339results about How to "High alarm accuracy" patented technology

The invention relates to an intelligent video monitoring method and a system thereof. The system comprises a camera, a first alarm device, a coding processor, a data analyzing processor and a display device. The method comprises the steps of detecting and tracking move targets. The intelligent video monitoring method and the system are executed on the base of common network television monitoring, not only have the advantages of common intelligent video monitoring, but also can bring better income for users. The invention mainly has the following advantages of (1) being capable of reliably monitoring all day long with 24*7; (2) being capable of improving alarm precision due to a strong intelligent characteristic; (3) being capable of improving response speed due to the strong intelligent characteristic; and (4) being capable of effectively enlarging the use of video resources.

The invention discloses a device detection and early fault warning system and method in a cloud computing environment. The system comprises a real-time monitoring module, a monitoring information presentation module, an early fault warning module and a warning module. The method comprises the following steps that firstly, real-time monitoring is conducted, wherein real-time information collection is conducted, and the real-time information is aggregated and presented; secondly, early fault warning analysis is conducted, wherein the collected information is subjected to early fault warning analysis; thirdly, a warning mechanism is triggered, wherein early warning information is classified. The device detection and early fault warning system and method can support protocols, autonomously and controllably select detecting indexes, adapt to different monitoring modes, customizing warning triggering conditions, extending the number of monitoring devices on a large scale and the like according to the types and the number of devices in a cloud computing data center, collection, monitoring, warning and fault positioning can be intensively conducted in a unified system, and the operation and maintenance efficiency is effectively improved.

The embodiment of the invention discloses an alarm processing method and device, computer equipment and a storage medium. The method comprises the steps of monitoring monitor data of a monitor object;according to preset alarm rules, determining alarm data in the monitor data, wherein the alarm data is the monitor data triggering the preset alarm rules; according to the alarm data, generating an alarm event, and recording the alarm event into a preset message queue; according to the preset obtained rules, obtaining the alarm event in the preset message queue; on the basis of machine learning rules and a preset knowledge base, preprocessing the alarm event; sending the preprocessed alarm event to a user terminal. According to the alarm processing method, alarm storm can be eliminated, meanwhile, the alarm accuracy can be improved, and the number of invalid alarms is decreased.

The invention provides a foreign matter invading detecting method and a foreign matter invading detecting device. The foreign matter invading detecting method comprises the following steps that infrared images within the monitoring scope are acquired by utilizing an infrared camera and are transmitted to an image collecting and processing system; whether a suspected foreign matter appears in the monitoring scope or not is determined by the image collecting and processing system according to the infrared images; when the suspected foreign matter appears, the laser light source and a visible light camera are focused on the suspected foreign matter within the monitoring scope, and filling light of laser light is conducted on the suspected foreign matter by utilizing the laser light resource; visible light images of the suspected foreign matter are acquired and transmitted to the image collecting and processing system; image registration and image fusion are conducted on the visible light images and images of the suspected foreign matter area in the infrared images by the image collecting and processing system; and information of the suspected foreign matter is provided by utilizing the fused images, and feature extraction and classification are conducted on the suspected foreign matter by utilizing the information of the suspected foreign matter, automatic identification and alarming for the suspected foreign matter are realized, and abundant and complete image information can be acquired in the time of dark light, dark skies and low visibility.

The invention relates to a mobile phone anti-theft and anti-loss alarming method based on the Bluetooth technology. The method comprises the following steps: creating a Bluetooth wireless connection between a mobile phone and an alarm; setting an alarming environment information value; obtaining an alarming distance threshold value Th; detecting a Bluetooth signal-strength value RSSI; estimating the distance Dis between the mobile phone and the alarm according to the received signal strength value RSSI and the alarming environment information value; and giving an alarm once the distance Dis exceeds the alarming distance threshold value Th. According to the invention, the alarm is more accurate with the environmental factor considered for the alarming distance; the alarming distance can be set according the requirement of the users; further, when the maximal transmission distance of the Bluetooth signal is exceeded, the alarm or the mobile phone can perform automatic detection and give an alarm; the current mobile phone GPS information can be automatically obtained and sent to a mobile phone number arranged in advance; and a method for bidirectionally detecting signal strength is adopted, thereby improving the alarming precision.

The invention discloses a wireless data-image dual acquirement anti-electricity-theft monitoring system and method which uses a microwave body sensor to conduct the real time detection to activities of people around an electricity meter box. Based on the method of the image shooting of a camera, the monitoring system provided by the invention uses a camera to continuously shoot and store the images of the activities of people around the electricity meter box and can real time transmit alarming information, electricity meter data and image information to a motoring server through GPRS network; and then, the motoring server can send the received alarming information to the mobile phones or computers of users in time, and users can read the alarming information from the mobile phones or computers of users in distance. Besides the functions of remote electricity meter data acquiring, the anti-electricity-theft monitoring and real-time alarming, the monitoring system also can transmit field images in time and obtain images stored by field equipment later for providing convincible proofs during handling the electricity theft of illegal users.

The invention discloses an intelligent guarding method based on radar and video integration. The intelligent guarding method comprises the steps that 1) radar monitors and video monitors are distributed in a specified monitoring area; 2) the radar monitors performs real-time monitoring, and when entering of an invasion target is monitored, the three-dimensional position coordinates of the monitored invasion target are outputted and early warning information is emitted, and the video monitored are controlled and started to acquire current synchronous images to be outputted simultaneously; 3) the three-dimensional position coordinates monitored by the radar monitors are mapped into corresponding position coordinates in the synchronous images so that radar detection coordinates are obtained; and 4) the invasion target is identified in the synchronous images according to the radar detection coordinates, and whether the invasion target is a target required to be alarmed is judged according to the image data of the identified invasion target so as to confirm alarm information. The intelligent guarding method based on radar and video integration has advantages of being simple in realization method so that intelligent identification and alarm of the invasion target can be realized and alarm accuracy rate is high.

The invention discloses a smog detection method based on video analysis. The smog detection method based on video analysis comprises steps of video image data acquisition, video image preprocessing, forward target extraction, flame static characteristic detection, flame dynamic characteristic detection, flame alarm decision, smog static characteristic detection, smog dynamic characteristic detection and smog alarm decision. The method is advantaged in that smog and flame are simultaneously detected in a combined static and dynamic characteristic mode, smog detection accuracy and stability are improved, operation complexity is further reduced, hardware realization is convenient, and the method can be applied to relatively complex environments.

The invention provides a method for detecting the obstruction pressure of an infusion pump. After an infusion pipeline is arranged on the infusion pump, the method comprises the following steps of: detecting an initial pressure value P0 of the infusion pipeline at first time, wherein the first time is the time of starting the infusion pump; detecting a real-time pressure value Pt of the infusion pipeline at second time, wherein the second time is any time after the infusion pump is started; and calculating a differential value of the real-time pressure value Pt and the initial pressure value P0, and outputting an alarm signal when the differential value is more than or equal to a preset pressure alarm threshold value M. The method can be used for disposable infusion sets made of different materials, and is high in alarm accuracy rate.

The invention provides a train early-warning system and a train early-warning method. The train early-warning system comprises foreign matter detection sensors, a foreign matter detection processing unit, an outlook server and intelligent terminals, wherein the sensors are installed along a railway or on a preset segment to collect environmental information, and the processing unit receives the environmental information collected by the sensors and judges whether foreign matter exists or nor; when no foreign matter exists, the environmental information is sent to the outlook server, and otherwise, a detection result is generated, the foreign matter is marked so that a foreign matter alarm can be formed and sent to the outlook server; the outlook server receives location and motion information, manual alarm information and active request information from some intelligent terminal, sets an alarm range and an outlook range related to the location, determines the corresponding sensor and sends the environmental information within the outlook range or the foreign matter alarm result within the alarm range and the locations of the other intelligent terminals to the intelligent terminal; the intelligent terminal generates information of the locations of the intelligent terminal and sends the information to the outlook server; when no foreign matter is detected within the alarm range, the intelligent terminal receives and displays the environmental information within the outlook range, and otherwise the intelligent terminal receives the environmental information within the outlook range and gives out an alarm.

The invention provides a method and system for allowing a parking sensor to resist interference. The method for allowing the parking senor to resist interference includes the steps of detecting interference waves, namely, counting pulses with set strength interference at an MCU back wave signal end in a set period of time before an obstacle is detected by an ultrasonic transducer, and judging whether the interference is strong or not according to the number of counted interference pulses; detecting the obstacle, namely, prolonging random delay so as to distinguish the obstacle from the interference waves when the ultrasonic transducer detects the obstacle. The method and system for allowing the parking sensor to resist interference have the advantages that interference signals and the obstacle are effectively distinguished, and therefore an alarm is accurately given, and the alarm accuracy is improved.

The invention discloses flexible micro-service monitoring framework architecture. On the basis of combination of advantages of the traditional distributed system monitoring technology and the distributed system tracking technology based on the service invoking chain, innovation points of a configuration management center, a micro-service instance client agent, and a reusable monitoring alarm template and the like are provided, so that defects of monitoring information incompleteness, low flexibility, and low extensibility and the like are overcome. With a non-intrusive service mode, the customization capability and reliability of the collection are improved. On the basis of a warning processing strategy issued by configuration and a reusable alarm policy template, the customized extensionprocessing capacity of warning is enhanced. According to a cluster analysis algorithm, statistic analysis is carried out on real-time and historical data and intelligent alarm and determination are carried out, so that the warning accuracy is improved. The flexible micro-service monitoring framework architecture has an important practical significance in ensuring the safe and stable operation of power system application services.

The invention relates to an alarming device, in particular relates to a system for nursing infant sleep at night. The system for nursing the infant sleep at night comprises the alarming device and a signal processing module, wherein the signal processing module is provided with a signal input end and a signal output end; the signal output end is connected with the alarming device; the signal input end is connected with a non-contact infrared temperature sensor and a photosensitive sensor. The non-contact infrared temperature sensor ensures that the system disclosed by the invention does not directly contact with the infant to guarantee use safety. If the infant kicks the quilt when sleeping, the system for nursing the infant sleep at night makes a prompting sound. The system for nursing the infant sleep at night is convenient and safe to use and has the advantages of high accuracy on alarming the behaviour of kicking the quilt by infants and the like.

The embodiment of the invention provides a method and a system for realizing composite entire optical fiber localizable perimeter alarm. An auxiliary optical fiber micro vibration sensor is arranged on a monitor optical cable provided with a precise positioning sensor; whether a disturbance signal exists is judged by the precise positioning sensor and the auxiliary optical fiber micro vibration sensor together, namely, whether people invade is judged; if the judgment is confirmed, an alarming signal is sent out, thus effectively improving the anti-interference capacity of the system, lowering effect caused by outside environmental factors like temperature and stress, and the like, reducing false alert rate and missing report rate, and improving the alarming precision of the monitoring system.

The invention discloses a performance collection agent for large internet host computer. Wherein, obtaining basic performance information and statistic data from host computer information acquisition module; providing standard SNMP interface to response acquisition request and provide real time data; TRAP alarm-generating module and MIB table update condition set and real time detect data to active send alarm contained SNMP TRAP information if performance index over alarm threshold. This invention fits to host computer with Linux, Solaris and other like-Unix OS.

The invention discloses a dynamic setting method of a differential threshold for online monitoring of transformers. The method includes the following steps: classifying and identifying the historicaldata of a transformer monitored in different operating environments and seasons; preprocessing the classified and identified historical data, and removing abnormal data from the historical data; usinga method based on K-Means clustering to dynamically calculate the discrimination threshold of the transformer based on the historical data with abnormal data removed; and based on a Spark distributedparallel computing framework, constructing a transformer equipment comprehensive warning model of threshold alarm based on the discrimination threshold and trend analysis, so as to differentially monitor the discrimination threshold of the transformer. The calculation time of the dynamic threshold is greatly shortened while the accuracy of alarm is improved.

An antitheft alarm system for the oil or gas delivery pipeline is composed of a central station and several terminal stations. Said central station consists of display screen, computer, sound-light alarm, interface, radio data transmission module, printer, UPS, and stabilized DC power supply. Said terminal station is composed of audio sensor, amplifier, signal processor, A / D converter, single-chip computer, interface, radio data transmission module, solar battery, etc. It can sense the theft in time to generate audio-video alarm signals, preventing pipeline from being damaged.

The invention relates to an optical fiber sensing natural gas pipeline leakage event identification method and an optical fiber sensing natural gas pipeline leakage event identification device, which relates to the field of a mechanical vibration measurement technology, an impact measurement technology and a pipeline system technology. A time domain feature (Pt) of a pipeline normal operation and leakage status signal, a frequency-domain characterization (Pf) and a noise characteristic (Pn) of an existing pipeline transmission signal and the waveshape recognition are comprehensively analyzed, a leakage confidence coefficient function model is built as follows: R=a1Pt+a2Pf-a3Pn, the leakage of a picked up vibration wave signal is evaluated to judge whether leakage happens to the pipeline or not, and different arithmetical parameters a1, a2 and a3 are arranged to regulate the confidence coefficient module according to the characteristics of the existing pipeline; the time domain, the frequency domain and wave form estimation performed on the leakage signal is that the signal can be accurately identified to be the leakage event according to a time-varying enveloping character and abruptness of the leakage signal and a center frequency distribution character of the stable leakage event signal, based on the feature classification of a stimulated leakage event. The optical fiber sensing natural gas pipeline leakage identification method and the optical fiber sensing natural gas pipeline leakage identification device provided by the invention can monitor the signal abnormalities in time and give an alarm with high accuracy at the primary state of the leakage.

The invention provides an alarm generation method and system. The alarm generation method is carried out in a cloud computing environment on the basis of a big data analysis technology. The method includes the following steps that: the operation data of a monitoring object and the operation data of at least one association object are collected on the basis of a predetermined collection policy, wherein the association objects are objects directly or indirectly affecting the operation state of the monitoring object; the pre-stored historical operation data of the monitoring object and the at least one association object are acquired on the basis of a predetermined data analysis policy, and data analysis is performed on the collected operation data of the monitoring object, the operation dataof the at least one association object and the acquired historical operation data of the monitoring object and the at least one association object, so that the performance trend and state change of the monitored object is obtained; and intelligent alarm analysis decision is performed on the performance trend and state change of the monitored object on the basis of an alarm policy, whether an alarm is to be generated is determined.

The invention discloses a gas pipeline leakage point detection device and a detection method, and relates to the field of gas pipeline detection. The gas pipeline leakage point detection device comprises a sensor module, a data transmission module, a fixed IP line, a server, a gas pipeline leakage alarm management system and a management computer. The sensor module acquires flow data, pressure data and infrasonic wave data of a gas pipeline. The data transmission module is connected with the sensor module. The fixed IP line is connected with the data transmission module. The server is connected with the fixed IP line, and the flow data, the pressure data and the infrasonic wave data are uploaded to the server through the data transmission module and the fixed IP line. The gas pipeline leakage alarm management system is installed in the server, receives, calculates and analyzes the flow data, the pressure data and the infrasonic wave data, shows the gas running state and gives an alarm.The management computer is connected with the server and used for managing the gas pipeline leakage alarm management system. By the adoption of the gas pipeline leakage point detection device and thedetection method, gas feature graphs of different road sections are provided, the number of influence factors such as the environment is reduced, the false alarm rate of gas alarms is reduced, and the detection accuracy and the alarm efficiency are high.

The embodiment of the invention relates to a multi-parameter monitoring data analysis method and a multi-parameter monitor. The method includes the steps that sign monitoring data collection is performed on a monitored object to obtain sign monitoring data of the monitored object; wave group feature recognition is performed on electrocardiogram data in the sign monitoring data to obtain feature signals of the electrocardiogram data, heart beat classification is performed on the electrocardiogram data according to the feature signals, heart beat classification information is obtained in combination with electrocardiogram basic law reference data, electrocardiogram event data is generated, corresponding electrocardiogram event information is determined, and whether or not the electrocardiogram event information is preset electrocardiogram abnormality event information is determined; if the electrocardiogram event information is preset electrocardiogram abnormality event information, first alarm information is output; whether or not abnormal data exceeding a corresponding set threshold value exists in one or more of pulse data, blood pressure data, respiration data, blood oxygen saturation data and body temperature data is determined, and other abnormality event information is generated according to the abnormal data; when the abnormal data exceeds the set threshold value, secondalarm information is output.

The invention belongs to the field of fire control, and discloses a smoke sensor management method. The smoke sensor management method comprises the steps of when a smoke sensor alarms, acquiring an alarm threshold value of a current smoke concentration of the smoke sensor as well as current environmental parameters of the smoke sensor; and according to the environmental parameters, finding a recommended threshold value of an alarm for the current smoke concentration of the smoke sensor, and adjusting the recommended threshold value as a current alarm threshold value of the smoke sensor. The recommended threshold value is adjusted as the current alarm threshold value of the smoke sensor, so that the smoke sensor can adaptively adjust an alarm threshold value according to different scene parameters; not only can the alarm precision of the smoke sensor be improved, but the number of reset times due to a false alarm can also be reduced; and the convenience in maintenance work is greatly improved.

The invention discloses a video-based moving object intrusion alarm method and relates to the field of security monitoring. The method comprises steps as follows: continuously acquiring indoor real-time monitoring images and inputting the images into scene mode computational algorithms to calculate the scene complexity; when the scene complexity is larger than the threshold, regarding the scenes as complex scenes, and otherwise, regarding the scenes as simple scenes; adopting different background parameter estimation algorithms for different scene modes respectively, and then extracting previous scene features by using background parameters; calculating the previous scene feature complexity, when the previous scene feature complexity is larger than the threshold, sending alarm information when judging moving objects intrude into a room, otherwise, updating the image background parameters, and continuously repeating the steps. According to the method, indoor monitoring scenes are divided into the simple scenes and the complex scenes, different detection algorithms are adopted for the different scenes, the adaptability of the alarm method to the different indoor scenes is improved, and the probability of false alarms of monitoring is decreased.

The invention discloses an alarm method based on position area division and a server. The method includes: acquiring alarm information reported on a terminal, wherein the information includes position coordinates of corresponding alarm points; extracting the alarm information within a set time period, and performing aggregation division on the position coordinates included in the alarm information to acquire aggregation areas; making statistics on number of the alarm information corresponding to the aggregation areas and setting an alarm notice according to the number of the alarm information. The areas of the alarm points can be divided automatically and accurately, accuracy in alarming is improved, and alarm cost is saved.

The invention discloses a continuous blood glucose monitoring device comprising a parameter estimation function filtering module. The continuous blood glucose monitoring device comprising the parameter estimation function filtering module can filter continuous blood glucose monitored signals to achieve accurate hyperglycemia and hypoglycemia alarming. Under the conditions of differences of different patients and different sensors, the noise levels of corresponding blood glucose monitored signals are different and accordingly need different filter parameters for filtering treatment. Therefore, according to the continuous blood glucose monitoring device comprising the parameter estimation function filtering module, the filter parameters can be adjusted according to the different patients and the different sensors. A filter parameter estimation method of the device can timely and accurately estimate the filter parameters required for Kalman filtering, so that better filtering treatment on the blood glucose signals can be achieved, and a solid foundation for improving the accuracy of real-time hyperglycemia and hypoglycemia alarming can be laid, and high significance can be obtained.

A low-load bladder urine-volume real-time monitoring and automatic alarming method comprises the following steps of (1) closely attaching a plurality of test electrodes onto a tested part of a patient and measuring an electric impedance value of a bladder in real time through a biological electric impedance measuring device according to a biological impedance technology; (2) selecting appropriate parameters through a digital filter algorithm, removing an interference signal and improving the signal-to-noise ratio of the electric impedance; updating the maximal electric impedance value in real time, and calculating an impedance threshold value and a variation rate of the impedance threshold value; and (3) establishing an expert diagnosis system through medical knowledge and clinical test experience, fuzzing the impedance threshold value and the variation rate of the threshold value, and establishing a fuzzy rule; and realizing the automatic urine discharging alarm according to the judgment of the fuzzy rule so as to remind the patient to urinate in time or notify the medical personnel. Due to the adoption of the method, the urine volume of the bladder can be accurately and dynamically predicted in real time, an alarm for urination can be issued, the patient is reminded of urinating in real time or the state of an illness can be remotely monitored through a wireless network, more safety and convenience in operation can be realized, and the interference resistance is strong.

The invention discloses a water traffic supervision and early warning system and method based on a machine learning technology. According to the system, big data and machine learning technologies aremainly utilized, historical ship track data are trained according to ship types and regions to obtain a ship navigation rule model which is more consistent with the actual navigation condition of theship, abnormal behaviors of the ships in the whole sea area in the administrative region are monitored in real time by utilizing the model, and finally, the abnormal behaviors are displayed to water traffic supervisors through an electronic nautical chart. Compared with a system for water traffic safety supervision and early warning based on rule setting, the system has the advantages of being higher in intelligent degree, complete in supervision water region coverage rate and low in early warning false alarm rate.

The invention relates to a fatigue driving monitoring system and a method thereof. The fatigue driving monitoring system comprises: a vehicle detection device which is used for monitoring the fatigue driving and a monitoring center which is used for discriminating the fatigue driving for a second time. The vehicle detection device further comprises: an image acquisition module, a master control module which is used for processing positioning pictures collected by the image acquisition module and discriminating the fatigue driving, a warning module and a communication module which is used for performing communication connections with the monitoring center. A first time discrimination for the fatigue driving can be performed by the master control module, and according to the discrimination results, a warning is sent out and simultaneously the positioning pictures are sent to the monitoring center for the second time discrimination. And then, a customer service representative of the monitoring center can remind the driver through the communication module. Double discriminations and a warning mode are adopted in the fatigue driving monitoring method disclosed in the invention. An inaccurate alarm probability can be reduced, the monitoring system is simple and costs are low.

The invention provides a transmission line mountain fire protection system comprising a background power GIS monitoring center and a front end system connected thereto through a transmission network.The front end system comprises an infrared video detection system for sending alarm information including location information and video data, an Internet of Things sensor for monitoring monitory point meteorological information including wind power, wind direction, temperature and humidity and smoke, and a Doppler radar for determining mountain fire information and fire location. The background power GIS monitoring center is used for determining, according to detection results, whether to start the Doppler radar to determine the mountain fire information and the fire location, analyzing and processing the received information, and then marking and making a prompt at the corresponding position of a power transmission line map. The transmission line mountain fire protection system is provided with the front end system with an integrated monitoring function. By combination with a power GIS, visual management of forest resource information can be achieved.

The invention relates to the field of security and particularly relates to an active security entrance guard control method and an active security entrance guard control system. The control system comprises a detection module, an alarming device and a relay connected with the detection module and the alarming device, wherein the detection module comprises a radar and a judgment device connected with the radar and is connected with a power supply; the radar is used for detecting an outdoor condition within a detection range in real time; the judgment device can instantly perform logic judgment if someone or something stands in the detection range; the judgment device can send an electric signal to the input end of the relay if a judgment result is not gate; the relay is used for closing and switching on a circuit to supply power to the alarming device after receiving the electric signal sent by the detection module; the alarming device is used for sounding an alarm after a power supply is switched on. The system can actively detect the outdoor condition, make a judgment on a person having some attempts or a functional object, actively sound the alarm to inform persons in a room and implement monitoring on the outdoor environment, so that the security level is increased; the alarming accuracy is high; the control system is difficult to crack and is low in cost.