557results about How to "Achieving identifiability" patented technology

The invention relates to a tunnel lining disease detection device based on an infrared temperature field and a gray level image. The tunnel lining disease detection device comprises a vehicle-mounted mobile platform, illumination equipment, a photoelectric encoder, a GPS (Global Position System) receiver, an inertia unit, a synchronous controller, an area-array camera, an infrared thermal imager, an acquisition server, a display control device and a power supply system; tunnel lining two-dimensional image data, infrared temperature field data and fracture surface deformation data are combined with positioning data of the GPS, the inertia unit and the photoelectric encoder to establish a tunnel model with gray level information, temperature information and fracture surface deformation; and tunnel lining cracks are analyzed, and the length, width and lining leakage water information of the cracks are automatically detected. For the tunnel lining disease detection device, the advantages of infrared temperature field detection and two-dimensional gray level image crack detection are combined so that the detection result is relatively reliable, the speed is rapid and the working efficiency is greatly improved.

The invention provides a voice wake-up control method and a voice wake-up control device and a terminal. The voice wake-up control method comprises the following steps: receiving first voice data, and carrying out voice recognition, thus obtaining a first recognition result; entering the wakeup mode if wakeup words exist in the first recognition result; receiving second voice data, and carrying out voice recognition, thus obtaining a second recognition result; and carrying out responding according to the second recognition result, and keeping the receiving for the voice after response. After the technical scheme is adopted, the convenience of voice wake-up control is realized.

The invention brings forward a traffic label identification method of vehicle-mounted laser scanning point cloud data. The method comprises the following steps: 1, point cloud real-time preprocessing; 2, point cloud structure feature obtaining; 3, multi-scale Markov random field point cloud clustering; and 4, traffic label identification. The method has the following advantages: "surface-shaped", "linear-shaped" and "scattered" features of point clouds are reinforced, differences between points are enhanced, and while under-segmentation is avoided, reasonable segmentation of the scale of a traffic label component can be rapidly realized; classification and identification of a traffic label can be conveniently realized from point cloud data of deficiency of a part of the traffic label, caused by ground object shielding or ground object self-occlusion; the method can effectively satisfy the requirements for rapid extracting, monitoring and identifying city components at present, can be conveniently promoted to the industry of manned or unmanned navigation and barrier avoiding based on computer vision, helps a driver to perform navigation and decision-making under complex road conditions, and effectively reduces the traffic accident probability.

The invention discloses a power channel corridor routing-inspection method based on a tilt photography three-dimensional reconstruction technology, wherein the method includes the steps: A, combining a laser radar data measurement technology and a tilt photography technology, and rapidly constructing power transmission line channel high-precision three-dimensional base map data by using the laser radar measurement technology; B, acquiring three-dimensional real scene data of a channel corridor by using the tilt photography measurement technology; and C, carrying out fused analysis of the three-dimensional real scene information and a laser radar channel base map, effectively identifying and extracting trees and obstacles in the channel corridor, and then generating a tree barrier assessment report. By using the method, qualitative analysis of the tree barrier can be effectively turned into quantitative analysis, the position of a to-be-felled tree in the channel can be calculated, the felling area is statistical, and thus the safe operation of the line corridor is ensured.

The invention relates to the power distribution net monitoring field and provides a real-time state monitoring recognition method for indicator lights of a power device fault indicator. In the method, digital video signals collected by image collecting equipment of a camera, and the like are processed; video frames are extracted from the video signals; monitoring targets are determined, that is the target region of each indicator light in the video frames, and corresponding numbers are distributed; the pixel color change and the intensity roughness of each indicator light in the target regions of two adjacent frames are used for identifying the flash alarming of the fault indicator; specific conditions of faults are determined according to the identified target numbers of the flash alarming and the combinations thereof; the result is real-timely transmitted to a backstage by a distribution communication network to remind working personnel of the fault happening. The real-time state monitoring recognition method realizes the real-time monitoring recognition alarming for the light state of the fault indicator of the power equipment, ensures the reliability of a system, facilitates the installation and the modification of the system and guarantees the safety of installing and maintaining personnel.

The invention discloses an intelligent washing method based on the wireless automatic identification technology for a washing machine. The intelligent washing method based on the wireless automatic identification technology for the washing machine relates to clothes where intelligent labels are attached, an intelligent label identification and reading device, an intelligent washing machine information processing device, a washing machine operation display screen ( a touch display screen ) and a user. According to the intelligent washing method based on the wireless automatic identification technology for the washing machine, information of the clothes is identified based on the wireless automatic identification technology, and the washing process customizing function is expanded. The intelligent washing method comprises the steps that (1) the information of the clothes can be identified through the intelligent label identification and reading device which is set by the washing machine or is connected with the washing machine, and (2) personalized customization of the washing process is achieved. Due to the fact that automatic identification of the information of the clothes and personalized customization of the washing process are achieved, the clothes washing effect is optimized, and the degree of intelligentization of the washing machine is increased. The invention further provides an idea of establishing a domestic clothes washing information database by connecting the washing machine with a network and uploading data.

The invention discloses a face identification method, a face identification device and a mobile terminal, and belongs to the field of identification of biological features. The face identification method comprises the following steps of acquiring a visible light face image set through a double-light-ray induction camera according to a preset acquisition rule; acquiring an infrared face image set through the double-light-ray induction camera according to the preset acquisition rule; judging whether a face template image matched with any one of face images in the visible light face image set and the infrared face image set exists on a home terminal; and when the face template image exists on the home terminal, passing through the face identification. According to the face identification method, due to the face identification by the double-light-ray induction camera, face image acquisition and face identification can be realized under different environment light ray conditions, and the accuracy of face identification is improved; and furthermore, the mobile terminal does not need to be provided with a plurality of cameras, so that the hardware space is saved, the performance-to-cost ratio is improved, and a user can carry and operate the mobile terminal conveniently.

The invention discloses a monocular real-time target recognition and pose measurement method. The method comprises the steps that various target object feature point data are obtained, and the target object feature point data and three-dimensional world coordinates and image coordinates of the four vertexes of a target plane are stored into a target database; a target to be recognized is selected, and target feature point data and target information are extracted from the target database; a video camera extracts real-time scenes, image preprocessing is carried out on the extracted real-time scenes, real-time scene feature points are extracted, and real-time image feature point data are obtained; target image feature points in the target database and the real-time scene feature points are matched; a homography is obtained through calculation through the matched feature point data, and target recognition is completed; pose measurement and position determination of the target are completed. According to the monocular real-time target recognition and pose measurement method, the speed advantage of an ORB algorithm is utilized, the single video camera is used as the sensing means, and real-time recognition and pose measurement of the moving target are achieved.

The invention relates to an autonomous working robot system. The autonomous working robot system comprises a robot body and a remote control system; the robot body comprises an all-directional moving platform cable of moving in the horizontal plane at will, a lifting mechanism installed on the all-directional moving platform and capable of lifting relative to the all-directional moving platform, an industrial robot installed on the lifting mechanism, a control cabinet and a positioning and recognizing system, wherein the control cabinet and the positioning and recognizing system are installed on the all-directional moving platform; the remote control system transmits automatic control signals to the control cabinet, the positioning and recognizing system feeds back positioning and recognizing signals to the control cabinet, and the control cabinet controls moving of the all-directional moving platform, lifting of the lifting mechanism and work of the industrial robot according to the automatic control signals and the positioning and recognizing signals. The autonomous working robot system can move in an all-directional mode, and is simple and compact in structure and high in operation accuracy, reliability and safety, and the intelligence and the practicability of the industrial robot are greatly improved.

The invention discloses an image recognition method and device and a video monitoring device. The method comprises the following steps: detecting a target object in image information by using a detection model trained based on a depth learning algorithm; recognizing the feature information of the target object by the recognition model based on the training of depth learning algorithm; extracting the structural features of the target object from the feature information. Thus, by integrating the depth learning technology of artificial intelligence and the video surveillance technology in depth,using the detection model and recognition module trained by depth learning algorithm to detect the target object in the image information and recognize the feature information of the target object, and then extracting the fine structural features of the target object, the image recognition efficiency and recognition accuracy are greatly improved, the high-efficient structured management of the massive video data is realized, the effective information resources are formed, and the retrieval speed is greatly improved, especially the intelligent real-time detection and recognition of the two mainobjects in the video, namely, the human and the vehicle.

The present invention provides a head carried stereo vision hand gesture identifying device and belongs to the field of computer vision and man-computer interaction technology. The head carried stereo vision hand gesture identifying device consists of four parts: stereo vision imaging head, stereo vision board, head carried display and worn computer. The stereo vision imaging head obtains the hand grey image of the wearer; the stereo vision board calculates the real-time the dense parallax map and transmits the dense parallax map and the grey image to the worn computer; and the worn computer completes hand tracking and hand gesture identifying operation and showing the calculation results in the head carried display. The present invention can realize the hand tracking and hand gesture identifying under worn computer environment, complete hand gesture mouse, hand language identification, hand written character identification, etc. and intelligent man-computer interface based on hand gesture.

The invention discloses a fast recording method with handwriting identifying function, which comprises the steps of collecting handwriting data that is hand input by a user, displaying the handwriting that is hand input by the user, identifying multiple handwritings that are hand input by the user, and editing identified results. The picture and text recording speed by using the fast recording method and the device thereof is almost same with the human recording speed when using papers and pens, and the fast recording method and the device thereof can realize novel automatic identifying and differentiating as well as late stage editing of the handwritings such as characters, diagrams and the like.

The present invention provides a fake plate vehicle identification and inspection system and method based on a vehicle-borne RFID tag and a dual-frequency information collection base station. The RF/video collection base station in a road in the system collects the RFID electronic tag number, the vehicle plate number, the vehicle color, the vehicle photo and other information of a running vehicle in the road and sends the information to a background database system in real time through a network, then the database compares whether the RFID electronic tag number, the vehicle plate number and the vehicle color are consistent with a database record or not, if not, the vehicle is identified as a vehicle with a fake plate, and the information of the vehicle plate number, the vehicle color, a vehicle model, the vehicle photo and the like are sent to nearby traffic police on duty to stop the vehicle. According to the system and the method, an RFID electronic tag is collected through the radio frequency technology, the vehicle plate number and the vehicle color are identified through the radio frequency identification technology, the real-time background comparison and warning information sending are carried out, and the real-time and accurate inspection of a vehicle with a fake plate can be realized.

The invention discloses an automatic detection and identification apparatus of a concealed object. The apparatus comprises a scanning device, an adjusting module, a segmentation positioning module, a bar and rod combination model generation module, a non-human-body object preliminary detection module, a non-human-body object distribution module and a category recognition module. By using the automatic detection and identification apparatus of the concealed object, the detection and the identification of the concealed object are turned to be automatic from manual, which reduce a usage requirement of personnel, decrease a personal error and shorten detection interpretation time.

The invention discloses an automatic building identification method based on a Fourier descriptor. The method is used for automatically identifying illegal buildings of illegal land use. The method comprises the following steps: an original building RGB color image is converted into a gray edge image through filtering, enhancement and edge detection; all the contour of the gray edge image is extracted according to a Fourier descriptor method; the contour points are written in the plural form, discrete Fourier transform is carried out, and then modulus operation is performed on the value after transformation to obtain a normalized Fourier descriptor; the extracted contour data is simplified according to a DP algorithm; a building shape standard template library is established according to the simplified building contour; the Euclidean distance with the standard template library is calculated, and the Euclidean distance is used to represent the similarity of two Fourier descriptors; and finally, whether the extracted contour is a typical building shape feature is judged. Therefore, the purpose of automatically identifying an illegal building in a video image is achieved.

The invention discloses a transformer fault classification and identification method based on a vibration analysis method. The method comprises the following steps: S1) selecting a transformer test object, and collecting transformer vibration signals under different states as sample data; S2) calculating the sample data by utilizing a Hilbert-Huang transform EEMD (ensemble empirical mode decomposition) method to obtain an intrinsic mode function; S3) extracting characteristic vector V in each intrinsic mode function component; S4) carrying out dimensionality reduction on the characteristic vector through a principal component analysis method, coordinates being projected to a two-dimensional image; S5) carrying out classification on the sample data through a K neighbor method; S6) calculating the distance between a test sample and an original sample through a distance formula; S7) carrying out mode recognition; and S8) outputting corresponding transformer fault type in mode recognition. Operation state of a transformer can be judged visually and effectively.

The invention discloses a forest fire pre-warning method and system based on deep learning and belongs to the field of firefighting safety. The method comprises: S1, allowing an unmanned aerial vehicle to sense, in real time, temperature and humidity information of a driving area, taking a forest image of the driving area, transmitting the forest image to a ground station; synchronously transmitting locational information to the ground station; S2, judging fire pre-warning according to the temperature and humidity information, and transmitting a fire pre-warning signal to the ground station; S3, allowing the ground station to receive the fire pre-warning signal, and using a deep learning algorithm to process the forest image to obtain whether a fire is about to occur or whether fire results are present; S4, transmitting fire information to a forest management center. The temperature and humidity information is sensed and subjected to comparison; visual judgment is made on chances for afire to occur; if chances for the fire to occur are great, the forest image is processed via the deep learning algorithm; fire pre-occurrence and post-occurrence conditions can be precisely recognized; it is convenient for relevant personnel to accurately acquire fire conditions in the first place.

The invention discloses an automatic detection and identification method for hidden articles. The method comprises the following steps of: performing millimeter-wave scanning on a detected person to obtain an original image; regulating the original image to obtain a target image; segmenting and locating parts of a human body according to the target image; generating a bar combination model; detecting a non-human body target according to the original image to obtain a non-human body target distribution original image; obtaining position distribution information of the non-human body target distribution original image relative to the human body through the bar combination model; and identifying the type of the non-human body target and displaying the position distribution information of the hidden articles relative to the human body. By the automatic detection and identification method for hidden articles provided by the invention, a manual mode of detection and identification for the hidden articles is changed to an automatic mode, demands on staff is lowered, human error is reduced, and the detection and judging time is shortened.

The invention provides a character identification method based on deep characteristic and shallow characteristic fusion, and a storage medium. A convolutional neural network model is trained to detectthe deep characteristics of an image to be identified, and shallow characteristics are integrated for analysis to realize the identification and the classification of characters on the image to be identified. Compared with a way that image characters are identified only through the shallow characteristics (which are obvious characteristics and can be judged by human eyes), the character identification method is characterized in that the shallow characteristic identification can be introduced to effectively increase the identification rate of the characters on the image to be identified. According to the character identification method, the deep characteristic identification and the shallow characteristic identification are combined, a robust license plate number character method is provided to improve the robustness of license plate number character identification under a monitoring environment, and license plate number identification accuracy is effectively improved.

The invention discloses an enclosed parking lot gateway intelligent fee charging and collecting system comprising an intelligent parking box, a local server, a cloud end server and a rail. Only the intelligent parking box needs to be additionally arranged without establishment of a local area network in an existing enclosed parking lot so that construction and maintenance cost can be saved. The local server is arranged so that storage can be performed in the local server firstly and timekeeping and fee charging can be performed under the situation of network disconnection. Prepayment can be realized. If payment is provided, a signal is transmitted to a control module, a fee collecting completion instruction is transmitted from the cloud end or local and the rail is controlled to be lifted so that automatic rail lifting can be realized without queuing when a vehicle leaves the parking lot. The local server is connected with the cloud end server and used for uploading the backup and downloading synchronous updating from the cloud end in a timing way so that data are accurate and reliable, and reliable data support is provided to a mobile inducing system.

The invention relates to a wheel type intelligent autonomous mobile service robot, which is divided into an upper part and a lower part arranged on a chassis. The robot comprises a control system, a movement mechanism, an embedded single board computer, a holder vidicon and sensors, wherein the movement mechanism is controlled by motor drive and (or) a controller; an industrial personal computer (IPC) is connected with the motor drive and (or) the controller by a serial port; the holder vidicon controls the orientation and the angle thereof by the serial port, provides the ambient environmental information of the robot, and connects the collected information with the embedded computer by an image collection card; the sensors are arranged on the upper part and the lower part of the robot, and are connected to the embedded computer after information processing; and the upper part and the lower part of the robot are in folding connection by an upper connecting plate and a lower connecting plate, and a transverse folding shaft and (or) an extraction and insertion part are arranged between the upper connecting plate and the lower connecting plate. The robot can realize autonomous obstacle avoidance according to the ultrasonic sensors, thereby increasing the capabilities of positioning and navigation and map building in none-artificial environments.

The invention relates to an intelligent blumeria graminis spore picture identification method. The method includes the steps of selecting different expert models to enable the intelligent identification accuracy to be capable of adapting to different requirements; pre-processing blumeria graminis spore pictures; dividing the blumeria graminis spore pictures; extracting the color, texture and shape features of the blumeria graminis spore pictures; conducting intelligent identification on the extracted features of the blumeria graminis spore pictures. By means of the intelligent blumeria graminis spore picture identification method, the blumeria graminis spore density in unit volume in air for a certain time can be rapidly calculated, and the basic conditions of blumeria graminis spore diseases are obtained. By means of the intelligent blumeria graminis spore picture identification method, automatic dividing of the blumeria graminis spore pictures is achieved, and the problem that an existing manual dividing method is low in efficiency is solved; automatic identification and automatic counting of the blumeria graminis spore pictures are achieved, and the problem that an existing manual (expert) identification method is low in efficiency and prone to making mistakes is solved; the intelligent blumeria graminis spore picture identification method can be suitable for the different manual (expert) using requirements and high in adaptability.

The invention discloses a device and a method for automatically detecting lens defects through modulation by an optical grating. The device comprises an isolation detecting system, a motion control system and a light source system, wherein the isolation detecting system is arranged in a camera bellows (13); the motion control system is arranged at the bottom of the camera bellows (13) and arranged on one side of the camera bellows (13); the device is characterized in that the optical grating (6) is fixed on a linear lead screw guide rail (5), a planar backlight (10) is fixed below a to-be-detected lens (4) in parallel and connected with a light source controller (11), and a main controller (12) controls the motion control system through a motion control card (9). According to the method, lens images are sampled twice through movement of the optical grating, the lens defects are classified, positioned and measured through analysis of gray values and morphological characteristics of bright and dark field images, and lens detection accuracy and efficiency are greatly improved.

A method for identifying Chinese full name according to Chinese short form of entity includes screening out candidate primitive set from normally used entry-bank according to abbreviation sentence to be identified, utilizing multi-path priority function combination to screen said set, calculate priority of candidate primitive, holding candidate primitive with high priority and seeking out one candidate primitive with highest priority as final result. The system used for realizing said method is also disclosed.

The disclosed image processing and recognition method for real-time monitor on power high-voltage circuit breaker comprises: with camera, decoder and video server, sending acquired signal to monitor center for remote video monitor; extracting target picture to recognize the ON/OFF state by sorting match with color and character structure features for fault analysis with accuracy ratio more than 98%. This invention can improve information level for power system.

The invention discloses a porcine respiratory disease automatic recognition alarming method. The method comprises two steps of constructing a support vector machine model of pig's cough sound and a disease a pig suffering from, collecting the pig's cough sound and recognizing signals. According to the porcine respiratory disease automatic recognition alarming method, pigs' cough sound signals are collected and analyzed through the support vector machine model, the automatic recognition and alarming for a porcine respirator disease are achieved, the pig's health condition can be remotely monitored at an appropriate time, a great number of human and material resources for porcine respiratory disease detection are saved, and the feeding efficiency of pigs is improved.

The invention discloses a sweet spot identification and comprehensive evaluation method for a tight sand reservoir. According to the method, eight conventional logging curve data are taken as a basis. By utilizing the SPSS data analysis software, common factors capable of comprehensively reflecting the characteristics of a reservoir in a target area are extracted based on the PCA (principal component analysis) method. According to the physical significance of each common factor, the sweet spots of the tight sand reservoir are recognized, and a sweet spot qualitative recognition model for the tight sand reservoir is established. On the above basis, a common factor calculation model for porosity and permeability is established in conjunction with physical property test data, so that the types of the reservoir are divided. According to the physical property parameters of various reservoir types and the parameter characteristics of common factors, a quantitative evaluation standard for the tight sand reservoir is determined. Therefore, the qualitative recognition and the quantitative evaluation for the sweet spots of the tight sand reservoir are realized. Based on the method, a novel idea and a novel method are provided for the interpretation and evaluation of the tight sand reservoir. Therefore, the interpretation and evaluation reliability of the tight sand reservoir is improved. The exploration and development cost is reduced.

The application relates to a signal processing method and device, a terminal, an earphone and a readable storage medium. The method comprises the steps of: when carrying out a conversation by the earphone, acquiring a sound signal of an external environment on the basis of an electroacoustic transducer on the earphone; identifying a feature audio in the sound signal, and judging whether the feature audio is matched with a preset sound model; and if yes, executing an operation of reminding a user according to a preset reminding mode corresponding to the feature audio. By the method, acquisitionand identification on sound of the external environment can be implemented only by utilizing an inherent device on the earphone, so that the user can also pay attention to the dynamic state around inthe conversation process of the earphone, safety and convenience in the process that the user uses the earphone are promoted and the user has better use experience.

The invention discloses a method for automatically identifying and playing panoramic videos. The method includes the steps: acquiring a video image frame in video data, and calculating the width-height ratio of the video image frame; respectively acquiring a color value of a margin row pixel pair and a color value of a margin line pixel pair in the video image frame when the width-height ratio of the video image frame is 2, and calculating an average value of color difference values of the margin line pixel pair and an average local fluctuation coefficient of the color difference values of the margin line pixel pair when variances of color difference values of the margin row pixel pair are smaller than or equal to variance threshold values of the color difference values of the margin row pixel pair; generating corresponding mapping spherical surfaces according to the video image frame to play when the average value of the color difference values of the margin line pixel pair is smaller than or equal to an average threshold value of the color difference values of the margin line pixel pair and a local fluctuation coefficient of the color difference values of the margin line pixel pair is larger than or equal to a local fluctuation coefficient threshold value of the color difference values of the margin row pixel pair. By the method, the panoramic videos are automatically identified and played.

The invention discloses a forest fire early warning method and system based on a fuzzy Bayesian network and belongs to the fire-fighting safety field. The method comprises the following steps that anunmanned aerial vehicle is equipped with a plurality of sensors to inspect a forest along a set route, senses data of a driving area in real time and sends the data to a ground station; the ground station combines the number of local sunny days and the number of flammable plants to carry out stage treatment on flammable grades, and carries out early judgment of fire warning according to temperature, humidity, smoke and gas information; the ground station receives the data of each sensor, then uses a fuzzy Bayesian network to process the sensor data, and calculates and acquires a fire occurrence probability; when the probability of the fire is high, the ground station sends a fire warning signal, whether there is the fire, a real-time situation of the fire and location information to a forest management center; and when the probability of the fire is low, the unmanned aerial vehicle flies at the same height along the set route. In the invention, a fuzzy Bayesian network algorithm is used to process the sensor data, the fire probability can be accurately calculated so that correlation personnel can accurately acquire a fire condition at first time.