1891results about How to "Realize automatic identification" patented technology

The invention discloses a mobile terminal, a direct charging power adapter and a charging method. The method comprises the steps: the mobile terminal detects the short circuit condition of two communication pins in the USB interface of the mobile terminal, when the mobile terminal is inserted by an external equipment which is the power adapter, the mobile terminal can automatically identify the type of the external connected charging equipment by adopting the power adapter communication; at the same time, a special express charge mode is designed for the direct charging power adapter, when a battery of the mobile terminal is concentratedly charged, the battery is directly charged with heavy current by using the charging voltage outputted by the direct charging power adapter, and the volt value of the charging voltage can be dynamically adjusted according to the variation of the voltage of the battery. According to the above, on the premise that the safety of the battery charge is guaranteed, the great increase of the battery charging speed is realized, the required time of single charging of the mobile terminal is shortened, the influences on daily use of user caused by the repeatedly and long time charging of the mobile terminal is reduced, and the user satisfaction is greatly improved.

The invention discloses a computer automatic identification method of photo face and live face, which comprises the following steps: (1) performing face detection and eye location; (2) capturing an eye area; (3) calculating an opening-closing level of the eyes in a normalized image; (4) establishing a model for judging wink actions through applying conditional random field theory; (5) processing each frame image in an unidentified video as per steps (1) to (3), and judging whether the wink action exists in the unidentified video through applying the model and the reasoning method of the conditional random field theory in the step (4), thereby completing the automatic identification of the photo face and the live face. The invention realizes the computer automatic identification of the photo face and the live face with a single camera head.

The invention provides a multi-modality medical image identification method based on deep learning. The method includes the steps that on the basis of multi-modality medical images of a patient's part to be detected, a registration method is adopted to display the multi-modality medical images in the same three-dimensional space; on the basis of the multi-modality medical images, R-CNN is adopted to identify lesion areas in the multi-modality medical images; according to coordinates of the lesion areas in the multi-modality medical images, lesion bodies are displayed in the same three-dimensional space, and according to image blocks corresponding to diagnosed lesion areas, a dense sampling method and a CNN are adopted to obtain occurrence probabilities of various preset disease types. The invention provides a multi-modality medical image identification device based on the deep learning. The device includes a multi-modality medical image display module, a lesion area detection module, a lesion body display module and a preset disease-type occurrence probability module. According to the multi-modality medical image identification method and device, the automatic identification of the lesion areas in the medical images is achieved, and effective reference data is provided for further diagnosis by doctors.

The invention discloses an electronic device, a bill information identification method and a computer readable storage medium. The method includes performing identification on bill type of a bill in abill picture by utilizing a pre-trained bill picture identification model after receiving the bill picture to be processed; performing inclination correction on the bill picture by utilizing a predetermined correction rule; determining to-be-identified fields corresponding to the identified bill type; determining a first identification model corresponding to each to-be-identified field, performing area identification on line field areas of the bill picture subjected to inclination correction by calling the corresponding first identification models so as to identify the target line character zone containing the character information of each to-be-identified field; determining a second identification model corresponding to each to-be-identified field and performing character identificationby calling the corresponding second identification models so as to identify the character information contained by the target line character zones of each to-be-identified field. The technical schemeachieves accurate and high-efficiency automatic identification on text information in bill pictures.

The invention discloses a laser vision guided automatic welding track tracking system which comprises an embedded type industrial personal computer with an image processing device, a laser vision sensor, a welding robot, matched welding equipment and a workpiece clamping workbench; the laser vision sensor is installed on a welding gun in an advanced parallel manner in the welding direction through a laser sensor fixing element; the welding gun is installed on a tail end flange disc of the welding robot through a welding gun fixing element; and the embedded type industrial personal computer is connected with the laser vision sensor through a circuit. The invention also discloses a laser vision guided automatic welding track tracking method. With adoption of the laser vision guided automatic welding track tracking system and method, without the process of teaching in advance, the welding production efficiency and the adaptive ability are improved through real-time detection and tracking; and meanwhile, the problem of tracking lag caused by advanced detection is prevented, and the problem that when a sensor is too near the welding gun, large noise of coupling feature images is caused by factors including strong arc light irradiation, high temperature and smoke dusts, thus the real time and the tracking accuracy of the system are restricted is solved.

The invention relates to an intelligent traffic guidance method based on a floating car under a congestion condition. The method includes that by means of a city traffic information collecting and processing system based on the floating car, real-time average traveling speed Vi of a city road network and a real-time traffic condition are obtained, and a congested road section is identified; and based on a road network topological structure, the congested road section is divided into a guidance control area and a guidance buffering area according to the real-time average travelling speed Vi and the real-time traffic condition of the road network, and corresponding guidance information is generated automatically. On the basis of the city traffic information collecting and processing system, the real-time average traveling speed Vi of the city road network and the real-time traffic condition are obtained, traffic congestion is identified, a range of the guidance control area and the guidance buffering area is calculated, and the corresponding guidance information is generated. By means of the intelligent traffic guidance method, the congested road section can be identified automatically, a possible affecting area is determined intelligently, a traffic guidance problem under the congestion condition is fully solved, loss caused by the traffic congestion is effectively reduced, and operation efficiency of the road network is improved.

The invention provides a method for rapidly and automatically identifying and removing ocular artifacts in an electroencephalogram signal and belongs to the technical field of biological information and the method is mainly applied to a process of acquiring and preprocessing the electroencephalogram signal. The method comprises the following specific steps of: carrying out discrete wavelet transformation on an acquired multi-channel electroencephalogram signal and an electro-oculogram signal to obtain multi-scale wavelet coefficients; using the wavelet coefficients connected in series as an input for analyzing an independent component, and rapidly acquiring the independent component by using a negative entropy criterion-based Fast ICA (Independent Component Analysis) algorithm; identifying the ocular artifacts through a cosine method, performing zero resetting on the independent component, and projecting the other components through ICA inverse transformation and returning to all electrodes of an original signal; and finally obtaining the electroencephalogram signal for removing the ocular artifacts through inversion of the wavelet transformation. By utilizing the method for rapidly and automatically identifying and removing the ocular artifacts in the electroencephalogram signal, the problems that an ICA method is poor in discrete effect and low in convergence rate when beingapplied to noisy electroencephalogram signals are solved, and the function of rapidly and automatically identifying and removing the ocular artifacts in the electroencephalogram signal is realized.

An interactive digital stereoscopic sand table system is composed of a stereoscopic image generating system and a man-machine interactive system. Opengl and other 3D engines are adopted by the stereoscopic image generating system to draw the three-dimensional terrain, a human eye tracking and pointing light technology is applied, stereoscopic display without assistance is achieved, and a series of image accelerating technologies is adopted to accelerate the rendering process of an image. A three-dimensional building model is arranged in a three-dimensional terrain target area, and precise space distribution and the good visual effect are achieved. A naked eye stereoscopic displayer is formed by the stereoscopic image generating system. The man-machine interactive system controls the three-dimensional terrain scene or three-dimensional model data in the stereoscopic image generating system through gestures, and is achieved by presetting a gesture recognition interface. The corresponding gestures control the three-dimensional terrain scene or the three-dimensional model data in the stereoscopic image generating system to be enlarged or reduced or horizontally moved or rotated or to enter, and the corresponding gestures capable of distinguishing different control significances can be configured according to needs.

The invention discloses an automatic transmission line identification system and method based on a multilayer convolutional neural network. The system comprises an equipment picture database, a targetdetection module, a target tracking module and a target identification module; the equipment picture database stores image or video information of obstacles on a transmission line in a classified way, and marks images or videos; the target detection module locates an obstacle target on the line in the video or image, and provides object position information of the present frame; according to thedetected object position information as well as prior information of structuring of the detection target, the target tracking module tracks the target online; and the target identification module identify types of different equipment online in different scales, backgrounds, illumination and angles. The system and method have the advantages that good characteristics that reflect the target can be learned automatically via deep learning, artificial design or redesign is not needed, execution can be realized via once training, and only model optimizing and multiple offline training are needed.

The invention relates to an electric commercial vehicle battery box single-trip replacement robot which has the advantages of reducing the land occupation because the size of a replacement robot is effectively reduced, and being easily matched with an electric bus because an installing mode of a battery replacement device in the existing replacement robot is changed into a suspension installing mode. The electric commercial vehicle battery box single-trip replacement robot comprises a frame assembly, wherein the frame assembly is arranged on a walking assembly, a temporary storage rack is arranged at one side of the frame assembly, a control cabinet is arranged at the other side of the frame assembly, a lifting transmission assembly is arranged at the top of the frame assembly and is connected with a lifting assembly and also connected with a balance weight assembly, an objective table assembly capable of rotating in situ is suspended at the lower part of the lifting assembly, a fork assembly and a battery push handle assembly are arranged at the bottom of the objective table assembly, V-shaped wheel sets matched with a rectangular steel upright of a replacement robot frame are arranged at four corners of the lifting assembly, an objective table assembly rotating drive device is arranged on the lifting assembly, and a limit device is arranged on the objective table assembly.

The invention discloses an inland river water area abnormal behavior ship automatic identification system and method; the method comprises the following steps: obtaining inland river water area ship navigation AIS message information, hydrology meteorology department environment information, CCTV video images and depth of field images in real time; parsing ship abnormal behavior mode types, and building a ship abnormal behavior sample database; building a depth learning network model to parse ship behaviors, thus obtaining ship abnormal behavior mode and GPS positioning information; detecting the ship in the CCTV video image, using the depth of field image to obtain the ship three dimension space information, and thus obtaining the ship video positioning information; fusing the GPS positioning information, the video positioning information, the ship abnormal behavior mode and ship detected characteristics, carrying out ship target association, and automatically identifying the abnormal behavior ship in the CCTV video. The method and system can effectively solve the problems that the abnormal behavior ship cannot be easily identified in the CCTV video; the method and system are high in identification rate, can provide safety warning for waterborne traffic, thus further improving the maritime affair supervision intelligent level.

The invention provides a remote sensing image water area automatic extraction method and system based on deep learning. The method comprises the following steps: preprocessing remote sensing image data, obtaining different water area indexes through waveband operation, obtaining prior feature information extracted from a water area, fusing the remote sensing image data, Google map tile data and the like to realize multi-source feature information fusion, and then constructing a data set through visual interpretation and vectorization; training, verifying and testing a semantic segmentation model WE-Net built by the convolutional neural network; and calling a remote sensing image water area segmentation model WE-Net to realize automatic classification of the water area, and outputting a binary grayscale image which is a classification and extraction result. The method has the advantages that a water area in a research area can be extracted by calling a remote sensing image water area segmentation model, manual visual interpretation can be replaced, manpower and material resources are saved, and auxiliary technical support is provided for updating of a high-precision image map, including lake area change detection, water system change and the like.

The embodiment of the invention discloses a content type detection method and device. The method comprises the following steps: extracting the features of content to be detected; adopting at least two kinds of classifiers matched with the content to be detected according to a feature extraction result, and performing type detection on the content to be detected; determining a final type detection result corresponding to the content to be detected according to type detection results obtained by the at least two kinds of classifiers. According to the technical scheme provided by the embodiment of the invention, the type of acquired content can be detected automatically, the detection time is shortened, and the detection cost is reduced.

The invention provides an illegal service vehicle detecting method and system. Based on traffic information collected by a bayonet detection system, the vehicle activity degree in a road network is analyzed through a clustering statistical method. A legal service taxi operating mode is tapped. Illegal service vehicles are detected from a group with the highest degree of activity. According to the method and the system, automatic illegal service vehicle identifying, blacklist managing, investigating and handling and other functions are realized; automatic detection of vehicles in the road network is realized; illegal service vehicles are identified; and an offsite enforcement system is provided with a reliable basis, which is conductive to urban road traffic management.

The invention discloses an eight-axis robot space curve welding system for recognizing a welding line by means of lasers. The system comprises a tilting/rotating two-axis positioner used for fixing a workpiece, a laser sensor, a laser sensor fixing element, a welding gun, a welding gun fixing element and a welding robot. The workpiece is fixed to the tilting/rotating two-axis positioner and does tilting and/or rotating motion along with the tilting/rotating two-axis positioner. The laser sensor is mounted on the laser sensor fixing element. The laser sensor fixing element is clamped on the welding gun. The welding gun is mounted on the welding gun fixing element. The welding gun fixing element is mounted on a flange plate at the tail end of the welding robot. Both the laser sensor and the welding gun can move along with the tail end of the welding robot. The invention further discloses an eight-axis robot space curve welding method for recognizing the welding line by means of the lasers. The problems that existing space curve welding line off-line programming is not high in precision, the teaching workload of space curve welding line teaching programming is large, and efficiency is low are solved. Efficiency and precision are high.

The invention provides a machine learning-based video content reviewing method and device. The method comprises the steps of extracting video information, audio information and text information in to-be-reviewed video resources; identifying and processing content violating rules of the video information through a trained convolutional neural network, and identifying and processing convent violating rules of the audio information and the text information separately through a trained recurrent neural network, so as to determine whether the video information, the audio information and the text information comprise content violating rules; and if the video information, the audio information or the text information comprises content violating rules, determining and outputting the type of the content violating rules included in the video information, the audio information or the text information. Through adoption of the method, content violating rules included in the video resources can be identified automatically, the video content is not reviewed by people, so that the video content is reviewed more efficiently.

The invention belongs to an electromagnetic compatibility fault diagnosis method and particularly relates to an interference source identification method in a system-grade electromagnetic compatibility fault diagnosis. The interference source identification method is characterized by comprising the following steps of: step 101, utilizing positioning sensitive equipment; step 102, carrying out fault tree analysis on the positioning sensitive equipment; step 103, performing the fault tree analysis so as to obtain a priority level of a coupling path; step 104, testing to obtain interference testing data; step 105, storing the testing data into a database; step 106, obtaining a potential interference source through the fault tree analysis of the step 102; step 107, searching and determining the priority level of the interference source; step 108, combining the step 105 and the step 107 to identify the interference source; step 109, judging whether the interference source is a determined interference signal or not; if not, carrying out step 110; otherwise, carrying out step 111; step 110, carrying out environment monitoring; and step 111, obtaining the determined interference signal and finally, finishing the compatibility fault diagnosis. The interference source identification method in an electromagnetic compatibility fault diagnosis system has the advantages of convenience for use, short period, low cost and controllable faults.

The invention discloses a washing machine control method and a washing machine and belongs to the field of washing machines and control methods thereof. The washing machine control method and the washing machine are designed in order to solve the problem that an existing method is difficultly applied to practice. The washing machine control method includes the steps that before each piece of to-be-washed clothing is put in a washing bucket or in the rolling and weighing process of the to-be-washed clothing, each piece of to-be-washed clothing is shot or photographed, and a control device confirms basic information of each piece of to-be-washed clothing according to comparison of at least one picture or at least one image intercepted from video recording images and clothing data in a database; the control device automatically selects washing procedures according to the basic information of all the to-be-washed clothing. By means of the washing machine control method and the washing machine, the problem that the existing method is difficultly applied to practice is solved, use is convenient, and the accuracy of judging clothing information is high.

The invention discloses a visual system and a working method for a high-voltage hot-line operating robot. The visual system for the high-voltage hot-line operating robot comprises an operation end. The operation end comprises a left mechanical arm and a right mechanical arm. The left mechanical arm and the right mechanical arm are both installed on an insulation bucket. A left stereoscopic video camera and a left stereoscopic camera are installed on the left mechanical arm. A right stereoscopic video camera and a right stereoscopic camera are installed on the right mechanical arm. A visible light video camera I is arranged on the front side of the insulation bucket. A video camera support is arranged on the back side of the insulation bucket. A visible light video camera II is arranged at the top end of the support. A ground remote end is connected with the left stereoscopic video camera, the right stereoscopic video camera, the left stereoscopic camera, the right stereoscopic camera, the visible light video camera I and the visible light video camera II. The invention further discloses a working method for the high-voltage hot-line operating robot. Operation staff can be thoroughly free from a high-altitude high-risk working environment, labor intensity is lowered, operation safety is greatly improved, automatic identification of the position and the posture of an operated object is achieved, and automation level and intelligent level of operation are improved.

The invention discloses a robot welding path autonomous planning method based on 3D point cloud data. The robot welding path autonomous planning method comprises the following steps of acquiring the original three-dimensional cloud data of a workpiece weld profile, and preprocessing the original three-dimensional cloud data; according to the workpiece weld characteristics, constructing ruler CAD models with the same characteristics, and converting characteristic surface information of ruler CAD models as three-dimensional point cloud data; performing local registration operation on the three-dimensional point cloud data of the ruler CAD models and the three-dimensional point cloud data generated after the workpiece weld profile is preprocessed; according to the local registration operation, performing continuous characteristic searching, thereby obtaining complete workpiece weld information; extracting weld position and posture information marked in the complete workpiece weld information; and processing the extracted weld position and posture information, and planning the robot welding path. The self-adaptability of robot welding can be improved, and the workload of scene teachingand off-line programming of operating staff can be remarkably reduced.