1803results about How to "Improve positioning accuracy" patented technology

The invention discloses an indoor positioning method, device and system based on visible light and a light source. The indoor positioning method based on the visible light comprises the steps that the light source is shot, and images which correspond to the visible light and are emitted from the light source are obtained, wherein the visible light is modulated and contains the identity information of the light source; light and dark strips in the images are obtained, wherein the light and dark strips in the images correspond to the identity information of the light source; the light and dark strips are identified to obtain the identity information of the light source; the position corresponding to the identify information of the light source in a map is sought, and the current position is obtained. According to the indoor positioning method, device and system based on the visible light and the light source, the problem that indoor positioning precision is low in the prior art is solved, and the effect of improving the positioning accuracy is achieved.

The invention provides a vehicle license plate recognition method, and relates to a method for image recognition. The method comprises the following steps of preprocessing an image; partitioning a vehicle region according to color and texture characteristics; extracting a remarkable factor graph of a vehicle region diagram; extracting candidate vehicle license plates by an Adaboost classifier based on expanded Harr-like characteristic; determining the position of a real vehicle license plate from the candidate vehicle license plates; partitioning the marked vehicle license plate from the corresponding vehicle region original diagram; carrying out character segmentation according to structural characteristic; and carrying out character recognition based on the improved template matching method. With the method provided by the invention, the defects that the application scene of the traditional vehicle license plate recognition method is relatively single, some traditional vehicle license plate recognition methods are only suitably used for single vehicle license plate recognition of the single scene and difficultly used for multiple-vehicle license plate recognition of multiple scenes, and the recognition rate is easily affected by strong light, haze and weak light environments are overcome.

The present invention relates to a device for inserting a self-expanding stent into a body vessel. The device comprises a tube, a pushing element and a grip having a housing via which the pushing element is secured on the grip. Further, the device comprises a stent carrier and a moveable element, the latter of which is guided in the housing of the grip and is coupled to the pushing element. Moving the movable element in the proximal direction effects a movement of the pushing element in the distal direction and a movement of the tube in the proximal direction.

The invention adopts the between-class square error and the gray scale information to realize the rapid positioning of the inside and outside boundaries of the iris. Firstly, the interested pupil region is extracted through blocking; the between-class square error is adopted to obtain the pupil binary threshold for the extracted pupil region; then the inside boundary of the iris is positioned accurately through the searching of the boundary points and the curve fitting; the interested region of the iris outside boundary is extracted according to the prior knowledge and the pupil position parameter; the selected region is processed with median filtering and first-order gradient conversion; the iris outside boundary is determined through the local gradient integration method; finally, the iris outside boundary parameter is determined through the circle fitting. The method avoids the image binary from depending on the histogram; the image positioning time is greatly improved because only the interested region is processed; the whole image is not processed; the experiment indicates that the robustness and the positioning efficiency of the algorithm can satisfy the real-time processing requirement of the image.

The invention discloses an eye location method and a device, wherein the eye location method comprises: obtaining information of glasses of a facial image which is to be located,primary locating the eye position of the facial image according to the information of glasses, confirming the opening and closing state of the eyes of the facial image according to the primary located eye position, locating the eye position according to the opening and closing state of the eyes. The eye location method and the device solve the problem that the accuracy of eye location is poor in relative technology, eye location accuracy is improved and speed and accuracy of face identification are further improved.

The invention discloses a network optimizing system and a network optimizing method. The system comprises a signaling acquisition device, a database server, a data processing module and an optimizing application module, wherein the signaling acquisition device is used for acquiring signaling data from a mobile communication network and storing the acquired signaling data; the database server is used for storing acquired network optimizing analysis auxiliary data and storing the processed signaling data; the data processing module is used for gathering network optimizing analysis basic data and the network optimizing analysis auxiliary data and accomplishing a multilayer database framework for data processing and application; and an optimizing worker calls an analysis result in a multilayer data framework in a data analysis module through the application module so as to realize work in the network optimizing process. By the network optimizing system and the network optimizing method, comprehensive data can be acquired, network problems can be truly and comprehensively reflected, and network performance can be further optimized comprehensively.

A recess 14 is provided in a lens accommodating portion 13 of a laser holder 10 for holding a collimator lens C, whereby positional accuracy and adhesion strength of the lens and a light source are improved.

The invention provides a cleaning method of power communication operation and maintenance data, and more particularly to a power operation and maintenance data cleaning method based on an isolation forest algorithm and a neural network. The method includes: firstly, using the improved isolation forest algorithm to construct an isolation forest model iForest solving a target problem; then definingan evaluation system of the isolation forest algorithm on abnormal data; and carrying out prediction correction on abnormal data attributes, which are detected through an isolation forest, through training the BP neural network. According to the method, optimization is carried out on a power communication operation and maintenance data cleaning method based on the isolation forest algorithm and the neural network, abnormality detection precision is improved, data correction errors are reduced, and effective optimization is realized for a power operation and maintenance data cleaning program onaspects of abnormal-data positioning accuracy, a data correction accuracy rate, training time, resource occupation and the like.

First elasticity information regarding elasticity of a subject in a first image and second elasticity information regarding the elasticity of the subject in a second image are acquired, and the first image and the second image are positioned with respect to each other on the basis of at least one of the first elasticity information and the second elasticity information.

The invention relates to a driver sound localization system and method for an automobile. The system comprises a first sound collecting device, a second sound collecting device and a control system, wherein the first sound collecting device and the second sound collecting device are used for collecting a first sound signal and a second sound signal; the control system is used for respectively processing the first sound signal and the second sound signal so as to output driver locating information; and the control system further comprises a noise reduction device, a filtering device, a sound activation detecting device, a long frame framing device, an envelope calculating device and an energy ratio calculating device and used for calculating the envelope energy ratio of the first and second sound signals according to the calculation results of the envelope calculating device and the long frame framing device. The driver sound localization system and method for the automobile have the advantages of relatively low cost and high locating accuracy and real-time performance.

The invention provides a pretreatment method of iris images based on gray information. A rough circle center (xo, yo) of a pupil is located through binary, mathematical morphology, gray projection and other operations, the point, which has a gray value larger than T and the shortest distance to the (xo, yo), is searched at a plurality of lines close to the (xo, yo) from the center to the two sides as a pupil boundary point; the accurate circle center and the radius of the pupil can be located through curve fitting; the gray level first difference of the lines where the searched pixel points lie is calculated and the point with the largest value of the sum of the level first difference is searched in the range of places where iris external boundary point possibly appears and taken as the iris external boundary point; the accurate circle center and radius of the iris external boundary is obtained after curve fitting. The quality of iris image is judged through calculating point sharpness and number of effective pixel points according to the normalized image. The pretreatment method of iris images of the invention not only can decrease the time needed by repeated iteration during location, but also can judge the quality of iris image accurately and quickly according to the extracted iris image.

The invention discloses a TOF and RSSI information fusion-based indoor wireless positioning method which is mainly used for solving a problem that in conventional indoor positioning technology lacks effective error control and is low in data utilization rate. An implementation solution comprises the following steps: step 1, according to communication time information between a target node and an anchor node, a symmetric bidirectional bilateral distance measuring algorithm is used to calculate distance between the two, and a fault threshold and an error threshold are set to filter the distance;step 2, according to RSSI value information between the target node and the anchor node, an MK model is used for converting the RSSI value information into distance between nodes after a Gaussian model is used for screening operation; step 3, the two types of distance is subjected to weighted fusing operation, and final distance is obtained; step 4, estimated solutions for the target node are obtained via circulation maximum likelihood estimation; step 5, the obtained estimated solutions are subjected to residual error weighted fusing operation, and coordinates of the target node are obtained. Via the method, insufficiency of conventional technologies that are large in positioning calculating errors and low in positioning result reliability, and data utilization rates and positioning andtracking precision are improved.

The invention relates to a iris location method based on border point search and SUSAN edge detection, wherein the method using projection method first, to do and horizontal gray projection for binary iris image filled by spot, obtain rough center of pupil; through vertical scanning gray curve, to find a point which gray value is greater than a threshold value as internal border point of iris; circle fitting a series of the internal border points, thus obtaining location information of inner edge of the iris; Through SUSAN edge detection method, to cause the situation of obvious external border of the iris characteristic solved well, through direction detection, obtaining radius of external border of the iris, and location information of external border of the iris accurately; locating external border of the iris through the SUSAN edge detection method outside edge of the iris position is a feature of the invention, comparing with general two-step iris location method, positioning accuracy rate of the invention is enhanced by 5 percentage, and the speed of the same is enhanced by 40 percent.

The invention relates to a natural gas pipeline safety monitoring device based on acoustical science active spurring and belongs to the technical field of pipeline monitoring. The process includes that a sound source is placed at an inlet of the head end of a pipeline to transmit sound waves into the pipeline, and when the sound waves spreading in the axial direction of the pipeline meet hydrates or the pipeline leaks, reflecting signals can be generated; a microphone is arranged near the inlet of the pipeline to collect reflected wave signals; the microphone outputs the reflected wave signals into a signal conditioning module, a multifunctional data acquisition card is used for conducting analog-digital conversion, and finally the signals enter a computer to be analyzed. Positioning of the hydrates and leakage of the pipeline can be conducted by calculating the time difference of the sound wave transmitting signals and the reflected signals, and therefore real-time monitoring on the natural gas pipeline is achieved. The natural gas pipeline safety monitoring device has the main advantages that the method is simple and easy to use, the positioning precision is high, the occupied resources of a system are few, and operation is reliable.

The invention discloses an indoor fingerprint map constructing method based on crowdsourcing fingerprint, and belongs to the indoor positioning technology based on the fingerprint. The method is capable of solving the existent problems of constructing the indoor fingerprint map based on the crowdsourcing fingerprint that the positioning accuracy is not high and the calculated amount is larger because the crowdsourcing fingerprint position marking is not accurate, the dimensions are different and the distribution is not uniform, and is used for the technical field of the communication and wireless network. The method comprises a step of grid division, a step of crowdsourcing fingerprint acquisition, a step of crowdsourcing fingerprint resolution, a step of crowdsourcing fingerprint number judgment, a step of AP screening, a step of directly constructing grid fingerprint and a step of fingerprint surface fitting. The method is capable of reducing the workload of the fingerprint acquisition, improving the positioning accuracy, and reducing the workload of the fingerprint comparison.

The present invention discloses a sound source positioning method and apparatus, solving the problem of low pickup accuracy in directed pickup of a target voice in the prior art. The method is applied to a terminal with two microphones at the top. The two microphones are respectively arranged at the front and the back of the terminal. The method comprises the steps of when the terminal is in a video call state, and when whether a target user exists in a shooting range of a camera is determined, collecting a sound signal by the two microphones and calculating, based on the collected sound signal, a sound pressure difference of the two microphones; determining, by using the sound pressure difference of the two microphones, whether conditions of determining a sound source direction with the sound pressure difference are met; if the conditions are met, determining, based on the sound pressure difference of the two microphones, whether the sound signal comprises a backward sound signal; and if it is determined that the sound signal comprises the backward sound signal, filtering the backward sound signal in the sound signal. In a low signal-to-noise ratio scenario, sound source positioning based on the sound pressure difference can help improve the pickup accuracy of the target sound source.

The invention discloses a global position system (GPS) drifting processing method based on ACC signals and a device using the GPS drifting processing method based on the ACC signals. The GPS drifting processing method based on the ACC signals includes the following steps: judging whether a vehicle is in a parking state or a driving state according to the ACC signals inside the vehicle or speed of the vehicle; if the vehicle is judged to be in the parking state, setting longitude, latitude, and mileage value into a constant value, and setting speed into zero; if the vehicle is judged to be in a driving state, setting a first speed threshold value and a second speed threshold value, if the speed is reduced below the first speed threshold value or increased above the second speed threshold value, the vehicle is judged to be in a drifting state, and abandoning current GPS information uploading and mileage accumulation. The invention can effectively shield drifting and improve positioning accuracy of the GPS.

The invention discloses a traffic sign detection and identification method based on collaborative bionic vision in a complex city scene, which includes the following steps: A, obtaining multiple to-be-detected images in a continuous scene; B, obtaining a cluster collaboration map of the to-be-detected image set; C, obtaining an attention saliency map of each to-be-detected image; D, obtaining a collaboration saliency map corresponding to each to-be-detected image; E, locating a sign ROI (Region of Interest); F, carrying out two-level biologically inspired transformation on the sign ROI by using a forward channel; and H, using a feature transformation map and traffic sign template images pre-stored in a database to carry out Pearson correlation calculation to complete the identification ofthe to-be-detected images. In the method, visual processing of a target by the human brain is simulated, and bottom-up visual processing and top-down visual processing processes are integrated. The collaborative nature of global images is considered, so that image location is accurate, and the robustness of identification is strong.

The embodiments of the invention disclose a sound source positioning method, a sound source positioning device and an electronic apparatus. The method includes the following steps that: when being in a sleep state, the electronic apparatus continuously receives speech signals; whether an interaction instruction corresponding to each of the received speech signals is a wake-up instruction is judged; if the interaction instruction is not a wake-up instruction, the sound source direction of the speech signal is recorded and is adopted as a first type sound source direction; if the interaction instruction is a wake-up instruction, the electronic apparatus is switched from the sleep state to a work state, and the sound source direction of the speech signal is positioned and recorded, and is adopted as a second type sound source direction; and the sound source direction of a user is positioned according to the first type sound source direction and the second type sound source direction. According to the sound source positioning method, the sound source positioning device and the electronic apparatus provided by the embodiments of the invention, the sound source direction of the user is positioned according to the first type sound direction of the speech signal received under the sleep state and the second type sound source direction of the speech signal received under the work state, and therefore, the accuracy of the sound source positioning of the user is greatly improved, and user experience is better.

The invention provides an IP address geographic position determination method. The IP geographic position determination method comprises the following steps of acquiring an IP address to be analyzed, searching the IP address to be analyzed through a disclosed IP base to obtain the published geographic position of the IP address to be analyzed, acquiring the last address geographic position corresponding to the IP address to be analyzed through a network detecting tool, and confirming the geographic position of the IP address to be analyzed according to the published geographic position of the IP address to be analyzed and the last address geographic position. The geographic position of the published IP address to be analyzed and the last address geographic position of the IP address to be analyzed are analyzed, the geographic position of the IP address to be analyzed can be determined according to an evaluation value of the candidate geographic position, so that the method has the advantage of improving locating accuracy. Furthermore, user experience on targeted delivery is improved. The invention further discloses an IP address geographic position determination system.

The invention discloses a license plate positioning method based on deep learning SSD framework, comprising the steps of producing license plate data set based on VOC data set format; transferring thelicense plate data set into 1mdb format; adding an assistant network configuration as SSD framework feature extraction layer and classification layer with ResNet residual error network being the basic network; establishing a SSD framework, and conducting training on the network model by means of the established SSD framework; conducting license plate positioning and model assessment by means of the trained model. The invention is advantageous in that license plate positioning is high in accuracy, low in miss rate, and fast in positioning speed; real-time detection of vehicles can be realized.

The invention relates to an electromagnetic-signal-time-inversion-based fault point positioning method for a transmission line. On the basis of an electromagnetic time inversion principle, a single observation point is set at any terminal in a power distribution network and a fault high-frequency transient signal within a limited period of time is measured and recorded; and time inverted sequenceprocessing is carried out on the measured signal, the processed signal is injected into a power distribution network simulation calculation model at an observation point, norm values at different guess positions in the power distribution network are calculated, and a fault position is determined by searching for a maximum peak value and a maximum energy root value. According to the method different form the traditional traveling wave determining method and impedance method, a power distribution network with a complex topological structure can be covered by one observation point without being affected by the fault impedance; and the excellent anti-noise performance is realized. The electromagnetic-signal-time-inversion-based fault point positioning method has the great practical value in fault positioning of the transmission line.

The invention discloses a high-precision inertial navigation positioning algorithm based on motion state detection. The method comprises: acquiring acquisition data of an accelerometer and a gyroscope, carrying out pretreatment to eliminate systematic errors of the accelerometer and the gyroscope and noises caused by pedestrian walking frictions; classifying pedestrian gaits to obtain a normal speed gait and a fast gait; according to the different gaits of pedestrians, carrying out offset correction on angular speed data collected by the gyroscope for each stride at any gait; on the basis of an INS and an error Kalman filter, determining a zero-speed moment of the pedestrian walking based on the different gaits of the pedestrians by using acceleration data and the angular velocity data; atthe zero-speed moment, updating pedestrian attitude, speed, and height information; and on the basis of an obtained pedestrian position coordinate, rebuilding a pedestrian 2D motion trajectory and acquiring a position height of the pedestrian at any time accurately after height update algorithm fusion, and rebuilding a 3D motion trajectory for pedestrians going up and down.

The invention discloses a weak supervision time sequence action positioning method and system based on bimodal cooperation. The method comprises the following steps: performing feature extraction on video clips in a non-edited video; performing action classification on the non-edited video based on a double-flow basic network to obtain a video clip attention weight sequence and an action classification result; obtaining a pseudo time sequence label based on the obtained video clip attention weight sequence; taking the pseudo time sequence label as time sequence supervision, training two single-mode sub-networks, and iterating until final fitting; and based on the two single-mode sub-networks obtained by iterative training, performing time sequence action positioning on the non-edited video. According to the method, training is carried out only under a category label of the video, and starting and ending time and categories of all action instances in the video can be obtained.