223 results about "Crowding in" patented technology

The present invention is a system, method, and apparatus for determining the impact of crowding on retail performance based on a measurement for behavior patterns of people in a store area. The present invention captures a plurality of input images of the people by at least a means for capturing images, such as cameras, in the store area. In the captured plurality of input images, each person's shopping path is detected by a video analytics-based tracking algorithm. A subset of the people is identified as a crowd in the store area. In relation to the crowd, the behavior patterns of the target person are measured. After aggregating the measurements for the behavior patterns over a predefined window of time, the present invention can calculate a crowd index and a crowd impact index for the store area based on the measurements. A crowd index shows the level of crowd density in the store area caused by a crowd, including traffic count of the crowd in the store area. A crowd impact index comprises a traffic count of the target people who make trips to the store area and a shopping time index, such as average shopping time changes of the target people, in relation to a crowd in the measured store area.

The invention provides a method for detecting group crowd abnormal behaviors in video monitoring. The method comprises the steps of: video target detection: obtaining video objects through edge information difference detection in successive frames, and obtaining video objects with movement change through frame difference of a foreground frame and a background frame, obtaining a relatively accurate movement target by combining two video object detection results; video target tracking: tracking targets to obtain corresponding movement tracks through a video particle-based long-period movement estimation method; group crowd detection: carrying out spectral clustering analysis on the distance between the tracks and advancing speed information through movement characteristics of the group crowd in video; and identification of group crowd abnormal behaviors: establishing a model for crowd tracks by using an MGHMM (Mixed Gaussian Hidden Markov Model), and identifying blockage and fall through sudden change of a normal track. The invention integrates technologies of crowd target detection, group target track, mode identification and machine learning.

A method and an apparatus for detecting an interest degree of a crowd in a target position are disclosed. The interest degree detection method includes projecting a depth image obtained by photographing onto a height-top-view, the depth image including the crowd and the target position; dividing the height-top-view into cells; determining density of the crowd in each cell; determining a moving speed and a moving direction of the crowd in each cell; determining orientation of the crowd in each cell; and determining, based on the density, the moving speed, the moving direction and the orientation of the crowd, the interest degree of the crowd in each cell in the target position. According to this method, the interest degree of the crowd in the target position can be detected accurately, even at a crowded place where it is difficult to detect and track a single person.

The invention provides a statistical method for the high-density crowd flow, which comprises the following steps: selecting a supervision region image from video images which supervise mobile crowd in real time; converting a colorful supervision region image into a gray level video image; comparing the absolute difference of pixels on corresponding positions among three adjacent frames in an input gray level video image sequence; carrying out thresholding to an obtained detection result to obtain a binarization image so as to extract the moving crowd in the image; the current supervision region image is subjected to abnormality detection; setting a region of interest, and collecting pixels from the region of interest according to the binarization image; and according to the correspondenceof a pixel number and a number, calculating the total number passing through the supervision region within unit time so as to calculate the crowd flow in real time. According to the statistical method, the high-density migrant crowd advancing to one direction can be subjected to flow statistics under the complex background.

The invention is suitable for video monitoring technologies and relates to a method and an apparatus for crowd behavior analysis in video monitoring. The method comprises: obtaining a video stream and dividing each frame of image in the video stream into image sub-blocks with different perspective degrees by taking human height as a size reference by row; extracting deep neural network features in the image sub-blocks; classifying and optimizing the deep neural network features, obtaining a corresponding vector feature set, establishing SVR mathematical models of different kernel functions according to the vector feature set, and making statistics on the number of people in crowds with different density; and adopting a camera calibration method for obtaining coordinate vectors of the deep neural network features, comparing displacements of the deep neural network features of the two continuous frames of image sub-blocks, and calculating a moving direction and a moving speed of the crowd according to the displacement. According to the method and the apparatus, the crowd in the video monitoring is tracked and analyzed to obtain feature information, such as the moving speed, the moving direction, the number of people and the like, of the crowd, the feature information and historical data are analyzed and compared, a state of the crowd is judged, and an alarm is given for an abnormal event.

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.

The invention relates to a large-scale virtual crowd real-time rendering method, which comprises the following steps of: 1, introducing the conventional grid model and extracting geometric information and animation information of the model; 2, performing octree space subdivision on the model, wherein approximate description of a part of the model related to geometric size of each node is stored in the node; 3, performing point sampling on the surface of the part of the model included by each node; 4, processing and modeling a sample point, wherein the step comprises the sub-steps of calculating sample point information by interpolation, selecting sample point animation information, oversampling and removing redundancy and the like; 5, establishing model sampling data of three-layer LOD (Levels of Detail) according to specified parameters; 6, performing view frustum culling accelerated by a GPU (Graphic Processing Unit) on a virtual crowd in a large-scale scene during the real-time rendering; 7, performing an LOD strategy accelerated by the GPU on the cuffing result, wherein the step comprises the sub-steps of selecting role LOD and ordering LOD; and 8, sequentially performing GPU skin-skeleton animation based instancing rendering on the role of each layer of LOD level. By adopting the method, quick real-time rendering of a large-scale virtual crowd can be realized.

The invention relates to an indoor emergency evacuation simulation method for a complex building. According to the method disclosed by the invention, a three-dimensional extended hierarchical node relation model (EHI-NRM) of an internal space unit of the complex building is automatically generated, and the update of a dynamic path of a large-scale complex building is supported; an improved cellular automaton model (ICA) can better simulate jam, avoidance, mass-following and other phenomena of a large-scale crowd during the evacuation process; and an optimal evacuation path is searched in real time in the macro-level through an EHI-NRM dynamic path-finding method, and the ICA is applied in the local level for simulating the behavior characteristics of the crowd. According to the method disclosed by the invention, the evacuation simulation of the large-scale crowd in the large-scale complex building is supported, and the method has important application values for ensuring the safety of staff in the building and improving the decision-making capacity of an emergency rescue department.

The present invention discloses a social network based message propagation model, which is a method, based on the special line of the crowd in the network and the average degree of the nodes in the social network, for carrying out modeling analysis on message propagation in the social network and proposing a node importance based rumor immune strategy. The dynamic equations of the <k> SLIR message propagation model are established in the small-world network; by virtue of the method disclosed by the present invention, influences of nodes in various states in the social network, on message propagation can be realistically taken into consideration; and according to the node importance based improved rumor immune strategy proposed by the present invention, propagation of rumors in social network can be better inhibited.

The invention discloses a method for guaranteeing the appointment order and improving the number source using efficiency for online appointment registering. The method includes the steps of real name authentication, appointment behavior management, nonperformance behavior management, clinical consultation behavior tracking, user behavior analysis, user award point management and user risk alarming. According to the method, patients outside a hospital can a wireless device within the wireless network coverage scope at any time and any place to achieve online remote appointment registering through a wired or wireless network, great convenience is brought to the patients, limitation of time and space is broken through, the problem that the appointment registering time for various traditional registering methods is excessively concentrated is solved, the number source using efficiency is improved, disease infections caused by person crowding in a hospital registering site are prevented, the workloads of the hospital are reduced, and the hospital can reasonably distribute medical resources. By means of the method, real name registering is adopted, so that rampant scalpers on the society are prevented.

The invention discloses a method for creating a contact group based on geographical location information, which is used for providing convenience for the crowd in same geographical location site to exchange personal contact information in bulk and create contacts; users can send own location and own contact way through an electronic device to a contact exchange server by a network;after receiving the geographical information and the contact information, the server judges composition of the crowd according to the location information and information transmitting time, and needs to exchange the contact information in bulk, and then the server sends the whole batch of contact information to a software which is used for adding the contact information in bulk and operating in all the electronic devices of the crowd, the software lists all the received contact information, and then, users of the software decide to add all or part of the received contact information in an address book of the electronic device, so that, the crowd can conveniently and quickly add the contact information in bulk.

The invention discloses a method for recognizing the happiness degree of a crowd based on deep learning. The method comprises: firstly classifying manually marked individual face images and normalizing image sizes to obtain a face happiness degree database and a face shielding degree database; separately dividing the face happiness degree database and the face shielding degree database into a training set and a verification set to train a convolution neural network; then identifying the happiness degree and the shielding degree of faces in an input group photo by using a trained network model; and finally calculating the happiness degree of the crowd in the image by using face happiness degree weighted way. The method analyzes the expression of the crowd in the image by using the deep learning, is more accurate compared with traditional methods of extracting PHOG and Gabor, and provides new ideas and approaches for crowd emotion recognition in the image.

The invention provides a crowd counting method based on a multi-scale context enhancement network, which comprises the following steps: inputting a picture, obtaining shallow features and deep features after feature extraction, performing feature fusion through a feature fusion module, sending the fused features into a multi-scale perception module, and finally, encoding the space and channel information of the features through a context enhancement module to obtain a density map with crowd distribution features. The estimated number of people in the current picture can be obtained by summingthe density image pixels. According to the crowd counting method based on the multi-scale context enhancement network, the multi-scale problem existing in crowd counting can be effectively solved, andmore accurate counting and density estimation can be carried out on crowds in a complex scene by modeling space and channel context information of a feature map. The invention is high in robustness,and can provide accurate data for the safety and planning of a large crowd gathering place.

The invention provides a crowd analysis method based on an attention mechanism and a deformable convolution neural network. The method comprises the following steps that in a training stage, firstly,an attention map generator (AMG) is trained through a crowd image and a background image, and the trained attention map generator model is used as a component trained by an auxiliary density map generator (DME); in the testing phase, only the trained density map generator is used to generate the corresponding density map for the input crowd image. The invention combines the attention mechanism togenerate an attention diagram to detect the area of a crowd and to reflect the crowding degree of the crowd area to a certain extent. The attention map is used as a priori knowledge of the crowd to train the deformable convolution neural network, so that the network can overcome the uneven distribution of crowds in the crowd scene, environmental noise and other problems, and generate accurate crowd density map.

The invention discloses an adaptive abnormal crowd behavior analysis method, which is used for analyzing crowd behaviors in a video image. The method comprises the following steps of performing streak line calculation on the video image; calculating a streak line flow; detecting abnormal behaviors; performing foreground detection on the video image of abnormal crowd behaviors; performing adaptive crowd density estimation comprising pixel-counting-based density estimation and texture-analysis-based density estimation, and finally dividing estimated density into four density levels, i.e. a low density level, a medium density level, a high density level and an ultrahigh density level, thereby finishing grading the abnormal crowd behaviors. According to the method, the concepts of streak line and streak line flow are introduced to analyze whether a crowd in the video image is abnormal or not; the method has the advantage of detection accuracy; the densities of crowds involved in the abnormal crowd behaviors in different density scenarios are estimated in an adaptive way, and the detected abnormal crowd behaviors are graded by using density estimation results as main characteristics; the method is used for accurately grading the abnormal behaviors (such as mass brawl) in crowded public places, and giving alarms.

The invention discloses a scenic spot visiting path planning method and device based on space-time constraint. The method comprises the following steps: establishing a visiting behavior model for predicting probability distribution of crowds in a scenic spot according to collected crowd visiting behavior characteristics; obtaining a space-time constraint condition associated with scenic spot visiting, and quantizing the space-time constraint condition associated with scenic spot visiting; constructing an objective function taking the visiting behavior model and the space-time constraint condition as total constraint conditions and planning the visiting path of the scenic spot according to the objective function. According to the scenic spot visiting path planning method provided by the invention, two factors comprising the crowd visiting behavior characteristics and the space-time constraint condition in the scenic spot are taken into consideration and are used as the total constraint conditions, and then the objective function is constructed, and path planning is combined with actual demands of users, so that the path can be well planned, a user is guided to adopt an optimal path for visiting and the problems in the prior art are solved.

The invention discloses a method for counting persons in a video based on LSTM (Long Short-Term Memory)-weighted neural network, and the method comprises the steps: firstly estimating a perspective according to different scenarios, and then generating an adaptive density map of the crowd; carrying out the down-sampling of continuous multi-frame images, inputting the images to a neural network, andtraining the network based on the images and its corresponding real adaptive density map; estimating the density map of the input images through the trained network, and predicting the number of persons based on the density map. According to the scale difference of the crowd in the scenarios, the method measures the different scale features obtained through network learning through a scale loss function. The method employs a weighted loss function for balancing the contributions of different regions for solving a problem that the crowd is not uniform in distribution. Meanwhile, the method obtains the correlation information of the adjacent frames through LSTM, performs the postprocessing of the predicted number of persons through smooth filtering, and improves the person counting accuracy.

The invention discloses a video crowd counting system and method. A front-end encoder performs feature extraction on a frame of image in a given video sequence; the common supervision module suppresses interference of a fixed background in a scene by utilizing related characteristics between a previous frame and a to-be-detected frame in a video sequence; the spatial attention module selects an attention area by utilizing shallow structure characteristics, and guides the system to distinguish foreground crowds from background interference; the multi-scale self-supervision module extracts different scale features of the crowd in the image through a multi-branch structure by using deep semantic features, adaptively integrates context feature information through a self-attention mechanism, and autonomously selects the most suitable scale branch feature; and the rear-end decoder is used for fusing the features extracted by the three modules and outputting a predicted crowd density map so as to calculate the number of people contained in the to-be-detected video frame. According to the invention, crowd number estimation is carried out on each contained frame of image according to the video sequence, and dense crowd counting for the video sequence is realized.

The invention provides a method for predicting epidemic situation by a spatial heterogeneity-based infectious disease propagation model. If subareas comprising an area 1 and an area 2 exist in a city, a common rule that crowd flow causes the propagation of infectious diseases and the statistical data (obtained in the form of questionnaire and the like) about the dynamic flow of the crowd in a day can be explained according to a formula, and a method with better operability is established on the basis. The invention aims at reasonably describing a fact, namely the flow that people go out early and come home late for work, shopping and the like does not cause the migration of population macroscopically, but can cause transregional diffusion of the infectious diseases. As the daily periodic flow of the population increases the number of infected persons in a net input subarea, diseases are diffused in space to change the development speed of the epidemic situation. Particularly, at the initial stage of the epidemic situation, the transregional diffusion has an extremely high speed. The thought has heuristic significance for searching regional economic problems such as transregional consumption, labor input and export, and the like.

The invention relates to a formula of Lanzhou-made beef noodle soup base and a preparation method of the Lanzhou-made beef noodle soup base. The formula of the Lanzhou-made beef noodle soup base is as follows by weight ratio: 500-2500 parts of ox bones, 1000-5000 parts of beef brisket, 110-500 parts of beef tallow, 3000-10000 parts of water, 50-220 parts of salt and 14-68 parts of spices. The invention further provides the preparation method of the Lanzhou-made beef noodle soup base. The preparation method comprises the steps of precooking raw materials, carrying out high-temperature hot-pressing extraction, standing, removing residues, performing thermal flavoring reaction, blending, homogenizing, emulsifying, sterilizing, filtering, regulating soup and the like; the soup base prepared by the method has the characteristics of good fragrance, rich taste and high contents of protein and calcium, and is particularly suitable for pregnant women, the crowds in growing period and the older crowds.

The invention discloses a density crowd counting method based on the HOG characteristic and the color histogram characteristic. The method includes the following steps that S1, the HOG characteristic of an acquired image region is extracted, and the color histogram characteristic of a detection window in which the HOG characteristic is generated is extracted; S2, a first SVM classifier is acquired based on HOG characteristic training, and a second SVM classifier is acquired based on color histogram characteristic training, wherein the first SVM classifier is used for pre-estimating a detection region, and the second SVM classifier is used for secondarily classifying the pre-estimated detection region; whether the detection region is a head region or not is determined by weighting and combining results acquired by the two SVM classifiers; S3, according to the detected head region, the number of crowds in a video can be counted through a region matching method based on an optical flow method. The density crowd counting method based on the HOG characteristic and the color histogram characteristic is good in accuracy and anti-interference performance.

The invention discloses a location information-based evacuation guidance information pushing urgent evacuation method and system thereof. The urgent evacuation method comprises the following steps: arranging a plurality of information source detectors, performing unique coding on each information source detector, issuing urgent emergency information to crowds in monitoring regions according to the acquired detecting information comprising location information corresponding to codes; pushing evacuation guidance information to crowds in different monitoring regions; re-adjusting and sending if finding that an evacuation guidance channel has a jam trend; continuously paying close attention to long-term retention people monitored in the monitoring regions, and sending evacuation guidance information; and detecting a site to be evacuated and rescuing people needing to be rescued in the site to be evacuated. According to the urgent evacuation method, the information source equipment is detected through distributing an information source detector, monitoring of people in the site to be evacuated, pushing of location information-based real-time evacuation guidance information, feedback of the information and updating of the evacuation guidance information can be realized.

The invention discloses a method for dividing a crowd in a surveillance video into small groups. The method comprises the steps of (1) performing pedestrian detection and tracking on each frame of image in the surveillance video, thereby obtaining pedestrian motion characteristics, (2) obtaining each pedestrian atom behavior in the video images, (3) establishing a motion characteristic correlation energy function of each pair of pedestrians, (4) calculating pedestrian subject degree values according to the interactive correlation of the pedestrians and finding out crowd sets, thereby completing the division of the small groups. An effective method is provided for studying the interactive behaviors of small groups in the surveillance video scenes and solving the problem of dividing the crowd into the small groups.

The invention relates to a people number testing and crowd situation monitoring method and system based on position credibility. The method comprises the following steps: calculating the position credibility of signaling in a region; acquiring current valid signaling of all mobile communication equipment which is relevant to a certain cell at present, and using the sum of position credibility as the position credibility of the cell; calculating the total number of a crowd in a region; sharing the total number of the crowd in the region into each cell according to the proportion of the position credibility of each cell in a region and the sum of the position credibility of the region to obtain the number of people in each cell; and analyzing the crowd situation in a monitoring region according to the obtained number of people in each cell. The system comprises signaling acquisition equipment, a signaling analysis subsystem, a cell monitoring subsystem and a task monitoring subsystem. A regressive strategy of the signaling position credibility is set, so that people number testing and effective monitoring of the crowd situation can be realized.

The invention provides a system and method for automatic updating of buffer video advertisements. The system for automatic updating of buffer video advertisements comprises an advertisement management module, a peer-to-peer (P2P) downloading module, an advertisement updating module and an advertisement screening module. Compared with the prior art, a method for automatic updating of buffer video advertisements is adopted. When the buffer video advertisements are played by users, the buffer video advertisements are subdivided aiming at different crowds according to specific playing time intervals, application platforms or video program contents. Brands aiming at different crowds in everyday life are selected, and videos which are distributed and buffered are provided. Through clear and smooth playing, better playing effect and higher target audience arrival rate are achieved.

The invention relates to a virtual experiment platform system and method for crowd evacuation feature testing and drilling, in particular to a virtual experiment platform system used for crowd evacuation feature testing and evacuation drilling and based on a virtual reality technology and a microscopic analogue simulation technology, and relates to the technical field of computer virtual application. According to the virtual experiment platform system and method, the evacuation features of crowds under different scene conditions are tested through construction of a computer virtual environment. The virtual experiment platform method comprises the steps that firstly, a crowd evacuation model is built in a computer visual programming environment; secondly, the operation that movement of a controllable virtual leading actor in the crowd evacuation model is controlled through a computer input device is achieved; finally, various virtual evacuation scenes are achieved by changing the building structures and the visual fields of the crowds in the crowd evacuation model and leading an emergency product in. A testing experiment is conducted on a built virtual experiment platform in a participation mode, the evacuation features of the crowds on different scenes can be tested and analyzed, the virtual experiment platform can be applied to evacuation drilling and training when an emergency happens, and the virtual experiment platform system and method have the advantages that the crowd evacuation feature testing and drilling can be easy and can be repeated.

The invention relates to a collision prevention method for multi-layered virtual communities, which relates to the technical field of the animation of virtual communities. The method mainly provides collision prevention technology of the multi-layered communities which reduces collision frequency and improves the efficiency in the process of community simulation so as to reduce the complexity of collision prevention simulation of the communities. The method comprises the steps of: performing spatial division according to the positions of static obstacles; performing grouping, the stimulation of groups and collision prevention among individuals in the groups on the virtual communities in a walkable area; determining collision types and performing collision prevention through collision forecast among the groups; and evaluating and relocating the collision prevention, and performing local optimization according to an evaluation result to generate global collision prevention speed. The method can effectively realize the collision detection and collision avoidance of virtual crowds in the animation of the virtual communities.