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.
36 results about "Crowd monitoring" 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
Bus stop people monitoring device and monitoring method thereof
InactiveCN102724484AExpand coverageImprove detection accuracyRoad vehicles traffic controlCharacter and pattern recognitionCrowd monitoringFunction optimization
The invention discloses a bus stop people monitoring device which comprises a video acquisition module and a video processing module; the video acquisition module is used for acquiring the real-time video data of a bus stop; and the video processing module is connected with the video acquisition module for pre-processing and analyzing the video data which is acquired by the video acquisition module so as to obtain the people state information of the bus stop and send the people state information to a remote control center. According to the invention, the people state information refers to people crowdedness information or the motion and abnormal behavior information of the people. According to the invention, the automatic detection for the state information of waiting passengers is completed by acquiring the video information from the bus stop, the manpower monitoring for the bus stop through eye observation is replaced, so that the coverage, the detection precision and the real-time performance of a bus stop monitoring system are improved, the basic information acquired by an existing bus dispatching management system is effectively supplemented, and the requirements of bus dispatching management on function optimization are met.
Owner:INST OF AUTOMATION CHINESE ACAD OF SCI
Crowd counting method based on deep residual network
ActiveCN106778502AAccurate estimateThe network parameter model is smallCharacter and pattern recognitionPattern recognitionCrowd counting
The invention discloses a crowd counting method based on a deep residual network. The method applies the deep residual network to extract the characteristic of each frame of image in a crowd monitoring video, wherein the input of the deep residual network is one frame of image; through 5*5 kernel convolution and pooling, an initial characteristic graph is obtained; through ten residual network units, characteristics are extracted; a main branch obtains a crowd density graph corresponding to an input image through 1*1 kernel convolution; an auxiliary branch obtains a people number corresponding to the input image through the 1*1 kernel convolution; and finally, through the integration of the crowd density graph, the people number estimation value of the input image is obtained. Each residual network unit has the structure that a 3*3 conventional kernel is accessed after a 1*1 convolution kernel, then, the 1*1 convolution kernel is accessed, a batch normalization operation and a linear rectification operation are added after each convolution kernel, and meanwhile, the output of a previous residual network unit also serves as the input of a next residual network unit through the 1*1 kernel convolution. By use of the method, an influence on crowd counting by scene transformation can be reduced, and a stable crowd counting effect is obtained.
Owner:SOUTH CHINA UNIV OF TECH
Method for analyzing and predicting large-scale crowd density
The invention provides a method for analyzing and predicting large-scale crowd density. The method comprises the following steps: performing crowd density analysis on an input video based on crowd density analysis with statistical characteristics, and acquiring a crowd density value of a single monitoring point; realizing the mutual conversion of the crowd density and the number of people through multi-stage linear fit; calculating the flow speed and the flow direction of crowd in the single monitoring point by an optical flow method, and acquiring the information of the flow speed and the flow direction of the crowd in the single monitoring point; and establishing a structure of a directed graph according to the relation between the spatial positions of each of monitoring points and the flow direction and the flow speed of the crowd, and performing the prediction of the number of the people and the crowd density in a period of time on an import monitoring hub node. Due to the method, the crowd density and the distribution of the number of the people in a large area can be automatically monitored in real time, and the prediction of the crowd density and the number of the people can be performed on an import place; and the information provided by the method has important reference value for a crowd monitoring department.
Owner:INST OF AUTOMATION CHINESE ACAD OF SCI
Selective feature background subtraction method aiming at thick crowd monitoring scene
InactiveCN102013022AEasy to detectOptimize detection resultsCharacter and pattern recognitionKernel principal component analysisCrowd monitoring
The invention provides a selective feature background subtraction method aiming at a thick crowd monitoring scene. Aiming at a problem that a traditional background subtraction method can cause higher missed inspection and error inspection rate under a thick crowd scene, the invention discloses the selective feature background subtraction method, which comprises the following steps of: creating a scene sparsity model; selecting a video frame having higher similarity to the sparsity model as a training sample, and obtaining an initialized feature scene based on batching principal component analysis; updating the scene sparsity model, selecting a video frame having higher similarity to the sparsity model to update the feature background by incremental principal component analysis; selectively rebuilding the background at pixel level; and solving an adaptive threshold to threshold a difference image and obtain a foreground image. The selective feature background subtraction method can inspect out slowly moving and static foreground objects well in the thick crowd scene with relatively steady light and simultaneously keep lower error inspection rate.
Owner:PEKING UNIV
Method and system for judging crowd density in image
ActiveCN102044073AConfidence Density Class EstimationQuick forecastImage analysisCharacter and pattern recognitionCrowd monitoringPosteriori probability
The invention provides a method and system for judging the crowd density in an image. The method comprises the following steps: 1. selecting a target region from a video image sample acquired in an image acquisition device by utilizing a block analysis unit, and carrying out block analysis of image blocks in the target region; 2. determining the composite form of two-classifiers by a coding unit;3. selecting a confidence training sample by a training unit, and respectively training each two-classifier; and 4. obtaining the crowd density grade category of the maximum posteriori probability through a decoding unit by means of a channel transmission model. The method can be suitable for obtaining the credible crowd density grade in different scenes and can provide the basis for crowd monitoring and safety guarantee of important regions.
Owner:北京汉王智远科技有限公司
Method for judging crowd density and number of people based on fish eye camera
InactiveCN103049765ARealize warning functions such as alarmTo achieve the purpose of crowd intelligent monitoringCharacter and pattern recognitionHuman bodyCrowd monitoring
The invention provides a method for judging crowd density and number of people based on a fish eye camera. The method comprises the following steps of: (1) acquiring a background image; (2) acquiring a crowd monitoring video image; (3) preprocessing the crowd monitoring video image; (4) performing foreground segmentation; (5) extracting a crowd target characteristic; (6) grading the crowd density; and (7) counting the people. The method aims to expand the monitoring range; the problem of inconsistency in sizes of human bodies and the problem of mutual sheltering of the human bodies in the high-density crowd existing in the conventional crowd monitoring method are solved; and the method has good real-time property and can be applied to a real-time crowd monitoring system.
Owner:武汉经纬视通科技股份有限公司
CAD (computer-aided design) people counting method based on FAST (features from accelerated segment test)
InactiveCN103577875ASolve the speed problemResolve accuracyCharacter and pattern recognitionCounting objects with random distributionCrowd monitoringVision based
The invention discloses a CAD (computer-aided design) people counting method based on FAST (features from accelerated segment test), and belongs to the field of computer vision-based people counting. The method is characterized in that after a crowd surveillance video image is subjected to filtering preprocessing, an FAST corner feature vector of a current image is obtained through a corner detection algorithm; a low-density crowd image and a high-density crowd image is divided according to the ratio of the number of feature points and the sum of pixels of the current crowd image, and foreground images of the low-density crowd image and the high-density crowd image are extracted; as for the foreground image of the low-density crowd image, the connected domain area T obtained through an erosion algorithm is taken as an FAST point, and as for the foreground image of the high-density crowd image, a neighbor domain is established for the core point of each pixel through an OPTiCS algorithm, then, the minimum reach distance from the core point of each neighbor domain to each pixel is taken as the minimum reach distance in each neighbor domain, and an FAST point vector X of the high-density crowd is constructed accordingly; a crowd evaluation model is constructed according to T, X and the distance D between a camera and the crowd; and a set training sample is taken as a test vector for performing SVM (support vector machine) training, so that the counting speed and the accuracy rate are increased.
Owner:BEIJING UNION UNIVERSITY
Unmanned aerial vehicle ground crowd monitoring system and monitoring method
ActiveCN108388838AReduce mistakesPrecise scheduling and deploymentScene recognitionResourcesIlluminanceWireless transmission
The invention discloses an unmanned aerial vehicle ground crowd monitoring system. The system comprises a ground information platform and at least one monitoring unmanned aerial vehicle; the monitoring unmanned aerial vehicle comprises a ground shooting camera, a processor, a wireless transmission mechanism and an illuminance sensor; the processor is bidirectionally connected with the camera and the wireless transmission mechanism; the wireless transmission mechanism wirelessly communicates with the ground information platform; and the illuminance sensor is bidirectionally connected with the camera or the processor. A monitoring method comprises the steps of identifying crowd density through image transparency; coloring crowd images with different densities; and finally calculating out crowd distribution change data. The system has the beneficial effects that the requirements on hardware of the unmanned aerial vehicle are low, and information of crowd number, density, movement and thelike is visually obtained; and the crowd density is colored, so that a manager can visually see a crowd distribution condition, personnel deployment of safety protection is accurately scheduled, the image analysis time is saved, and the working efficiency is improved.
Owner:CHONGQING UNIV OF POSTS & TELECOMM
Position spot matching-based video identifying, tracking and positioning system
ActiveCN105847756AExact matchImprove efficiencyTelevision system detailsNetwork topologiesCrowd monitoringIdentity recognition
The invention relates to space information technologies and specifically relates to a position spot matching-based video identifying, tracking and positioning system. A video map is established via an AP monitoring camera, a WIFI mobile terminal user group is set as a monitoring target, a user group positioning video image taken at a certain time is obtained, a spot pixel map of all target spots is formed via video feature analyzing operation, and mobile phone positions and ID information of the user group are extracted to form a spot vector map; the spot pixel map and the spot vector map are subjected to spatial overlaying operation, space-time coordinates are used as pointers, a corresponding relation between user images and mobile phone information of users is established, video pixel spots and mobile phone positioning spots are subjected to multiple times of overlaying operation and matching operation, and therefore attributes such as user mobile phone identification numbers and the like are given to pixel human images; mobile terminal information can be precisely matched with video human images, large-scale population monitoring and identity recognition can be realized, traditional manual processed can be replaced, and efficiency improvement and cost reduction can be realized.
Owner:SHENZHEN INST OF ADVANCED TECH
Crowd fleeing event detection method and system based on direction-clustering model
ActiveCN106845389AImprove detection accuracyImprove robustnessCharacter and pattern recognitionCrowd monitoringHigh density
The invention discloses a crowd fleeing event detection method and system based on a direction-clustering model. In order to solve the problem that the crowd fleeing event detection method is low in detection accuracy, the technical scheme comprises the steps of extracting moving tracks from crowd monitoring videos, thereby obtaining a track coordinate matrix, and calculating speeds and directions of moving particles on the moving tracks through the track coordinate matrix; on the basis of the randomness of the speeds and directions of the moving particles, establishing the direction-clustering model which represents a moving state of a crowd; calculating a direction-clustering index of each frame of crowd monitoring video according to the direction-clustering model; extracting an event detection threshold self-adaptively from all obtained direction-cluster indexes, comparing the event detection threshold with the direction-clustering index of each frame of crowd monitoring video, and finally detecting a crowd fleeing event of the crowd monitoring video. The method is widely applied to a middle and high density crowd and the detection accuracy is high.
Owner:SHANDONG UNIV
Subway crowd behavior label identification method based on base station position
InactiveCN110910293AReduce operating costsRealize monitoringData processing applicationsParticular environment based servicesCrowd monitoringSimulation
The invention discloses a subway crowd behavior label identification method based on a base station position, and the method comprises the following steps: S1, obtaining the user data of a subway operator base station, processing the user data, and obtaining the position of a cellphone user time dimension; S2, building a subway crowd recognition model: enabling the operator base stations to correspond to subway stations, building a subway region configuration table, and recognizing subway crowds; and S3, establishing a crowd label model, and performing statistics to obtain the number of inbound people, the number of outbound people and the number of exchanged people of the subway station in a fixed time interval. According to the method, the metro crowd behavior label is obtained by combining operator user signaling data, base station positions and a modeling algorithm. In combination with a previous subway crowd monitoring means, subway crowd monitoring is completed through another scene, and automation and precision are achieved.
Owner:广州丰石科技有限公司
Cascaded multi-scale-based dense face detection method
ActiveCN110046595AImprove accuracyImprove global detection resultsCharacter and pattern recognitionPattern recognitionFace detection
The invention relates to a cascaded multi-scale-based dense face detection method. According to the method, the detectors with various scale ranges are trained respectively, each object detector is cascaded according to a specific scale range to optimize an existing network structure, and the strategy can be carried in a depth model of face detection, has good expansibility, and is more suitable for dense small face detection. The method can be applied to the specific scenes, such as intensive crowd monitoring, classroom people counting, etc., and has very strong application value.
Owner:FUZHOU UNIV
Community lighting system and method based on crowd activity big data
PendingCN113660757AGuaranteed lighting effectsReduce wasteEnergy saving control techniquesClosed circuit television systemsCrowd monitoringImaging analysis
The invention discloses a community lighting system and method based on crowd activity big data, and relates to the technical field of community lighting systems. The system comprises a community monitoring platform and a plurality of road lamp control terminals. The community monitoring platform is in communication connection with the plurality of road lamp control terminals; the road lamp control terminals are in electric signal connection with two same-side road lamp circuits and a floor lamp circuit; street lamps on the same side of a road are connected in parallel to form a same-side street lamp circuit; and floor lamps on two sides of the road are connected in parallel to form the floor lamp circuit. A camera shoots a plurality of crowd monitoring images and transmits the images to an image analysis module; the image analysis module analyzes the plurality of crowd monitoring images in the same time interval to obtain crowd flow quantity information and transmits the crowd flow quantity information to a crowd activity analysis module; a control module compares a dynamic crowd flow quantity table with a lamp control threshold table to control the two same-side street lamp circuits or the floor lamp circuit to be switched on; and the lighting effect can be guaranteed, and waste can be reduced.
Owner:安徽极光照明工程有限公司
Crowd counting method for real scene
InactiveCN111753671AQuality improvementNo loss of statistical precisionCharacter and pattern recognitionNeural architecturesCrowd countingCrowd monitoring
The invention discloses a crowd counting method for a real scene. The method is characterized by adopting a geometric Gaussian adaptive kernel function to generate a real crowd density map as a real value to guide training; inputting the crowd image into the convolution operation of the local receptive field, fusing the generated adaptive feature maps of different scales, inputting the fused feature maps into a deep neural network model, and obtaining the number of people in the scene through regression solution and an integral method according to the obtained estimated density map. Compared with the prior art, the method is simple and convenient, strong in real-time performance and high in accuracy of people counting, can quickly obtain a high-quality crowd density map by adopting a lightweight network structure, does not lose too much statistical precision, occupies a small memory space of model parameters, and is particularly suitable for various scenes with high real-time performance requirements, such as attendance systems, crowd monitoring systems and the like.
Owner:EAST CHINA NORMAL UNIV
A method and system for managing intelligence policing information of migratory bird community
ActiveCN109377433AQuick statisticsEasy to monitorData processing applicationsCharacter and pattern recognitionCrowd monitoringCritical path method
A method and system for managing intelligence policing information of migratory bird community are disclosed. The model and location of the house model nodes in migratory bird communities are quicklyidentified by unmanned aerial vehicles, and an AOE network of the direction path from the command center to each bayonet through the house model nodes is formed, a key position is calculated, a face recognition system is arranged at the critical path node to collect the basic information of migratory birds in the migratory birds community, people who leave a cell are recognized by face recognitionfrom a video on a critical path, which can quickly count and identify the common migratory birds in the community, can quickly count the number of migratory birds in the community houses and floatingpopulation convenient for migratory birds crowd monitoring and management guard against security risks emergent housing model node can be quickly reacted control and processing.
Owner:广东世寰智能科技有限公司
Stadium crowd monitoring method based on intelligent video identification technology
InactiveCN108960165AAccurate identificationGood real-time processing abilityImage enhancementImage analysisVideo monitoringCrowd monitoring
The invention belongs to the technical field of video monitoring, and discloses a stadium crowd monitoring method based on an intelligent video identification technology. The stadium crowd monitoringmethod adopts a video acquisition module, an image processing module, a target processing module, a server module and a crowd density calculation module. According to the stadium crowd monitoring method, the image processing module adopts an improved self-adaptive Gaussian mixture model for background modeling, segments foreground pixels to adapt to variation of ambient light rays through statistical discrepancy between pixels corresponding to all frames in a video within a period of time and an established background model; meanwhile, the crowd density calculation module determines a currentcrowd density sampling value, and analyzes the current crowd density in different ways, so as to obtain more precise crowd density information, thereby avoiding the situation of decrease in density analysis precision caused by improper analysis methods, and improving the precision of crowd density acquisition.
Owner:HUNAN CITY UNIV
Location data real-time wireless transmission method for burst high load condition
ActiveCN103313269AImprove real-time performanceNetwork planningWireless transmissionCrowd monitoring
The invention discloses a location data real-time wireless transmission method for burst high load condition. The location data real-time wireless transmission method comprises the following steps: (1), setting two threshold values c1 and c2 for number of connections for communication AP, wherein c1 and c2 are natural numbers, c1 is smaller than c2, k is larger than 0 and smaller than 1, k is a real number and is 0.7 generally; C2 is the maximum channel number for wireless protocol support; and (2), selecting the communication AP with the minimum load for connection according to the position of positioning equipment at present and the load of all APs in a range of taking the position as a circle center and semidiameter as r by the positioning equipment, and then uploading location data to the AP. The method is successfully applied to a monitoring system based on wireless indoor positioning; and the practice shows that an indoor positioning system configured with the method can be good in real-time performance in dense crowd monitoring.
Owner:B SOFT CO LTD
Crowd monitoring method based on generative adversarial network, apparatus and device, and medium
The invention provides a crowd monitoring method based on a generative adversarial network, which can be applied to the technical field of artificial intelligence. The method comprises the following steps: training a generative adversarial network, and after training is finished, estimating the number of people in a target monitoring area by using a generator model in the generative adversarial network to obtain a second crowd density estimation graph based on a second crowd image of the target monitoring area, wherein in the training process, a first crowd image is used as input of a generator model, and the generator model is trained to output a first crowd density estimation graph; meanwhile, taking the first crowd density truth value graph and the first crowd density estimation graph as input of a discriminator model so that the discriminator model can discriminate the similarity between the first crowd density truth value graph and the first crowd density estimation graph, and repeating the training process continuously until the discriminated similarity meets a preset threshold condition. The invention further provides a crowd monitoring device and equipment based on the generative adversarial network, a storage medium and a program product.
Owner:INDUSTRIAL AND COMMERCIAL BANK OF CHINA
5G planning site recommendation method based on big data
PendingCN113988898AImprove collection efficiencyImprove accuracyMarketingNetwork planningCrowd monitoringCrowds
Owner:ANHUI TELECOMM PLANNING & DESIGNING +1
Low-complexity dense crowd analysis method based on deep learning
PendingCN110852189AReduce monitoring errorsImprove reliabilityCharacter and pattern recognitionReal time analysisCrowd monitoring
The invention discloses a low-complexity dense crowd analysis method based on deep learning. The method comprises the steps of (1) sampling to obtain a picture data set; (2) labeling the picture dataset; (3) selecting a Gaussian convolution kernel, performing Gaussian convolution operation on each marking point of each picture to obtain a corresponding crowd distribution thermodynamic diagram, and counting the real number of pedestrians in each picture; (4) randomly dividing the obtained picture data set into a training set and a test set according to a proportion of 8:2, respectively takingthe training set and the test set as inputs of a training model and a test model, and carrying out offline training to obtain a low-complexity deep learning model for analyzing dense crowd distribution conditions; and (5) decoding the new crowd monitoring video stream in real time, inputting the decoded new crowd monitoring video stream into the training model, representing the crowd distributionsituation by a thermodynamic diagram output by the model, and integrating the thermodynamic diagram to realize real-time analysis of dense crowds. According to the invention, a more excellent crowd monitoring analysis effect can be obtained.
Owner:TIANJIN UNIV
Flood emergency evacuation method based on real-time crowd data fusion
ActiveCN113902168AImprove efficiencyGood effectClimate change adaptationForecastingCrowd monitoringThe Internet
The invention discloses a flood emergency evacuation method based on real-time crowd data fusion. The method comprises the following steps: 1, constructing a two-dimensional hydrodynamic model, and determining the range of a flood risk area and a safe area; 2, developing a position service interface, and accessing the Internet in an emergency state to obtain real-time crowd monitoring data; 3, developing a mobile application of flood emergency evacuation, and collecting user crowd filling data; 4, performing overlay analysis on the LBS real-time crowd monitoring data and the crowd data acquired by the mobile application by adopting a multi-source data fusion technology; 5, constructing a flood emergency evacuation model based on the real-time crowd fusion data, and dynamically planning a crowd evacuation route; and 6, pushing the flood early warning message and the evacuation route information to the crowd in the risk area. The method has the advantages that the accuracy and timeliness of crowd recognition are improved, and the efficiency and effect of emergency risk avoiding and evacuation of crowds in flood risk areas are improved.
Owner:长江信达软件技术(武汉)有限责任公司 +1
Method and system for judging crowd density in image
ActiveCN102044073BConfidence Density Class EstimationQuick forecastImage analysisCharacter and pattern recognitionCrowd monitoringPosteriori probability
The invention provides a method and system for judging the crowd density in an image. The method comprises the following steps: 1. selecting a target region from a video image sample acquired in an image acquisition device by utilizing a block analysis unit, and carrying out block analysis of image blocks in the target region; 2. determining the composite form of two-classifiers by a coding unit;3. selecting a confidence training sample by a training unit, and respectively training each two-classifier; and 4. obtaining the crowd density grade category of the maximum posteriori probability through a decoding unit by means of a channel transmission model. The method can be suitable for obtaining the credible crowd density grade in different scenes and can provide the basis for crowd monitoring and safety guarantee of important regions.
Owner:北京汉王智远科技有限公司
Intelligent statistical method and device for advertisement attention crowds and computer readable storage medium
PendingCN113378765AEasy to monitorGuaranteed privacyCharacter and pattern recognitionMarketingFace detectionCrowd monitoring
The invention discloses an intelligent statistical method and device for advertisement attention crowds and a computer readable storage medium. The method comprises the steps of collecting image data through a camera device; detecting all faces in the image data through a terminal face detection algorithm, and labeling each face uniquely; through a terminal tracking algorithm, respectively calculating the stay duration of the tracked and detected face; recognizing related information of each face through a terminal face attribute recognition algorithm; sending the face related information to a background management system, and enabling the background management system to carry out classified statistics and people flow summarization according to the face related information. According to the invention, intelligent analysis of advertisement watching crowds can be realized, operation is carried out at the equipment terminal, picture data is not collected, privacy of the advertisement watching crowds is ensured, and related information obtained through analysis is transmitted to the background management system, so that an accurate classification statistics function of advertisement attention crowds is realized, and accurate advertisement putting and advertisement attention crowd monitoring are facilitated.
Owner:四川启睿克科技有限公司
Method for analyzing and predicting large-scale crowd density
Owner:INST OF AUTOMATION CHINESE ACAD OF SCI
A real-time wireless transmission method of positioning data for sudden high-load situations
ActiveCN103313269BImprove real-time performanceNetwork planningWireless transmissionCrowd monitoring
The invention discloses a location data real-time wireless transmission method for burst high load condition. The location data real-time wireless transmission method comprises the following steps: (1), setting two threshold values c1 and c2 for number of connections for communication AP, wherein c1 and c2 are natural numbers, c1 is smaller than c2, k is larger than 0 and smaller than 1, k is a real number and is 0.7 generally; C2 is the maximum channel number for wireless protocol support; and (2), selecting the communication AP with the minimum load for connection according to the position of positioning equipment at present and the load of all APs in a range of taking the position as a circle center and semidiameter as r by the positioning equipment, and then uploading location data to the AP. The method is successfully applied to a monitoring system based on wireless indoor positioning; and the practice shows that an indoor positioning system configured with the method can be good in real-time performance in dense crowd monitoring.
Owner:B SOFT CO LTD
A Fast-Based Computer Aided CAD People Counting Method
InactiveCN103577875BSolve the speed problemResolve accuracyCharacter and pattern recognitionCounting objects with random distributionCrowd monitoringVision based
The invention discloses a CAD (computer-aided design) people counting method based on FAST (features from accelerated segment test), and belongs to the field of computer vision-based people counting. The method is characterized in that after a crowd surveillance video image is subjected to filtering preprocessing, an FAST corner feature vector of a current image is obtained through a corner detection algorithm; a low-density crowd image and a high-density crowd image is divided according to the ratio of the number of feature points and the sum of pixels of the current crowd image, and foreground images of the low-density crowd image and the high-density crowd image are extracted; as for the foreground image of the low-density crowd image, the connected domain area T obtained through an erosion algorithm is taken as an FAST point, and as for the foreground image of the high-density crowd image, a neighbor domain is established for the core point of each pixel through an OPTiCS algorithm, then, the minimum reach distance from the core point of each neighbor domain to each pixel is taken as the minimum reach distance in each neighbor domain, and an FAST point vector X of the high-density crowd is constructed accordingly; a crowd evaluation model is constructed according to T, X and the distance D between a camera and the crowd; and a set training sample is taken as a test vector for performing SVM (support vector machine) training, so that the counting speed and the accuracy rate are increased.
Owner:BEIJING UNION UNIVERSITY
A Dense Face Detection Method Based on Cascaded Multiscale
ActiveCN110046595BImprove accuracyImprove global detection resultsCharacter and pattern recognitionFace detectionCrowd monitoring
The invention relates to a method for dense face detection based on cascaded multi-scale, which trains detectors of various scale ranges respectively, each object detector is aimed at a specific scale range, and then cascades them to optimize the existing The network structure, this strategy can be carried in any deep model of face detection, has good scalability, and is more suitable for dense small face detection. It can be applied to specific scenarios such as dense crowd monitoring and classroom population statistics, and has strong application value.
Owner:FUZHOU UNIV
A method and system for crowd escape event detection based on direction-cluster model
ActiveCN106845389BImprove detection accuracyImprove robustnessCharacter and pattern recognitionCrowd monitoringHigh density
The invention discloses a method and system for detecting crowd escape events based on a direction-cluster model. In order to solve the problem of low detection accuracy in the crowd escape event detection method, the technical solution is to extract the movement trajectory from the crowd monitoring video to obtain the trajectory coordinate matrix, and then calculate the speed and direction of the moving particles on the movement trajectory through the trajectory coordinate matrix ; Based on the speed of the moving particles and the disorder of the direction, set up the direction-cluster model representing the motion state of the crowd; calculate the direction-cluster index of each frame of crowd monitoring video according to the direction-cluster model; from all obtained The event detection threshold is adaptively extracted from the direction-cluster index, and then the event detection threshold is compared with the direction-cluster index of each frame of crowd surveillance video to finally detect crowd evacuation events in the crowd surveillance video. This method is widely used in medium and high-density populations with high detection accuracy.
Owner:SHANDONG UNIV
Aggregated crowd monitoring method and device and computer storage medium
The invention provides a gathered crowd monitoring method and device and a computer storage medium, and the method mainly comprises the steps: obtaining each target monitoring crowd meeting a preset gathered crowd number threshold value from each monitoring image according to the preset gathered crowd number threshold value, carrying out the recognition of each target object from each target monitoring crowd according to each target object recognized from each target monitoring crowd, obtaining each target coincidence value corresponding to each target object, and determining each target object of which the target coincidence value exceeds a preset coincidence threshold value according to the preset coincidence threshold value. Therefore, clustering analysis can be carried out on the gathered crowd.
Owner:GUANGZHOU YUNCONG INFORMATION TECH CO LTD
Specified crowd monitoring method and device as well as storage medium
The invention discloses a specified crowd monitoring method and device as well as a storage medium, and belongs to the field of computer processing. The method comprises the following steps of acquiring a sound of the surrounding environment of a first terminal to obtain a first voice signal; detecting whether a sound of a specified type exists in the first voice signal or not through a first sound detection module, and detecting whether the first voice signal is a sound of a specified user or not through a first voiceprint recognition model; and when the first voice signal is the voice signalof the specified user, and the sound of the specified type exists in the first voice signal, transmitting prompt information to a second terminal. According to the specified crowd monitoring method and device, a prompt operation is carried out only when the first voice signal of the specified type of the specified user is detected, so that false operations caused by the detection of a voice signal of a type specified by others is avoided, and the monitoring accuracy is improved.
Owner:HANGZHOU HIKVISION DIGITAL TECH
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