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.
43 results about "Adaptive sensing" 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
Adaptive sensing for early booting of devices
InactiveUS20130054945A1Well formedDigital computer detailsHardware monitoringActivation actionBiological activation
Automatically performing configuration or activation activities on a device. A method includes collecting at least one of operational or environmental information about a device. The at least one of operational or environmental information about a device is used to determining an anticipated usage of the device. Based on the determined anticipated usage, at least one configuration or activation action is performed putting the device into a normal use state.
Owner:MICROSOFT TECH LICENSING LLC
Adaptive sensing network
ActiveUS7369047B2Electric signal transmission systemsHand manipulated computer devicesData signalComputer analysis
A plurality of modules interact to form an adaptive network in which each module transmits and receives data signals indicative of radio-frequency identification signals, and indicative of proximity sensing at the module. A central computer accumulates the data produced or received and relayed by each module for analyzing inventory, pricing and customer responses to transmit through the adaptive network signals representative of information to be displayed at selectively-addresses modules in response to computer analyses of the data accumulated from modules forming an adaptive network.
Owner:ACEINNA TRANSDUCER SYST CO LTD
Adaptive compressed sensing-based non-local reconstruction method for natural image
InactiveCN102722896AValid reservationKeep information2D-image generationPattern recognitionAdaptive compression
The invention discloses an adaptive compressed sensing-based non-local reconstruction method for a natural image. The problems of serious reconstructed image information loss and the like in the prior art are mainly solved. The method is implemented by the steps of: (1) dividing an image into N 32*32 sub-blocks, obtaining a basic sensing matrix Phi' according to a basic sampling rate b and a sensing matrix Phi, and sampling a signal by utilizing Phi' to obtain a basic observation vector; (2) estimating a standard deviation sequence {d1, d2, ..., and dN} of the image according to the basic observation vector; (3) adaptively allocating a sampling rate ai for each sub-block according to the standard deviation sequence {d1, d2, ..., and dN}, and constructing an adaptive sensing matrix, and sampling the signal by utilizing the adaptive sensing matrix to obtain an adaptive observation vector; (4) forming an observation vector of each sub-block by using the basic observation vector and the adaptive observation vector; (5) obtaining an initial solution x0 of the image according to the observation vector; and (6) performing iteration by using x0, and reconstructing the original image until consistency with a finishing condition is achieved to obtain a reconstructed image x'. The method has the advantages of high image reconstruction quality, clear principle and operational simplicity, and is applied to the sampling and reconstruction of the natural image.
Owner:XIDIAN UNIV
Systems and methods for equipment performance modeling
An equipment performance modeling platform is disclosed. In certain embodiments, an adaptive sensing coordinator acquires sensor measurements, configures and processes the sensor measurements for a specific statistical model, and sends the measurements to a server. A server performs data processing, provides storage (e.g., local or in a database), and provides an interface for data extraction. Statistical models are used to interpreting sensor values for a type of equipment, and a labeling mechanism labels performance occurrences.
Owner:SIGSENSE TECH
Adaptive Sensing of a Programmable Modulator System
InactiveUS20150116563A1Television system detailsTelevision system scanning detailsWave shapeSignal of interest
A technique to collect measurements that are adapted to a signal / scene of interest is presented. The measurements are correlations with patterns that serve as modulating waveforms. The patterns correspond respectively to rows of a sensing matrix. The method uses a sensing matrix whose rows are partitioned into blocks. Each block corresponds to a distinct feature or salient property of the scene. For each block, the method collects a number of measurements of the signal / scene based on selected rows of the block, and generates one or more associated statistics for the block based on said measurements. The statistics for the blocks are then analyzed (e.g., sorted) to determine the most important blocks. Subsequent measurements of the signal / scene may be based on rows from those most important blocks. The original measurements and / or the subsequent measurements may then be used in an algorithm to reconstruct the signal / scene.
Owner:INVIEW TECH CORP
Adaptive sensing network
ActiveUS20060226990A1Electric signal transmission systemsHand manipulated computer devicesData signalRadio frequency
A plurality of modules interact to form an adaptive network in which each module transmits and receives data signals indicative of radio-frequency identification signals, and indicative of proximity sensing at the module. A central computer accumulates the data produced or received and relayed by each module for analyzing inventory, pricing and customer responses to transmit through the adaptive network signals representative of information to be displayed at selectively-addresses modules in response to computer analyses of the data accumulated from modules forming an adaptive network.
Owner:ACEINNA TRANSDUCER SYST CO LTD
Adaptive sensing system
ActiveUS20140077988A1Improve securityReduce the amount requiredGeological detection using milimetre wavesRadio wave reradiation/reflectionEngineeringElectromagnetic radiation
An adaptive sensing system including a passive sensor that receives electromagnetic radiation, an active sensor that emits and receives electromagnetic radiation, a detection unit that detects the presence of human beings and objects other than human beings in a region of observation, and a control unit that controls the active sensor and the passive sensor based on a result of the detection by the detection unit.
Owner:SONY CORP
Rainfall adaptive sensing method of automobile windscreen wipers
ActiveCN101750965ARain intensity level adjustableIncrease flexibilityVehicle cleaningAdaptive controlFrostPoor adaptive skills
The present invention relates to a rainfall adaptive sensing method of automobile windscreen wipers. The existing techniques have the shortcomings of poor adaptive capability and low control accuracy. The method comprises the following steps: first, a controller in a rainfall sensing module is initialized, and a rainfall strength quantified threshold is read from a nonvolatile memory after initialization; a rainfall strength quantified grade is subsequently read by the rainfall sensing module from a motor control module for windscreen wipers; then, the current rainfall strength quantified grade is sensed and calculated by the rainfall sensing module through an infrared transmitter; finally, the current rainfall strength quantified grade is sent to the motor control module for windscreen wipers, the windscreen wipers are relatively controlled by the motor control module for windscreen wipers, and the current rainfall strength quantified grade is updated. The method has the advantages of adjustable rainfall strength grade, good flexibility, strong adaptive capability and capability of overcoming the influence of temperature, natural light strength and frost on rainfall detecting algorithm.
Owner:南通儒尚电动车科技有限公司
Adaptive sensing system
ActiveUS8723717B2Low incommodation of individualsLow exposition of individualsGeological detection using milimetre wavesRadio wave reradiation/reflectionEngineeringElectromagnetic radiation
Owner:SONY CORP
Adaptive sensing method for smart home
InactiveCN105743750ARealize "smartAchieve intelligenceAssess restrictionWireless commuication servicesInformation typeAdaptive learning
The present invention relates to an adaptive sensing method for a smart home. The method comprises the following steps: protocol initialization; channel scanning; establishment of a ZigBee network; listening of network information; application of a node to access the network; address allocation; information requesting; information type; data and information acquisition at a terminal; uploading of data to a user; sending by the user; control information; transmission of data to a terminal node; and adaptive learning of an algorithm. The method provided by the present invention is implemented by using the system automatic learning sensing algorithm plus ZigBee. Not only the role of a remote control is replaced, but also real ''intelligence'' is realized. By learning and sensing living habits and lifestyles of human, needs of different ages, different characters, different genders, different preferences, different individual needs, the device is enabled to know how to serve the human. Therefore, the real ''intelligence'' is achieved, and the big data statistics is introduced to the smart home system.
Owner:北京绿源普惠科技有限公司
Sensing system adaptive receiving method based on digital channelization instantaneous parameter measurement
ActiveCN109617631AIncrease probability of interceptImprove accuracyTransmission monitoringChannel parameterIntermediate frequency
The invention discloses a sensing system adaptive receiving method based on digital channelization instantaneous parameter measurement. The method comprises the steps that 1), a display control subsystem configures sensing receiving channel parameters and controls realization of an instantaneous adaptive sensing mode; 2), an external electromagnetic environment and signals are injected into a comprehensive radio frequency subsystem through utilization of a radio frequency interface; 3), radio frequency signals are amplified and filtered to obtain intermediate frequency signals, and the intermediate frequency signals are sent to a sensing processing subsystem; 4), an FPGA module of the sensing processing subsystem caches received signals, processes the received signals, and sends a processing result to the display control subsystem; and 5), the display control subsystem receives the processing result, judges the processing result and outputs a judgment result. According to the method, high intercept probability and high sensitivity adaptive sensing and receiving of radar and communication signals in a wide instantaneous bandwidth range can be realized, so the problem that conventional broadband sensing receiver equipment is huge and is high in power consumption and cost can be offset to a relatively great extent.
Owner:华航高科(北京)技术有限公司
Power control circuit for wire compensation and compensation method of the same
InactiveUS20110037445A1Enhancing level of feedbackIncrease level of feedbackBatteries circuit arrangementsDc-dc conversionSelf adaptiveControl circuit
A power control circuit with wire compensation is provided. The power control circuit is applied in a power converter, which has an output coupled to a load through a power wire. The power control circuit has an adaptive sensing circuit and a controller. The adaptive sensing circuit is utilized for detecting an output voltage of the power converter and a current on the power wire and generating a feedback signal according to the output voltage and the current on the power wire. The controller is utilized for adjusting a level of the output voltage according to the feedback signal.
Owner:NIKO SEMICON
A vehicle network cognitive radio adaptive spectrum sensing method
ActiveCN105490761AImprove energy detection performanceOptimum Energy Judgment ThresholdTransmission monitoringEnergy variationFusion center
The present invention relates to a vehicle network cognitive radio adaptive spectrum sensing method. The method comprises the steps of: establishing a cognitive vehicle network consisting of a spectrum sensing fusion center, cognitive vehicles and an authorized user; according to energy detection results and signal-to-noise ratios sent by the cognitive vehicles and a preset signal-to-noise ratio choosing value, selecting members of a primary cognitive group participating in cooperation, and calculating a normalized quotient value corresponding to the signal-to-noise ratio of each member in the primary cognitive group; acquiring a signal-to-noise ratio preset threshold, a signal-to-noise ratio optimal threshold and a joint screening parameter value of each of the primary cognitive vehicles, and selecting secondary cognitive vehicles participating in cooperation; and finally, performing an adaptive sensing fusion by the spectrum sensing fusion center according to the spectrum sensing results from the secondary cognitive vehicles, acquiring an optimal energy judgment threshold value adapted to the energy variation of the received signal under a moving state of the cognitive vehicles, and selecting optimal cooperative ultimate cognitive vehicles for cooperative sensing. According to the invention, the number of the optimal cooperative ultimate cognitive vehicles is obtained when the minimum spectrum detection error is ensured, so that the cooperative detection complexity is reduced.
Owner:北京旭辉新锐科技有限公司
Media access control method for cognitive sensor network based on lead sensing
InactiveCN106612536AResolve transmission conflictsEnables low power operationPower managementConnection managementLine sensorCarrier signal
The invention relates to a wireless sensor network technology, and specifically relates to an adaptive media access control method for a cognitive sensor network based on lead sensing. The method supports a sleep-wake up mechanism of cognitive sensors, and effectively solves a problem of idle sensing of the cognitive sensors and a problem of collision among the cognitive sensors by adopting a technology of combining lead sensing and carrier sensing. In addition, an adaptive sensing and duty ratio adjustment strategy is provided, and low-power-consumption running of the cognitive sensor network is realized under the premise of ensuring sufficient protection for a primary user. According to the invention, a lead sensing based adaptive media access control mechanism is defined, so that low-overhead reliable access of the cognitive sensor network for authorized frequency band can be realized without the need of a common control channel.
Owner:SHENYANG INST OF AUTOMATION - CHINESE ACAD OF SCI
Visual target detection method for detection robot
PendingCN111814726AImprove real timeImprove accuracyCharacter and pattern recognitionNeural architecturesPattern recognitionSpatial positioning
The invention discloses a visual target detection method for a detection robot. The method comprises the following steps of: constructing a hybrid attention adaptive sensing network; training the hybrid attention adaptive sensing network; and detecting the visual target of the detection robot by using the trained hybrid attention adaptive sensing network. The hybrid attention adaptive perception network comprises a global attention hierarchical network, a target space positioning network, a self-adaptive local attention sensing network and a target classification and identification network. According to the method of the invention, target positioning and identification tasks can be completed in a unified framework; the backbone networks are all based on weight sharing under a global attention mechanism, the advantages of a two-stage method and a one-stage method can be integrated; and high accuracy and low omission ratio are achieved while high real-time performance is achieved. The method and device are suitable for high-requirement working conditions of the detection robot.
Owner:NANJING INST OF TECH
Adaptive sensing system
ActiveUS20140197979A1Low incommodation of individualsLow exposition of individualsGeological detection using milimetre wavesRadio wave reradiation/reflectionImaging processingElectromagnetic radiation
The present invention relates to the fields of electromagnetic sensing, automatic security screening and contraband detection. The present invention especially relates to an adaptive sensing system, a sensing method and a corresponding computer program product. The adaptive sensing system according to the present invention comprises an optical or infrared camera for generating image information relating to a region of observation, a passive sensor for receiving electromagnetic radiation, an active sensor for emitting and receiving electromagnetic radiation, an image processing unit adapted to detect the presence of human beings and objects other than human beings in the region of observation based on the generated image information and a control unit. In case the presence of a human being is detected, the control unit is adapted to control the passive sensor so as to receive electromagnetic radiation from at least the region where the human being is detected and, in case the presence of an object other than a human being is detected, the control unit is adapted to control the active sensor so as to transmit and receive electromagnetic radiation to and from at least the region where the object is detected. By using the camera together with an image processing unit, the type of sensor that is applied for sensing is adapted according to the sensed object. This allows individuals to roam freely thereby increasing the convenience for the individuals and allows for a sensing which is unperceived by the individuals. Further, exposition of individuals to electromagnetic radiation is low as individuals are sensed with a passive sensor.
Owner:SONY GRP CORP
Adaptive sensing apparatus
ActiveUS20130194203A1Reduced sensed dataEasy to understandInput/output processes for data processingSensor arraySensing data
An adaptive sensing apparatus, including: a sensor array, having N sensing points, wherein N is a positive integer; a driver unit, coupled with the sensor array; and a control unit, coupled with the driver unit; wherein the control unit has at least one adaptive sampling modes for controlling the driver unit to drive the sensor array and derive M sensed data, wherein M is a positive integer and M<N.
Owner:RICH IP TECH
Adaptive sensing apparatus
ActiveCN103226402AInnovative designInput/output processes for data processingSensor arraySensing data
An adaptive sensing apparatus, including: a sensor array, having N sensing points, wherein N is a positive integer; a driver unit, coupled with the sensor array; and a control unit, coupled with the driver unit; wherein the control unit has at least one adaptive sampling modes for controlling the driver unit to drive the sensor array and derive M sensed data, wherein M is a positive integer and M<N.
Owner:RICH IP TECH
A method for environment adaptive sensing wireless communication channel estimation and signal reconstruction
ActiveCN108400948BEfficient exclusionRobust estimatesChannel estimationMachine learningChannel state informationInterference (communication)
The invention relates to an environment self-adaptation sensing wireless communication channel estimation and signal reconstruction method based on optimal recovery measurement induced by machine learning. The environment self-adaptation sensing wireless communication channel estimation and signal reconstruction method comprises steps that by using base station storage equipment, pilot frequency signals of time-space proximity, channel state information, and recovery measurement information are stored; a receiving end is used to receive the pilot frequency signals transmitted by a transmittingend, and by combining with the base station storage information, the machine learning method is adopted to realize the environment self-adaption sensing channel state and determine the optimal recovery measurement; the channel state information and the optimal recovery measurement are adopted to realize anti-interference, denoising transmission signal reconstruction. Based on the effective information stored on the communication base station and the machine learning principle, fast, effective learning, estimation, and elimination of influences of complicated noises on the wireless communication system can be realized, and therefore the robust estimation and the signal reconstruction of the wireless communication channels are realized in the same time or in shorter time by adopting the self-adaption way.
Owner:XI AN JIAOTONG UNIV
Self-adaptive sensing design
The invention discloses a self-adaptive sensing design. A clock signal having a clock pulse width duration is received. A delay time is received. A first relationship and a second relationship between the clock pulse width duration and the delay time are determined. A new clock is generated that has a first new clock pulse width duration determined by the first relationship and the delay time and a second new clock pulse width duration determined by the second relationship and the clock pulse width duration. Switching between the first new clock pulse width duration and the second new clock pulse width duration is automatic based on the first relationship and the second relationship.
Owner:TAIWAN SEMICON MFG CO LTD
Urban sensing base station
PendingCN112765423AReduce investmentSave on separate constructionData processing applicationsDigital data information retrievalComputer hardwareSound sources
A city sensing base station disclosed by the present invention comprises a sensing terminal, a control terminal and a communication terminal, the sensing terminal comprises a panorama sensing module, a sound source sensing module, a space and state sensing module, an environment sensing module and a biological detection module, and the above modules respectively carry out information interaction and adaptive sensing with the control terminal through a CAN bus. The control terminal is in communication connection with the communication terminal, and achieves information sharing and transmission with an external terminal through the communication terminal; the communication terminal comprises a short-range communication module and an optical fiber communication module; the control terminal comprises an end-side operation module, and the end-side operation module is an SOC chip integrated with an NPU acceleration module by adopting an ARM architecture; multi-element information required by urban comprehensive treatment is comprehensively captured, information entries are unified, meanwhile, data management cost is reduced, data quality is improved, data realization ability is improved, and urban comprehensive treatment is efficiently supported at low cost.
Owner:CENT & SOUTHERN CHINA MUNICIPAL ENG DESIGN & RES INST
Systems and methods for in-frame sensing and adaptive sensing control
ActiveCN109642953AImage enhancementTelevision system detailsComputer graphics (images)Display device
A method for operating an electronic display includes receiving, using a controller, sensor data related to operational parameters of the electronic display based at least in part on illuminating a sense pixel of at least one row of pixels of the electronic display, wherein a first set of pixels below the at least one row of pixels renders a portion of a first image frame and a second set of pixels above the at least one row of pixels renders a portion of a second image frame. The method also includes adjusting, using the controller, image display on the electronic display based at least in part on the sensor data.
Owner:APPLE INC
Rainfall adaptive sensing method of automobile windscreen wipers
ActiveCN101750965BRain intensity level adjustableIncrease flexibilityVehicle cleaningAdaptive controlFrostPoor adaptive skills
The present invention relates to a rainfall adaptive sensing method of automobile windscreen wipers. The existing techniques have the shortcomings of poor adaptive capability and low control accuracy. The method comprises the following steps: first, a controller in a rainfall sensing module is initialized, and a rainfall strength quantified threshold is read from a nonvolatile memory after initialization; a rainfall strength quantified grade is subsequently read by the rainfall sensing module from a motor control module for windscreen wipers; then, the current rainfall strength quantified grade is sensed and calculated by the rainfall sensing module through an infrared transmitter; finally, the current rainfall strength quantified grade is sent to the motor control module for windscreen wipers, the windscreen wipers are relatively controlled by the motor control module for windscreen wipers, and the current rainfall strength quantified grade is updated. The method has the advantages of adjustable rainfall strength grade, good flexibility, strong adaptive capability and capability of overcoming the influence of temperature, natural light strength and frost on rainfall detecting algorithm.
Owner:南通儒尚电动车科技有限公司
Adaptive Control Irrigation and Drainage System of Bottom Lysimeter Pit
InactiveCN104020690BReduce salt contentReduce labor intensityProgramme control in sequence/logic controllersEngineeringLysimeter
Owner:JIANGSU COASTAL WATER CONSERVANCY SCI RES INST +1
Ultra large power two-dimensional semiconductor lock phase array stable oscillation mode technique
InactiveCN100588058CStable oscillationSemiconductor laser arrangementsLaser arrangementsWavefrontShape change
This invention provides a double-path adaptive sensing compensated mode-stabilizing system technology, which puts forward a method for setting up two paths of parallel adaptive compensated mode-stabilizing systems with exchangeable positions including setting up a subsystem related to CCD1for testing change of an outer cavity and a subsystem related to CCD2 for compensating the change of the outercavity, in which, each path of the subsystems for testing the change test the He-Ne laser wavefront slope related parameters reflected by the outer cavity mirror and compute the shape-change volume of the outer cavity and necessary compensation volume, then the subsystems for compensation coordinated to each other compensate a directional change of the outer cavity, and a double-path mode-stabilizing system carries out cooperated optimized compensated operation on the basis of testing one direction of shape-change parameter by each path of adaptive sensing compensated mode-stabilizing systemto counteract the change of position of super-mode optical image aroused by beta-disturbance.
Owner:蔡然
An intelligent self-adaptive sensing separation, cutting and finishing system for sterile medical cotton swabs
InactiveCN107160461BImprove adaptabilityIncrease productivityMetal working apparatusAgricultural engineeringThreaded rod
Owner:深圳市美时依日用品有限公司
An Adaptive-Aware Block Chain Hybrid Consensus Mechanism Framework and Its Method
ActiveCN110474968BMeet the needs of the consensus mechanismImprove scalabilityFinanceUser identity/authority verificationSoftware engineeringConsensus
Owner:NANJING UNIV OF POSTS & TELECOMM
Adaptive communication receiving upper computer and lower computer
InactiveCN107040485ATake full advantage of high-speed processingAchieve receptionModulation type identificationReceiver specific arrangementsFrequency spectrumSelf adaptive
The invention discloses an adaptive communication receiving lower computer and an adaptive communication receiving upper computer. The lower computer senses radio spectrum signals, analyzes useful channel information in the radio spectrum signals, and outputs the useful channel information; the upper computer receives useful channel information, recognizes a first communication parameter in the useful channel information, and outputs the first communication parameter; and the lower computer receives the first communication parameter, configures the first communication parameter as a communication parameter of target radio signals, receives and demodulates the target radio signals, and outputs demodulation data of the target radio signals. The adaptive communication receiving upper computer and lower computer can realize adaptive sensing and recognition on wireless transmitting parameters, then realize reception of radio data for adjusting the transmitting parameters at any time, and thus have strong generality.
Owner:SOUTHWEAT UNIV OF SCI & TECH
A Frequency-Domain Hybrid MAC Protocol Communication Method Based on Adaptive Perception
ActiveCN104486057BImprove transmission qualityImprove experienceTransmission path divisionLink quality based transmission modificationQuality of serviceWireless transmission
The invention discloses a hybrid frequency-domain MAC (medium access control) protocol communication method based on self-adaptive perception. The hybrid frequency-domain MAC protocol communication method comprises the following steps: receiving data transmission requests of one or more multimedia users, and detecting transmission characteristics of the multimedia users; dividing a channel into a plurality of sub-channels on a frequency domain on the basis of a multi-carrier wireless transmission platform, and analyzing the channel quality of each sub-channel; distributing MAC protocols and the sub-channels for the multimedia users according to the transmission characteristics of the multimedia users and the channel quality of each sub-channel; carrying out data transmission by the multimedia users in the corresponding sub-channels according to the acquired distributed MAC protocols. According to the hybrid frequency-domain MAC protocol communication method based on self-adaptive perception disclosed by the invention, mixing of a plurality of MAC protocols is carried out by using a frequency-division multiplexing technology; the self-adaptive perception capacity of data transmission is enhanced; relatively good self-adaption to diversified transmission requirements is achieved; the service quality for the users is improved; the total network throughput is increased.
Owner:GUANGZHOU HKUST FOK YING TUNG RES INST
Improved Densebox target detection method and device and storage medium
PendingCN112270216ASimple structureGuaranteed uptimeCharacter and pattern recognitionNeural architecturesPattern recognitionComputation complexity
The invention discloses an improved Densebox target detection method, an improved Densebox target detection device and a storage medium, and aims to solve the technical problems of large network parameter redundancy, high calculation complexity and insufficient target detection precision of an existing target detection algorithm. The method comprises the following steps: acquiring historical roadimage data, and carrying out image preprocessing; performing central region adaptive perception based on the preprocessed image to obtain a training sample set of the road image; training a pre-constructed CNN network by using the training sample set to obtain a trained CNN network model; and processing the to-be-detected road image by using the trained CNN network model to obtain a road target detection result. The invention optimizes the CNN network structure, gives full play to the performance of the network, effectively balances the back-propagation loss weighting of various scales of targets through employing the adaptive sensing center region, and improves the target detection precision.
Owner:南京佑驾科技有限公司
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