249results about How to "Good real-time performance" patented technology

The invention discloses a head posture estimation method based on depth information and a color image. The method comprises the steps of firstly utilizing a histogram projection method to quickly position a head position in a depth information grey-scale map; then utilizing skin color detection algorithm to eliminate hair noise and clothes noise except the skin in the head area in a color image; utilizing a camera imaging principle to normalize the head area resolution, and homogenizing the depth information grey-scale map; and finally extracting a section regional geometric vector set from the obtained normalized grey-scale map to describe the variation rule of the head posture. According to the features of the depth information grey-scale map, the geometric feature of a face and particularly the symmetrical characteristics of the face about a nose tip, a novel head posture description characteristic code is designed, the head posture is estimated by utilizing a random forest regression machine, and the method has the advantages of good real-time property, high precision, high robustness and high reliability and can be widely applied to the application fields such as human face recognition and human-machine interaction.

The invention belongs to the technical field of intelligent transportation, and relates to a front vehicle detection method based on monocular vision, which comprises the steps of: acquiring a vehicle front road condition original image, capturing a subimage, carrying out histogram equalization on the subimage, extracting a vehicle front road surface average gray threshold; obtaining a gray threshold by adopting an improved OTSU method; calculating a binarization threshold; estimating a binarization result, segmenting and reinforcing a target according to an estimation result; filtering; obtaining a key position line expressing a bottommost line in a vehicle bottom shadow, carrying out line fusion on the key position line, then extracting target information of an image to be used as a target result of a current frame; and matching the target result of the current frame with a target result of the last frame and information of a tracking target result, and carrying out classifying decision on the target result of the current frame according to a matching result, and determining a final detection result of a front vehicle of the current frame. The front vehicle detection method has the characteristics of good instantaneity, high detection accuracy rate and good robustness.

The invention proposes a visual navigation system of unmanned planes, wherein a collaborative interaction method of an unmanned plane cluster comprises the following steps of: determining the unmanned plane of meeting the collaborative condition within the communication coverage by one unmanned plane in the unmanned plane cluster; building an unmanned plane collaboration group according to the unmanned plane meeting the collaborative condition; determining an interunit route among a plurality of unmanned planes in the unmanned plane collaboration group; distributing collaborative tasks to a plurality of unmanned planes in the unmanned plane collaboration group according to link state information of the interunit route; estimating the link state according to the movement states of the plurality of unmanned planes in the unmanned plane collaboration group; and updating the unmanned planes in the unmanned plane collaboration group and the collaborative task of each unmanned plane according to the assessment result. The visual navigation system of the unmanned planes has high reliability and high communication quality, and can well adapt to a communication environment of the unmanned plane cluster in visual navigation.

The invention discloses a method and a system for splicing images of unmanned aircrafts in real time. The method and the system mainly solve the problem of poor image splicing real-time performance or obvious splicing traces in the prior art. The method includes a training stage: acquiring training images before the unmanned aircrafts execute tasks, extracting local features of the training images and building vocabulary trees; an online stage: acquiring practical earth observation images when the unmanned aircrafts execute the tasks, extracting local features of the images, retrieving the vocabulary trees to quickly search spatially adjacent images, matching the spatially adjacent images, computing transformation relations among the images, splicing the images according to the transformation relations and removing splicing joints. The method and the system have the advantages that the images of the unmanned aircrafts can be spliced by the aid of the method and the system, and broad vision field ranges can be provided for users; the method and the system are high in real-time performance and good in splicing effect, and requirements of application places in multiple fields can be met.

The present invention discloses a working method of a real scene navigation system. The navigation system comprises a navigation device and an imaging device. The working method comprises that when a vehicle drives according to a preset navigation path, the imaging device follows the vehicle and real-timely shoots the real-time image around the current vehicle; if a complex intersection exists in front of the vehicle, a processor module matches the real-time image and the street scene image of corresponding position and pre-stored in a data memory, combines the preset navigation path, and determines the position, the road and the right driving direction of the current vehicle; and a display module is controlled to display the corresponding navigation images, wherein the real-time image in front of the current vehicle, and the vehicle driving direction matched with the navigation path and labeled by the arrow are contained in the navigation image.

The invention discloses an atmospheric particle black carbon aerosol quality concentration monitoring instrument, including an air monitoring room. The upper end of the air monitoring room is connected with a suspended absorption electromagnetic iron. The top of the air monitoring room is provided with a LED light source array. The air monitoring room is communicated with an air inlet. The bottompart of the air monitoring room is a glass plate, which is equipped with a breathable window. A quartz filter paper belt is arranged under the air monitoring room. Two reference and measurement photoelectric detectors are arranged under the quartz filter paper belt. One detector is used for reference and another detector is used for test. With an optical attenuation method adopted, the invention has the advantages of good real-time performance, high precision and low cost, improved automation degree, time and labor-saving performance and all-weather automatic continuous operation. The continuous and real-time on-line monitoring of the atmospheric particle black carbon aerosol is ensured.

A method and a device for producing vector vortex beam are belonging to the vector vortex beam technology area, to solve the problem of how to adopt a simple method and device to produce high quality vector vortex beam, the emergent laser beam from the laser under collimation and beam expanding after passing beam expander and collimating lens, and arranges pinhole at the focal position between beam expander and collimating lens for laser beam filtering; light beam after collimation and beam expanding is normally incidented on polarizer through aperture diaphragm, and the linearly polarized lights generated is incidented on the depolarization beam splitter, linearly polarized lights through transmission of depolarization beam splitter reaches the effect window of the reflecting pure-phase liquid crystal spatial light modulator, and conducts phase modulation for the linearly polarized lights by load grayscale images of PC control terminal, to acquire the relevant vortex beam; light path of vortex beam after depolarization beam splitter reflects, and becomes circularly polarized light after 1 / 4 wave plate to incident on radial analyzer, to generate radial polarized vortex beam; and acquires vector vortex beam in need through polarization rotator.

A method based on template match for automatically recognizing the ST segment in electrocardiogram includes such steps as using template match method to search R point, S point and sequential two slope variation points J1 and J2, and defining the segment between J1 and J2 as St segment.

The invention discloses a special equipment of digital loop bus control system - bus controller, its communication process being, the PC bus control module sends the data from the PC to the data buffer zone (61); the bus protocol analysis module (63) accesses to the data buffer zone (61), to obtain the data and translate them into the instructions accordance with bus protocol, and then through the physical layer control module (64) the physical layer interface (68) sends the data to the controlled equipment. The feedback information from the above controlled equipment passes the physical layer interface, the physical layer control module, the bus protocol analysis module in turn, and is sent to the data buffer zone; the PC uses the PC bus control module to access data buffer zone to obtain the data. In addition, the machine data storage area uses the said PC bus control module to exchange data with the PC. The bus controller of the invention has characteristics of high-speed, good real-time, good reliability, and good interface compatibility.

The invention relates to an adaptive clutter suppression moving-target signal processing method, which is mainly applicable to moving-target signal detection in a clutter environment in the field of radar detection. The adaptive clutter suppression moving-target signal processing method comprises processing flows as follows: firstly, dynamically matching pulse-pressed signals; carrying out primary compensation processing on the signals and sending the processed signals into narrow-band filter sets; respectively carrying out distance unit constant false-alarm processing on the signals output by each filter set, and obtaining a detecting result by selecting large output; and calculating an FIR (Finite Impulse Response) coefficient which uses a speed center as a main peak of a filter by using a given movement speed of a target which is focused on, and changing the coefficient of the filter in a adaptive manner. With the adoption of the method disclosed by the invention, the clutter is restrained obviously, the signal to noise ratio of the movement target is improved through the adaptive method, so that the signal detection performance is finally improved. Furthermore, application of VHDL (VHSIC Hardware Description Language) in FPGA (Field Programmable Gate Array) is completely realized. The method disclosed by the invention has wide application prospect in fields such as the radar detection.

The invention discloses a system and a method for correction of distance walking error of a photon counting three-dimensional imaging laser radar. Firstly, distance walking errors of a photon counting three-dimensional imaging laser radar are demarcated with multiple points to obtain the distance running errors under different laser pulse response ratios. Then, a manner of the mathematical fit is adopted to obtain the function of the distance walking errors about the laser pulse response ratios, and the function of the distance walking errors is recorded as a distance running error function. Finally, during the working process of the photon counting three-dimensional imaging laser radar, distributions of the laser pulse response ratios of the original three-dimensional distance images are counted, and the function of the distance walking error function is adopted to forecast the distance walking errors and correct the original three-dimensional distance image using compensation so as to obtain the corrected three-dimensional distance images. The photon counting three-dimensional imaging laser radar distance walking error correction system and the method are capable of eliminating the distance walking errors.

The invention relates to a multimedia network advertisement releasing system which comprises terminal machines and a server, wherein the terminal machines are used for playing advertisement; the server is used for receiving advertisement release and controlling advertisement playing, and the server and each terminal machine are connected with an internet; and the server comprises an advertisement release controlling module, a terminal machine selecting module and an advertisement release executing module, wherein the advertisement release controlling module is used for receiving the advertisement content released by an advertiser, and the advertisement content contains videos, pictures or roll titles and is stored in a storage module; the terminal machine selecting module is used for selecting each terminal machine according to the area of the released advertisement selected by the advertiser; and the advertisement release executing module is used for transferring the advertisement content in the storage module to the selected terminal machine and inserting the advertisement content into the original advertisement content playing sequence table to be played sequentially. The system of the invention can automatically release the advertisement content of each terminal machine and has good flexibility and excellent real-time property.

The invention discloses a method for diagnosing the fault of intelligent traffic capturing equipment based on an image abnormal characteristic. An aim of diagnosing the fault of the capturing equipment is fulfilled by a method for intelligently identifying an abnormal image by a computer, so that the complicated and low-efficiency manual diagnosis method is avoided. The method comprises the following steps of: firstly, establishing a mapping relation from the abnormal image to the fault of the equipment, and implementing a high-practicability license plate positioning method based on a color characteristic and a character texture characteristic according to the requirements of normal characteristics; secondly, adopting an abnormal image identification method based on multi-characteristic combination, and researching the adaptability of an identification algorithm; and finally, performing high-observability visualization processing on fault information of complicated comprehensive equipment. According to an equipment fault diagnosis system, fault diagnosis for the capturing equipment can meet requirements on high instantaneity, high accuracy and high efficiency; and a humanized and scientific fault diagnosis method is supplied.

The invention relates to a palmprint-based authentication unlocking method, terminal and system, and the method comprises the following steps: using a mobile terminal to acquire a palmprint image of a user; processing the palmprint image and acquiring palmprint characteristic parameters; performing identity authentication on the user according to the palmprint characteristic parameters and a local database; and instructing a door access system to unlock after the user passes the authentication. A palmprint identification technology is applied to the hand-held mobile terminal, thereby realizing palmprint identity identification in any shape and posture at any time and any place; the method has the advantages of good real-time property, low identification error rate, strong robustness, good expansibility and the like; by adopting the method, not only can the safety of the door access system be improved, but also the convenience is brought to the user; and the method can be widely applied to ordinary door access systems and other systems, such as automobile identity identification systems and the like, which need to perform identity identification for unlocking.

The invention discloses a human eye aberration measurement device and the measurement method, which relates to the field of measurement technology; the method firstly uses an optical path which is composed of a Hartmann-Shack wavefront sensor to measure the human eye wavefront aberration, makes use of a Zernike polynomial equation to carry out wavefront reconstruction and obtains the human eye wavefront aberration which is measured objectively by calculation; at the same time, a visual target is used in the same optical path to measure the human eye subjective aberration, so as to obtain the human eye aberration of the subjective measurement based on the judgement of the displayed visual target of the people to be measured; finally, the different weight values are set according to the different ages and genders of the people to be measured, as well as the calculation results of the statistical analysis in the past, the human eye wavefront aberration of the objective measurement and the aberration of the subjective measurement are subject to weighted information fusion according to the set weight values, and the human eye wavefront aberration after the fusion is finally obtained. The method combines the advantages of different measurement methods on the basis of weighted information fusion, which can improve the measurement accuracy of human eye wavefront aberration.

The invention provides a gutter track compression method based on a G2 continuous Bezier curve. The method comprises the following steps of a continuous small-line-segment screening step: regions to be compressed are determined through the continuous small-line-segment screening step; a fitting step: shape value points in each region are fit into a three-order Bezier curve through the fitting step; an error estimation step: the error estimation step is adopted for controlling the precision during the fitting step execution; a transition fairing step: a G2 continuous firing processing path is generated through the transition fairing step. The gutter track compression method has the advantages that the linear cutter path in the numerical control processing code can be compressed into the G2 continuous Bezier curve, each section of Bezier curve only comprises one curvature extreme value point, the data compression rate is high, the whole algorithm does not have the iteration, the real-time performance is good, the estimated error is very similar to the real error, the fitting precision can be effectively controlled, and the method can be applied to the high-speed and high-precision numerical control processing.

The invention discloses a visible detection method of the welding quality of a circuit board based on a support vector machine, which comprises the following steps: (1) acquiring an image of a weldingpart of the circuit board; (2) extracting a gray histogram of the welding image; (3) adopting an entropy-based image segmentation method to divide the welding image into three chroma strips; (4) taking three variables of area, barycentric ordinate and secondary moment from each chroma strip as characteristic quantities of the welding quality detection of the circuit board; and (5) taking the characteristic quantities as inputs of a support vector machine classifier, judging that the welding quality belongs to normal soldering, excessive soldering or insufficient soldering by three output values of the support vector machine classifier, and finally obtaining a welding quality result. The invention can overcome the problems of low manual detection efficiency, slow speed, low precision, highomission ratio, easy fatigue of detection personnel, and the like, and improves the automation degree of electronic manufacturing and production as well as the product quality.

The invention provides a corridor vanishing point rapid detection algorithm based on a K-means method. The method is characterized by carrying out earlier stage processing comprising down-sampling, gray processing, histogram equalization and Canny edge detection after obtaining image data returned by a robot in real time; carrying out line extraction on the image obtained in the previous step by utilizing a probability Hough transformation algorithm; and finally, classifying the detected lines into four kinds by utilizing the K-means algorithm according to the slope, calculating the mean value of the midpoints of each cluster of lines, then, establishing four lines to replace the lines detected in the previous step by utilizing the slope obtained by cluster and the midpoint mean values, dividing the four lines into two groups randomly, calculating the intersection point respectively, and taking the midpoint of the intersection point as a vanishing point. The method can rapidly detect the position of the vanishing point, and then, the heading direction of the robot is corrected by utilizing the vanishing point, so that the navigation of the robot can be realized. Compared with the conventional vanishing point detection method, the vanishing point rapid detection algorithm in the invention has the advantages of being simple and efficient, good in real-time performance and high in stability.

The invention discloses an automatic adjustment system for automobile rearview mirrors. Two camcorder lenses are mounted on an inner rearview mirror, face to the head of a driver, and are used for detecting and extracting the orientation and the position of the head and the orientation and the position of the body of the driver; a corner sensor is mounted on a steering wheel and is used for detecting the rotating angle of the steering wheel so as to obtain the direction of automobile front wheels; a vehicle-mounted computer extracts out the orientation of the head of the driver, the three-dimensional space movement of the body of the driver, and the gazing direction of eyes of the driver through images shot by two independent optical image sensors, and through cradle heads, the directions of three rearview mirrors are adjusted so that the driver obtains the best view. According to the automatic adjustment system disclosed by the invention, the rearview mirrors can be automatically adjusted to provide the driver with the view of the most needed region, the disadvantages that a conventional rearview mirror system cannot be dynamically adjusted, view blind areas exist, and objective views are inconsistent with actual views are overcome, and the automatic adjustment system has enormous aids to the driving of the driver on roads.

The invention relates to a control method of the whole network balancing of a central heating system, and belongs to the technical field of heating control and provides the control method of the whole network balancing of the central heating system which is capable of automatically identifying whether heating capacity of a heat source is enough or not, achieves the comfort heating when heating capacity of the heat source is enough and achieves the homogeneity heatingwhen heating capacity of the heat source is insufficient. The control method comprises the steps that predicting and calculating of thermal load, adopting dynamical real-time calculation for thermal load variation; disposing and calculating by collecting outdoor actual temperature; evaluating heating capacity of the heat source; using heating power condition of the worst beltway heating station in heat supply network for judging heating capacity of the heat source; according to the equivalent external temperature of the worst beltway heating station, realizing autobalance of the whole network between each heating station; identifying temperature control curve; introducing a thermal load correction factor and a relative discharge coefficient. The control method has wide use for central heating control.

The invention discloses a system capable of utilizing remote meteorological monitoring to realize the disaster prevention and a method therefor. The system comprises a server and a plurality of remote client sides; and the remote client sides are used for monitoring local meteorological data and sending the meteorological data to the server. The corresponding remote meteorological monitoring method comprises the following steps: the remote client sides adopt an NTP (Network Time Protocol) to obtain the time information of the server, thereby realizing time synchronization; the software version of the server and the remote client sides are synchronous through a network; the server monitors the states of the remote client sides through a heartbeat mechanism; and the remote client sides acquire the meteorological data for transmitting to the server. The system provided by the invention can utilize the network of the telecom operator to transmit the meteorological data, is economical and simple, and has good real-time performance. Under the condition of poor communication, the data can be locally cached; under the condition of unimpeded communication, the cached data is uploaded to the server, thereby ensuring the accuracy of the meteorological data; and the server can monitor the state of the remote client sides in a real-time manner, thereby improving the reliability in meteorological data acquisition.

The present invention belongs to the field of electronic and control technology. In the concrete, it relates to an intelligent pressure-regulated water supply energy-saving control method. Said method includes the following several steps: water pump unit can be used for pumping water and supplying water to user, the pressure gauge positioned in main pipeline can be used for transferring the detected pressure to the controller, and said controller can adopt PID regulation combined fuzzy control method and can utilize control box to control water pump operation and its operation frequency. Said invention also provides the working principle of said water supply control method and its concrete operation steps.

The invention relates to a self-adaptation adjustment level cloud platform, which comprises a base, a top cover, floating blocks, a support, a support supporting shaft, rolling bearings, a cloud platform and a screw, wherein the base is a rectangular cavity container with an opening on the top; the top cover is located on the top portion of the base; a small opening is opened in the middle of the top cover; a bump is respectively set in the middle of two side edges of the top cover; a round hole is opened in the middle of the bump; two rolling bearings are mounted inside the round hole; two ends on the bottom of the support are connected to two identical floating blocks; the top portion of the support is penetrated through the small opening in the middle of the top cover and is fixed on the bottom of the cloud platform through the screw; a small hole is opened on the position above the middle of the support; the support supporting shaft is penetrated through the small hole; and the rolling bearings are inserted into the two ends. According to the invention, under the effect of the opposite torque produced by the floating blocks, the cloud platform can be automatically adjusted to a level position, so the work of the apparatus won't be influenced; and the function of self-adaptation adjustment can be realized without needing a large whole size, thus the cloud platform provided herein is convenient to use and has good practicality.

The invention relates to a wireless intelligent inspection method of a warehouse and a special robot and belongs to the technical field of electronic technology application. According to the technical scheme, fixed-point non-contact charging is achieved by the wireless energy transmission technology, a photoelectric sensor is used to identify path information, tracking moving detection in the warehouse is achieved by driving a motor and a steering engine, a temperature and humidity sensor and an ionization smoke sensor are integrated to detect temperature and humidity in the warehouse and fire smoke in real time, the information are sent to an upper computer in a wireless communication manner, and real-time data information is provided for temperature and humidity control in the warehouse and fire alarm. The wireless intelligent inspection method and the special robot have the advantages that the information is sent to the upper computer through a wireless communication module, and wireless and intelligent management of the warehouse is achieved; and measurement precision is high, real-time effect is high, mounting is simple, and maintenance cost is low.

The invention discloses a multi-train splice angle measurement method based on a rear-view binocular camera. According to the invention, a binocular visual system is adopted; by extracting and fitting a point cloud profile of a front panel or a side panel of a trailer, information output of a splice angle of the trailer is obtained. In the method, the camera is installed on a back plane of the trail by facing the trailer, and can be integrated into a sensing system of the trailer, and can be applicable to different trailer systems without changing installation positions. The method is suitable for all multiple vehicles.

The invention aims at providing a workpiece measuring system based on a five-axis numerical control system to solve the problems of the prior art that the real-time property of acquisition of running data of all the axes of the numerical control system is not strong, the acquisition system is complicated to realize, and the numerical control system does not have generality and expansibility. A counting device acquires encoder feedback signals of motor encoders of all the axes of a numerical control machine; a displacement sensor is arranged at the cutter clamping part of the numerical controlmachine, and used for replacing the cutter, detecting the displacement signals from the displacement sensor to the surface of the workpiece and sending the signals to a industrial control machine; and the industrial control machine is used for reading the encoder feedback signals and displacement signals regularly, and processing the encoder feedback signals and displacement signals to obtain a three-dimensional point set of the workpiece. The workpiece measuring system has good real-time property, generality and expandability; and the hardware is connected simply, conveniently and reliably, thus the workpiece measuring system is convenient to use and operate, and has high measuring precision.

The invention discloses a turning chatter detection method, and relates to the technical field of detection. In the turning process, the state of a machine tool can be reflected in dynamic cutting force. The turning chatter detection method includes the steps that firstly, an off-line data training model is used, force signals are decomposed to a sixth layer through wavelet packet transformation, energy of each node is worked out, and a 64-dimension feature vector is obtained; dimensionality reduction is conducted on the feature vector through least squares support vector machine-regression feature elimination (LSSVM-RFE), redundancy features are eliminated continuously, optimal features are selected out, and a least squares support vector machine classifier is trained according to the optimal features; and each selected feature corresponds to one wavelet packet node, in the on-line detection process, only a small wavelet packet matrix is needed to decompose force signals to the small wavelet packet nodes selected in the off-line training process, the feature vector is built and input into the classifier, and a detection result is obtained. By the adoption of the dimensionality reduction method, the turning chatter detection method has the beneficial effects of being high in speed and high in identifying accuracy and effectively guaranteeing the machining safety and the product quality.

The invention provides a differential updating method and system of map data, and a server. The differential updating method of the map data comprises the following steps: dividing the map data into a plurality of display grid areas according to the state of road network; detecting map data with a new version number when a data updating request of a navigation client is received, comparing the map data with the new version number with map data with an original version number, and identifying the display grid area with data change; obtaining differential data according to the display grid area with data change; and sending the differential data to the navigation client in order to make the navigation client update the displayed map data according to the differential data, wherein the differential data is obtained according to increased data recording, deleted data recording and updated data recording of the display grid area with data change. The map data is updated only through updating the differential data without updating the whole data packet, so the volume of updated data is small, and the real time property is good.

The invention discloses a system and a method for positioning a medium voltage distribution network using power line carrier communication. The system comprises a plurality of nodes, and each node has number and fault information; and the system also comprises a carrier communication network connected with the nodes and a host controlling and processing system connected with the carrier communication network. The method comprises the following steps of: inputting, acquiring, judging whether a zero sequence voltage is greater than a threshold value, judging whether a fault exists and whether the fault is a false grounding fault, judging a neutral point grounding mode and positioning fault points by adopting different methods for positioning fault zones. The system uses the power line carrier communication technology as main means of fault information transmission and distribution network communication, has the advantages of economy, practicability, strong adaptability, simple channel maintenance and high reliability, has openness and compatibility, can be used as a common channel by each distributed automatic subsystem, meets various demands of distribution network management, greatly reduces the investment, and accurately positions the fault points through least square.

The invention relates to a service state online detection method and system based on components, belonging to the computer field. The system comprises a component automatic generation module, a component management module, a component updating module, a component configuration module, a service state detection module, a statistics and analysis service module and a component output interface. The detection method comprises the following steps: initializing the system, starting the components, component executing, changing the configurations of the components, updating the components and logging out the system. The system of the invention adopts component architecture to provide the service state detection function automatically, efficiently and instantly; the system supports dynamic extension, and can update the components one by one without influencing the system; and the system can form a component gallery supporting various service state detections and effectively realize the reuse and accumulation of the technology.