38results about How to "Improve analysis processing speed" patented technology

The invention discloses an endoscopic image processing method and system. The method comprises the following steps: carrying out pretreatment on a plurality of images collected by an endoscope; carrying out classification on the endoscope images obtained after pretreatment according to a missing item curve graph under an HSV space, and deleting images hard to recognize, wherein the images hard torecognize are fuzzy, and are of no effect for focus judgment, so that the images hard to recognize can be deleted to reduce follow-up image processing workload; calculating image similarity, and deleting redundancy images, the similarity of which is beyond the similarity threshold, wherein the redundancy images, the similarity of which is larger, are of no effect for focus judgment, so that by deleting the redundancy images and keeping effective images, follow-up image processing workload can be reduced, image analysis processing speed is accelerated and doctor's workload is relieved; and training a focus position classifier, and recognizing images having focus through the focus position classifier and marking focus positions in the images to assist doctors to read films. The method improves efficiency of the doctors and prevents the doctors from causing false inspection and missing inspection due to too much workload.

The invention proposes an object detection and location method and system based on depth data. The method comprises the steps of acquiring a depth map by using depth data acquired by a depth data sensor, constructing a background model of the depth map, acquiring an object foreground region under the perspective of the depth map, and carrying out initial segmentation of the object foreground region; mapping the object foreground region after the perspective of the depth map to an overhead perspective by using a projection matrix, and segmenting the object foreground region under the overhead perspective again according to the location difference of an object in the horizontal space; extracting depth features of the foreground region, training an object detection module, and carrying out detection positioning for adhered objects by using the object detection module; and carrying out three-dimensional coordinate location correlation tracking for detection positioning results on an overhead map, mapping the detection positioning results to an original depth map coordinate, and obtaining a final object detection result. The invention can complete accurate object detection and location in a quick and robust manner under severely blocked and changing illumination conditions.

The invention provides a spacecraft flight data analysis and recording device, system and method. The device is installed inside the spacecraft, including: a data acquisition module, a data storage and protection module, a data rapid analysis and interpretation module, and a telemetry and positioning launch module; The data acquisition module acquires multi-channel spacecraft data, sends the data to be stored to the data storage and protection module, and sends the performance monitoring data to the data rapid analysis and interpretation module; the data storage and protection module compresses and stores the data to be stored; The data rapid analysis and interpretation module quickly interprets the performance monitoring data online, and outputs the fault data to the telemetry and positioning launch module; the telemetry and positioning launch module downloads the fault data and is used to launch emergency positioning after the spacecraft touches the ground Signal. The invention can monitor the on-orbit status of the spacecraft, diagnose faults and transmit the data to the ground, and can analyze the status of the spacecraft when the spacecraft falls to the earth.

The invention discloses a medical data analysis system integrating structured image data. The system comprises an image information structuralization module, a fusion and preprocessing module and a machine learning algorithm module. According to the invention, aiming at the problem that medical image data and structured data in medical electronic medical records are difficult to fuse and analyze,a distributed data analysis platform implemented based on Spark and Hadoop employs an image information structuralization module for analyzing the medical image data through a computer vision technology and carrying out structuralization conversion on key information, integrates the structural data such as other diagnostic information and demographic information of the same patient in the electronic medical record system, and performs the missing value processing and classification data conversion through a data preprocessing module, performs the data analysis and result visualization in combination with a machine learning algorithm module, and achieves a high-efficiency medical data analysis system, thereby improving the utilization rate of various multi-dimensional medical data, and meeting different subject research requirements of researchers.

The invention belongs to the technical field of unmanned driving, and discloses an intelligent unmanned vehicle quantitative evaluation system. The intelligent unmanned vehicle quantitative evaluationsystem comprises a program detecting module, an electric equipment detecting module, a speed detecting module, a fault detecting module, a power consumption detecting module, a data processing module, a cloud service module, a quantitative evaluation module, a display module and a recorder module. Due to the cloud service module, the data analysis processing speed can be greatly increased, and the quantitative evaluation efficiency can be improved; meanwhile, due to the quantitative evaluation module, unmanned vehicles can be quantitatively evaluated more scientifically and accurately, the improvement direction can be found, rapid development for the unmanned vehicle technology is promoted, and therefore it is ensured that the unmanned vehicle can be safely driven under the real traffic environment.

An analysis processing system 100 includes: an object detection unit 101 which acquires an image taken with a camera 110, detects an object having a preset feature in the acquired image, and sets a predetermined range with reference to a position where the object is detected in the image, as an object region; and a new object region specification unit 102 which, on the basis of information of the object region, specifies the object region including an object newly appearing in a newly acquired image as a new object region, and sets a priority degree representing the degree of priority of execution of predetermined analysis processing on the new object region so as to be higher than the priority degree of the other object region.

The invention belongs to the technical field of oil well digitization, in particular relates to a method for judging oil well indicator diagram similarity. The method comprises the following steps: (1) a first oil well indicator diagram on every day is analyzed; if the similarity C of a second oil well indicator diagram and the first oil well indicator diagram is not lower than 99%, the analysis is not performed, and the analysis result of the first oil well indicator diagram is adopted to express; otherwise, the analysis is performed; (2) the similarity comparison is performed for a third oil well indicator diagram and the first and second oil well indicator diagrams; if the similarity C of the third oil well indicator diagram and one of the first and second oil well indicator diagrams is not lower than 99%, the analysis is not performed, and the analysis result of the similar oil well indicator diagram is adopted to express; otherwise, the analysis is performed; and (3) the analogy is performed in sequence by the process to finish the analysis of the Nth oil well indicator diagram. The method optimizes the data analysis through judging and acquiring the indicator diagram similarity, so that the unnecessary calculation and storage are reduced, the analysis time is saved, the computer operation load is reduced, the improvement of the data analysis processing speed and the enhancement of the database storage and query efficiency are facilitated.

The invention discloses an intelligent behavior analysis method suitable for a narrow space. The method is used for identifying and analyzing a human behavior in a small space. The method comprises the following steps of (S1) acquiring a depth image in the narrow space by using a depth camera, (S2) dividing a human body into a plurality of body components based on the depth image, (S3) performingclassification and judgment and generating a human body skeleton system based on the body components, (S4) tracking and analyzing a motion track of the human skeleton system to identify the behavior state of a human body, and (S5) determining whether an early warning is generated based on an identification result. The intelligent behavior analysis method and device suitable for the narrow space ofthe invention can accurately identify and analyze the behavior states of multiple target characters in the narrow space, the recognition accuracy is high, the early warning can be completed at a device end after the identification is completed, the warning after the transmission to the background server for processing is not needed, and the timeliness is good.

The invention discloses a vibration table-based material damping coefficient measurement method and device, and relates to the field of material measurement. In order to achieve the purpose, a signalgenerator is utilized for generating steady-state frequency voltage, so that the vibration table has an exciting force, and the exciting force makes the material generate a dynamic displacement response curve under different loading forces, the material damping coefficient is worked out according to exciting signal information of a signal generator and dynamic response information of the material,and meanwhile by means of a designed measurement device, adjustment and pressure loading are facilitated. The device comprises an exciter, a beam applying pressure and a test piece clamped between anupper fixing pressing plate and a lower fixing pressing plate, a laser displacement sensor is installed on the upper fixing pressing plate; a pressure sensor is installed on the lower fixing pressingplate, the signal collected through a signal collector is fed back to a computer, and the damping coefficient of the material is resolved. Accordingly, not only is the measurement damping coefficientaccurate and the measurement stability is high, but also clamping is easy, the pressure is loaded conveniently, and the method and device are applicable to test analysis of various damping materials.

The invention provides a real-time log clustering analysis method based on a reverse table. The method comprises the following specific steps: 1, initialization: defining a packaging structure of eachword in a log; 2, preprocessing the original log, including regularization replacement, sensitive word bank extraction, word segmentation by a word segmentation device, part-of-speech tagging and public variable extraction; and 3, obtaining a template, including log grouping, inverted table scoring, template obtaining, template display layer content updating and inverted table updating. The method has a real-time log clustering function, the universality of the template is improved, the logs can be processed in parallel, and the analysis and processing speed is increased.

The invention provides a method for collecting wrong information on hardware used for quickly and accurately collecting wrong information on hardware in a server. The method comprises the following steps: step 1: dividing nodes and configuring a node controller extension module; step 2: customizing a register list and a data structure by a user; step 3: setting a server interruption function; step 4: rebooting the server such that the server is in the standby state; step 5: collecting hardware information by nodes when hardware errors occur in the server. The method utilizes the expansion feature of a node controller of a high-end server. Therefore, the function of collecting and saving information on hardware state is fulfilled when a system errors. Without considering in-band system state, the function can read information directly by an out-band system. By making detailed analyses of read information, concrete positions can be located.

The present invention belongs to the technical field of bridge damping, and discloses a control system in a damping bridge. The control system comprises a camera monitoring module, a pressure detection module, a vibration detection module, a central control module, a cloud service module, a data assessment module, a data storage module, an alarm module and a display module. The control system employs the cloud service module to greatly improve the speed for analysis and processing of the bridge vibration monitoring data and improve the monitoring efficiency; and moreover, the control system employs the data assessment module to perform mathematical statistics of detection data and make scientific and accurate determination so as to avoid generation of a condition that data processing is not accurate caused by man-made subjective factors.

The invention discloses a vehicle track smoothing method and device based on a millimeter-wave radar, belongs to the technical field of traffic systems and radio detection, and is used for solving the technical problem that an existing millimeter-wave radar cannot truly reflect a vehicle driving track under the influence of internal and external data noise and interference signals. The method comprises the following steps: carrying out noise reduction processing on traffic information to obtain preliminary filtering data; carrying out correction processing to obtain corrected target vehicle coordinates; constructing a one-dimensional plane vehicle motion state space model; carrying out two-dimensional conversion to obtain a two-dimensional plane vehicle motion state space model; performing updating prediction to obtain a target two-dimensional plane vehicle motion state space model; and through the preset trajectory smoothing gain matrix after the measurement error transformation function is substituted, correcting the target two-dimensional plane vehicle motion state space model after the measurement error transformation function is substituted to obtain a final state equation so as to realize smoothing processing of the vehicle motion trajectory detected by the millimeter wave radar.

The invention relates to a method for detecting gene editing efficiency and a gene editing mode and an application of the method, and belongs to the technical field of gene detection. The method comprises the following steps: S1, extracting genomic DNA of a sample, designing primers for a to-be-detected region, and amplifying the primers; S2, constructing a library to perform high-throughput sequencing, and filtering, splitting and splicing the data to obtain a sequence of the to-be-detected region; S3, comparing the sequence of the to-be-detected region with a genome reference sequence to obtain the gene editing efficiency and mode of each sample; and S4, performing significance analysis on the gene editing efficiency of processing group samples and control group samples, and outputting acorrected result. Compared with the prior art, the method has the advantages that the gene library construction process is simplified, the data analysis and processing speed is increased, the economy, sensitivity, specificity and accuracy of gene editing efficiency detection are improved, and multi-dimensional evaluation of a gene editing mode is also provided.

The invention discloses an environment monitoring method. The environment monitoring method comprises the following steps: acquiring a source code sent by an environment sensor arranged in an indoor working environment; capturing feature data according to a preset feature library and the source code; filtering out abnormal data according to a preset filtering model and the feature data; and sending the feature data and the abnormal data to a terminal. The invention also discloses an environment monitoring system, a terminal and a computer readable storage medium. The intelligent degree of environment monitoring is improved.