31results about How to "Real-time detection results" patented technology

The invention provides an abnormal behavior detection method and system based on a human skeleton, and a medium, and the method comprises the steps: S1, building a training video sample database, andbuilding an original video database with a preset frame length according to a public violent behavior database; s2, according to the obtained original video database, extracting human body skeletons in all video samples in the original database by utilizing an open-source attitude estimation algorithm OpenPose to obtain a skeleton video database; s3, deframing all the obtained video samples in theskeleton video database into a skeleton picture stream by using an FFmpeg tool to obtain a skeleton picture stream; S4, sequentially inputting the obtained skeleton picture streams into a 3D-DenseNetnetwork model for training, so as to obtain a trained 3D-DenseNet network model. The human skeleton and the 3D-DenseNet are used for abnormal behavior detection for the first time, the detection accuracy is high, the robustness is high, and the detection result can be output and updated in real time.

The invention discloses a system for visually identifying and analyzing as well as identifying drug allergy. The system comprises an optical and digital image acquiring device, a digital image processing device and a drug allergy identifying and analyzing device, wherein the optical and digital image acquiring device is used for providing a light source and acquiring the digital image, and sending the digital image to the digital image processing device; a polarizer and an analyzer in the optical and digital image acquiring device are used for strengthening the digital image of the detected object, and the cubic aberration of the digital image is corrected through a lens; the digital image processing device is used for receiving the digital image, capturing motion, performing filtration and feature enhancement on the image after sensing a target code, determining a target specimen type according to target specimen characteristics and bar code information after obtaining the target specimen image, selecting a detecting method to obtain detected results, processing and sending the detected results to the drug allergy identifying and analyzing device; the drug allergy identifying and analyzing device is used for identifying drug allergy by combining a mode identifying algorithm with preset CLIS (cost-of-living index) identifying standards in the drug allergy identifying and analyzing device, and obtaining the identifying conclusions.

The invention relates to an attenuation total reflection surface enhanced infrared optical device for DNA identification and hybridization dynamics analysis. The attenuation total reflection surface enhanced infrared optical device comprises an attenuation total reflection surface enhanced infrared optical window in which an island-shaped nanometer gold film is plated on the surface of a silicon hemisphere, an optical table base, a fixed support region, an infrared light spectrum pool, a PDMS (Polydimethylsiloxane) sealing ring and the like, wherein the silicon hemisphere plated with the gold island-shaped film is placed on the optical table base, a gold film surface of the optical window is toward the infrared light spectrum pool, and the middle of the optical window is sealed by the PDMS sealing ring; the light spectrum pool, the PDMS sealing ring and the silicon hemisphere optical window are screwed-in and fixed through an external thread of the fixed support and an internal thread of an upper support of the optical table base so as to form the surface enhanced infrared spectrometer for DNA analysis. The testing device, provided by the invention, has the advantages of simple structure, convenience for operation and small required sample amount, and can be stably used for a long time and convenient for real-time on-line detection of infrared spectrum signals at a waveband of 1100cm<-1> to 4000cm<-1>, and high-sensitivity analysis of DNA molecules, so that DNA identification and hybridization mechanisms and kinetics research can be realized.

The invention relates to a gas concentration detection device and a gas concentration detection method. The gas concentration detection device comprises a vacuum detection cavity, a gas concentrationdetection sensor, a vacuum sampling element and a detection analyzer, wherein the sampling element is connected with the detection cavity; the detection cavity is connected with an outer sealed cavityused for accommodating to-be-detected gas; the gas concentration detection sensor is arranged in the detection cavity; the detection analyzer is connected with the gas concentration detection sensorand the sampling element. According to the gas concentration detection device, the concentration of the gas is detected by the gas concentration detection sensor and the vacuum detection cavity, so that an accurate detection result can be obtained; gas in the sealed cavity is sampled by the sampling element, and a greater accurate detection result is obtained the analysis of the detection analyzer; in addition, whether the sensor goes wrong or not is judged by comparing the two concentration detection results by the detection analyzer, so that wrong concentration information due to the failureof the sensor is avoided. Therefore, the detection results are more accurate.

The invention discloses a product surface scratch detecting method based on machine vision, and relates to the technical field of machine vision defect detection. The product surface scratch detectingmethod specifically comprises the steps that signals are received, and image information is collected; texture inhibition is conducted on images through a convolutional neural network, nonclassical feeling wild inhibition is conducted on the collected images first, then the inhibited images are input into the trained convolutional neural network to be subjected to texture estimation, and at lastthe images are subjected to dynamic iteration inhibition to initially obtain scratch images; lagged double-threshold scratch connection is conducted, breakage scratches in a small range are connected,a high threshold and a low threshold are adopted to conduct binaryzation on the images, and the edges of the images are connected with the high threshold as the basis and the low threshold as the compensation; and the scratch images are thinned. According to the product surface scratch detecting method, mobile phone partition images are quickly collected in real time and are subjected to a seriesof treatment, so that surface scratches are efficiently and accurately detected, and detecting results are displayed in real time.

The invention discloses an Internet of Things function detection device for an Internet of Things household appliance. The material net detector comprises a material net detector body, a bottom plate and a central processing system, protective plates are fixedly connected to the two sides of the top of the bottom plate; a fixing plate is fixedly connected between the opposite sides of the protection plates; the top of the fixing plate is fixedly connected with a heat conducting plate; the top of the heat conduction plate is fixedly connected with the bottom of the Internet of Things detector body, the bottom of the fixing plate is fixedly connected with a fixing frame, the bottom of the fixing frame is fixedly connected with cooling fins, and the bottom of the inner wall of the fixing frame is fixedly connected with a refrigerator. According to the Internet of Things function detection device for the Internet of Things household electrical appliance, heat generated by the Internet of Things detector during working can be dissipated in time, meanwhile, certain resources are saved through cyclic utilization of heat conduction oil, certain economic cost is reduced, and follow-up household electrical appliance detection work can be normally carried out.

The invention discloses a dam body flow path detection robot, relates to the technical field of detection and aims at solving the technical problems of large quantity of detection data which needs tobe processed, relatively low detection efficiency and inconvenience in detection in the prior art. The dam body flow path detection robot comprises a vehicle frame, walking wheels, walking drive devices, a laser generation device, a camera, ultrasonic sensors, a main controller, a first assistance processor, a second assistance processor and a mobile phone; and the main controller is used for at least performing compression processing on a part which is irrelevant to a region, generating bending or breaking with a laser line, in an image, judging whether a dam body is damaged or not and / or thedamage degree according the image after compression processing and sending a judgment result to the mobile phone, and the mobile phone displays whether the dam body is damaged or not and / or the damage degree. The dam body flow path detection robot provided by the invention is used for reducing the quantity of the detection data which needs to be processed and improving the detection efficiency and the convenience of detection.

The invention discloses a wall-across human body motion detection method based on short-time Fourier transform. The method comprises the following steps: firstly, receiving a signal waveform, which is pre-coded by virtue of a transmitter, by virtue of a receiver; then, segmenting the received signal into various sections of signals, and conducting short-time Fourier transform on each section of the signal so as to obtain a transformation matrix; then, computing a variance vector of the transformation matrix; and finally, by computing the range of the variance vector and comparing the computed range with a threshold, detecting whether human body motion occurs behind a wall or not. The detection method disclosed by the invention can solve the problem on weak target detection in a strong noise environment through the short-time Fourier transform, and the detection method can effectively detect whether the human body motion occurs behind the wall or not, so that the accuracy of detecting the human body motion is greatly improved.

The invention discloses a rapid microorganism detecting device based on mie scattering. The rapid microorganism detecting device comprises a laser device, an optical focusing system, a detector array frame, a sample pool and photoelectric probes. Laser beams emitted by the laser device form parallel light after being aligned and are then focused on and irradiate microorganism samples in the sample pool through the optical focusing system, microorganisms emit scattered light to space after being irradiated by lasers, the scattered light is received by the photoelectric probes around the sample pool, received photoelectric signals are analyzed and calculated through a computer on the basis of the mie scattering theory, and the current form of the microorganisms can be detected in real time. By means of the rapid microorganism detecting device, the microorganisms are rapidly detected in real time; according to the optical scattering principle, the detection speed and accuracy are increased, signals are collected, processed and analyzed in real time in the collection process, and wide application prospects are achieved.

The invention discloses full-automatic aluminum-plastic bubble cap detection equipment, which comprises a first conveying mechanism; a material blocking mechanism which is arranged at the discharging end of the first conveying mechanism; a first detection mechanism which is arranged above the first conveying mechanism; a second conveying mechanism which is arranged behind the first conveying mechanism; an overturning mechanism which is used for overturning aluminum-plastic bubble caps located at the material blocking mechanism on the first conveying mechanism and then placing the aluminum-plastic bubble caps on the second conveying mechanism; a second detection mechanism which is arranged above the second conveying mechanism; and a sorting mechanism which is arranged at the discharging end of the second conveying mechanism. According to the full-automatic aluminum-plastic bubble cap detection equipment provided by the invention, efficient, rapid and automatic detection of the front and back surfaces of the aluminum-plastic bubble caps and fillers in the bubble caps is realized; the full-automatic aluminum-plastic bubble cap detection equipment greatly reduces the false detection rate of subjective manual visual detection, guarantees the correctness and reliability of a detection result, accelerates the detection efficiency, and effectively reduces the labor cost of detection; the equipment is simple in structure, convenient to install and debug, capable of turning over and adjusting speed and accurate in resetting; the shooting accuracy is high; and the time cost is greatly saved.

The invention provides an online detection method for an oil pipe field. The method comprises the following steps: (1) equipment installation; (2) parameter setting; (3) instrument calibration; (4) simulation test; (5) oil pipe detection; (6) field evaluation; (7) field identification; (8) equipment detachment; and (9) detection report. An oil pipe in a well is detected on line by using a well mouth oil pipe detection instrument during drilling. The method is low in operation cost, detection results are obtained in real time, time apart of drilling is not occupied, drilling in an operation process is not different from conventional drilling, and additional operation risk is not added. The operation cost of oil pipe detection is reduced, and the construction safety and aging are enhanced.

The invention discloses a method for returning to the position of a safety helmet and recognizing the safety helmet based on a face detection frame. The method comprises: establishing a multivariate machine learning model which is based on the center coordinate, width and height information of the face frame and is related to the same kind of position information of the safety helmet; and learningto obtain an influence coefficient of the face frame and the safety helmet according to the primary face frame information and a related learning formula, and substituting the influence coefficient and the secondary face frame information into a linear correlation equation to solve to obtain a candidate position of the safety helmet. The problem that automatic identification of the safety helmetis very difficult due to challenge problems such as shielding, small size, few data sets, small object identification, safety helmet carrier identification and the like of the safety helmet in an actual scene is solved. And meanwhile, compared with the human face, the pedestrian has large shielding and flexible changes, the detection is difficult when crowds are dense, and evidence cannot be obtained without the human face. According to the invention, face detection in a multi-face monitoring scene is realized, whether a crowd wears the safety helmet is judged, and video frames are stored as evidences to give an alarm at the same time.

The invention belongs to the technical field of aflatoxin determination methods, and provides a method for determining aflatoxin B1 based on immunomagnetic beads. The determination method comprises the steps of activating the magnetic beads, modifying the magnetic beads with antigens, preparing an immunomagnetic bead system, carrying out flow cytometry detection and the like. According to the method for determining aflatoxin B1 based on immunomagnetic beads, the pretreatment method is conventional and concise, is clear in operation, high in instrument automation degree and sensitive and accurate in analysis, a large number of detection results can be rapidly obtained in real time on the basis of a flow cytometer, the detection limit of the concentration of aflatoxin B1 is low, and the detection limit can reach 0.2034-0.3107 microgram / L.

The invention discloses an online training method for realizing target detection on unmanned equipment, and solves the problems that target detection and network training cannot be performed in parallel in real time and the detection result is inaccurate in the prior art. The method comprises the following implementation steps: respectively designing a target detection network according to the characteristics of a panoramic video, a visible light video and an infrared video, and carrying out preliminary training; Judging whether target related images and information exist in the information transmitted into the unmanned equipment or not; Selecting a corresponding image library according to the new target image and the information, and expanding the image library; And carrying out online training on each target detection network, finally obtaining new network structure parameters, and replacing a previous network parameter file. According to the invention, an on-line training mode is adopted, target detection and network training can be performed in parallel in real time, the target detection precision is higher, and the method can be used for unmanned equipment in an operation state.

The invention discloses a partition human body motion detection method based on continuous wavelet transformation. The partition human body motion detection method is characterized in that a receiver is used to receive a signal waveform after precoding of a transmitter; the received signal can be segmented into signal segments, and the continuous wavelet transformation of each signal segment can be carried out to acquire a transformation matrix, and then the variance vectors of the transformation matrix can be calculated; and at last, by calculating the maximum value of the variance vectors, and the maximum value can be compared with the threshold value to detect whether the human body motion occurs behind the wall. By adopting the continuous wavelet transformation, the weak target detection problem in the strong noise environment can be solved, and whether the human body motion occurs behind the wall can be effectively detected, and therefore the accuracy of the partition human body motion detection can be greatly improved.

The invention discloses a real-time water quality monitoring system and method based on the Internet of things. The method is applied to information control center equipment, a monitoring device and unmanned equipment, wherein the information control center equipment, the monitoring device and the unmanned equipment are in communication connection. The method is characterized in that a first instruction is sent by the information control center equipment to the unmanned equipment, the monitoring device is clamped by the unmanned equipment, and the monitoring device is moved to a first waters;a second instruction is sent by the information control center equipment to the monitoring device, the water quality of the first waters is detected by the monitoring device, and first water quality data corresponding to the first waters is generated; the first water quality data is sent by the monitoring device to the information control center equipment, and the first water quality data is received and processed by the information control center equipment.

The invention relates to an attenuation total reflection surface enhanced infrared optical device for DNA identification and hybridization dynamics analysis. The attenuation total reflection surface enhanced infrared optical device comprises an attenuation total reflection surface enhanced infrared optical window in which an island-shaped nanometer gold film is plated on the surface of a silicon hemisphere, an optical table base, a fixed support region, an infrared light spectrum pool, a PDMS (Polydimethylsiloxane) sealing ring and the like, wherein the silicon hemisphere plated with the gold island-shaped film is placed on the optical table base, a gold film surface of the optical window is toward the infrared light spectrum pool, and the middle of the optical window is sealed by the PDMS sealing ring; the light spectrum pool, the PDMS sealing ring and the silicon hemisphere optical window are screwed-in and fixed through an external thread of the fixed support and an internal thread of an upper support of the optical table base so as to form the surface enhanced infrared spectrometer for DNA analysis. The testing device, provided by the invention, has the advantages of simple structure, convenience for operation and small required sample amount, and can be stably used for a long time and convenient for real-time on-line detection of infrared spectrum signals at a waveband of 1100cm<-1> to 4000cm<-1>, and high-sensitivity analysis of DNA molecules, so that DNA identification and hybridization mechanisms and kinetics research can be realized.

The invention relates to a gas concentration detection device and a gas concentration detection method, comprising a vacuum detection chamber, a gas concentration detection sensor, a vacuum sampling element and a detection analyzer; the sampling element is connected to the detection chamber, and the detection chamber is connected to an external storage The sealed chamber of the gas to be detected is connected, the gas concentration detection sensor is arranged in the detection chamber, and the detection analyzer is respectively connected with the gas concentration detection sensor and the sampling element. The above-mentioned gas concentration detection device detects the gas concentration through the gas concentration detection sensor and the vacuum detection chamber, and can obtain real-time and accurate detection results. The gas in the sealed chamber is sampled through the sampling element, and analyzed by the detection analyzer to obtain More accurate detection results, and by comparing the two concentration detection results with the detection analyzer, it is judged whether the sensor is faulty, thereby avoiding the wrong concentration information obtained due to sensor faults, and making the detection results more accurate.

The invention provides an algae detection system based on a planar electrode array. The algae detection system comprises a multi-electrode sensor array and a micro-pipeline, the multi-electrode sensor array comprises a plurality of groups of electrodes, and each group of electrodes consists of interdigital electrodes with unequal widths and intervals; the interdigital electrodes are arranged symmetrically and asymmetrically, are packaged in the water flow channel and are used for measuring the capacitance of a water body; the micro-pipeline comprises a water inlet, a water flow channel and a water outlet; algae water enters the water flow channel through the water inlet, the number of algae is detected through the multi-electrode sensor array, and finally the algae water flows out through the water outlet. The beneficial effects of the algae detection system are that the algae detection system can provide a real-time detection result, also can achieve the miniaturization and low power consumption of the sensor, reduce the manufacturing cost, and effectively supplement a conventional detection means.

The present invention provides a human skeleton-based abnormal behavior detection method, system and medium, including: step S1: establish a training video sample database, and construct an original video database with a preset frame length according to the public violent behavior database; step S2: according to The obtained original video database uses the open source attitude estimation algorithm OpenPose to extract the human skeleton in all video samples in the original database to obtain the skeleton video database; Step S3: Utilize the FFmpeg tool to deframe all the video samples in the obtained skeleton video database into Skeleton image stream to obtain the skeleton image stream; step S4: Input the obtained skeleton image stream into the 3D-DenseNet network model for training in sequence, and obtain the trained 3D-DenseNet network model. The present invention uses the human skeleton and 3D-DenseNet to detect abnormal behaviors for the first time, with high detection accuracy, strong robustness, real-time output and updated detection results.

The invention discloses a harmful gas concentration detection device and a detection method. The harmful gas concentration detection device comprises a detection trolley and a control device; the detection trolley is composed of a base, a multi-section telescopic rod and an electric push rod; the telescopic end of the multi-section telescopic rod is fixedly provided with a stepping motor, and the output end of the stepping motor is fixedly connected with a first wireless signal transmission device; according to the gas concentration detection device, the concentration of gas is detected through the gas concentration detection sensor and the vacuum detection cavity, and a real-time and accurate detection result can be obtained; the gas in the sealed cavity is sampled through the sampling element, and a more accurate detection result is obtained through analysis of the detection analyzer; and the detection analyzer is used for comparing two concentration detection results to judge whether the sensor fails or not, so that the situation that wrong concentration information is obtained due to the failure of the sensor is avoided, and the detection result is more accurate.

The invention discloses an improved random forest model for coronary heart disease pre-diagnosis and a pre-diagnosis system thereof, which are characterized in that nearly hundreds of indexes used in clinical examination of coronary heart disease patients are screened based on feature selection in combination with a statistical machine learning algorithm, a model with high prediction precision is established, and the model can be used as a basis for whether coronary angiography is carried out or not. The risk that a patient suffers from the coronary heart disease at present is calculated by combining clinical examination indexes, image detection results and electronic medical record information of the patient, and an evaluation basis is provided for subsequent definite diagnosis.

The invention discloses a real-time water quality monitoring system and method based on the Internet of Things. The method is applied to information control center equipment, monitoring devices and unmanned equipment. The information control center equipment, the monitoring device and the unmanned equipment The devices are all connected by communication, including: the information control center device sends a first instruction to the unmanned device, and the unmanned device clamps the monitoring device and moves the monitoring device to the first water area; The information control center equipment sends a second instruction to the monitoring device, and the monitoring device detects the water quality of the first water area and generates first water quality data corresponding to the water quality of the first water area; the monitoring device sends the first water quality data to the information A control center device, the information control center device receives and processes the first water quality data.

The invention discloses rapid microorganism detection equipment based on Mie scattering and a spatial light modulator. The equipment comprises a laser, an optical system, a detector spherical array frame, a cuvette and photoelectric detectors, wherein laser beam emitted by the laser forms parallel light after being collimated and is converged by the optical system and irradiated to a microorganism sample in the cuvette, a microorganism emits scattered light to the space after irradiated by the laser light, the scattered light is received by photoelectric detectors surrounding the sample pool, a computer performs analysis and calculation on received optoelectronic signals on the basis of the Mie scattering theory, and the form of the current microorganism can be detected in real time. Microorganisms are rapidly detected in real time by the device, the detection speed and accuracy are improved by means of the optical scattering principle, and signals are acquired, processed and analyzed in real time in the acquisition process.

The invention provides an online detection method for an oil pipe field. The method comprises the following steps: (1) equipment installation; (2) parameter setting; (3) instrument calibration; (4) simulation test; (5) oil pipe detection; (6) field evaluation; (7) field identification; (8) equipment detachment; and (9) detection report. An oil pipe in a well is detected on line by using a well mouth oil pipe detection instrument during drilling. The method is low in operation cost, detection results are obtained in real time, time apart of drilling is not occupied, drilling in an operation process is not different from conventional drilling, and additional operation risk is not added. The operation cost of oil pipe detection is reduced, and the construction safety and aging are enhanced.

The invention discloses a partition human body motion detection method based on continuous wavelet transformation. The partition human body motion detection method is characterized in that a receiver is used to receive a signal waveform after precoding of a transmitter; the received signal can be segmented into signal segments, and the continuous wavelet transformation of each signal segment can be carried out to acquire a transformation matrix, and then the variance vectors of the transformation matrix can be calculated; and at last, by calculating the maximum value of the variance vectors, and the maximum value can be compared with the threshold value to detect whether the human body motion occurs behind the wall. By adopting the continuous wavelet transformation, the weak target detection problem in the strong noise environment can be solved, and whether the human body motion occurs behind the wall can be effectively detected, and therefore the accuracy of the partition human body motion detection can be greatly improved.

The invention discloses a wall-across human body motion detection method based on short-time Fourier transform. The method comprises the following steps: firstly, receiving a signal waveform, which is pre-coded by virtue of a transmitter, by virtue of a receiver; then, segmenting the received signal into various sections of signals, and conducting short-time Fourier transform on each section of the signal so as to obtain a transformation matrix; then, computing a variance vector of the transformation matrix; and finally, by computing the range of the variance vector and comparing the computed range with a threshold, detecting whether human body motion occurs behind a wall or not. The detection method disclosed by the invention can solve the problem on weak target detection in a strong noise environment through the short-time Fourier transform, and the detection method can effectively detect whether the human body motion occurs behind the wall or not, so that the accuracy of detecting the human body motion is greatly improved.

The invention discloses a machine vision identification analysis and drug sensitivity identification system, comprising: an optical and digital image acquisition device, a digital image processing device and a drug sensitivity identification analysis device. The optical and digital image acquisition device is used to provide the light source and collect the digital image, send it to the digital image processing device, use the polarizer and analyzer set in it to enhance the digital image of the measured object, and use the lens to correct the stereoscopic image of the digital image Poor; the digital image processing device is used to receive digital images and perform motion capture. When the target object is perceived to be stacked, the image is filtered and the feature is enhanced. After the target sample image is obtained, the target sample type is determined according to the target sample characteristics and barcode information. The detection method is selected, the detection results are obtained, processed and then sent to the drug sensitivity identification analysis device; the drug sensitivity identification analysis device performs drug sensitivity identification through the pattern recognition algorithm combined with the preset CLIS identification standards, and gives the identification conclusion.

The invention provides an airfield pavement disease detection method. The airfield pavement disease detection method comprises the steps of obtaining a trained YOLOv5 target detection model and a DDRNet semantic segmentation model; the trained YOLOv5 and DDRNet are optimized on the basis of a reasoning optimizer; the optimized YOLOv5, the optimized DDRNet and an image acceleration decoder are deployed on a movable inspection body; controlling the movable inspection body to run according to a preset running path, and controlling the image acquisition device to acquire an image; the image acceleration decoder acquires the acquired image in real time and decodes the acquired image; the decoded image is detected by the optimized YOLOv5, and a first detection result is obtained; and the optimized DDRNet performs contour information extraction on the image area with the disease based on the first detection result to obtain a second detection result. The invention also provides an airport pavement disease detection system. According to the invention, the detection result can be obtained in real time in the inspection process.