456results about How to "Detection speed" patented technology

The invention relates to a nondestructive detection method for tea quality based on a near infrared spectrum and a machine vision technology and a device thereof. The detection method comprises the following steps: spectrum and image acquisition to tea are synchronously performed, obtained initial data are subjected to preprocessing, feature extraction and fusion, and then an expert evaluation result is combined to establish a quality grade evaluation model of the tea to quickly and nondestructively detect the comprehensive internal and external quality of the tea. The detection device comprise a spectrum acquisition device, an image acquisition device and a computer, wherein the spectrum acquisition device and the image acquisition device finish the signal acquisition of a tea sample and then transfer a signal to the computer; and the computer finishes the extraction and fusion of feature information, and then substitutes in the pre-established model to judge a final result of the quality of the tea. The method applies a fused nondestructive detection means based on the two technologies to the detection process of the comprehensive quality of the tea, has the advantages of high detection accuracy, good result consistency, strong automation degree and so on, and creates conditions for standardized classification of the quality of the tea.

The invention relates to a laser detection device and method for gear parameters. The laser detection device is characterized in that a worktable is provided with an internal point; a laser displacement sensor is arranged on a bracket; the bracket is arranged on a linear motor sliding block of a sliding table; the sliding table is arranged on an angular displacement rotating system and is fixedlyconnected to a rotating disk together with a rotating shaft; a casing of the angular displacement rotating system is arranged on a lifting arm through screws; the lifting arm is connected with the vertical surface of a machine body through a high-precision linear guide rail and a sliding block; a servo motor drives a ball screw which is fixedly connected to the vertical surface of the machine body to rotate; and a data acquisition and communication system is arranged on a rotating shaft upper plane of the angular displacement rotating system. Tested workpieces are subjected to data measurement, acquisition, transmission, reconstruction, separation, comparison and display to finish the full process of detection. According to the laser detection device and method, the non-contact and blind spot-free measurement is realized, the detection speed and measurement precision are improved; the difficult problem that a pinion is difficult to detect is solved; and in the measuring process, the gear is stationary and a measuring head does measuring movement, thus the measuring error caused by mounting the gear is reduced.

The invention discloses a product detection method based on machine vision. The product detection method can achieve automatic detection of product defects by use of machine vision and template matching, locate the coordinates of defective products, control a mechanical arm to grab the unqualified products and to place the unqualified products in a disqualification area by a data acquisition card, and convey products passing through detection to the next workstation by a production line. The product detection method can achieve subtle high-precision detection of missing, deflection and parameter errors of such electronic components as resistors on a PCB, as well as status disqualification of a dial switch; through edge grabbing arrangement of the six-degrees-of-freedom mechanical arm, the detected unqualified products are automatically grabbed away from the production line to realize automation of the whole process; and in combination with matching and high-precision location of edge detection, the approximate positions of the products are found by matching at first, then the pixel coordinates and the angle of a corner of each cuboid product are determined via detection of two edges, the unqualified products are automatically grabbed out, and the product detection method is suitable for detecting different products.

The invention discloses a pedestrian flow monitoring method based on pedestrian detection and tracking. The method includes: acquiring and decoding a camera video stream to obtain single-frame RGB images, performing pedestrian detection on each image frame to obtain a group of pedestrian positions, calculating similarity, matching the pedestrians of every two adjacent image frames so as to track the pedestrians and obtain motion trajectory of each pedestrian, setting detection lines in the monitoring video, and judging pedestrian flow in different directions through the obtained pedestrian trajectories. The method is based the latest developments of pedestrian detection in computer vision, high in detection accuracy, fast in detection and promising in development prospect. By combining the method with a fast tracking method based on similarity and using a multi-scale detection method from sparsity to density, detection speed is further increased, fast pedestrian tracking is realized, detection and tracking speed can reach 10FPS on a current common computer, and practical level is reached.

Belonging to the technical field of laser detection, the invention relates to a novel laser spectroscopy induced detection system, especially to a molten steel component online detection system, which is obtained by gathering lasers on a molten steel surface and conducting analysis through induced plasma spectroscopy. The laser spectroscopy induced online molten steel component detection system includes: a concave reflecting mirror, a convex reflecting mirror, a window mirror, a casing pipe, a steel furnace, a computer, a detection point distance dynamic monitoring system, a feedback regulation control device, a laser light source, a light beam turning system, an echelle spectrometer, an integral delay detection system, a laser beam quality control system and the like, and can realize accurate detection of manganese, magnesium, sulfur, carbon and other 20 components contained in molten steel. The detection system provided in the invention can realize real-time detection of molten steel components, reduce the smelting cost, and save resources.

The invention relates to a hot topic detection method of Chinese micro-blogs. The hot topic detection method includes the following steps of (1) filtering junk micro-blogs based on a certain junk filtering rule at first, (2) preliminarily gathering keywords distributed in the micro-blogs to obtain a primary word set expressing topics, retrieving the most similar first (i)k(/i) micro-blogs of each micro-blog, and then enriching the characteristics of each micro-blog by virtue of the result of retrieval and the result of preliminary keyword gathering to obtain the enriched characteristic vector of the characteristics of each micro-blog, and (3) clustering all of the micro-blogs by an incremental clustering method based on the enriched characteristic vector of the characteristics of each micro-blog to obtain a clustered topic set, next, performing topic popularity calculation on the clustered topic set through a certain topic popularity calculation formula, and finally, obtaining a hot topic list. The method is capable of performing hot topic detection on the Chinese micro-blogs efficiently and accurately, and also high in detection speed, high in accuracy, wide in application range and high in applicability.

The invention belongs to the field of nondestructive testing and relates to a method for nondestructive measurement of a residual stress field in a metal plate through ultrasonic waves. The method for nondestructive measurement of the residual stress field in the metal plate through the ultrasonic waves is beneficial to conducting nondestructive evaluation on the residual stress in the metal plate. The single-time measuring time of the method is only about 20 seconds and is dozens of times less than the single-time measuring time of a traditional X-ray residual stress measuring method, and the detection speed is high; meanwhile, the measurement depth in the method is adjustable, the maximum depth can reach 3mm and is dozens of times that of the measuring depth in the X-ray measuring method, and thus the measuring depth is large. The method is provided for measuring large-range residual stress distribution inside the plate, and a three-dimensional diagram or a contour map of the residual stress distribution can be obtained. The cost for the single-time measuring of the method is dozens of times less than that of the X-ray measuring method, obvious economy is achieved. The method is free of radioactivity and is safer compared with the X-ray measuring method.

The invention relates to an intelligent fusion method for depth images based on area shades and red green blue (RGB) images. The intelligent fusion method is characterized comprising the steps of collecting the depth images and the RGB images of the same scene at the same moment, selecting large area invariance associated characteristics of the depth images and the RGB images; utilizing the large area invariance associated characteristics to perform image registration; setting an interested depth range in the depth images after registration, and obtaining new depth images only containing the interested depth range; generating the shades for target objects; and performing fusion on the shades and the registered RGB images. The intelligent fusion method has the advantages that the fused images contain depth information and color and texture information, algorithm complexity is reduced, accuracy in target object recognition is greatly improved, the detection speed and the tracking speed are improved, and registration precision is enhanced.

A device for checking rapidly leakage detecting block gasification of landfill is provided. An emitting electrode is placed in protection layer of geomemberance of landfill, and a receiving electrode is placed in the soil under the film of geomemeberance, two ends of signal source are connected between emitting electrode and receiving electrode. Multiple detecting electrode are placed in protection layer, each of which is connected with data collecting processor respectively, orientating by detecting the electric potential difference of each point. Signal is connected with data collecting processor and controlled by said data collecting processor. Each detecting electrode signal is added to active low pass filter after low pass filtering and transient suppression, output signal is entered analog-to-digital converter to transmit, data of each point is carried on leak judgement and the corresponding coordinate position is showed on display. The device of present invention has advantages of high speed detecting, high veracity and high omission factor.

The invention relates to a method for rapidly identifying dominant spoilage bacteria of livestock meat. Characteristic response signals of characteristic gas produced when the dominant spoilage bacteria of the livestock meat are cultured in a defined culture medium, which are detected by visual array sensors, are collected by utilizing a scanner; a detection result is displayed in a map manner through a signal recognizing and processing system; and the species of the detected dominant spoilage bacteria of the livestock meat are determined according to the relationship between color changes of a map and the specie and the concentration of the detected gas. The method has the advantage that the dominant spoilage bacteria of the livestock meat can be rapidly identified on the premise that complicated morphological, physiological, biochemical and molecular biological experiments do not need to be conducted on the spoilage bacteria. By using the method, different dominant spoilage bacteria of the livestock meat can be rapidly identified, so that the method has direct practical significance to further pointed adoption of fresh preservation measures and the prolongation of the shelf life of chilled pork.

The invention discloses a static three-dimensional face in-vivo detection method based on deep learning, and the method comprises the steps: shooting a color image through a color camera, and shootinga depth image through a depth camera; when a face is detected in the color image, obtaining a feature vector corresponding to the face through a first convolutional neural network and a second convolutional neural network according to the color image and the depth image; and judging whether the face is a living body or not through a pre-trained living body detection classifier according to the feature vector corresponding to the face. Only two cameras are adopted, the characteristics of color images and depth images are combined, the technologies of deep learning, machine learning and the like are combined, the speed, the passing rate and the anti-counterfeiting rate of human face living body detection are greatly increased, the cost is low, and the precision is high.

The invention relates to a pavement crack detection method based on convolution neural network and image recognition, belonging to the field of traffic pavement detection. The method is based on a convolution neural network chip and a recurrent neural network (the convolution neural network chip is used to detect pavement cracks and the recurrent neural network is used to generate statements describing the types of cracks). The method includes steps: the original image of pavement cracks is pre-marked, the intensity normalization and pixel saturation pretreatment are carried out on the pavement image according to the pre-marking results, the pre-processed pavement images are input into a convolution neural network (CNN) model for training (using different pavements as samples to train theneural network), the network structure and model parameters are determined, the trained network is used to detect the complex pavement, and the type of pavement cracks is determined. The pavement crack detection system with depth learning function is composed of pavement image acquisition equipment, an image pre-processing device, a memory, USB external equipment, a microprocessor and so on.

A method for detecting the freshness of mangos by the aid of an electronic nose includes (1), placing a mango to be detected in a sealed container and allowing the mango to stand at normal temperature for 30 to 60 minutes; (2), sucking gas in the sealed container by a sample feeding needle of the electronic nose at the normal temperature for 30 to 60 seconds, and detecting the gas via a gas sensor array in the electronic nose; and (3), collecting data acquired by the gas sensor array, processing the acquired data, obtaining a freshness detection value and evaluating the freshness grade of themango according to preset corresponding relation of freshness grades and a threshold value range. The method has the advantages that detection speed is fast, and the reliability of detection results is fine.

The invention relates to equipment and a method for on line detecting and sorting light-emitting diode (LED) bulb lamp finished products. Based on the off-line detection mode of an integrating sphere-spectral radiometer, the invention designs a station rotary platform, a detection tool, a detection mechanism, a detection system, a sorting mechanism and a control system for realizing integrated cooperative control of the whole equipment by specially aiming engineering application of an automatic production line. The station rotary platform drives the detection tool to rotate to pass through each station; LED bulb lamps are grabbed by the detection mechanism grabs from the detection tool which rotates to the detection station and then are conveyed to the detection system to perform finished product detection; and the detected LED bulb lamps are sorted by the sorting mechanism from the detection tool which rotates to the sorting station. The equipment provided by the invention has the characteristics of high detection speed, high detection precision, high automation degree and intelligent degree and high cost performance, can be seamlessly integrated to the automatic production line of the LED lamps to realize whole-process automatic production, and also can serve as an independent finished product detection unit.

The invention discloses a fraud website detection method. The method comprises steps as follows: URLs (uniform resource locators) of websites are acquired, whether the websites are in existing website databases is detected, classified detection is performed according to website traffic ranking values, detection items include domain name matching, website titles, website page content, website DOMs (document object models) and fraud information in page images, corresponding influence factors are acquired, the influence factors are subjected to weighted summation, a security coefficient is calculated and compared with a set threshold value, the to-be-detected websites are divided into fraud websites and credible websites, and the lower the website traffic ranking is, the more the detection items are set. The method has the advantages that the fraud websites which are not recorded in a blacklist can be identified accurately and rapidly, and system resources can be distributed reasonably.

The invention provides a network anomaly detection method based on an artificial immunity principle belonging to information safety field. The invention implements the network anomaly detection method capable of fast detecting with high detection accuracy by simulating biological immune system response to external antigen, training antigen data collection and artificial immune system study, and detecting network anomaly. The network anomaly detection method has superior characteristics of a non-linearity of the biological immune system, cloning selection, immune network and immunological memory, solves the problems of low detection speed and low detection accuracy in the present network anomaly detection. The invention also applies to the pattern recognition, machine learning fields and has wide application prospect.

The invention relates to a frequency-point detection method, a device and user equipment. The method comprises the following steps of: carrying out frequency spectrum scan; dividing the frequency spectrum of a specified frequency band into a plurality of frequency spectrum envelopes, and determining the effectiveness of each frequency spectrum envelope; and carrying out autocorrelation detection of a primary synchronization signal (PSS) to the frequency point of each effective frequency spectrum envelope, and determining the effective frequency point. According to the frequency-point detection method, the device and the user equipment, the frequency-point detection efficiency is increased.

The invention discloses a system for detecting formaldehyde emission rate of an artificial board, which comprises a detection box device, an air path device, a water path device, a cyclic sampling device and a system control system; wherein the detection box device has a hollow cavity therein for accommodating a sample to be detected; the air path device is used for filling air into the hollow cavity of the detection box to keep the pressure in the cavity at a standard test pressure; the water path device is used for providing a heat-insulation layer for the detection box device and heating the air filled into the detection box to keep the temperature in the cavity of the detection box device at the standard test temperature; the cyclic sampling device is used for collecting the mixture gas of air and formaldehyde emitted from the test sample in the detection box device and detecting the mixture gas sample to obtain the formaldehyde emission rate in the sample; and the system control device is used for respectively controlling the pressure, the temperature and the sampling sequence of the air path device, the water path device and the cyclic sampling device. The inventive detection system has the advantages of short detection time, high control accuracy, easy operation, etc.

The invention discloses a PCB hole site and hole diameter detecting system and detecting method which solve the problems that at present, comprehensive detection of the indexes like hole sites of a printed board completed through a drilling machine can not be achieved due to the limitation of testing equipment, and the detecting efficiency is low. The PCB hole site and hole diameter detecting system comprises a feeding device. The feeding device comprises a feeding workbench drive part. The feeding workbench drive part is provided with a feeding workbench. A mechanical arm supporting beam is connected with a mechanical arm supporting beam connecting frame, the mechanical arm supporting beam connecting frame is fixedly connected with a mechanical arm connecting frame, and a left mechanical arm and a right mechanical arm are fixed on the mechanical arm connecting frame. The mechanical arm supporting beam is further provided with a video camera supporting beam, the video camera supporting beam is fixedly connected with a video camera mounting plate, and the video camera mounting plate is provided with a detection video camera. A main control computer is used for comparing the element of an image captured by the detection video camera and a designed standard value, hence, a PCB is detected, and whether the PCB is qualified or not is judged.

The invention discloses a bacterium drug-resistant gene detection method, a gene chip and a kit. The kit comprises a primer pair for amplifying the bacterium drug-resistant gene to be detected, and detection probes. The gene chip comprises probes for detecting the bacterium drug-resistant gene to be detected. The method for detecting the drug-resistant gene by using the kit and gene chip comprises the following steps: 1) carrying out PCR (polymerase chain reaction) amplification on the drug-resistant gene in the sample DNA (deoxyribonucleic acid) to be detected by using the primers in the kit; 2) carrying out fluorescence labeling reaction on the amplified product and the detection probes in the kit; and 3) hybridizing the fluorescence-labeled amplified product with the gene chip to determine the drug-resistant gene contained in the sample. The detection method disclosed by the invention covers the detection of the most common 16 drug-resistant genes in clinic, and is beneficial to implementing rapid diagnosis of clinical bacterium drug resistance conditions, thereby providing supports for reasonably selecting therapeutic drugs in clinic.

The invention discloses a commodity positioning identification method. The method comprises the steps of obtaining an input to-be-identified image; Inputting the to-be-identified image into a pre-trained neural network model, and extracting an area corresponding to a commodity in the to-be-identified image; Neural network model trained in advance is Faster- An RCNN network model; Intercepting an area corresponding to the commodity as a subgraph, and inputting the subgraph into a pre-trained image classification neural network model; Pre-trained image classification neural network model as VGG-A Net network model; And calculating the probability that the sub-image belongs to each commodity category through an image classification neural network model, and identifying the category of the commodity in the to-be-identified image. According to the method, video memory occupation can be reduced, the detection speed can be increased by about ten times, and meanwhile the recognition accuracycan be improved. In addition, the invention further provides a commodity positioning identification device and equipment with the technical effects and a computer readable storage medium.

The invention discloses a machine vision detection method based on four-colour printed matter registration detection marks, comprising the following steps of: presetting graphs of the four-colour printed matter registration detection marks, and taking the circle centre of a black solid circular mark graph as a reference of the registration detection marks, wherein the circle centre of a yellow annular mark graph, the circle centre of a pinkish red annular mark graph, and the circle centre of a cyan annular mark graph are respectively as same as the circle centre of the black solid circular mark graph; acquiring images of preset graphs of the registration detection marks during a printing process; respectively obtaining coordinates of the circle centres of the registration detection marks in the images by a computer system; calculating registration deviation via the coordinates of the circle centres; comparing the squared value of the registration deviation with a deviation tolerance level; and finally, outputting a registration deviation result. The registration detection marks are simple in structure and small in occupied space, and camera can be convenient to rapidly and accurately shoot. According to the corresponding detection method, only deviation analysis does need to be performed via circle centre parameters, thus being high in detection efficiency, intuitive in result, and capable of realizing online detection for high-speed printed matters.

The invention belongs to the electromagnetic ultrasonic non-destructive detection field, provides a method for detecting the defects of a steel rail by using the electromagnetic ultrasonic technology, and a device thereof, and aims at solving various problems of the existing steel rail detection method and meeting the need of the development of the high-speed electrified railway. The device consists of a probe, a circuit system, a storage unit and a display unit. The detection device uses an electromagnetic ultrasonic body wave to realize effective detection to the rail head, the rail web and the rail base of the railway by the cooperative work of a plurality of ultrasonic probes. The detection method does not need to use an acoustic couplant, has simple structure and strong adaptive capacity to environment and can realize high-speed steel rail detection.

The invention provides a system for detecting surface defects of a metal plate based on a deep convolution neural network. The system can be used for detecting the surface defects of a metal plate in real time. The system comprises a camera, a mounting frame used for mounting the camera and a processor module, wherein the mounting frame stretches across a conveyer belt on an industrial site; the camera is arranged on the mounting frame and is used for collecting a surface image carried by the metal plate on the conveyer belt in real time; the processor module is used for adopting a deep convolution neural network algorithm for recognizing the defects of the surface image carried by the metal plate collected in real time. The system provided by the invention is suitable for the technical field of machine vision.

The invention discloses a device for detecting the on-off state of the direct current switch protective circuit and method thereof, comprising: a signal generator and a signal comparison circuit, wherein the output end of the signal generator is connected with the output end of the direct current switch protective circuit and one output end of the signal comparison circuit. The signal generator is used for generating a preset signal wave and transmitting the preset signal wave into the direct current switch protective circuit and the signal comparison circuit. Another input end of the signal comparison circuit is connected with the output end of the direct current switch protective circuit and outputs the detection signal. The said device can detect the on-off state of the direct current switch protective circuit as true as steel, such as cell fuse, load breaker, nonempty open; and the speed of testing is high and the real time and reliability of the power supply monitoring can be greatly increased.

The embodiment of the invention discloses an intrusion detection method and a device thereof in a self-organized network, which belong to the field of wireless networks and can improve the detection speed on the premise of ensuring the detection accuracy. The intrusion detection method in the self-organized network comprises the following steps of: receiving data, acquiring data characteristics and constituting the characteristics into an original characteristic set; dividing the characteristics in the original characteristic set into groups based on information gain to obtain all characteristic groups; adopting a support vector machine to screen an optimal characteristic subset from all characteristic groups based on a minimum classification error judgment principle of the support vector machine; and analyzing the optimal characteristic subset and judging whether the network is intruded. The invention can be used for improving the detection speed on the premise of ensuring the detection accuracy.

The present invention discloses a Hoh Xil Tibetan antelope detection method based on a convolutional neural network. The objective of the invention is mainly to solve the problems that the Tibetan antelope population statistics is slow in speed and not accurate in the prior art. The method comprises the steps of: 1) constructing a training data set, performing marking of Tibetan antelope images obtained through enhancement of the collected data, and obtaining a training data set; 2) employing a k-means algorithm to perform target frame dimension clustering of the training data set, obtaining the most effective priori frame information of the Tibetan antelope data set, and constructing a convolutional neural network with 19 convolutional layers and 5 maximum pooling layers; 3) performing training of the Tibetan antelope data by employing the convolutional neural network to obtain a Tibetan antelope detection and classification model; and 4) employing a trained model to perform detectionof the Tibetan antelope images, draw concrete positions of Tibetan antelopes and mark classes of the Tibetan antelopes. The Hoh Xil Tibetan antelope detection method based on a convolutional neural network can more rapidly and accurately perform detection and classification of the Tibetan antelopes, and can be used for scientific protection and management of the Tibetan antelopes in natural reserves.

The invention discloses an NT-ProBNP detection kit. The NT-ProBNP detection kit comprises a calibrator, a cleaning solution, a substrate solution, a pretreatment solution, an enzyme conjugate workingsolution and a magnetic bead conjugate working solution; the pretreatment solution contains pyridine, the enzyme conjugate working solution contains NT-ProBNP antibody labeled by enzyme, and the magnetic bead conjugate working solution contains magnetic beads labeled by the NT-ProBNP antibody. The NT-ProBNP detection kit can accurately measure NT-ProBNP in a whole blood sample, the lowest limit detection of the kit is 20 pg/ml, the linearity range is 20-5,000 pg/ml, the detection sensitivity is high, the linearity range is wide, and the result is accurate. The invention further discloses a using method of the NT-ProBNP detection kit. The NT-ProBNP detection kit is simple in using step, the detection time of an NT-ProBNP is shortened, and quick and sensitive detection of the NT-ProBNP is achieved.

The invention relates to a precise on-site measuring device and measuring method for sphericity of a spherical surface, belonging to the technical field of mechanical measurement. The measuring device comprises a main shaft mechanism, a rotation mechanism, a driving mechanism, a sensing mechanism and an encoder mechanism, wherein a workpiece to be measured is arranged on the main shaft mechanism;the center of the rotation mechanism is rotatably connected with the main shaft mechanism; the sensing mechanism is fixedly arranged on the rotation mechanism and is connected with the encoder mechanism; and the driving mechanism is connected with the rotation mechanism. Compared with the traditional off-line manual measuring method or measuring method by a three-coordinate measuring machine, theinvention has the advantages of high detecting speed and high degree of automation on the premise that the precision of measurement is ensured, and realizes automatic on-site measurement of the sphericity error.

The invention discloses a sit-up detection system and method based on human body and skeleton key point recognition, and the system comprises an image collection module which employs a high-definitioncamera to collect a video image of a testee; the image recognition module which is used for extracting human skeleton key points of the testee in the continuous frames; the action detection module which is used for detecting the change condition of an included angle formed by a straight line formed by the waist key points and the shoulder key points and a relative horizontal position of the skeleton key points of the human body of the testee in the continuous frames to judge whether the testee lies down or sits down or sits down; the judging and counting module which is used for judging and recording the frequency of completing sit-up of the testee within the testing time; and the data display module which is used for displaying the frequency of sit-ups completed by the testee within thetest time. The method is high in detection speed, low in cost and suitable for single-person or multi-person detection, and can be applied to sports home work, practice detection in an emergency response state and other scenes.