3784results about How to "Strong real-time" patented technology

The invention discloses an unmanned vehicle dynamic path programming method based on environment uncertainty, comprising steps of establishing a vehicle kinetics model, establishing a dynamic environment model and necessary conditions for anew programming a path, obtaining a motion state original value of the unmanned vehicle, a vehicle motion state original target value and a vehicle motion state candidate target value, generating a candidate path, obtaining an optimal path through selection based on a safety index and a rapidity index, and reprogramming the optimal path of the unmanned vehicle when the unmanned vehicle motion environment satisfies the condition where the new path can be programmed. Compared with the prior art, the invention can not only satisfy the safety requirement for safety driving, but guarantees the driving efficiency under the constraint of the vehicle model. The invention realizes the coordination optimization of the performance index through distribution of various weights, realizes the real-time planning under the condition where a plurality of dynamic obstacles exist, and effectively improves the safety of the unmanned vehicle driving.

The invention discloses a machine vision and inertial navigation fusion-based mobile robot motion attitude estimation method which comprises the following steps of: synchronously acquiring a mobile robot binocular camera image and triaxial inertial navigation data; distilling front/back frame image characteristics and matching estimation motion attitude; computing a pitch angle and a roll angle by inertial navigation; building a kalman filter model to estimate to fuse vision and inertial navigation attitude; adaptively adjusting a filter parameter according to estimation variance; and carrying out accumulated dead reckoning of attitude correction. According to the method, a real-time expanding kalman filter attitude estimation model is provided, the combination of inertial navigation and gravity acceleration direction is taken as supplement, three-direction attitude estimation of a visual speedometer is decoupled, and the accumulated error of the attitude estimation is corrected; and the filter parameter is adjusted by fuzzy logic according to motion state, the self-adaptive filtering estimation is realized, the influence of acceleration noise is reduced, and the positioning precision and robustness of the visual speedometer is effectively improved.

The invention relates to a self-adaptive background modeling and moving target detecting method which comprises the following steps: establishing an initial background, extracting a moving target binary mask, updating a self-adaptive background and detecting a moving target: firstly, determining the pixel gray value of the initial background by using an inter-frame difference method; successively, carrying out binarization treatment on a difference image by using a self-adaptive threshold valve when a difference image is obtained by a current frame image minus a background image and post-treating of morphological filtering and the like to obtain the moving target binary mask; then, carrying out dynamic update on the gray value of a pixel which is not corresponding to the moving target binary mask in the background image by adopting an region-based background updating method; and finally, carrying out logic 'and' operation by using the moving target binary mask and the current frame input image to detect the moving target. The invention can effectively establish the reliable initial background and carry out real-time dynamic update on the background to solve the problem that the detection accuracy of the moving target is influenced by background disturbance and illumination change.

The invention discloses an automatic guidance system based on radio frequency identification labels and vision, and the method of the automatic guidance system. The invention is characterized in adopting a four-wheel structure, wherein two front wheels are used for steering and two rear wheels are used for driving; a direct current motor is used as the travelling and driving device, which is driven to steer by a stepping motor; the invention is provided with a wheel steering angle positioning device, so the invention has relatively high dynamic response ability; a black and white parallel guide belt is adopted as a guide path, with the radio frequency identification labels discontinuously laid below, and red work station characters arranged at both sides; CCD collects road surface information, and the brightness of light source adaptive controls according to image gray information; characters are extracted by utilizing color differences; straight lines are rapidly HOUGH transformed and identified; a control signal is sent to AGV controller after processed by an industrial control computer, and the direct current motor and the stepping motor are controlled. In order to effectively realize the communication dispatch between AGVS in real time, radio frequency identification labels are adopted for positioning, and a wireless transceiver module is adopted for communication between AGVS and a host. The invention has the advantages of good environmental adaptability and navigation precision, and lower cost.

The invention discloses a video flame-detecting method based on multi-features fusion, which is characterized in that: a fast Gaussian hybrid model is established and a pixel counter is arranged when a computer reads a first frame image a monitoring site captured by a colored camera; when the computer reads new images of a second frame and the following frames, a fast Gaussian hybrid method is firstly used for carrying out motion detection so as to extract a moving object and then a flame color decision is carried out to the moving object to obtain an alternative flame area; and finally, flicker analysis is carried out on the alternative flame area so as to identify a real flame object. The video flame-detecting method carries out modeling to flame color characteristics, motion characteristics and flickering characteristics in flame areas; various flame detection interfering resources are gradually and rapidly eliminated in accordance with the recognition sequence of motion, color and flickering. The test results show that the method has relatively strong robustness; in addition, based on an AMD 2.04GHz processor, the processing speed can reach 22 frames per second for video images with pixels of 320 multiplied by 240.

The invention proposes a robot global path planning method based on deeply enhanced learning, which belongs to the robot learning and global path planning technology fields. The method comprises: in the training session: firstly, installing a top-view camera in a scenario; constructing a deep neural network; after a training path is created, outputting the executing actions by the deep neural network according to the images photographed by the camera; and according to the execution effect of the actions, optimizing the parameters of the deep neural network; then, updating the position of a target; performing different path planning trainings to obtain a final deep neural network; and in the execution session: outputting the executing actions for the robot by the final deep neural network according to the images photographed by the camera so that the robot executes the actions; and if the robot reaches the position of the target after its execution of the actions, then, completing the global path planning by the robot. The method of the invention is very practical in use, does not require manual participation, or the entrance of a scenario for constructing an environment map in advance. The method can be applied to multiple scenarios at a low cost.

The invention discloses a third-party data service system based on Internet-of-Things data collecting. The third-party data service system comprises a data collecting cloud service module, a Web portal management module, a Web Service remote calling assembly module, a mobile application module and a data center management module. The data collecting cloud service module comprises a thread pool dispatching management module, a load optimization management module, a network management module, a data communication management module, a data storage module and an alarm module. The Web portal management module comprises a user and authority management module, an equipment management module, a monitoring point management module, a real-time monitoring module, a visual customization module, a spare part management module, an after-sale maintenance management module, a repair management module, a remote operation management module and a remote diagnosis module. The mobile application module comprises a real-time inquiry module, an alarm inquiry module, a repair registration module, a user feedback module, a maintenance inquiry module and a real-time warning module.

This invention relates to a device for monitoring peccancy cars based on omnibearing vision sensors including a microprocessor, a monitor sensor monitoring road situations and traffic signal lamps, in which, the sensor, an omnibearing vision sensor, is connected with the microprocessor including: an image data read module, an image data file storage module, a sensor rating module, a virtual test line designing module, a designing module for roadway transit directions, a designing module for traffic signal lamp state test regions, an image spread process module, a color space transforming module, an adaptive background deduction process module, a connected region identification module, a moving car tracing module and a car paccancy judgment module with a road paccancy judgment unit for directions and a road paccancy judgment unit without roadway directions.

The invention discloses a method and a system for voiceprint recognition based on vector quantization, which have high recognition performance and noise immunity, are effective in recognition, require few modeling data, and are quick in judgment speed and low in complexity. The method includes steps: acquiring audio signals; preprocessing the audio signals; extracting audio signal characteristic parameters by using MFCC (mel-frequency cepstrum coefficient) parameters, wherein the order of the MFCC ranges from 12 to 16; template training, namely using the LBG (linde, buzo and gray) clustering algorithm to set up a codebook for each speaker and store the codebooks in an audio data base to be used as the audio templates of the speakers; voiceprint recognizing, namely comparing acquired characteristic parameters of the audio signals to be recognized with the speaker audio templates set up in the audio data base and judging according to weighting Euclidean distance measure, and if the corresponding speaker template enables the audio characteristic vector X of a speaker to be recognized to have the minimum average distance measure, the speaker is supposed to be recognized.

A chip used for realizing communication between multi-kernel in chip is prepared as setting a sharing storage in chip, providing data transceiving buffer region and data staring channel, carrying out data transceiving and interacting in said sharing storage to realize communication mechanism of data-sharing and data-interacting as well as interruption-interacting by using ARM kernel and DSP kernel to write data in address unit preset by ARM kernel/DSP kernel through said sharing storage and informing the opposite party to fetch data.

The invention provides a flow-based abnormal communication behavior detection method and system, and belongs to the field of passive discovery of network security abnormal events. The detection systemcomprises: a configuration management module used for configuring a white list IP, a key target IP and a general target IP, a data acquisition module and a storage module used for acquiring and storing network flow data information, a key target abnormity detection module and a general target abnormity detection module used for detecting key targets and general targets respectively, and an abnormity evaluation module. According to the detection method provided by the invention, different methods are adopted to construct flow models for important network nodes and common network nodes, networkanomaly detection is carried out respectively, network events of important targets and common targets are associated, and network intrusion behaviors and abnormal communication behaviors with certainhazards are mined. The method has good discovery capability for various types of traffic abnormal behaviors, and is low in computation complexity for flow data, and is high in abnormity discovery real-time performance.

The invention relates to an embedded omnidirectional ball vision object detection and mobile monitoring system and an embedded omnidirectional ball vision object detection and mobile monitoring method. Omnidirectional ball vision is a visual system with a global domain visual field and can acquire all scenes of the whole global domain at one time without the revolving and scanning of a camera. The system comprises an omnidirectional ball vision imaging system (comprising two fish-eye panoramic lens, two CMOS image acquisition chips, an FPGA controller and an SRAM memory chip), and a multi-path DSP parallel image processor (comprising a master control DSP and two paths of DSP parallel image processors). The imaging system acquires omnidirectional ball vision images by matching the two fish-eye panoramic lens and the two CMOS chips, wherein the master control DSP is responsible for data scheduling and communication, and the two paths of the parallel DSPs are independent from each other and can process the identification tracking of a static navigation mark and the real-time monitoring of a dynamic object in parallel. The method and the system have the advantages of high integrity, small volume and quick processing speed and are particularly suitable in the military or domestic field such as safety monitoring, mobile vehicle body navigation and the like.

The invention provides a text emotion classifying method in the stock field, belonging to the technical field of stock tendentiousness analysis. The text emotion classifying method is characterized in that feature selection is carried out on an enlarged stock emotion word through public news information comprising stock news and the like and by using an improved evaluation group; feature weighting selection is carried out on emotion word in the stock Chinese text by using absolute word frequency weighting; and finally, tendentiousness analysis is carried out on stock news by using a Bayes, K-NN or SVM (support vector machine) text emotion classifying algorithm. The method provided by the invention has the advantages of simplicity and feasibility, and is convenient for calculation.

The invention provides a QR recognizing method based on image processing. The method includes the following steps of (1) preprocessing which includes graying, image enhancement, binaryzation and image denoising; (2) locating which includes determining position information of 12 angle points on a QR code sign position detection graph and position information of angle points at the right lower corner of the QR code symbol; (3) decoding which includes conducting geometrical correction according to various position information of the acquired QR code signs in the locating phase, extracting standard QR code signs and drawing a sampling network. The method has the advantage that the method can be applied to the automatic field of industrial production, achieves an automatic recognition function of QR codes without manual participation, and can solve the problem in actual application that the image background is complex, the image quality is not high, and the QR code position detection image proportional characteristics are damaged. The algorithm can reach the high identification rate of 98% under the stable operation condition. The algorithm is high in real-time performance. Time used by recognizing a frame of an image is about 150 ms.

The invention relates to a monocular vision ranging method based on edge point information in an image and belongs to the unmanned aerial vehicle navigation and positioning technical field. The method includes the following steps that: two frames of images are selected from an image sequence captured by a downward-looking monocular camera fixedly connected with an unmanned aerial vehicle so as be adopted to construct an initial map and an initial depth graph, a first frame is adopted as a first key frame in the map, and a camera coordinate system corresponding to the first frame is adopted as a world coordinate system, and initialization is completed; and three threads, namely, a motion estimation thread, a map construction thread and a depth graph estimation thread are carried out parallelly, wherein the motion estimation thread aligns known map and depth graph information with a current frame so as to obtain a ranging result, and optimizes the existing map information according to the ranging result, and the map construction thread and the depth graph estimation thread operate simultaneously so as to maintain the map and depth graph information. According to the method of the invention, the multi-core architecture of a modern processor is fully utilized, and the edge point information in the image can be effectively utilized, and based on corner point information, the efficiency of the algorithm is improved. The method has higher adaptability.

The invention provides an image perspective-based micro unmanned aerial vehicle indoor autonomous navigation method. An indoor environment is divided into a corridor, a step and a room, a environmental form is determined by analyzing perspective characteristics of a visual image, obstacle detection is further performed by methods with vanish points, center lines or light streams to obtain corresponding navigation and control information, and micro unmanned aerial vehicle indoor autonomous obstacle avoidance and flight can be realized. An environmental three-dimensional model is not needed, the algorithm operating time can be greatly shortened, the real-time property of a control instruction is improved, and the method has high autonomous property and high reliability. The method is low in calculated amount, high in real-time property, low in hardware requirement and high in positioning accuracy and provides a feasible technical scheme for engineering application to indoor navigation of a micro unmanned aerial vehicle.

The invention relates to a text classification method of a Chinese web page based on steam clustering, belonging to the technical field of internetwork data mining. The text classification method comprises the following steps of: acquiring a web page in real time; removing unprocessed labels in the format of the web page, and analyzing the characteristic information of texts of the web page; segmenting the content of the texts, using as ngram participles, and forming a plurality of word strings; computing the weight value of each word string; extracting the word string with a high weight value, and using the word string with the high weight value and the corresponding weight value thereof as characteristic vectors; computing the similarity of the characteristic vectors and characteristic information and a known class; computing obtained total similarity, and classifying the texts to the know class or establishing a new class; judging whether the know class is divided into two subclasses or not according to the number of characteristic items of the known class; and storing processed text records and the information of the known class. The text classification method sufficiently excavates the effective information of web page texts aiming at the characteristics of the web page texts and is incremental, fast, effective and more practical.

The invention is used in an evolution network. After eNodeB of the evolution network base station receives the request for updating the tracing area from a UE, the method comprises: a) said eNodeB selects a MME/UPE satisfying best QoS from the MME/UPEs connected to it as the destination MME/UPE after reselection; b) said eNodeB sends an access request to said destination MME/UPE; c) said MME/UPE interacts with the serving MME/UPE of said UE before reselection to get the mobility management context of said UE; d) said MME/UPE executes the location update registration process for said UE and becomes the serving MME/UPE of said UE after reselection.

The invention discloses a device and method for monitoring the evolution and distribution of a mining-induced fracture. Generation, evolution and distribution of the mining-induced fracture are monitored through a method of monitoring acoustic wave or vibration generated in fracture of coal or rock. The device mainly comprises an anti-explosion acoustic wave monitor, an anti-explosion power source and a ground monitoring analysis center, wherein the anti-explosion acoustic wave monitor consists of a sonic sensor and a signal conversion and data acquisition instrument; the sonic sensor is arranged on a roadway base plate, an anchor rod tail end or a drill hole; and an acoustic wave or vibration signal monitored by the sonic sensor is collected and processed by the signal conversion and data collection instrument, and is transmitted to the ground monitoring analysis center through an optical fiber port to be subjected to processing, positioning and quantitative analyzing and be labeled on a plane, a cross section or a space diagram according to the position and size, so as to show the position and size of the fracture. The device and method provided by the invention has the beneficial effects of large monitoring range, a large amount of comprehensive monitoring information, high automation degree, strong instantaneity and capability of being applied to monitoring and forecastingthe coal rock dynamic disasters, such as rock burst, and outburst and water burst of coal and gas and the like.

The invention discloses a negative obstacle detection method based on the local structure feature of a laser radar point cloud. In collected laser radar point cloud data, three structure features including local point cloud distance hopping, local point cloud dense distribution and local point cloud height decreasing are detected line by line; on the basis of the three structure features, candidate point pairs which may belong to a negative obstacle are obtained through extraction and screening in single line laser point cloud; all candidate point pairs obtained by the laser point cloud of each line laser are clustered on the basis of point pair length consistency and spatial position consistency to obtain a negative obstacle candidate area; and through area filtering and point pair amount filtering, obtaining a negative obstacle area. By use of the method, the negative obstacle in environment can be effectively detected, and the method has the advantages of good detection success rate, small calculation cost and high instantaneity.

The invention discloses a mid-term air traffic conflict detection method based on 4D flight path and radar data, which relates to air traffic control automation. In the method, accurate 4D flight path data and real-time radar data are projected onto a display panel of an air traffic control system, each aircraft pair is filtered according to the accurate 4D flight path data and the real-time radar data, and aircrafts which are unlike to come into conflict with other aircrafts in 30 minutes are determined; and the detection is focused on the aircraft pairs which have potential to run into conflicts, the covariance between the relative speed and relative position of the aircraft pairs is calculated by using coordinate transformation according to the vertical interval and time interval of two aircrafts, and then the probability that a predicted position interval is smaller than a safe interval at time t is calculated and a detection report is made. In the invention, the drawbacks of long-term and short-term conflict detection are overcome, and the long-term conflict detection, mid-term conflict detection and short-term conflict detection are combined to ensure flight safety. The average conflict detection time is about 0.028 seconds, and the method has high real-time performance.

The invention provides an accurate and rapid road violation and parking full-automatic snapshot system. The system comprises a front-end monitoring point part, a network transmission part and a centermanagement unit. The vehicle detection technologies mainly comprise the vehicle dynamic detection technology and the vehicle tracking technology. A matched vehicle tracking method is estimated by utilizing the motion detection method based on time-based motion historical images and feature-point optical flows. In order to achieve a better motion detection effect, a shadow removing method is usedand a moving vehicle is more accurately detected. The multi-feature point optical flow detection tracking mode is adopted, and the tracking accuracy is obviously improved in combination with a vehicleshielding solution. The system is powerful in function and is sufficient to meet the requirements of various application occasions. By adopting the system, the functions of the remote control on a ball machine at a front end monitoring point, the previewing of the video monitoring, the automatic detection of the illegal parking, the automatic identification of license plate numbers, the association of the high-definition video recording with illegal behavior videos, the storage and the browsing of the vehicle information, the system management, the remote maintenance and the like are realized.

The invention discloses a motor function rehabilitation monitoring system based on a wireless body area network. The system comprises a sensor terminal node, a wireless gathering node, a wireless body area network gateway, a personal terminal, a remote medical terminal and an information feedback system, wherein the sensor terminal node comprises a medical sensor, a signal conditioning circuit, a microprocessor unit and a wireless transceiver unit which are sequentially connected, the medical sensor sends collected data into the signal conditioning circuit for preprocessing, and the wireless transceiver unit is controlled to perform wireless transmission after the data is processed by the microprocessor unit; the data collected by the sensor terminal node sequentially passes through the wireless gathering node and the wireless body area network gateway and is respectively transmitted into the personal terminal and the remote medical terminal, and the data is transmitted into the information feedback system after being processed by the remote medical terminal, and is displayed by a 3D model built through the information feedback system. The monitoring system can be used for monitoring the exercise rehabilitation situation of a patient in real time, providing reasonable guidance and advices for subsequent rehabilitation training and improving the rehabilitation training effect.