118results about How to "Improve readiness" patented technology

The invention relates to a method for tracking a moving target in a complex scene. The method comprises the following steps of: obtaining a statistical histogram by adopting a component H background weighting method in an initially designated image area; creating a colour updating probability distribution graph with an adaptive background by utilizing a Bayes formula for each image of a video stream in the tracking process, updating target colour probability in a search region in real time, iterating the adaptive background updating colour probability distribution graph to obtain a position of the center of mass by utilizing a Camshift algorithm; and carrying out motion prediction by adopting a greedy prediction method in the tracking process, and continuously repeating the tracking step. By applying the method in the invention, the problem that the tracking on the moving target is not ideal enough in the complex scene can be solved, and the accuracy and the robustness are better.

The invention discloses an intelligent wheelchair dynamic gesture recognition method based on Kinect depth information and relates to the field of intelligent wheelchairs. A method of dynamic gesture recognition based on Kinect depth image information is adopted, and the intelligent wheelchair dynamic gesture recognition method has strong expansibility, can solve problems of influence on gesture detection caused by complex backgrounds, large-area skin color interference and the like and can accurately and effectively separates hands. Subsequently, a method combining Camshift and Kalman filtering is adopted to fast and effectively track gestures, a fused feature extraction method is adopted, and accuracy of dynamic gesture recognition is improved. When the intelligent wheelchair dynamic gesture recognition method is applied to an intelligent wheelchair control system based on dynamic gesture recognition, fast and accurate dynamic gesture command recognition can be achieved, the intelligent wheelchairs can be safely and stably controlled, and the natural and visual man-machine interaction mode between people and the intelligent wheelchairs is achieved.

The invention discloses an electronic medical record database system which comprises a data entry module, a user login module, a data storage module, a data management module and a query analysis module, wherein the data entry module is used for entering electronic medical record data; the user login module is used for a user to log in the electronic medical record database system, and carrying out identity authentication and authority identification; the data storage module is used for storing the electronic medical record data and the individual information and authority information of the user; the data management module is used for setting and managing the individual information and the authority information of the user, and adding, deleting and modifying data in the data storage module according to input orders of the user with authority based on the authentication and identification results of the user login module; and the query analysis module is used for querying the electronic medical record data according to the query criteria input by the user, and counting and analyzing the query results to obtain the analyzed medical record data. The invention establishes the electronic medical records of patients, standardizes data management of the patients, and provides an approach to analysis and diagnosis for medical care personnel.

The invention provides a target situation fusion sensing method based on multiple sensors. The target situation fusion sensing method comprises the steps: monitoring a detection region, and obtainingmulti-target situation information data in a recognition environment; reconstructing a point cloud target and a three-dimensional scene model based on the visual features; detecting a target track, and carrying out registration fusion on a local track and an overall track; obtaining a target identity through a DS evidence theory to realize target friend or foe grouping; and analyzing the behaviorsituation of the enemy target, obtaining the threat degree of the enemy target, and taking suppression measures according to the threat degree level. The invention further provides a device which comprises a measuring and positioning system, an information fusion system, a situation awareness and threat evaluation system, a decision-making system and a display system. The target situation fusion sensing method realizes target situation awareness and threat assessment based on DS evidence theory and target data multi-fusion, and realizes target and scene reconstruction by using point cloud so that accurate information can be provided for detection and identification of the shielded target, scene reproduction, track detection and prediction, battlefield target situation awareness and the like.

The present invention provides one kind of installation task managing method, installing machine, preparing and backup method and installation flow line. Among the installing machines, the current configurations of the element suppliers for different pieces of equipment and the configurations of the element suppliers the production programs of different installing machine are transferred mutually. Furthermore, the installation job designated to some installing machine may be transferred to some other one with the element suppliers for executing the installation job. In this way, corresponding to the current configurations of the element suppliers, the installing jobs for the base plate as the production object may be designated to different installing machines, and the preparing jobs on element suppliers, etc of the operator may be decreased.

The invention reveals automobile chassis automatic detection equipment and an automobile intelligent detection system. The automobile chassis automatic detection equipment comprises a model acquisition module used for identifying a unique identification code of a vehicle and obtaining information of the vehicle, wherein the information comprises vehicle models and set specifications correspondingto the models; a position adjusting mechanism used for adjusting the vehicle to a preset position; an image acquisition module used for obtaining an image of a vehicle chassis set area; an image comparison module used for performing comparison on the image obtained by the image acquisition module and a set image in a database, whether a vehicle chassis is abnormal or not can be determined; and a key comparison area automatic formation module used for labeling a long-time accumulation area or/and a same-batch problematic area. The automobile chassis automatic detection equipment and the automobile intelligent detection system are capable of reducing labor cost, increasing preparation rate, and increasing work efficiency.

The invention discloses a dynamic gesture recognition method based on Kinect depth information. Two static gestures for determining the start and end of a dynamic gesture are recognized through a depth image sequence obtained by a Kinect sensor. After the start gesture is detected, the position of a hand in a depth image is found through a depth threshold method, and then, the coordinates of the palm are found according to the palm features to carry out tracking. After the end gesture is recognized, tracking is stopped, and the track of the dynamic gesture is obtained. The gesture track is encoded using eight reference direction vectors, and the dynamic gesture is compared with reference dynamic gestures through an accelerated DTW (Dynamic Time Warping) method to get a recognition result quickly. By using Kinect depth information, the influence of external environments such as complex background, skin color and illumination can be eliminated. By adding the static gestures for determining the start and end and optimizing the DTW method, the efficiency and accuracy of dynamic gesture recognition are improved.

The invention discloses a shopping mall building air conditioner cooling load prediction method based on GBDT, a storage medium and equipment, and the method comprises: collecting cooling load data, and carrying out the normalization processing to serve as the cooling load energy consumption prediction; establishing a load prediction model based on a gradient lifting decision tree algorithm; inputting the preprocessed data into a prediction model for training, selecting a grid search-cross validation mode, and optimizing the three hyper-parameters with the maximum influence on the performanceof the GBDT model; establishing a final cold load prediction model by completing parameter optimization of the prediction model, and obtaining a predicted cold load curve according to the parameters and the structure of the prediction model; and evaluating the prediction performance of the prediction model, adopting the prediction error for evaluation, enabling the deviation between the true valueand the prediction value to form the prediction error, and completing mall building air conditioner cooling load prediction. The method has good prediction precision, universality and applicability,and is especially suitable for large public buildings with periodically changing cold loads.

The invention relates to an auxiliary intelligent reviewing system for power transmission and transformation project design. The auxiliary intelligent reviewing system comprises the following realization steps of: project key feature index system library building; design information collection and checking; key feature index intelligent comparison and evaluation; and statistical analysis. The auxiliary intelligent reviewing system has the advantages that the centralized management on the design reviewing of projects at 110kV or below 110kV, and the reviewing efficiency is improved; a complete data management platform can be built for filing and reviewing service information and data in a unified way; the project design quality informatization evaluation can be performed, and a design credit performance tracking system can be completed; and a project techno-economic indicator system can be built, unified reviewing measurement standards can be provided, and the intelligent reviewing of the project design can be assisted.

A method of speech processing includes receiving at least two separate, but temporally overlapping speech waveforms in real time; extracting a pitch waveform from each of the speech waveforms by segmenting the speech waveform pitch synchronously, fixing an analysis window size, and analyzing the speech waveform in real time; concatenating each pitch waveform by interpolating the pitch waveform at each pitch epoch, synthesizing a synthesis window size according to a desired speech playback speed, and generating a synthesized output pitch waveform; queuing each of the output waveforms so as to sequence each speech waveform serially one after the other such that the waveforms are mutually separated upon playback; and outputting each of the queued output waveforms to a selected playback device.

The invention provides a method and a device for searching similar images based on perceptual hash. The device comprises an input unit, a difference unit, a searching unit, a screenshot unit, a perceptual hash algorithm unit, a comparison unit, and an output unit. The device has beneficial effects that after an input original image and a screenshot image of the original image are processed by the perceptual hash algorithm, the input original image and the screenshot image are respectively compared with images in a search library, so that under the condition that the input image is the screenshot image of a certain image, the source of the original image can be found. The device and the method improve accurate rate of the perceptual hash algorithm, and provide a new thinking for searching similar images.

The invention provides an enclosure assembly configured to enhance accessibility to a drive unit of an agricultural applicator. The enclosure assembly generally includes a first panel and a second panel pivotally connected to the enclosure assembly and moveable between closed and open positions. In the closed position, the first panel is positioned in general alignment with the second panel. The enclosure assembly also accommodates an exhaust outlet extending upward from the drive unit. The forward end of the first panel includes a first cutout portion and the rearward end of the second panel includes a second cutout portion each configured in the closed position to receive the exhaust outlet. From the closed position, the first panel pivots in a rearward direction and the second panel pivots in a forward direction, relative to the forward direction of travel, to access the drive unit.

The invention relates to a hyperspectral image based overripe Lonicera edulis fruit identification method. The method comprises the following steps: 1, acquiring a hyperspectral image of a Lonicera edulis fruit; 2, sampling fruit and background pixels in the hyperspectral image, analyzing and providing an image background removal function model; 3, removing the image background according to the functional model established in step 2; 4, adopting a median filtering, morphological filtering, spatial processing and threshold determining method to remove noises and determine the position of the fruit; 5, sampling pixels of an overripe fruit and a ripe fruit, selecting a most discriminative waveband through a stepwise forward variable selection method, and adopting a linear discriminant analysis method to establish and discriminate the function models of the overripe fruit pixel and the ripe fruit pixel; 6, classifying all fruit pixels according to the discrimination models established in step 5, and respectively marking; and 7, adopting a majority principle to classify all the fruits. The identification method utilizes the spectral information of objectives and also utilizes the spatial information of fruits, so the discrimination rate is improved.

Presented herein are systems, methods, and devices that provide for stimulation of nerves and/or targets such as mechanoreceptors, tissue regions, mechanoresponsive proteins, and vascular targets through generation and delivery of mechanical vibrational waves. In certain embodiments, the approaches described herein utilize a stimulation device (e.g., a wearable device) for generation and delivery of the mechanical vibrational waves. As described herein, the delivered vibrational waves can be tailored based on particular targets (e.g., nerves, mechanoreceptors, vascular targets, tissue regions) to stimulate and/or to elicited particular desired responses in a subject.

The invention discloses a method for rapidly determining the content of organic matter in soil. The method comprises steps as follows: 0.05-0.5 g of a soil sample is weighed and added to a digestion tube, 0.1-0.3 g of bismuth nitrate is added, and 10-15 mL of a potassium dichromate-concentrated sulfuric acid solution with the concentration being 0.4 mol/L and 3-5 mL of strong phosphoric acid are added; the digestion tube is placed in a digestion device provided with a graphite heating plate and suitable for simultaneous digestion of large batches of determined samples, accurate heating at 180 DEG C is performed, and organic carbon in the soil is oxidized; residual potassium dichromate in the digestion tube is titrated with a ferrous sulfate standard solution under electromagnetic stirring; then the amount of potassium dichromate consumed by the sample is multiplied by an oxidation correction coefficient, and the content of the organic matter in the soil is calculated. The method has the advantages of being high in accuracy, good in repeatability, simple to operate, low in energy consumption, low in cost, capable of saving time and labor, reliable in determined results and the like.

The invention discloses a method for a music player to display lyrics and an apparatus thereof and belongs to the Internet field. The method comprises the following steps: when a terminal user clicks to play a song, acquiring lyric information of the song, wherein the lyric information comprises starting time and duration of each word in the song; according to the lyric information, displaying the each word one by one with the playing of the song. In the embodiments of the invention, through recording time information of the each word in the song, a preparation rate of the playing is high so as to increase an experience feeling of a user.

The invention discloses a security event prediction method, apparatus and device, and a computer readable storage medium. The security event prediction method comprises the following steps of obtaining a predicted security event in a to-be-predicted host; sorting the predicted security events according to a time sequence relationship and/or an attack stage and/or a risk level occurring in the predicted security events to obtain input variables; and inputting the input variable into a pre-trained security event prediction model, and determining a prediction result corresponding to the to-be-predicted host, the prediction result at least comprising a security event appearing in the next step. According to the invention, the safety time prediction model is constructed; predicting a security event which is about to happen to the network equipment which is currently subjected to the network attack; according to the method and the system, multi-step attack behaviors possibly suffered by a network system in the future, final targets of hacker invasion and facilities and equipment possibly threatened are predicted, so that effective targeted measures can be taken in advance for defense andprevention, and the security of the network is improved.

The invention provides a method for manufacturing printed wiring substrates which can manufacture printed wiring substrates each having resin dielectric layers of uniform thickness and excellent surface flatness while maintaining favorable cutting performance in a dicing step. A multi-printed wiring-substrate panel is manufactured which includes a metal plate having a first main surface and a second main surface, and resin dielectric layers disposed on the first and second main surfaces. The metal plate has first depression portions and second depression portions. The first depression portions are opened at the first main surface and arranged discontinuously along predetermined cutting lines. The second depression portions are opened at the second main surface and arranged discontinuously along the predetermined cutting lines. The multi-printed wiring-substrate panel is cut along the predetermined cutting lines into a plurality of printed wiring substrates.

The embodiment of the invention provides a target account identification method and device, equipment and a storage medium. The target account identification method comprises the steps of obtaining statistical information of target data uploaded by terminals corresponding to multiple accounts and historical data uploaded by terminals corresponding to each account in a preset time period; performing data processing on the target data uploaded by the terminal corresponding to each account in multiple dimensions to obtain a target word vector of each account in each dimension; performing dimension reduction processing on the target word vector of each account in each dimension to obtain a clustering identifier of each account in each dimension; and training a gradient boosting decision tree model according to the clustering identifier of each account on each dimension and the statistical information of the historical data uploaded by the terminal corresponding to each account, and determining whether each account is a target account or not. According to the embodiment of the invention, the problem that the identification accuracy cannot be effectively improved in the prior art can besolved.

Embodiments of the invention provide an information reception control method. The method comprises the following steps of: in response to an access request of an automatic information reception service, detecting state information of associated information processing equipment; and controlling access of the automatic information reception service according to a detection result of the state information. The embodiments of the invention furthermore provide another information reception control method which comprises the following steps of: sending an information processing task to the associated information processing equipment according to information automatically received from a server; detecting feedback of the information processing equipment; and controlling the access of the automatic information reception service according to a detection result of the feedback. The embodiments of the invention furthermore provide devices related to the methods. According to the methods and devices, the information processing efficiency can be improved, and the information reception can be adaptively adjusted according to real processing conditions of the information so as to decrease the information leakage rate.

Provided is a vehicle speed sensor mounting structure for mounting a vehicle speed sensor by means of a simple configuration to an area in which maintenance is easily performed while protecting the vehicle speed sensor. A vehicle speed sensor (77) is secured to a crank case (64) by fastening the vehicle speed sensor (77) together with a protector (83), which covers the upper section of the vehicle speed sensor (77), by means of a fastening member while the axis (O) of the roughly cylindrical main body (78) of the vehicle speed sensor (77) is tilted a prescribed angle ([theta]) towards the rear side of the vehicle body when viewing the vehicle from the side and on a position which is on the upper side of a sub-shaft (35) and the rear side of a shift drum (150) with respect to the vehicle body. By inserting the main body (78) of the vehicle speed sensor (77) into a through hole (73) formed on the crank case (64), the detection unit (78a) of the vehicle speed sensor (77) faces the tip of the tooth of a second-speed driven gear (G2). The through hole (73) through which the main body (78) is inserted and a fastening hole (74) through which the fastening member (81) is inserted are disposed on a fastening base (72) formed on the crank case (64). The fastening hole (74) is disposed on the outside in the vehicle width direction of the through hole (73).