50results about How to "Optimize the identification method" patented technology

A graphical user interface (GUI) which displays a map image showing the location of a camera whose sensed image is distributed via a network, and further displays a camera icon indicative of the position and states of the camera on the map image. When a user designates an area desired to be sensed on the GUI after the user obtains authorization to control the camera, control values for controlling facing direction and the angle of view of the camera are calculated. The calculated control values are transmitted to a camera server via the network, and the camera server controls the camera on the basis of the control values.

The invention provides an electrocardiographic data sampling method, which is to sample the following data from an electrocardiograph: starting and ending points of a P wave, starting and ending points of a quantum resonance spectrometer (QRS) wave, starting and ending points of a T wave, form of the P wave, base line of the P wave, position of subwave of the QRS wave, form of the QRS wave, base line of QRS wave, form of the T wave, base line of the T wave, and heart beat rate diagnosis result. The invention also provides an electrocardiographic data sampling device for sampling the data. An electrocardiographic database obtained by using the sampling method and the sampling device provides a test platform with better automatic electrocardiograph characteristic identification and a better diagnosis method.

The invention relates to product anti-counterfeiting method, in particular to a CCQR (Colorful Coded Quick Response) anti-counterfeiting method. According to method, anti-counterfeiting information, commodity unique codes and check codes are generated into novel zoned colorful QR (Quick Response) codes which are called as CCQR codes as anti-counterfeiting marks through a specific encoding method by using structural characteristics in color codes and QR codes, such as characteristics of colorful cell matrix combination, quantity, color and quick response. Through a series of steps of generating the CCQR codes, warehousing, printing the CCQR codes, providing special mobile phone software for consumers for scanning, comparing warehoused commodity information on a server through automatic network connection by virtue of the mobile phone software and finally feeding truth and falseness results back to the consumers by using mobile phones, the problem that the anti-counterfeiting cost of manufacturers is high is solved, a simple, convenient, quick and general commodity truth and falseness recognition method is provided for the consumers, and the consumers are enabled to have the ability of distinguishing the truth and the falseness of commodities.

The invention provides an identification and separation device for waste plastics. The device comprises a crushing plant, a friction assembly, an accelerating unit, a constant magnetic field unit, a comparing unit, and a collecting unit. A variety of standard pure plastics or waste plastics are crushed by the crushing plant and then are charged by the friction assembly, the charged plastics enter into the accelerating unit for acceleration and then enter into a constant magnetic field at a same speed with an included angle formed by the track of the plastics and the direction of the magnetic field being greater than zero, thereby forming different movement tracks, the comparing unit compares the movement tracks of waste plastic particles with the movement tracks of a variety of standard pure plastic particles so as to determine that a waste plastic and a standard pure plastic which has a same movement track as the waste plastic does are of a same kind, and the collecting unit collects waste plastic particles which have similar movement tracks in the magnetic field. The invention also provides an identification and separation method for waste plastics. According to the invention, the disadvantages that an optical method for identification of waste plastics is work-environment-demanding and expensive can be overcome, and the purposes of easy operation and low cost in identification and separation of waste plastics of automobiles are achieved.

A display device includes a first light-transmissive glass plate having a first electrode for connection to a power supply, a second light-transmissive glass plate having a second electrode for connection to the power supply, a light dispersing element sealed between the first and second glass plates for transmitting light when voltage is applied and dispersing the light when the voltage is not applied, a light-transmissive transparent element laminated on the second glass plate and having a predetermined refractive index, a light guide plate laminated on the transparent element and having a refractive index lower than the transparent element for surface-emitting the light toward a side viewed by a user, a light emitting part provided on a lateral side of the light guide plate for emitting light, and a display control part for turning on or off the voltage applied to the first and second electrodes.

The invention provides a cable identification method and a device based on an active excitation-type multiple-frequency induction current. The method comprises the following steps of taking a loop formed by a cable armor layer, a grounding wire and ground as a secondary coil; through an excitation source, generating a coded alternating current signal to drive a primary coil; then, generating an induction voltage of a specific curve in the secondary coil, and inducing and generating a coded loop current with a corresponding characteristic in a loop formed by a high voltage cable armor, two-endgrounding wire and the ground; simultaneously, through a high precision current transformer, collecting an induction loop current, acquiring a cable grounding impedance and realizing state and characteristic monitoring of the cable. In the invention, through autonomous communication of a coded induction current generated through active excitation on high voltage and extra-high voltage cables, sitemulti-point networking is completed and then whole line identification and tracking of the cable are realized.

An image recording / reproduction apparatus reads image data from a recording medium storing plural image data to display the read image data on a TV monitor or the like, and selects image data of a same aspect ratio to simultaneously index display plural small images of thus selected image data on the TV monitor. Reduced images of an aspect ratio of 4:3 and 16:9 are formed respectively from image data of an aspect ratio of 4:3 and 16:9, and the number of displayed small image is changed according to the aspect ratio, thereby displaying a larger amount of information within a limited display space in an easily recognizable manner.

The invention discloses a currency identification method and a currency identification device. The currency identification method comprises steps that an infrared transmission image of to-be-identified currency is acquired; position, direction, and characteristic information of optically variable ink in the infrared transmission image are determined; the version information and the denomination information of the to-be-identified currency are determined. By identifying the position, the direction, and the characteristic information of the infrared transmission image of the currency, the version information and the denomination information of the currency are further determined, and an effect of determining version information and denomination information of Hong Kong dollars quickly and accurately is achieved.

The invention discloses a traffic sign display device, a traffic sign identification method and device, equipment and a medium. The traffic sign display device includes a pattern display area, whereinthe pattern display area is used for displaying an electronic identification pattern, the electronic identification pattern is associated with the current traffic sign information and the advance notice traffic sign information, and the electronic identification pattern is a two-dimensional code pattern and / or a web address character pattern. The method is advantaged in that problems of low identification standardization degree of traffic signs and less information carrying amount of texts and graphs in the prior art are solved, the effect of large amount of information carried by the electronic identification pattern is realized, the traffic signs are improved, and achievement of the automatic driving technology is facilitated.

The invention belongs to the technical field of identity recognition and relates to a palm print recognition method based on cross gradient encoding of an image with stable characteristics. The palm print recognition method based on cross gradient encoding of the image with the stable characteristics comprises the steps that an angular point between the index finger and the middle finger in the palm print image and an angular point between the ring finger and the little finger in the palm print image are detected respectively, rotary correction is conducted on a tangent line which is formed through the two angular points, and then the image of a region of interest in the original palm print image is defined; an energy functional model is established after an normalized palm print image is obtained through conducting grey level normalization on the image of the region of interest, the image with the stable characteristics is obtained through solving, and then cross gradient encoding is carried out on the image with the stable characteristics to obtain cross gradient encoding characteristics which can be used for palm print matching and recognition; a matching result is output automatically after matching of a palm print is achieved. The palm print recognition method based on cross gradient encoding of the image with the stable characteristics has the advantages of being simple, high in recognition accuracy, low in algorithm complexity, short in recognition time, and high in anti-interference performance.

An image recording / reproduction apparatus reads image data from a recording medium storing plural image data to display the read image data on a TV monitor or the like, and selects image data of a same aspect ratio to simultaneously index display plural small images of thus selected image data on the TV monitor. Reduced images of an aspect ratio of 4:3 and 16:9 are formed respectively from image data of an aspect ratio of 4:3 and 16:9, and the number of displayed small image is changed according to the aspect ratio, thereby displaying a larger amount of information within a limited display space in an easily recognizable manner.

The invention provides an aircraft landing gear state judgment method based on image recognition, and the method comprises the following steps: 1), continuously collecting an aerial target image through an image collection module erected on an aircraft runway; 2) identifying an airplane and the position of the airplane in the aerial target image by adopting an airplane identification model; 3) acquiring the flight state of the aircraft according to the group of image sequences obtained in the step 2); 4) extracting an aircraft image from the aircraft identification result; 5) identifying the undercarriage in the aircraft image by adopting an undercarriage identification model; 6) extracting an undercarriage image from the undercarriage recognition result, and 7) comprehensively judging whether the folding and unfolding state of the undercarriage is correct or not by combining the flight state of the aircraft and the undercarriage image. According to the invention, through accurate identification of the aircraft landing gear and in combination with the aircraft flight state, state judgment of the landing gear is effectively achieved, and the accuracy and stability of detection are improved.

The invention discloses a lane line recognition method and device, computing equipment and a computer storage medium, and the method comprises the steps: obtaining the motion state data of a vehicle at a current moment t, predicting the pose condition of a lane line at a moment t+deltat, and obtaining the lane line pose prediction data at the moment t+deltat; when the t+deltat moment is reached, obtaining lane line pose observation data at the t+deltat moment according to a lane line parameter equation determined based on the road image at the t+deltat moment; performing fusion processing on the lane line pose prediction data at the t+deltat moment and the lane line pose observation data at the t+deltat moment to obtain target lane line pose data at the t+deltat moment; and fitting the pose data of the target lane line at the t+deltat moment to obtain a fusion parameter equation of the lane line at the t+deltat moment. According to the scheme, visual detection and motion state data ofthe vehicle are fully fused, and high-precision and high-robustness lane line identification is realized.

The invention provides an active excitation type multi-frequency induced current cable identification method and device. The active excitation type multi-frequency cable identification method comprises steps of using a loop formed by a cable armoring layer, grounding wires and the ground as a secondary coil, generating a coding AC signal through an excitation source to drive a primary coil, generating induced voltage with a specific curve in the secondary coil, generating coding loop current with corresponding characteristics through induction in the loop formed by the high voltage cable armoring layer, grounding wires on two ends and the ground, collecting induction loop current through a high accuracy current mutual inductor, and obtaining cable grounding impedance to realize monitoring of state and characteristics of a cable. The active excitation type multi-frequency cable identification method and device can finish on-site multi-point networking through coding induced current autonomous communication on the high voltage or extra-high voltage cable which is generated through active excitation and then realize cable whole circuit identification and tracking.

The invention discloses a live recognition method for a low-voltage cable line. Multiple cables with unknown path directions are arranged; the in-phase current values of the head ends and the tail ends of the multiple cables are measured respectively; and if the current values of the head end and the tail end are the same, the head end and the tail end are judged to be located on the same cable line. The live recognition method for the low-voltage cable line has the following advantages that current in the head and tail ends of the cable is measured through a simple and frequently-used device,the measured current in the head and tail ends is then compared, and thus, the cable line of the head end and the tail end can be recognized. The recognition method is simple, convenient and effective, and the needed cost is low.

The invention discloses a human body detection and face recognition system and method, and belongs to the technical field of video stream real-time monitoring and face recognition, and the method comprises the steps: 1, carrying out the motion detection of an obtained video stream transmitted by a camera; 2, executing human body detection according to a motion area obtained by motion detection; step 3, executing face feature extraction in a local face database; step 4, executing multi-image fusion in the video stream; step 5, performing face detection on the detected human body area; step 6, performing face recognition after face detection is performed; the face feature extraction and recognition method is further optimized, so that the detection and recognition precision and the real-time performance of the system in practical application and the adaptive capacity in a complex scene are remarkably improved, and the robustness is good.

The invention provides a fish identification and vaccine injection method based on a fractal theory and a BP (Back Propagation) algorithm. The method comprises the steps of acquiring a color image offish; performing preprocessing and image segmentation on the color image to obtain a target image; extracting a characteristic value of each segmented target image by use of a fractal theory algorithmto obtain a comprehensive characteristic vector group; training the comprehensive characteristic vector group by use of a BP neural network algorithm, and identifying an image which meet the combination requirement of a specific part of the fish in the target image; and performing vaccine injection on the fish meeting the requirement. According to the fish identification and vaccine injection method based on the fractal theory and the BP algorithm, a novel method is provided for representation of the body part of the fish by use of the fractal theory algorithm, eight characteristic values forrepresenting the fish can reflect the information of the body part of the fish and facilitate distinguishing. Through the combination of the fractal theory and the BP algorithm, the image of the combination of a fish head and a back spine is effectively identified, a good identification method is provided for fish vaccine injection, mechanical identification is achieved, automatic injection is adopted in an injection process, and thus the manpower burden is alleviated.

The invention discloses a face image recognition method, a server, a terminal and a service device, and belongs to the technical field of Internet. The method comprises the steps of obtaining a reference face image corresponding to a user identifier, wherein the user identifier is obtained by decrypting the encrypted information sent by a terminal receiving a broadcast message; adding the reference face image into a face image list, wherein at least one to-be-matched reference face image of the terminal receiving the broadcast message is stored in the face image list; and determining a face image matched with the to-be-identified face image by matching the to-be-identified face image with the to-be-matched reference face image in the face image list. According to the invention, the reference face image of each terminal receiving the broadcast message is added to the face image list, so that the face image is identified based on the face image list. Since the to-be-identified face imagedoes not need to be matched with each reference face image in a face database, the calculation amount during face identification is greatly reduced.

The invention discloses a method and system for identifying the queuing number of battery replacing users of a battery replacing station, and the method comprises the steps: setting a virtual fence according to the position of the battery replacing station, and enabling the range of the virtual fence to cover the range of the battery replacing station; receiving user information uploaded by a user, wherein the user information comprises position information of the user; and judging whether the user is located in the virtual fence or not according to the position information, and if so, determining that the user is a queuing user. The queuing number of the battery replacing users in the battery replacing station can be recognized and obtained in real time in a full-automatic mode, the usersneeding to replace the batteries can obtain the queuing number in the battery replacing station in advance, and therefore the battery replacing time can be arranged to reduce unnecessary waiting, theburden of workers of the battery replacing station can be reduced, and power exchange resources can be distributed more reasonably.

The invention provides a method for fish identification and vaccine injection based on fractal theory and BP algorithm, comprising: obtaining a color image of fish; performing preprocessing on the color image, image segmentation to obtain a target image; The eigenvalue of the target image obtains the comprehensive feature vector group; the BP neural network algorithm is used to train the comprehensive feature vector group, and in the target image, the image that meets the combination requirements of the specific parts of the fish is identified; the fish that meet the requirements are vaccinated injection. The invention provides a brand-new method for characterization of fish body parts by adopting a fractal theory algorithm, and the eight eigenvalues ​​representing fish can better reflect the information of fish body parts and facilitate distinction. Combining fractal theory and BP algorithm to effectively identify the image required by the combination of fish head and back, it provides a good identification method for fish vaccine injection, realizes machine identification, and uses automatic injection in the injection process to reduce the labor burden.

The invention belongs to the technical field of identification, and relates to a palmprint recognition method of cross-gradient coding under a stable feature image. First, the corner points between the index finger and the middle finger, the ring finger and the little finger in the palmprint image are respectively detected, and the two corners The tangent line formed by the points is rotated and corrected to segment the image of the region of interest of the original palmprint image; then the image of the region of interest is normalized by grayscale to obtain the normalized palmprint image, and an energy functional model is established and solved to obtain Stable feature image, and then perform cross-gradient encoding on the stable feature image to obtain cross-gradient encoding features for palmprint matching and recognition; after the palmprint matching is completed, the matching result is automatically output; the recognition method is simple, the recognition accuracy is high, the algorithm complexity is low, and the recognition time is short. Short, strong anti-interference.

The invention relates to the field of carbon emission reduction strategy calculation, in particular to a random forest-based carbon intensity key influence factor identification method. Compared with a traditional carbon strength impact factor analysis method, the method has the advantages that data selection is flexible, and the method is not limited by dimensions, important impact factors in multiple potential impact factors can be accurately recognized, the defect of data dimension limitation of the traditional analysis method is overcome, scientific reference is provided for accurate implementation of a carbon emission reduction scheme, and the method is suitable for popularization and application. And a relative emphasis is provided for formulating a regional carbon emission reduction policy.

The invention discloses a touch panel, which is used for solving the technical problem in the prior art that an operation way of the touch panel is inconvenient. The touch panel comprises a first functional region, a second functional region and a third functional region, wherein the third functional region is positioned between the first functional region and the second functional region, and the surface of the third functional region is provided with a convex-concave structure. The invention also discloses electronic equipment which uses the touch panel, and a corresponding control method.

The invention provides a method and a system for identifying a transition resistor during a short-circuit fault of a power system, and the method comprises the steps: injecting a DC voltage into the power system through a high-voltage injection resistor, and detecting and collecting an output current Idc, three-phase voltages Ua, Ub and Uc, and three-phase load currents Ia, Ib and Ic; when the power system operates normally, calculating equivalent insulation resistance R of the power system; according to the collected three-phase voltages Ua, Ub and Uc and the collected three-phase load currents Ia, Ib and Ic, judging the fault type; and calculating equivalent transition resistance R<transition> of the power system. The system is applied to the method. The identification device, the system and the identification method are used for identifying and calculating the transition resistance under the insulation state and the fault of the power system, the mechanism is clear, the physical significance is clear, and the effectiveness is high.

The application discloses a multi-antenna UWB NLOS identification method, compared with a common identification method based on a single-antenna propagation model, the method introduces a phase parameter of a UWB receiving signal as an identification feature, utilizes correlation of multi-path antenna receiving signals, and compares with a threshold value trained in advance by using a machine learning method to perform NLOS identification.The feature information extracted by the method is rich and has good distinguishability.

The present invention discloses a telecommunication fraud number recognition method, system and electronic device based on feature fusion, which relates to the cross-technical field of artificial intelligence and communication technology. The method includes: obtaining and processing multiple specified attribute fields in each telecommunication data in a telecommunication data set, obtaining a multidimensional feature vector corresponding to each one-dimensional feature vector, and further obtaining a telecommunication time series data set; generating simulated abnormal telecommunication time series data based on a Gaussian random noise simulation abnormal sequence generation algorithm and a telecommunication time series data set; constructing a telecommunication fraud number recognition model, and training the telecommunication fraud number recognition model based on a balanced telecommunication time series data set; and using the trained telecommunication fraud number recognition model to perform fraud recognition on new telephone numbers. The present invention can more accurately extract the common features of fraudulent calls and improve the accuracy and efficiency of telecommunication fraud detection.

The invention discloses a reactor state evaluation method, a device and a system based on an immune algorithm, comprising the following steps: obtaining a reactor state index vector; The number of state detectors is optimized by improved immune recognition algorithm. Using the optimized state detector to classify the reactor state evaluation index vector, the final state evaluation results are obtained. The invention improves the traditional immune algorithm, optimizes the survival strategy of the state detector, and greatly improves the state identification efficiency of the reactor.

The invention discloses an ergonomic mobile hard disk fingerprint mute optical mouse and a fingerprint identification method thereof, being characterized in that mouse left key second-generation fingerprint identification devices are each fixedly mounted below the mouse left key, below the mouse right key and in the shell on the left side surface of the mouse respectively for fingerprint identification; a mobile hard disk chip is mounted at the tail in the mouse; a mouse internal photoelectric device, a mobile hard disk chip, three mouse left key second-generation fingerprint identification devices and a USB interface mouse computer connecting line are connected in the mouse through a USB three-in-one line; the mobile hard disk switch is located in the transverse center of a shell on the bottom face of the mouse; the distance between the mobile hard disk switch and the front end of the mouse is within 1 / 2 of the longitudinal length of the mouse; and the built-in timer is connected withthe three mouse left key second-generation fingerprint identification devices in series. The ergonomic mobile hard disk fingerprint mute optical mouse has the advantages of being diverse in functionand convenient to carry. The fingerprint identification method of the ergonomic mobile hard disk fingerprint mute optical mouse has the characteristics of safety, simplicity and convenience.

A time measurement device includes: a higher-digit indication hand that is configured to indicate a higher digit of a measured time; a lower-digit indication hand that is configured to reciprocate and indicate a lower digit of the measured time on a forward route and on a return route; a first drive unit that is configured to drive the higher-digit indication hand; a second drive unit that is configured to drive the lower-digit indication hand; a time counter that is configured to measure a time; a first drive controller that is configured to control the first drive unit to drive the higher-digit indication hand based on the measured time measured by the time counter; and a second drive controller that is configured to control the second drive unit to drive the lower-digit indication hand based on the measured time measured by the time counter, the second drive controller reciprocating the lower-digit indication hand at a predetermined period, and the first drive controller moving the higher-digit indication hand at a time interval equal to or less than a half of the predetermined period.