93results about How to "Taking into account real-time" patented technology

The invention discloses a method for quickly identifying two-dimension code system type in images, comprising a learning training process and a classification identifying process. The learning training process is as follows: collecting and building a sample image set of various two-dimension code images; converting each sample image into a grey image, performing Gaussian smoothing filtering and binaryzation to obtain binaryzation images; scanning prospect boundaries of the binaryzation images in the horizontal and vertical directions, obtaining an outer boundary point set of the two-dimension code; enabling the two-dimension code to be horizontal by rotating images, achieving horizontal correction of the two-dimension code; performing partitioning, combining and normalizing for the two-dimension code; performing fast wavelet transform for the normalized sample image to obtain a wavelet characteristic sample set. The classification identifying process is as follows: extracting wavelet characteristic of the to-be-identified image to build a distance measurement model; using the K nearest neighbor algorithm to identify code system type. The method is convenient and quick, has real-time performance, accuracy and high identification rate.

The invention provides an intelligent anti-theft device of an automobile based on an in-vehicle communication system, comprising a body control module (BCM) and an in-vehicle communication system. The BCM acquires the vehicle window state and the anti-clamping information sent by a vehicle window anti-clamping module via an LIN (Local Interconnect Network) bus and receives remote control information at the same time to carry out anti-theft setting on the vehicle; the anti-theft setting information and the window and door information are sent to the in-vehicle communication system by a controller area network (CAN) bus. The in-vehicle communication system acquires the concerned automobile parameters of users, including window and door information, fuel amount and tire pressure via the CAN bus; the whole vehicle is positioned by an integrated global positioning system (GPS) functional module; the vehicle positioning information and the acquired information are informed to the users in time by an integrated global system for mobile communication (GSM) functional module, so that the intelligent anti-theft effect of the vehicle is realized.

The invention relates to an electromyographic signal classification method based on a multi-kernel support vector machine. For a sample with complex distribution, based on the classification performance of a single-kernel support vector machine, the classification accuracy and the quantity of support vectors are easily influenced. The method combines a multi-kernel support vector machine method with a binary tree combination strategy and comprises the following specific steps of: collecting electromyographic signals of the lower limbs of a human body through an electromyographic signal acquisition instrument; denoising the electromyographic signals containing interference noise by using a wavelet coefficient inter-scale correlation denoising method; extracting the features of the denoised electromyographic signals to obtain the features of the electromyographic signals by using denoised wavelet coefficients; and classifying on the basis of the multi-kernel support vector machine. The method can well meet the multi-classification requirement of lower extremity prosthesis control, and takes into account both accuracy and instantaneity, and has broad application prospects in the multi-movement mode recognition of intelligent prosthesis control.

The invention relates to a deep-sea vessel dynamic positioning oriented high-precision real-time state estimation method and system. The method includes: separating a high-frequency signal caused by a first-order wave force from a low-frequency vessel motion signal so as to obtain a high-frequency motion component and a low-frequency motion component; in a marginalized particle filter frame, subjecting both the high-frequency motion component the low-frequency motion component to parameter estimation and state estimation; using results of the parameter estimation and state estimation as input of next-cycle parameter estimation and state estimation, and repeating the steps until the end. The deep-sea vessel dynamic positioning oriented high-precision real-time state estimation method and system has the advantages that the difference between high-frequency linear motion and low-frequency linear motion is fully considered, the nose parameter estimation method applicable to both high-frequency and low-frequency motions is provided, the state estimation method based on marginalized particle filter and oriented towards vessel dynamic positioning is therefore provided, and state estimation precision increase and timeliness are balanced.

The invention discloses a video fingerprint extraction method based on the SURF algorithm. Feature points of a video key frame are extracted through the SURF algorithm, a feature vector set of the feature points is generated, then clustering is performed on the generated feature point set using the K-means clustering algorithm, each clustering center is taken as a visual word of the video so as to generate a visual word set of the video, the visual words of the video are used to replace feature vectors of the original feature points in the key frame, and statistics is performed on the word frequency information of the visual words, the word frequency information of each key frame visual word is subjected to the quantification process and represented by a binary sequence, that is the fingerprint information of the key frame, and finally, the fingerprint information of all key frames are serially connected according to the timing sequence to generate the fingerprint information of the video. The video fingerprint extraction method has advantages of good accuracy and good robustness, and can get a certain balance in terms of the real-time performance.

The invention relates to a computer technology, and provides a news information recommendation method for a smart television, used for solving the problem that news information cannot be recommended by the existing smart television. The technical scheme provided in the invention can be summarized by comprising the following steps of: constructing a corresponding massive news information resource library in the background at first, then, constructing the latest news information library from the massive news information resource library according to the time freshness, analyzing an information browsing record under a terminal account stored by a service side, extracting a characteristic keyword set, obtaining information of the geographical position, where a smart television client side is, and a social hotspot keyword set in the current time simultaneously, then, searching an information content having relatively high association degree with keywords or nearby information contents from the latest news information library by using browsing record characteristic keywords, social hotspot keywords and the position information of the smart television client side, and finally, obtaining the final information recommendation set. The news information recommendation method for the smart television disclosed by the invention is convenient for users and applicable to smart television systems.

The invention discloses a control method and device for an air conditioner set. The control method comprises the steps that target environment parameters are obtained; based on the target environmentparameters, according to a preset air conditioner set control model, control parameters of each air conditioner in the air conditioner set are predicted, wherein the air conditioner set control modelis obtained in the mode that a neural network model is trained through a preset data set, the preset data set comprises environment parameters of the environment where the air conditioner set is located in the preset historical period, the control parameters of each air conditioner in the air conditioner set, and power consumption parameters of the air conditioner set. Through the control method and device, the technical problem of a poor energy saving effect of an air conditioner in the prior art is solved.

The invention provides a parking lot-vehicle cooperated intelligent parking system and a method based on robot vision. The system consists of a parking lot service center, vehicle-mounted equipment of an intelligent vehicle and a user mobile terminal, wherein the parking lot service center comprises a vehicle tracking module, a path planning module, a data management module and a communication module; the vehicle tracking module is used for detecting a vehicle target in a driving area of the parking lot, and obtaining the correct position, and comprises a global tracker, a plurality of local vision sensor groups and corresponding local trackers; the path planning module is used for planning a driving path from the current position of the vehicle to a terminal point; the vehicle-mounted equipment comprises a communication module and a vehicle control module; the vehicle control module is used for controlling the intelligent vehicle to automatically drive to the terminal point according to the path which is planned by the service center and received by the communication module; the user mobile terminal is used for sending the request information of driving into / out of the parking lot to the parking lot service center. The system is used for realizing the automation and intelligence of the vehicle driving into / out of the parking lot.

The invention provides a timeliness and face quality considered filtering selection method and system. The filtering selection method comprises a receiving step, a feature extracting step, a quality scoring step, a quality rating step, a judging step, a storing step and a returning step. The timeliness and face quality considered filtering selection method provided by the invention has the beneficial effects that the filtering selection method adopts a supervised machine learning method based on real mass data to obtain a fuzzy evaluation standard of face image quality which is convenient for a machine to effectively retrieve, and in a certain period of time, a method to quickly decide and select high quality images is provided, which can reduce the invalid storage and search volume under the mass data; and a cascade configuration method is provided for rapid filter selection, which considers both the timeliness and image quality, and also improves the flexibility.

The invention discloses a large-scale fire situation analysis system based on spatial positioning. The system comprises data acquisition assemblies, a data communication assembly, a data processing platform, and a data analysis and display platform. The data acquisition assemblies are capable of carrying out spatial positioning and acquiring ambient environment parameters. The data acquisition assemblies collect ambient environment parameters and send the collected data and position information externally regularly by a wireless transmitting module. The data communication assembly receives data sent by the data acquisition assemblies, filters the data, and forwards the filtered data to the data processing platform. The data processing platform receives the data sent by the data communication assembly and processes the data to obtain situation information being able to reflect the fire situation. The data analysis and display platform is used for displaying the processed fire situationdata in real time and carrying out fire situation analysis and evaluation based on the fire situation. Therefore, the development trend of the fire can be sensed in real time and the fire situation isdisplayed at the data analysis and display platform, so that the disaster level is evaluated.

The invention discloses a multi-exit evacuation method based on prediction time. The multi-exit evacuation method comprises the following steps: 1, proposing prediction evacuation time to acquire a formula; 2, carrying out optimal planning based on a global path of A* algorithm; and 3, calculating a formula of exit evacuation capability. According to the multi-exit evacuation method based on the prediction time disclosed by the invention, by fully taking consideration of key points including a distance of every pedestrian to the exits, pedestrian expected speed, the total number of the pedestrians corresponding to each exit and different evacuation capability of different width exits, of crowd evacuation from multiple exits, a calculation method of evacuation time required by selection ofdifferent exits by the pedestrian is given, and the evacuation is simulated according to actual scenes. An experimental result proves that compared with a conventional mode, the time prediction modeldisclosed by the invention has the advantages that the evacuation to the pedestrian is simulated and predicted preferably, and effective help is provided for drawing an emergent evacuation plan.

The invention relates to a seeding monitoring method based on a wheat seeder. The method includes the following detailed steps that (1), an analog voltage signal and land wheel speed data are collected; (2) the analog voltage signal is analyzed according to feature information of the analog voltage signal; (3) the seeding state is determined according to the analyzed feature information of the analog voltage signal and the land wheel speed data. According to the method, a high-power infrared photoelectric seeding sensor is used, the seeding sensor directly outputs the analog voltage signal, a single chip microcomputer is used for collecting the voltage signal, a state judgment algorithm is designed according to features of voltage, voltage change, and continuity and discontinuity of wheat sowing in line, the defect of poor anti-dusting performance of a photoelectric monitoring device is overcome, three seeding states such as normal state, blocking state and blank pipe state can be well monitored, real-time performance and accuracy can be considered simultaneously, and miss-seeding can be timely and accurately discovered. The invention further discloses a seeding monitoring device and system based on the wheat seeder.

The invention relates to the technical field of new energy vehicle remote monitoring and intelligent analysis, in particular to a new energy electric vehicle multifunctional data acquisition and intelligent analysis system. The new energy electric vehicle multifunctional data acquisition and intelligent analysis system comprises a vehicle-installed data acquisition terminal, a data transceiving protocol, a cloud enterprise platform, a government supervision platform and a data visualization display system, wherein the data visualization display system comprises a mobile platform and a remote service platform. According to the multifunctional data acquisition and intelligent analysis system for the new energy electric vehicle, by designing the multi-interface data acquisition terminal suitable for an electric vehicle, acquired data sources are complete, the data format conforms to the national standard, data transmission takes real-time performance, safety and availability into consideration, various specific intelligent applications are carried out based on collected data, the received data are processed and analyzed through the powerful storage, operation and processing capacity of the cloud enterprise platform, specific functions such as position service, driving behavior analysis and fault diagnosis are achieved, and various user main body requirements of research personnel,after-sales personnel, drivers, government supervision and the like are met.

Provided are an edge computing system, communication control method, and computer-readable recording medium having a communication control program stored therein capable of appropriately controlling data communication between an edge device and an edge server, ensuring real-time data processing real time performance and storage of all data. The edge device (30) determines the state of the edge server (40) and at least one of the communication loads between the edge device and the edge server and sends data to the edge server (40) in one of a first data sending mode in which multiple data received by a sensor (20) is sent continuously and a second data sending mode in which data selected based on a priority of pre-allocating to the sensors (20) among multiple data and saving the rest data temporarily and sending later.

The invention discloses a dynamic human face tracking method. The method comprises the steps of S1, tracking a target by using a feature-based tracking algorithm, and when the tracking of the target is lost, going to and executing the step S2; S2, predicting a human face region position after the tracking is lost, establishing a feature point template, matching pixel points of the predicted humanface region position with the current feature point template, initializing an optical flow tracking algorithm by successfully matched feature points, tracking the target, and according to a loss stateof the feature points, updating the feature point template; and S3, when a target position which can be tracked by the feature-based tracking algorithm is restored, returning to and executing the step S1. The method can be suitable for human face tracking under complex conditions of deflection, shielding and the like, and has the advantages of simple implementation method, high tracking efficiency and precision, capability of taking stability and timeliness into account, high environmental adaptability, good anti-interference capability and the like.

The invention discloses an obstacle trajectory prediction method and device, equipment and a medium. The obstacle trajectory prediction method and device are suitable for unmanned equipment (or calledunmanned vehicle or automatic driving equipment). The method comprises the following steps: acquiring a dynamic obstacle type and image or point cloud data recognized in the driving process of the unmanned equipment; selecting a first-level prediction model from a plurality of level prediction models of the same type according to the type of the dynamic obstacle; adjusting the level of the prediction model or the number of the dynamic obstacles according to a relationship between a prediction duration sum value of the first-level prediction model and a duration threshold value to obtain the optimal level of the prediction model or the optimal number of the dynamic obstacles; enabling the optimal level prediction model to perform trajectory prediction based on the image or point cloud dataof the dynamic obstacle; or enabling the prediction model to perform trajectory prediction based on the image or point cloud data of the optimal number of dynamic obstacles. According to the invention, the obstacle trajectory prediction mode is optimized, and the trajectory prediction real-time performance and prediction precision can be both considered.

The invention discloses a message processing method between different devices, a server and a computer storage medium. The first equipment and the second equipment adopt different operating systems, wherein the first device and the second device both communicate with the MQTT server, the MQTT server is further connected with the IOT server, the IOT server determines that the first device successfully logs in the IOT server and receives a task request sent by the first device and forwarded through the MQTT server, and the task request carries service content of the first device; the IOT servergenerates a corresponding service task according to the service content, and pushes the service task to the MQTT server; thus the MQTT server pushes the service task to a second device subscribing theservice task to execute the service task. According to the method disclosed in the technical solution, when the messages between different devices are processed, the real-time performance of the messages can be considered, the utilization of network resources is reduced, and the network flow consumption is reduced.

The invention discloses a non-cooperative signal sensing system and a multi-dimensional parameter estimation method of a satellite-borne passive SAR and belongs to the technical field of radars. The invention provides a non-cooperative SAR signal sensing system and the non-cooperative SAR signal multi-dimensional parameter estimation method. The non-cooperative SAR signal sensing system comprises a zenith sensing antenna, a direct signal array receiving unit, a ground detection antenna and an echo signal array receiving unit, and receives non-cooperative SAR direct signals and echo signals. The non-cooperative SAR signal multi-dimensional parameter estimation method involves a direct-arrival signal time-frequency-space characteristic estimation unit and an antenna beam pointing parameter estimation unit and achieves multi-dimensional parameter estimation and antenna pointing estimation of non-cooperative SAR signals. Compared with a traditional satellite-borne SAR system, the satellite-borne passive SAR does not need to transmit any signal, can sense and capture available non-cooperative SAR signal sources in space in real time, and uses the non-cooperative SAR signal sources to perform double-station SAR imaging detection.

The invention discloses a client network media information management method and a client system. The method comprises the following steps: a. establishing a buffer area in the client internal memory; b. generating a plurality of data structures in the buffer area according to the type of the network media information; c. performing a classified storage to the received network media information according to the data structures. By performing a classified storage to data through establishing a buffer area in the client internal memory, real-time performance and high-efficiency of the processing of client system data and experience of subscribers are both considered, therefore, processing speed and processing quality of the client system are improved effectively and satisfaction degree of subscribers to the client products is also improved.

The invention discloses an ultra-low power consumption passive wake-up method and system. The method specifically comprises the steps: S10, monitoring air signals every t0 second; S20, judging whetherthe field intensity of the air signals is greater than a set threshold value or not, and if yes, executing the step S30; if not, executing the step S40; S30, entering a synchronous word waiting mode,and preparing to receive data; and S40, entering a sleep mode. The invention provides a passive wake-up mechanism of preamble sequence loading time slot information. Through special fragment design on the leader sequence of the wake-up sequence, the low-power-consumption node starts the shortest receiving time length to reliably receive the effective data and identifies that the invalid frame immediately returns to the sleep mode, the power consumption saving effect is achieved to the maximum extent, and the real-time performance of communication is considered.

The invention provides a frame adjustment method in support of real-time video cache multi-way read. A data sharing cache mechanism which is mainly based on a master cache, and partially based on a second level cache is introduced. The condition that the integrated speed is reduced due to the fact that the read speed of one reader is relatively slow is avoided; the read completeness of video frames is ensured; and moreover, the demands of different readers for the video timeliness and fluency can be all taken into consideration.

The embodiment of the invention discloses a diagnosis method and device, and a computer-readable storage medium. The diagnosis method comprises the following steps: a standby host receives first data through a serial bus, and identifies the received first data as a request message sent by a communication host; the standby host receives second data through the serial bus, and identifies the received second data as a response message sent by a slave station; and the standby host carries out diagnosis on the status of communication between a master station and the slave station according to the request message and the response message. The diagnosis method and device and the computer-readable storage medium adopting the technical scheme have the advantages that the standby host identifies the request message sent by the communication host and the response message sent by the slave station in sequence, and then carries out the diagnosis according to the request message and the response message (instead of the standby host sending the request message to achieve the diagnosis), so that both real-time diagnosis on the status of the communication between the master station and the slave station and smooth master station communication can be achieved.

The embodiment of the invention provides a mold state monitoring method and device, an industrial personal computer, a storage medium and a system, and the method comprises the steps of obtaining a template image of a target mold and a to-be-detected image, the template image being an image of the target mold in a normal state, and the template image comprising a region of interest of the image of the target mold; according to the region of interest of the template image, adopting a pyramid template matching algorithm to identify and position the to-be-detected image to obtain a target region of the to-be-detected image; determining sensitive sub-regions contained in the target region according to a pixel difference between the target region and the region of interest; and according to the area of the sensitive sub-region, determining whether the target mold is abnormal, so that automatic monitoring of the mold quality is realized, the real-time performance and the accuracy of mold abnormality detection are considered, and the mold monitoring quality and the production efficiency are improved.

A programmable logic device configuration method and system. The invention provides a PLD configuration method and system, the method comprising: the client and the server are connected through the tcp socket protocol, the server is connected to the PLD through the programmer; when the server receives the communication data from the client, the programmer connects the Send the communication data to the PLD; the PLD executes the communication data, and sends the execution result to the client through the programmer and the server; the client processes and outputs the execution result. Through the implementation of the invention, the client connects to the server through the tcp socket protocol to realize remote programming and downloading, realizes the purpose of time-sharing online debugging and configuration for multiple users, and solves the technical problem that the existing PLD configuration technology cannot be used for remote configuration.

The invention relates to a dynamic environment information detection method based on a semantic segmentation network and multi-view geometry, and the method comprises the following steps: calibratinga camera, and removing image distortion; acquiring and inputting an environment image; segmenting the input image through a semantic segmentation network to obtain masks of all objects and realize preliminary dynamic segmentation; ORB feature points being extracted from the input image, and then a descriptor being calculated; detecting and eliminating dynamic feature points by using a method of combining multi-view geometry and semantic information; matching the ORB feature points to obtain pose information of the robot; judging and inserting a key frame, and performing point cloud processingthrough a local mapping thread to obtain a sparse point cloud map; loop detection being used for optimizing the pose and correcting the drift error. According to the invention, the operation precisionand robustness of the RGBD SLAM system in a high-dynamic environment are improved. And meanwhile, by using the lightweight semantic segmentation network, the system storage and time expenditure can be reduced, and the real-time performance of the system is also considered while high precision is maintained.

The invention discloses an overvoltage chopped wave energy consumption balance control system applied to a train. The system comprises a train network control system and transmission control units. The train network control system obtains running data of each motor train section through the corresponding transmission control unit and dynamically adjusts the regenerative braking and resistance braking working conditions of each motor train section. The train network control system sends out an overvoltage chopped wave threshold lifting mark according to the condition in the running process of each motor train section, each transmission control unit adjusts an overvoltage chopped wave opening / closing threshold in real time according to the corresponding overvoltage chopped wave threshold lifting mark and middle direct current, and overvoltage chopped wave energy consumption balance control is achieved. By the adoption of the overvoltage chopped wave energy consumption balance control system, the real-time performance is high, control is accurate, overvoltage chopped wave energy consumption balance control can be achieved under the working conditions of train electric braking, traction and idling, long-time and large-range chopped wave energy consumption balance control at a whole train level is guaranteed, the real-time performance and flexibility in the adjusting process can be taken into consideration as well, and safety of a chopped wave pipe element and a braking resistor is protected.

The invention relates to a data filtering method. Through a series of formulas, the weighted average of original data with predication value is obtained so that a filtering purpose is achieved. The invention also provides a precise location method for coordinates of skeleton points. By obtaining a basis of reference, movable coordinates of skeleton points are obtained so that the skeleton points are precisely located.

The embodiment of the invention discloses a video file processing method, a terminal, a server and a system. The video file processing method comprises the steps: a transmission request is received, and a target video file and a target receiver are determined according to the transmission request; network information sent by the target receiver is acquired; video transcoding parameters are determined according to the network information; and the video transcoding parameters and the target video file are sent to a preset server, so that the server conducts transcoding processing on the target video file according to the video transcoding parameters. According to the method, the experience in the video sharing process can be better improved, and the real-time performance and the speed in thevideo transmission process are achieved simultaneously.

The invention discloses a position increment information issuing method and system. The method comprises the following steps: a terminal reporting position increment information; if the position of the terminal is within the preset scope of the position of position increment information, verifying the position increment information through other terminals; and if verification reaches a preset condition, issuing the position increment information. The method provided by the invention can verify the position increment information issued by a user so as to ensure the authenticity.

The invention discloses an electric energy quality communication method applied to a microgrid. In the method, data transmission is performed based on transmission control protocol (TCP) / internet protocol (IP) by using a network interface as a physical interface; two ports are formed on an electric energy quality device and are used for transmitting data with a background monitoring system and defining stipulations to perform hierarchical processing on the data; the two ports comprise a real-time data port and an off-line file port; the real-time data port transmits a message by a passive waiting-for-call mechanism; and the off-line file port transmits a message by an active information-uploading mechanism and the passive waiting-for-call mechanism. By the electric energy quality communication method, various types of data of the electric energy quality can be transmitted and a reasonable data transmission flow is found, so that the problem that the electric energy quality data cannot be transmitted in the conventional stipulation is solved, information which a user wants to see can be displayed quickly, unobstructed network and data transmission without packet loss are guaranteed, and the problem about how to transmit a large number of electric energy quality data is solved.