Product
Patsnap Eureka
For R&D, Patsnap Eureka makes reading and utilizing patents & technical documents easy.
Patsnap Eureka AIR
Designed for self-driven R&D workflows. Generate viable solutions, solve complex R&D challenges, empower your innovation with AI.
Patsnap Eureka Materials
Designed for material experts only. Revolutionize your material R&D, from search, analyze, to developing new materials.
Feature
TechResearch
Generate reliable direction feasibility study reports for your R&D in just a few steps.
TechSeek
Discover and master advanced knowledge NOW. Basics, ideas, possibilities, all at once.
TechMind
As an expert in R&D Theories, TechMind can generates customized viable solutions instantly.
TechRisk
Analyze your overall solution with one click, know your potential R&D risks in advance.
TechMonitor
Get weekly tech updates, stay abreast of the latest tech innovations and key insights.
Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
51results about How to "Suppress false alarms" patented technology
Efficacy Topic
Property
Owner
Technical Advancement
Application Domain
Technology Topic
Technology Field Word
Patent Country/Region
Patent Type
Patent Status
Application Year
Inventor
Detection method for accidental precursor access
ActiveCN101295999AReduce computationReduce the difficulty of data processingModulated-carrier systemsWireless communicationTime domainAbsolute threshold
The invention discloses a method for detecting a random access leader. After a random access channel (RACH) signal is treated with the simplified time domain-related operation, noise mean estimation is carried out to each root sequence; an absolute threshold is then detected according to a signal obtained by the noise estimation and signals in a search window are detected; the signals which exceed the detection threshold are screened and then a timing position can be determined in a fast and accurate way so as to provide reliable uplink timing adjustment information to a mobile terminal, guarantee the accuracy of the uplink synchronization and effectively eliminate the timing error due to the over-sampling and reduce the false alarm in the detection.
Owner:ZTE CORP
System and method for detecting low-speed small target under sea cluster background
ActiveCN104215951ATroubleshoot probing issuesSuppress false alarmsWave based measurement systemsTime frequency domainEnvironmental geology
The invention discloses a system and a method for detecting a low-speed small target under a sea cluster background. The method includes that S1, a radar transceiving unit acquires signals of the low-speed moving small target under the sea cluster background; S2, the radar transceiving unit sends received signals to a radar echo processing unit to be processed to generate radar echo data and sends the radar echo data to a detection unit; S3, the detection unit processes multiple continuous radar echoes and establishes corresponding time frequency domain two-dimension planar graphs to effectively eliminate false-alarm targets in different areas. The system and the method are suitable for detection of dim and small targets moving at low speed under sea cluster background interference during downward-looking detection of sea-surface targets through radar. By the system and the method, the problem of radar downward-looking detection of the low-speed moving small target under the sea cluster background can be solved; time frequency domain CFAR (constant false alarm rate) processing technology is adopted to decompose target echoes and sea cluster data to a time frequency domain two-dimension plane for processing.
Owner:SHANGHAI RADIO EQUIP RES INST
Heart-rate estimation method, device and system based on fusion of electrocardiogram and pulse signals
InactiveCN107693000AImprove accuracySuppress false alarmsDiagnostic recording/measuringSensorsEcg signalEstimation methods
The invention discloses a heart-rate estimation method and device based on fusion of electrocardiogram signals and pulse signals. The heart-rate estimation method includes the steps that heart rate estimation is carried out based on the electrocardiogram signals and the pulse signals respectively; the electrocardiogram signals and the pulse signals are subjected to signal quality evaluation respectively, and the signal quality index of the electrocardiogram signals and the signal quality index of the pulse signals are obtained; based on the two signal quality indexes, the two estimated heart rate values are subjected to kalman filtering processing; the two estimated heart rate values subjected to kalman filtering processing are subjected to weight fusion. By means of the heart-rate estimation method, the accuracy of heart-rate estimation can be effectively increased, and a reference is provided for clinical caring.
Owner:SHANDONG UNIV
Device and method for detecting and suppressing influence generated by camera moving in monitoring system
ActiveCN101426080ASuppress false alarmsTelevision system detailsImage enhancementMobile cameraImaging processing
Provided is a device and process for detecting and restraining the impact of mobile camera moving in a monitoring system, the device including: an image capturing module for capturing new images; an image processing module, for comparing the captured new images with the scene model, updating the scene model based upon the comparative result, and determining the pixel status in the image according to the updated result of the scene model to test whether the camera has moved. If the camera is detected to have moved, the error alarm resulting from camera moving is restrained.
Owner:SAMSUNG ELECTRONICS CO LTD +1
Remote sensing image change detection method based on saliency measurement
InactiveCN102629377AImprove the surrounding interferenceSuppress false alarmsImage enhancementImage analysisPattern recognitionNatural disaster
The invention discloses a remote sensing image change detection method based on saliency measurement. Using the current change detection method is easily influenced by noise interference so that a false alarm rate is high in a detection result. The method of the invention mainly aims at solving the above problem. The method is characterized by: inputting two time phase remote sensing images; firstly, carry out median filtering on each image respectively so as to obtain two filtered time phase images; then calculating a gray scale difference graph of the two filtered time phase images and a difference graph based on a Chi-square distance respectively, carrying out saliency measurement on the gray scale difference graph so as to obtain one saliency map; and then, carrying out fuzzy c-means segmentation on the difference graph based on the Chi-square distance and the saliency map respectively; finally, correcting a segmentation result of the saliency map so as to generate a final change detection result. An experiment result shows that by using the method of the invention, noise interference can be effectively restrained and precision of the detection result can be increased. The method of the invention can be used in fields of natural disasters analyses, city program constructions and the like.
Owner:XIDIAN UNIV
Random access method
InactiveCN104053244AReduce overheadSuppress false alarmsWireless communicationRandom access memoryPower delay profile
The application discloses a random access method. The method comprises the following steps that: user equipment (UE) sets a cyclic shift Ncs according to a cell radius, uses the Ncs to generate a code word, and sends the code word to a network side; for each RRU in a BBU coverage range, reception data of each antenna of the RRU are respectively processed to obtain a power delay profile (PDP); if the RRU only has one antenna, user detection is carried out at a current detection window according to the PDP of the antenna; and if the RRU has a plurality of antenna, PDPs of all antennas are combined and user detection is carried out at a current detection window according to the combined PDPs, wherein the length of the detection window is obtained by the cell radius; the RRU reports related access information of the user detected in the current detection window to the BBU; and the BBU determines a current random access user based on the related access information. According to the invention, the provided method is suitable for the distributed scene with one BBU and a plurality of RRUs.
Owner:POTEVIO INFORMATION TECH CO LTD
Point target movement velocity detection method based on multiple linear moveout scanning, extending and sampling
A point target movement velocity detection method based on multiple linear moveout scanning, extending and sampling comprises the following steps: (1) establishing a multiple linear moveout scanning detection device; (2) using each linear detector to detect point targets in an extending and sampling manner; (3) processing Nt groups of image data acquired by each linear detector to obtain sub-pixel images; (4) performing non-uniformity correction and sub-pixel match on two sub-pixel images processed by the two adjacent processed linear detectors, then performing difference computation to complete the background subtraction; (5) performing threshold filtering on difference images processed by the two adjacent processed linear detectors, extracting positive and negative point pairs in the difference images by adopting the neighborhood constraint criterion, so as to complete the target detection and extraction of moving points in once scanning process; (6) marking regions of paired positive and negative points extracted in the step (5) respectively, calculating movement velocity and movement directions of the targets according to the position relation of the marked regions of the positive and negative points; (7) averaging the movement velocity and the movement directions obtained in the step (6) to obtain the velocity and the direction of a detected target.
Owner:CHINA ACADEMY OF SPACE TECHNOLOGY
Fire behavior early warning method based on machine learning monitoring video image smog
ActiveCN108363992ASolve the problem whether it is caused by fireImprove fire warning rateCharacter and pattern recognitionNeural learning methodsPattern recognitionData set
The invention discloses a fire behavior early warning method based on machine learning monitoring video image smog. The method is characterized by comprising the steps of firstly, collecting and marking an image data set of various smog scenes, wherein the type of non-fire-behavior early warning smog scenes is A, and the type of fire behavior early warning smog scenes is B; secondly, conducting non-fire-behavior early warning smog scene training through a context target detection layer; thirdly, conducting fire behavior early warning smog scene training through the context target detection layer, and repeating the second step, wherein training images are B-type fire behavior early warning smog images; fourthly, detecting suspected fire behavior images. The method has the advantage of solving the problem that a traditional machine learning method classifier cannot accurately distinguish whether detected smog is produced by fire disasters or not. The context relation of the area where smog is located is judged through a context target detection method, and the false warning rate and warning omission rate are reduced on the premise of improving the fire behavior early warning rate.
Owner:NANJING JULI INTELLIGENT MFG TECH INST CO LTD
Infrared dim small target detection method of constructing entropy contrast ratios by utilizing directional derivatives
ActiveCN107194355AImprove noise immunitySuppress false alarmsCharacter and pattern recognitionSmall targetLeast squares
The invention relates to an infrared dim small target detection method of constructing entropy contrast ratios by utilizing directional derivatives. The method comprises the four main steps of: based on least square surface fitting, quickly solving first-order derivatives, which are in four directions respectively, of each pixel of an infrared image by using a facet model and convolution operations; redesigning, starting from a mathematical imaging model of a dim small target, information entropy calculation formulas at a central area in a small-range neighborhood based on directional derivative features combined with gray-scale distribution information; similarly redesigning information entropy calculation formulas for a surrounding area of the small-range neighborhood, utilizing a characteristic of strong contrasts between the center area of the dim small target and the surrounding area to construct the entropy contrast ratios, utilizing the measures to suppress backgrounds in derivative subgraphs of each direction, and enhancing the target; and fusing the entropy contrast ratios of the derivative subgraphs of each direction by means of multiplication, further suppressing the edge clutter backgrounds, and highlighting the dim small target. The method can be widely used in dim small target detection of infrared images, and has a broad market prospect and application value.
Owner:BEIHANG UNIV
Moving object detection method fusing color and texture information for performing block background modeling
ActiveCN104077788AEffective foreground partSuppress false alarmsImage analysisObject detectionColor difference
The invention discloses a method for detecting a moving object in video. The method comprises the steps of calculating texture pattern characteristics of a current video frame, dividing the current video frame into small blocks, combining every four adjacent small blocks into a large block, calculating a texture pattern characteristic histogram of each large block, and updating a texture pattern characteristic background model in each large block; according to the texture pattern characteristic background models and the texture pattern characteristic histograms of the large blocks, obtaining the probability, belonging to the background, of the large blocks under texture characteristics, and therefore performing average solving on the overlapped small blocks to obtain the probability, belonging to the background, of the small blocks under the texture characteristics; according to color information, updating a current main background image; according to the main background image and the color information, obtaining a color difference value of the current video frame and the small blocks of the main background image; according to the probability, belonging to the background, of the small blocks under the texture characteristics and the color difference between the small blocks and the main background image, judging whether the small blocks belong to the background or not; according to a judgment result of a foreground and the background, obtaining foreground blocks through segmentation, and using a communication domain for performing analysis to obtain a moving object detection result.
Owner:INST OF AUTOMATION CHINESE ACAD OF SCI
Multi-temporal SAR image change detection method based on deep learning
ActiveCN111080678ASuppress human interferenceSuppress speckle noiseImage enhancementImage analysisPattern recognitionComputer vision
The invention discloses a multi-temporal SAR image change detection method based on deep learning. Compared with the prior art, neighborhood information is substituted into classification and clustering is carried out by taking super pixels as units, so that human interference during rectangular patch generation is inhibited, clustering uncertainty is reduced, and speckle noise influencing interpretability of the SAR image is also inhibited. Moreover, change detection is used as classification of two stages, so that a large number of false alarms caused by speckle noise are suppressed. In a first stage, we simply aggregate DI into varying and non-varying classes. In the second stage, low-rank sparse decomposition (LRSD) is adopted for preprocessing based on the internal difference betweenthe change caused by speckle noise and the change of the real object. The low-rank term of the LRSD enables the false change caused by the speckle noise to be recovered to the original state, and thesparse term separates the speckle noise from the image, thereby greatly weakening the impact on the subsequent classification from the speckle noise.
Owner:CHONGQING UNIV
Moving target detecting method wireless sensor network head node equipment
ActiveCN102123417ASolve the defect that the probability of moving targets is smallSave node capacityNetwork topologiesWireless sensor networkingDecision threshold
The embodiment of the invention discloses a moving target detecting method and wireless sensor network head node equipment. The method comprises the following steps of: detecting a signal which is transmitted by a moving target by using a first sub-node; activating other sub-nodes within a length specified by the first sub-node to detect the moving target when the moving target is detected by the first sub-node; searching a triangle which meets three conditions from the sub-nodes within the specified length when the moving target is detected by the sub-nodes; when the triangle which meets the three conditions is searched out, determining a circular area by taking the mass center of the triangle as a circle center and taking the detecting radius of the first sub-node as a radius, and calculating the total number of nodes that the probability of finding the moving target by using the sub-node is more than a node detecting threshold in the area; and comparing the total number of the nodes with a preset decision threshold. The problem that the probability of finding the target by using a single node is low can be effectively solved by implementing the invention.
Owner:CHINA NUCLEAR POWER TECH RES INST CO LTD +1
A vehicle detection method based on multiple sub-images and image saliency analysis
ActiveCN108629225ASolve problems that are difficult to detectEasy to detectImage enhancementImage analysisMultiple frameVehicle detection
The invention provides a vehicle detection method based on multiple sub-images and image saliency analysis. The method comprises the following steps: S1) carrying out saliency pretreatment based on multiple sub-image fusion; S2) carrying out boundary correction on a candidate target area comprising a target vehicle; S3) carrying out accurate judgment on the corrected target candidate area; S4) carrying out multi-frame joint and de-superposition; and S5) outputting a target window area coordinate and finishing vehicle detection. The method is low in time complexity and high in real-time performance, and can be suitable for various different scenes, such as rainy days or night.
Owner:ZONGMU TECH SHANGHAI CO LTD
Point object detection method based on multiple-linear time difference scanning and expansion sampling
ActiveCN104143196AAchieve inhibitionImplement extractionImage analysisMathematical CalculusPoint object
Provided is a point object detection method based on multiple-linear time difference scanning and expansion sampling. The point object detection method comprises the steps of (1) constructing a double-linear-detector imaging device; (2) performing point object detection through each linear detector in an expansion sampling method; (3) respectively processing Nt groups of image data collected by each the linear detectors to obtain sub-pixel images, performing heterogeneity correction on two sub-pixels processed by the two linear detectors, performing sub pixel matching, and performing calculus of differences to complete background removal; (4) performing threshold filtering on residual images obtained through difference in the step (3), extracting positive and negative point pairs in the residual images through a neighborhood constraint criterion to complete detection and extraction of a moving point object in a scanning process, and forming neighborhood constraint criterion (as specified in the specification) according to imaging time differences of different linear detectors and the target movement speed, wherein delta D represents a distance between a positive area and a negative area, vmin represents the minimum movement speed of the detected object, vmax represents the maximum movement speed of the detected object, and GDS represents ground sampling distances of the linear detectors.
Owner:CHINA ACADEMY OF SPACE TECHNOLOGY
Method and device for transmitting messages
ActiveCN108234156ASuppress false alarmsDoes not affect intercommunicationData switching networksSoftware simulation/interpretation/emulationEngineeringInterconnection
The invention provides a method and device for transmitting messages. An aggregated link trunk is set between a first device and a second device. A state machine of a maintenance association end point(MEP) of the first device is currently located on a first single board of the first device. The level of the MEP of the first device is different from that of the MEP of the second device. The methodcomprises the steps that when the state machine of the MEP of the first device is migrated from the first single board to a second single board of the first device, the first device suppresses faultalarm and sends an alarm indication signal (AIS) to the second device according to a preset frequency; and when the state machine of the MEP of the first device is migrated completely from the first single board to the second single board of the first device, the first device recovers the fault alarm and stops sending the AIS. The false alarm resulting from state machine migration timeout is effectively suppressed through utilization of the alarm indication signal (AIS). The method and the device are simple and feasible. Interconnection is not influenced.
Owner:XFUSION DIGITAL TECH CO LTD
Method for inhibiting random access code false alarm
The invention discloses a method for inhibiting random access code false alarm. The method comprises the following steps: measuring a peak value corresponding to the random access code in a target detection window; deducting non-target detection window leakage energy from the peak value to obtain a correction peak value corresponding to the random access code; according to the correction peak value and an absolute threshold, judging whether a user appearing in the target detection window is false alarm; if so, marking in the target detection window. After the embodiment of the invention is applied, the false alarm is effectively inhibited under the condition that the multi-user normal access probability is guaranteed.
Owner:POTEVIO INFORMATION TECH
Vehicle detection method and system based on image segmentation technology
ActiveCN108629226ASolving intractable puzzlesReduce false alarmsImage enhancementImage analysisMultiple frameVehicle detection
The invention discloses a vehicle detection method based on image segmentation technology. The method comprises the following steps: collecting a background image comprising a vehicle; carrying out secondary image segmentation on the background image to obtain a target image comprising the vehicle; carrying out boundary correction on the target image; detecting candidate windows of a current framegenerated according to a neighborhood range, where the vehicle is detected, in multiple frames target images before the current frame through multi-frame joint, and serving the window, where the vehicle is detected, in the candidate windows as a target window; and carrying out image de-overlapping processing on all frames of target windows to obtain a target region comprising the vehicle; and outputting a target region coordinate. The invention also discloses a vehicle detection system based on the image segmentation technology. The system comprises an image acquisition module, an image segmentation module, an image de-overlapping module and an output module.
Owner:ZONGMU TECH SHANGHAI CO LTD
Polarization information fused landslide identification method and device under complex background
PendingCN114494282AImprove accuracySuppress false alarmsImage analysisRadio wave reradiation/reflectionPolarimetric synthetic aperture radarSynthetic aperture radar
The invention belongs to the technical field of complete polarization synthetic aperture radar image processing, and particularly relates to a polarization information fused landslide identification method and device under a complex background, and the method comprises the steps: carrying out the registration of an image, which has the same polarization combination mode as the single-polarized SAR image before the landslide, in a single-polarized SAR image before the landslide and a PolSAR image after the landslide; constructing a dual-time-phase SAR image pair, and generating a coherence graph through coherent change detection to extract a change region; extracting a plurality of polarization characteristic parameters from the preprocessed PolSAR image after landslide, and fully fusing the polarization characteristic parameters by using TOPSIS with weight to carry out landslide detection so as to obtain a suspected landslide area; and fusing the change area and the suspected landslide area extracted from the coherence map through logic AND operation to obtain a final landslide area. According to the method, the TOPSIS is used for fusing the polarization information to perform landslide detection, and coherent change detection is combined, so that the accuracy of landslide detection can be greatly improved under the condition of effectively inhibiting the false alarm rate.
Owner:PLA STRATEGIC SUPPORT FORCE INFORMATION ENG UNIV PLA SSF IEU
Water treatment monitoring method and system
The invention discloses a water treatment monitoring method and system. The method comprises steps of setting monitoring points at different nodes of a water treatment process, setting a time window at each monitoring point, and setting a time window length, an alarm threshold and a monitoring frequency; calculating the relative position of each time window; monitoring data of each monitoring point; moving the time window position of each monitoring point; calculating an alarm state of each monitoring point time window; summarizing alarm states of the time windows of the monitoring points, analyzing summarized data, and judging whether alarm logic is met or not; if so, generating an alarm; if not, inhibiting the alarm, skipping to a step S130, and continuing execution according to the methods in steps S130 to S160. The method is advantaged in that an alarm conforming to the technological process is accurately generated in a water treatment scene, and a problem of false alarm caused byabnormal data is effectively inhibited.
Owner:杭州青泓科技有限公司
Divide-and-conquer detection method based on semantic segmentation network
PendingCN112327265AAvoid influenceSuppress false alarmsWave based measurement systemsAlgorithmRadar detection
The invention discloses a divide-and-conquer detection algorithm based on a semantic segmentation network. According to the method, clutter region segmentation of a distance Doppler domain is realizedby means of a semantic segmentation network, a detection strategy is formulated according to the characteristics of different clutter region main bodies and edges, appropriate detectors and reasonable detection parameters are selected from alternative detector groups to complete divide-and-conquer detection, and false alarms are effectively suppressed while a target is detected to the greatest extent. The technology is of great significance to radar detection of low-altitude small targets. Compared with a detection plane normalization method, the method has the advantages that detection planeconversion is not needed, the calculated amount is smaller, the influence of a parameter estimation result on the detection plane conversion is avoided, and the robustness is higher.
Owner:BEIJING INSTITUTE OF TECHNOLOGYGY
Safety alarm method and device based on image recognition
PendingCN113420631ASuppress false alarmsReduce labor costsCharacter and pattern recognitionRecognition algorithmEngineering
The invention provides a safety alarm method and device based on image recognition. The method comprises the following steps: acquiring a recognition result image of a to-be-processed image by a target image recognition algorithm; determining the similarity between the to-be-processed image and a misrecognition image in a misrecognition image library according to the recognition result image; and according to the similarity between the to-be-processed image and the misrecognition image in the misrecognition image library, carrying out safety alarm on the to-be-processed image. Therefore, when the image information which does not meet the safety requirement is recognized by the target image recognition algorithm, the error recognition result is filtered by using the preset error recognition image library, and then the safety alarm is performed, so the error alarm of the target image recognition algorithm is inhibited, excessive human intervention is not needed, the labor cost is reduced, the response speed is high, the requirement of real-time safety alarm is met, and accurate safety alarm is provided for safety monitoring of an engineering site.
Owner:GLODON CO LTD
Anti-lose warning device based on radio and anti-same frequency interference warning method
InactiveCN1588467AOvercoming co-channel interference and high power consumptionSuppress false alarmsAlarmsTime-division multiplexingEngineering
The invention discloses a loss resisting alarm device based on wireless, the device is used to prevent the loss of expensive box and other things. The device is made up of signal transmitting part and receiving part. The transmitting part is placed in the box, the receiving part is carried by user, when the distance between the user and the box exceeds a certain distance, the receiver sends out harsh noise or vibration to alarm. The invention uses microchip to control the wireless transiting and receiving models. At the same time, it reduces the energy consumption of wireless transmitting model and receiving model, prolongs the lifespan of battery.
Owner:ZHEJIANG UNIV
A point target moving speed detection method based on multi-line time-difference scanning extended sampling
A point target movement velocity detection method based on multiple linear moveout scanning, extending and sampling comprises the following steps: (1) establishing a multiple linear moveout scanning detection device; (2) using each linear detector to detect point targets in an extending and sampling manner; (3) processing Nt groups of image data acquired by each linear detector to obtain sub-pixel images; (4) performing non-uniformity correction and sub-pixel match on two sub-pixel images processed by the two adjacent processed linear detectors, then performing difference computation to complete the background subtraction; (5) performing threshold filtering on difference images processed by the two adjacent processed linear detectors, extracting positive and negative point pairs in the difference images by adopting the neighborhood constraint criterion, so as to complete the target detection and extraction of moving points in once scanning process; (6) marking regions of paired positive and negative points extracted in the step (5) respectively, calculating movement velocity and movement directions of the targets according to the position relation of the marked regions of the positive and negative points; (7) averaging the movement velocity and the movement directions obtained in the step (6) to obtain the velocity and the direction of a detected target.
Owner:CHINA ACADEMY OF SPACE TECHNOLOGY
An Adaptive Object Detection Method Based on Fine Clutter Image
ActiveCN106291492BEasy to implementImprove detection abilityWave based measurement systemsPattern recognitionRadar signal processing
The invention belongs to the field of the radar signal processing technology, and discloses an adaptive target detection method based on a fine clutter map. An improved fine clutter map is adopted, and ground clutters and sea clutters are updated in different ways according to different clutter attributes. Different from traditional clutter map updating methods where only the amplitude information is updated, the method of the invention simultaneously counts and updates amplitude and variance parameters and applies the variance information in the subsequent signal weighting so as to effectively suppress false alarms which may be caused by sea peaks. Different from traditional constant false alarm threshold methods, the method of the invention adopts the technical scheme of simultaneously seeking fast and slow threshold constant false alarm thresholds and automatically selects the fast and slow constant false alarm thresholds according to certain criteria, thereby effectively improving the constant false alarm effect.
Owner:利国智能科技(昆山)有限公司
A point target detection method based on multi-line time-difference scanning extended sampling
Provided is a point object detection method based on multiple-linear time difference scanning and expansion sampling. The point object detection method comprises the steps of (1) constructing a double-linear-detector imaging device; (2) performing point object detection through each linear detector in an expansion sampling method; (3) respectively processing Nt groups of image data collected by each the linear detectors to obtain sub-pixel images, performing heterogeneity correction on two sub-pixels processed by the two linear detectors, performing sub pixel matching, and performing calculus of differences to complete background removal; (4) performing threshold filtering on residual images obtained through difference in the step (3), extracting positive and negative point pairs in the residual images through a neighborhood constraint criterion to complete detection and extraction of a moving point object in a scanning process, and forming neighborhood constraint criterion (as specified in the specification) according to imaging time differences of different linear detectors and the target movement speed, wherein delta D represents a distance between a positive area and a negative area, vmin represents the minimum movement speed of the detected object, vmax represents the maximum movement speed of the detected object, and GDS represents ground sampling distances of the linear detectors.
Owner:CHINA ACADEMY OF SPACE TECHNOLOGY
A vehicle detection method and system
ActiveCN108268866BImprove real-time performanceImprove accuracyCharacter and pattern recognitionPattern recognitionComputer graphics (images)
The present invention provides a vehicle detection method and system, comprising: performing image preprocessing on an input image to obtain a preprocessed vehicle candidate area containing a vehicle image; correcting the boundary of the vehicle candidate area; and accurately judging the corrected area by a classifier The vehicle candidate area to determine whether the input image contains the target vehicle image. Among them, the image preprocessing is to calculate the distance parameter according to the frequency and pixel value of each pixel of the input image; perform exponential operation on the distance parameter to obtain the saliency feature value, and obtain the saliency image; normalize the saliency image to obtain the saliency analysis image; normalize the input image to obtain the stretched image; subtract the stretched image from the saliency analysis image to obtain the target image, process and select the target image to obtain the vehicle candidate area. The invention suppresses the background information of the input image by enhancing the local contrast, and improves the real-time performance and accuracy of vehicle detection.
Owner:ZONGMU TECH SHANGHAI CO LTD
Suspended ceiling radar ground false alarm suppression method
InactiveCN110940975AThe principle is simpleEasy to implementRadio wave reradiation/reflectionTarget signalRadar detection
The invention discloses a suspended ceiling radar ground false alarm suppression method, which comprises the steps of S1, detecting an area in a carriage through a suspended ceiling radar detection system to obtain a carriage internal structure characteristic signal, and simultaneously obtaining a carriage internal area target characteristic signal through a suspended ceiling radar; and S2, matching the obtained regional target signal in the carriage with the obtained internal structure characteristics of the carriage to obtain a target signal after characteristic matching, and filtering out false alarms. The method has the advantages that the principle is simple, implementation is easy, false alarm suppression can be achieved, and accuracy is improved, and has the other advantages.
Owner:HUNAN NOVASKY ELECTRONICS TECH
Vehicle-mounted radar data association method and device
ActiveCN113064164AImprove continuityImprove stabilityRadio wave reradiation/reflectionIn vehicleRadar
The invention provides a vehicle-mounted radar data association method and device. The method comprises the steps of setting two sets of data association thresholds for each track prediction point, namely, a first data association threshold and a second data association threshold; for each track prediction point, determining whether the measurement value is a candidate measurement value of the track prediction point or not through the first data association threshold and the cumulative number of times that the measurement value falls into the data association thresholds of other track prediction points; and weighting all candidate measurement values of the track prediction point, and taking the weighted candidate measurement values as final association data of the track prediction point to be used for updating the track, so that the phenomenon of misassociation is reduced. The measurement value which falls into the second data association threshold and does not fall into the first data association threshold is labeled, so that the measurement value cannot be used as a new track start, false alarm of the same target caused by large measurement value distribution is inhibited, and track continuity and stability are improved.
Owner:BEIJING JINGWEI HIRAIN TECH CO INC
A fire early warning method based on machine learning to monitor smoke in video images
ActiveCN108363992BSolve the problem whether it is caused by fireImprove fire warning rateCharacter and pattern recognitionNeural learning methodsPattern recognitionData set
Owner:NANJING JULI INTELLIGENT MFG TECH INST CO LTD
Who we serve
- R&D Engineer
- R&D Manager
- IP Professional
Why Patsnap Eureka
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com