41results about How to "To achieve the effect of real-time monitoring" patented technology

The invention discloses a panoramic picture method based on a hemisphere annular panoramic camera which includes the following steps: firstly, dividing an original image into four small areas, transforming coordinates and forming an isosceles trapezoid image; secondly, stretching the isosceles trapezoid image into a rectangular image through a bilinear transformation method. When one area is processed, corresponding relationship of coordinates can be directly applied to the rest three areas. Finally the four areas are connected from head to tail in sequence. A strip-shaped 360 DEG panoramic picture is obtained and regarded as a rectangular image capable of being accepted by human being and processed by a computer. A certain breakthrough on rapidity of algorithm is achieved. The aim is to achieve effect of real-time monitoring. Image quality is good enough to satisfy general video monitoring requirement.

The invention provides a ship target detection method based on joint training of deep learning features and visual features, which includes the following steps: sample data collection, CNN feature extraction, traditional moment invariant feature and LOMO feature extraction, feature dimension reduction, feature fusion network FCNN construction, and training the network with sample data and testingthe model with test data. Compared with the prior art, the visual feature extraction process of the invention comprehensively considers the characteristics of the ship shape, color and texture, so that the detection process is interpretable, and other features other than the traditional features can be learned in the normalized CNN back propagation process. This method is fast and efficient, highaccuracy, for complex scenes such as clouds and fog, cloudy days, rain and other circumstances still have good detection results, high robustness. Features complementary to the traditional features can be extracted, and the speed is very fast, can achieve the effect of real-time monitoring.

The invention discloses a method for computing flicker indexes on the basis of Beidou navigation. The flicker indexes are measured by amplitude flicker indexes S4T and phase flicker indexes sigma phiduring ionized layer flicker monitoring after trend of the amplitude flicker indexes S4T and trend of the phase flicker indexes sigma phi are eliminated by means of filtering. A process for computingthe amplitude flicker indexes S4T after the trend of the amplitude flicker indexes S4T is eliminated by means of filtering includes steps of A-1), computing signal strength SI; A-2), filtering the signal strength SI to obtain signal strength SI'; A-3), eliminating the tread by means of filtering to obtain the amplitude flicker indexes S4T. A process for computing the phase flicker indexes sigma phi after the trend of the phase flicker indexes sigma phi is eliminated by means of filtering includes steps of B-1), computing carrier phases phi after the trend is eliminated by means of filtering; B-2), acquiring the phase flicker indexes sigma phi. The method has the advantages that information of the signal strength SI and the carrier phases phi of satellite signals can be directly outputted,ionized layer flicker conditions can be computed by the aid of the information, and the method is convenient, simple, stable and reliable as compared with original equipment.

The invention discloses a non-invasive measurement of hemoglobin concentration based on principle of optical reflection. The method comprises the following steps: arranging a light source and a photoelectric detector; determining the relationship between absorbance and the concentrations of oxyhemoglobin and reduced hemoglobin in deep tissue; a light source emitting near-infrared incident light with wavelength lambda 1 and lambda 2, a first photodetector and a third photodetector respectively acquiring the absorbance reflected by human skin tissue; the light source emitting near-infrared incident light with wavelength lambda 1 and lambda 2, and a second photodetector and the fourth photodetector respectively acquiring the absorbance reflected by human skin tissue; by introducing the correction coefficients [omega](i) 1 and [omega] (i) 2, the concentrations of oxyhemoglobin and reduced hemoglobin in deep tissues were obtained respectively. The concentration of hemoglobin tHb in deep tissues was obtained by adding the two concentrations together. The invention realizes non-invasive measurement of hemoglobin concentration, has low measurement cost and high measurement accuracy.

The invention provides a control method and device of an intelligent device. The method includes the steps: the intelligent device, on the basis of an SIP (session initiation protocol), receives a control message, which is forwarded from a user terminal by a management server through the internet and a local area network on the basis of the SIP; the control message is analyzed; the intelligent device is controlled according to device parameters and control information in the analyzed control message; if control completion or failure is determined, a control completion message or control failure message is transmitted to the management server through the local area network and the internet on the basis of the SIP; the management server forwards the control completion message or control failure message to a user terminal through the internet and/or the mobile communication network on the basis of the SIP. The control method and device has the advantages that the user terminal can transmit the control message to the intelligent equipment more quickly and more stably, chances that the intelligent device has a delay in receiving the messages from the user terminal are slimmed, and the user terminal is allowed to control the intelligent device in real time.

The invention discloses an air quality monitoring system, which comprises a sensor unit, processing units and a monitoring terminal. The sensor unit is used for detecting the parameter information ofthe air quality. Each processing unit is used for receiving the parameter information transmitted by the sensor unit and performing data analysis on the parameters, wherein the standard information ofvarious indexes of the air is stored in the processing unit. The processing unit compares the received parameter information of the air quality with the standard information stored in the processingunit, then figures out a specific unqualified parameter in all parameters of the air quality, and outputs display data and an alarm signal. The monitoring terminal receives the data analysis result information transmitted by the processing unit. The monitoring terminal and a plurality of processing units perform real-time data communication in a wireless communication mode. The system is used formonitoring the components of fine particulates, carbon dioxide, the humidity, the temperature and carbon monoxide in the air quality in real time. When a certain parameter index exceeds a set threshold value, the system sends an alarm signal to notify a user. The effect of monitoring the air quality in real time is achieved.

The present invention discloses a host abnormality detection method and system. The method comprises: constructing a list of sensitive hosts and collecting host running resource characteristics of the sensitive hosts; using the PCA algorithm to extract main characteristics of the host running resource characteristics; using the DBSCAN algorithm to carry out cluster analysis on the main characteristics to determine whether there is an abnormality point; and finally, using the sliding window algorithm to collect statistics of the number of abnormality points in the window and determining whether the sensitive host is an abnormal host according to the number of abnormality points. According to the method disclosed by the present invention, the known and unknown host abnormal behaviors within a duration can be effectively detected, the detection efficiency is significantly improved, the resource utilization rate is reduced, and the real time detection is improved; and in addition, without training, the method is efficient and simple, the system overhead is small, and host abnormality can be detected in real time.

The invention provides a smoking behavior and calling behavior identification method based on a video stream. The method comprises the following steps: S1, collecting a data set of model training; S2,installing and compiling a caffe framework supporting 3D convolution; S3, building a classification network architecture based on Tiny_darknet-3D deep learning; S4, setting hyper-parameters of the training network model; S5, directly obtaining a monitoring video stream from monitoring equipment of a to-be-monitored scene; S6, sending the video data obtained in the step S5 into a pre-trained modelin the step S3 for 3D convolution processing, and outputting a classification result; and S7, setting a threshold value according to the confidence value of the target, removing the target with a relatively low confidence value, and storing the image. According to the smoking behavior and calling behavior recognition method based on the video stream, the problems that a traditional smoking and calling detection method is prone to causing target missing detection, the false detection rate is high, an original video cannot be directly recognized, and time dimension information is lost are solved.

The invention provides a weld joint morphology monitoring method, system and device and a readable storage medium. The method comprises the following steps: welding the target welding part according to the target process parameters, and acquiring a welding joint image acquired in the welding process and temperature information corresponding to each pixel in the welding joint image to obtain a reconstructed welding joint morphology, searching a preset welding joint morphology database based on the target process parameters, and determining a target welding joint morphology corresponding to thetarget process parameters. The weld joint morphology of the target welding part is monitored by comparing the reconstructed weld joint morphology with the target weld joint morphology. According to the scheme, the weld joint morphology can be monitored in real time, and due to the fact that the reconstructed weld joint morphology in the scheme can visually reflect the weld joint morphology of thetarget welding part in an image mode, visualization of the weld joint morphology is achieved, and observation is convenient.

The invention discloses a wireless multipoint temperature and humidity measuring system, which comprises a wireless data acquisition system and a wireless data master supervision part, wherein the wireless data acquisition system comprises a plurality of temperature and humidity data acquisition points, acquires temperature and humidity data at a certain time interval, and packs and transmits the data through a wireless module; the whole process is controlled by a microprocessor; and a wireless module of the wireless data master supervision part receives the data, stores the data in a secure digital (SD) memory card, and transmits the data to a personal computer (PC) through a serial port to achieve the effect of monitoring in time. The wireless multipoint temperature and humidity measuring system has the advantages of simple structure, convenience for operation, low cost, high practicability, low power consumption and the like.

An intelligent networked bottle blower is composed of an extruder with material hopper and cylindrical body with electrically heating rings and driven by motor, moulding head installed to the end of said cylindrical body, ejection cylinder, mould, moving cylinder for controlling the opening and closing of mould and control computer with network interface for remote control and maintenance. Said cylinders are controlled by hydraulic workstation. The data readers equipped with all units can seed their data to control computer.

The invention relates to an intelligent-network-based self-propelled spray irrigation device which is characterized in that a control board (2), a spray water pump (4), a power driving motor (7) and a rechargeable battery device (8) are arranged in a vehicle body; a spray pipe (3) is connected to a water outlet of the spray water pump (4) through a pipeline; a liquid fertilizer storage tank (6) is connected to the upper part of the vehicle body (1); the control board (2) comprises a wireless network receiver and is connected to a computer host; the spray water pump (4) is connected to the control board through a signal line; the power driving motor (7) is connected to the control board (2) through a signal line; the rechargeable battery device (8) is connected to both the spray water pump (4) and the power driving motor (7) through electric wires, thus providing power source for the spray water pump (4) and the power driving motor (7). A wireless control module involved in the spray irrigation device is used for receiving a signal of a plant growth management system executed by the computer host, so as to implement a spray irrigation action. The invention provides a method for realizing intelligent movable spray irrigation for an agricultural greenhouse.

The invention belongs to the technical field of remote sensing data interpretation methods, in particular to a crop interpretation method based on an SAR technology. Aiming at the conditions that an optical remote sensing image cannot be used under the influence of thick cloud and other atmospheric conditions under extreme weather conditions, by a lot of experiment analysis, and by combining the high visual characteristics of the optical image and the high penetrability characteristics of the SAR image, and aiming at the condition that the optical image in a project research area is hardly used, the interpretation work such as the qualitative and quantitative interpretation of crop the types is completed through matching of the ROI features of the SAR time sequence images and the optical images, so that the problem that optical remote sensing images cannot be used under severe disaster conditions is solved, and the experiment extraction precision reaches 87.7%, the disaster conditionscan be rapidly and efficiently determined in disaster areas with severe weather conditions, and a new method is provided for accurate extraction and interpretation of crop disasters.

The invention discloses a new energy group vehicle thermal runaway risk assessment method based on digital twinning. The method comprises the following steps: preprocessing battery data; establishing a new energy vehicle group; establishing a cloud battery model; extracting the thermal runaway probability information gain of the thermal runaway inducement; and performing thermal runaway early warning. According to the method, refined digital twinborn modeling of single vehicle thermal runaway can be realized, group digital twinborn modeling of vehicle group thermal runaway behaviors is realized, a probability sequence of thermal runaway in group vehicles is given, and thermal runaway early warning information and battery state information for single vehicles are provided for new energy vehicle manufacturers and battery manufacturers; the bicycle thermal runaway risk which cannot be quantitatively evaluated is converted into evaluation of the thermal runaway probability in the bicycle group, quantitative description of the bicycle thermal runaway probability is achieved, and prediction of the bicycle thermal runaway event and comprehensive management of the group thermal runaway risk are achieved.

A monitoring system is installed on two projection devices and comprises a setting unit, a sensing module and a microcontroller module. The setting unit sets the two projection devices as a first projection device and a second projection device. When one of the first projection device and the second projection device is in an operating state, the other is in a closed state. The sensing module is arranged on the first projection device and the second projection device. The sensing module is used for sensing the operation state of the first projection device or the second projection device and outputting a sensing signal. The microcontroller module detects the operation state of the first projection device according to the sensing signal, and outputs a control signal to the second projectiondevice when the first projection device breaks down; or detects the operation state of the second projection device according to the sensing signal, and outputs a control signal to the first projection device when the second projection device fails.

The invention discloses a water quality biological pollution online monitoring mechanism, and belongs to the field of water pollution detection. The water quality biological pollution online monitoring mechanism comprises a hollow vertical rod arranged at the bottom of a water body. During detection, firstly, air is filled into the hollow vertical rod; air enters a slow air cavity in the self-isolation sampling ball to extrude the false-seal sampling hemisphere, so that the false-seal sampling hemisphere expands under the action of air, the false-seal ring ball expands towards the shape under the action of air extrusion, the false-seal sampling hemisphere is through inside and outside, and water entering the sampling table enters the false-seal sampling hemisphere at the moment, and contacts with the water quality sensor for detection, in the process, sampling and detection can be combined into a whole, and compared with the prior art, the time for transporting a sample to detection equipment after sampling is effectively saved, the effect of real-time monitoring is achieved, and the monitoring efficiency and accuracy are effectively improved.

The invention relates to the technical field of car cover solar charging, and discloses an electric motorcycle new energy pure electric car solar charging system, which comprises a car cover, a main control system, a signal receiving system, a solar power-on system and an automatic telescopic car cover system, wherein the main control system is connected with a signal receiver, a signal output device and the automatic telescopic car cover system. According to the invention, firstly, the car cover is controlled to be automatically unfolded through the mobile phone APP, then the solar power-on system in the mobile phone APP is controlled, the car cover can isolate an automobile from being directly exposed to the sun, the automobile is protected, and a battery is also protected, so that in summer, a motorcycle does not need to worry about that a saddle pad scalds buttocks, an automobile does not need to worry about the conditions that a carriage is too hot and gas which is harmful to health and is volatilized due to the fact that interiors or other objects are too hot is exhausted before driving, and the problems that the automobile is quickly aged due to exposure to the sun and the service life of a battery is shortened when the automobile is charged are solved.