissue presence and positioning information using a limited number of signals communicated between the electrical pads and a controller located remotely from the end effector.

The invention relates to a Raspberry Pi-based fault arc positioning detection and electrical fire early warning method, and belongs to the field of fault arc fire. According to the method, Raspberry Pi is used as a core processing unit, multiple types of sensors are integrated, and multiple kinds of alternating current and direct current load data are collected to establish a typical multi-dimensional data waveform library; deep processing is carried out on multi-time-frequency features and wavelet transform features of the signals in combination with a residual neural network, multi-dimensional features of a fault arc are comprehensively captured, and alternating-current and direct-current universal fault arc detection is achieved; multi-dimensional data are analyzed, and the arc danger level is evaluated through the time difference of fault arcs detected by different sensors, so that graded alarm is realized. Meanwhile, the Bayesian network is used for reasoning and judgment, and accurate positioning of the fault arc is achieved. Through cooperative work with the cloud host, a remote monitoring and management platform is established. The invention provides an electrical fire early warning solution which is intelligent, real-time and high in reliability.

The invention discloses a power cable fault type automatic identification and positioning detection method and system, and relates to the technical field of fault detection, and the method comprises the steps: collecting an electrical parameter signal of a power cable and electromagnetic field distribution data outside a line, constructing a double-domain feature space of a cable operation state, and executing the spatial-temporal feature decomposition, forming an electrical characteristic sequence and an electromagnetic field characteristic spectrum, and respectively inputting the electrical characteristic sequence and the electromagnetic field characteristic spectrum into a fault type identification module and a fault position prediction module; the fault type identification result generated by the fault type identification module and the fault position candidate area determined by the fault position prediction module are integrated through a feature cascade network, a fusion decision result is generated, and the fault type and the fault position are determined. According to the invention, the technical problem that the traditional single-domain information detection is limited in identification capability and unstable in positioning precision in a multi-type fault scene is solved, and accurate identification and high-precision positioning of fault types are realized through parallel processing and fusion decision making of electrical parameters and electromagnetic field information.

The invention discloses a learning behavior monitoring method, an intelligent table lamp and a storage medium, and relates to the technical field of intelligent equipment, the method is applied to the intelligent table lamp, and the intelligent table lamp comprises a camera module and a position detection module; the method comprises the following steps: acquiring a scene video through a camera module, and identifying at least one target object in the scene video; under the condition that the main guardian information corresponding to the target object is obtained, position information corresponding to the target object is obtained through a position detection module; identifying behavior information corresponding to the target object according to the position information and the scene video; and under the condition that the behavior information accords with the preset abnormal information, preset prompt information is output through a prompt module, and the prompt information is sent to the main guardian according to the main guardian information. According to the invention, bad learning habits or abnormal behaviors of students can be detected in real time and prompted, and one or more student objects can be identified and monitored.

A method comprises registering, by an application executing at a computer system in an inventory system, a tag identifier received from a tag in an inventory environment with location data indicating a location of the tag based on an audio attribute of an audio signal received from the tag, initiating, by the application, a scan of the tag to obtain tag data from the tag and to receive the audio signals from the tag by transmitting a signal to the tag after registering the tag identifier with the location data of the tag, and triggering, by the application, activation of an audio emitting device of the tag to emit an alert signal indicating whether a reader device is in a read range of the tag.

The invention belongs to the field of train structure health monitoring, and discloses a bogie tube plate structure welding seam detection method and device, and the method comprises the steps: obtaining a Lamb wave signal of a to-be-detected tube plate structure welding seam region, and carrying out the preprocessing, and obtaining a preprocessed Lamb wave signal; on the basis of the preprocessed Lamb wave signal, the position of the weld crack defect of the to-be-detected tube plate structure is predicted through the RAPID tomography technology, and a weld crack defect positioning detection result is obtained; inputting the preprocessed Lamb wave signal sequence into a bogie tube plate structure welding seam detection model to obtain a welding seam crack defect quantitative detection result; outputting a welding seam crack defect positioning detection result and a quantitative detection result as welding seam detection results; according to the invention, the positioning and quantitative detection result of the welding seam damage of the bogie tube plate structure can be quickly and accurately obtained, the high-precision detection requirement of the welding seam of the bogie tube plate structure is met, and the safe operation of a rail transit vehicle is ensured.

The invention relates to the field of smart home, and particularly provides an air purification device, method and equipment, a storage medium and a product. The device comprises a position detection module, an animal attraction module and an air purification module; the position detection module is used for detecting the real-time position of the target animal; the animal attraction module is used for sending attraction information interested by a target animal, and the attraction information comprises at least one of sound information, light information and smell information; and the air purification module is used for purifying surrounding air according to the real-time position and the attraction information. By means of the device, the effect of improving the efficiency of the air purification process can be achieved.

The invention discloses a PCB welding spot defect positioning detection method and system based on deep learning, and the method comprises the steps: S1, collecting visible light data and thermal imaging data of a PCB, carrying out the preprocessing, and obtaining the preprocessed visible light data and thermal infrared data of the PCB; s2, according to the pre-processed visible light data and thermal infrared data of the PCB, feature extraction and feature alignment are carried out respectively, and a textural feature map and a temperature feature map after alignment are obtained; s3, carrying out feature calibration, and generating a fusion feature map; s4, calculating a positioning feature map and an optimized enhanced feature map, and finally outputting a welding spot defect detection frame set; s5, calculating a sub-pixel feature map, and outputting a defect distribution probability map; and S6, converting the defect distribution probability graph into a binary defect mask, and outputting a final defect detection result in combination with morphological closed operation. The method can solve the problem that a traditional PCB welding spot defect positioning method is insufficient in small defect recognition accuracy.

A cleaning apparatus includes: a robot cleaner including a motion driver, and a dust bin to store dirt; a station including a dirt container, a seating portion on which the robot cleaner is seated and including an inlet through which the dirt is introduced from the dust bin; and at least one processor to control operations of the robot cleaner and the station. The robot cleaner further includes a location detection sensor configured to obtain information about a location of the robot cleaner, the station further includes a pressure sensor configured to obtain information about a pressure inside the dirt collection duct, and the at least one processor is configured to control the motion driver to adjust the location of the robot cleaner to allow an opening of the dust bin to correspond to the inlet based on the information obtained by the location detection sensor and the pressure sensor.

A transmitter at a first location transmits the message at a symbol rate of the reference clock using a first carrier, whose phase is locked to a phase of the reference clock and whose frequency is a first integer times a frequency of the reference clock. It also transmits the message at the symbol rate of the reference clock using a second carrier, whose phase is locked to the phase of the reference clock and whose frequency is a second integer times the frequency of the reference clock. The second integer is unequal to the first integer. A receiver at a second location receives the message at the first carrier and at the second carrier, and accurately determines a time of a first phase difference between the first carrier and the second carrier. It determines a time of receiving the message from the time of the first phase difference.

Existing localization techniques for passive ambient backscatter devices may not be sufficient to perform accurate location detection, tracking, or providing location updates of the backscatter devices. To address this, devices and methods, and processes that facilitate improved localization of the backscatter devices are described herein. A network device in a network transmits a tone sequence to excite a backscatter device. At least one peer network device of a set of peer network devices communicatively coupled to the network device determines one or more phase difference values between the transmitted tone sequence received by the at least one peer network device and a reflected tone sequence received at the at least one peer network device from the excited backscatter device. The network device receives the one or more phase difference values and determines a location of the backscatter device.

The invention discloses a steel rail corrugation detection method and device based on computer vision, and relates to the technical field of rail transit, and the method comprises the steps: 1, periodically and automatically collecting a high-resolution steel rail surface image, and carrying out the preprocessing; 2, carrying out steel rail region detection on the preprocessed steel rail surface image, and extracting a steel rail sub-image; step 3, carrying out corrugation position detection on the steel rail sub-graph to obtain a corrugation area coordinate; and 4, mapping the coordinates of the corrugation area to a coordinate system of the steel rail surface image to obtain full-image corrugation positioning. According to the method, advanced image processing and deep learning algorithms are adopted, the steel rail corrugation characteristics can be effectively extracted from a complex background, high-precision disease recognition and positioning are achieved, compared with a traditional method, the method has higher detection sensitivity and lower false alarm rate, and the precision ratio and recall ratio of steel rail corrugation detection can be remarkably increased.

The present application relates to an Artificial Intelligence (AI) hand type device that emulates human hand capabilities, delicately to autonomously identify and pick up small and fragile objects, including but not limited to nails, screws, and microchips, with precision. Equipped with advanced sensors, algorithms, and AI, the device accurately locates object positions and angles using computer vision technology and a high-resolution camera. It performs quality inspection analysis, object placement, movement and mechanical operations autonomously, based on AI decisions according to the real time perspective of its surrounding environment.The device's AI-driven robotic arms adapt their grip strength, pressure and temperature for handling tiny delicate items such as eye-glass screws and larger objects such as motorized drill machines. With the ability to learn from domain experts, the present device autonomously executes tasks based on past experiences.Notably, the device allows human interaction through voice commands, user interface, or physical assistance to teach it object identification, precise location detection, quality control readings and mechanical operations to perform a certain skilled task.

The embodiment of the invention provides a target detection method and device, a controller and automatic driving equipment, and the method comprises the steps: obtaining a multi-view image of a target region where the automatic driving equipment is located, and corresponding camera parameters, and the target region comprises a to-be-detected target object; performing feature extraction on the multi-view image, fusing camera parameters to obtain a three-dimensional feature image of the target area, performing rasterized semantic segmentation and offset prediction on the three-dimensional feature image to respectively obtain a grid mask image and offset information, and performing image segmentation on the grid mask image and the offset information; the grid mask image is used for indicating information of a target grid occupied by the target object in each grid of the three-dimensional feature image, and the offset information is used for indicating position offset information of the target object in the target grid; and determining the position information of the target object according to the offset information and the information of the target grid in the grid mask image. By adopting the scheme, the obtained position information error of the target object is smaller, and the position detection result of the target object is more accurate.

The invention relates to the field of labeling position detection, in particular to an intelligent identification and verification method and system for a two-dimensional code production labeling position, and the method comprises the steps: collecting the overall image data of a target product in real time; according to the overall image data, identifying product reference features in the overall image data, and dynamically generating a positioning frame matched with the product; according to the overall image data, extracting a two-dimensional code labeling contour, and calculating a geometric center point of the two-dimensional code labeling contour; establishing a space mapping model of the geometric center point and the positioning frame, and calculating an overlapping area proportion of the two-dimensional code labeling contour and the positioning frame in the whole image data through the space mapping model as an initial overlapping ratio; acquiring scene characteristics of a labeling environment and product surface attribute parameters, and calculating a deviation value of the overlap ratio through a preset compensation algorithm; correcting the initial overlap ratio based on the deviation value, and judging whether the corrected deviation value is greater than a preset deviation threshold value or not; and if the corrected overlap ratio is greater than a preset deviation threshold value, judging that the labeling position is correct.

An object of the present disclosure is to make it possible to isolate whether an abnormality has occurred in any one of sections of an optical fiber and a device.The present disclosure provides an optical power feeding system including: a light source that outputs power feeding light to an optical fiber; a plurality of optical nodes connected in series to the optical fiber; and an optical tester that transmits test light from the light source side of the optical fiber toward the plurality of optical nodes and detects reflected light of the test light, in which each optical node includes: a photoelectric conversion element that converts the power feeding light into electricity; a power storage unit that stores electric power converted by the photoelectric conversion element; an optical switch that switches an output destination of the power feeding light propagated through the optical fiber between the photoelectric conversion element included in the optical node and another optical node connected to the optical fiber; a control unit that switches connection of the optical switch in accordance with a control signal superimposed on the power feeding light; and a test light cut filter that reflects, toward the optical tester, the test light output from the optical switch to the photoelectric conversion element.

Disclosed are systems and methods including computing-processes, which may include layers of machine-learning architectures, for assessing risk for calls directed to call center systems using carrier signaling metadata. A computer evaluates carrier signaling metadata to perform various new risk-scoring techniques to determine riskiness of calls and authenticate calls. When determining a risk score for an incoming call is received at a call center system, the computer may obtain certain metadata values from inbound metadata, prior call metadata, or from third-party telecommunications services and executes processes for determining the risk score for the call. The risk score operations include several scoring components, including appliance print scoring, carrier detection scoring, ANI location detection scoring, location similarity scoring, and JIP-ANI location similarity scoring, among others.

The invention provides an open-circuit fault positioning and detecting system and an open-circuit fault positioning and detecting method based on a dual active bridge resonant converter (DBSRC). The open-circuit fault positioning and detecting system and the open-circuit fault positioning and detecting method based on the dual active bridge resonant converter (DBSRC). Aiming at DBSRC single-tube and multi-tube open-circuit faults, by analyzing characteristic quantities such as resonant capacitor voltage direct-current bias, bridge arm midpoint voltage mean deviation and resonant current direct-current bias and combining a threshold value correction strategy, rapid fault detection and accurate positioning are achieved. According to the method, a plurality of characteristic quantity joint criteria are introduced, the problem of positioning fuzziness caused by the fact that a traditional method depends on a single characteristic quantity is solved, and the reliability and the response speed of fault detection are remarkably improved by means of collaborative optimization of a hardware sensor and a software algorithm. The method does not need a complex control algorithm, has the advantages of being easy to implement, low in cost, high in compatibility and the like, and is suitable for the fields of direct-current microgrids, energy storage systems, power electronic transformers and the like.

To provide an information management device, an information management method, a vehicle system, and a program that can more appropriately cause a lane deviation alarm to operate on the basis of a surrounding state.SOLUTION: An information management device includes: a communication section that communicates with a plurality of vehicles with which a lane deviation alarm can operate; a position detection section that detects a position where the lane deviation alarm has operated for each vehicle on the basis of information acquired from the plurality of vehicles by the communication section; and an identification section that identifies a position where the lane deviation alarm operates frequently in the plurality of vehicles on the basis of position information detected by the position detection section.SELECTED DRAWING: Figure 4