17 results about "Crowding in" patented technology

This invention focuses on the 3D reconstruction of dynamic crowds in large-scene videos and introduces the DyCrowd framework, which reconstructs 3D position, pose, and shape of hundreds of people from a large-scene video. Our approach addresses frequent occlusions and modeling challenges in high-density crowds through a top-down strategy. This includes pre-reconstruction, matching individual movement sequences, and multi-stage iterative optimization. During the optimization process, we introduce a group optimization method with an asynchronous motion consistency loss. This method clusters individuals with similar trajectories, using high-quality and unoccluded movements within the group to guide the recovery of occluded individuals, thereby mitigating long-term occlusion issues. Furthermore, to address the lack of ground-truth human reconstruction labels in current large-scene datasets, we introduce a virtual benchmark dataset called VirtualCrowd for dynamic crowd reconstruction in large-scene videos.

The invention relates to the technical field of computer vision, and discloses a competition people stream monitoring and early warning method based on multi-dimensional feature fusion video analysis, which comprises the following steps: acquiring an original video stream, receiving the acquired multi-path high-definition original video stream, and carrying out parallel processing on the original video stream through a first path and a second path respectively; based on the obtained crowd kinetic energy field, crowd entropy field and high-precision density map, constructing a quantitative risk model fusing multi-dimensional features to realize risk decision; and explainable crowd fluid state semantics and risk levels are output to a user through a four-level early warning decision-making mechanism based on a comprehensive risk index given by the quantitative risk model fusing the multi-dimensional features. According to the method, core vision algorithms such as dense optical flow calculation, crowd density estimation of a deep convolutional neural network and crowd behavior modeling based on statistical fluid mechanics are comprehensively utilized, and real-time and quantitative perception and dynamic risk early warning of the microscopic state of dense crowds in scenes such as large stadiums and competition sites are achieved.

The invention belongs to the technical field of urban rail transit safety management, and particularly discloses an urban rail transit station crowd stability identification and early warning method, which comprises the following steps: acquiring personnel action data under various crowd flow movement scenes, quantifying conflict events among personnel based on a Worronoi diagram and a speed obstacle model, and obtaining quantitative characteristics; abstracting personnel as nodes, abstracting conflict events as directed edges, and constructing a time-varying conflict network; setting a percolation threshold value, and continuously analyzing a communication state and a conflict index set of the conflict network in a threshold value increasing process; generating a stability criterion according to the change trend of the connected subgraph along with the threshold value, judging the stability of the target scene in combination with the conflict index set, and outputting an early warning signal; the method has the following advantages that individual microscopic behaviors and system macroscopic steady-state characteristics can be described at the same time, multi-scene stability criteria are unified, steady-state real-time recognition and instability early warning of people in the rail transit station are achieved, and the in-station passenger flow safety management level can be improved.

The invention discloses an unmanned aerial vehicle aerial image dense crowd counting and grade classification method based on a multilayer CNN, and the method comprises the following steps: carrying out the standardization preprocessing of an input unmanned aerial vehicle aerial image I; multi-scale features of the image are extracted through multi-layer convolution and pooling operation, and a high-level semantic feature map F is obtained; a context aggregation module is utilized, adaptive average pooling of different scales is adopted to capture global to local context information, and a feature map F'with attention weight is generated through convolution fusion; a rear-end decoder recovers spatial details by using cavity convolution, a single-channel density map D is output through convolution operation, and a crowd counting result is obtained through integration; and finally, based on the density map D, dividing four density intervals through a threshold value: analyzing and marking a region above medium density by using 8 connected domains, and outputting a visualization result on the image I. According to the invention, grading and counting of crowd density in an unmanned aerial vehicle aerial photographing scene can be accurately realized, and applications such as public safety monitoring and large-scale activity management can be effectively supported.

The application discloses a kind of real-time data-driven crowd behavior modeling simulation methods for digital twinning, comprising: constructing three-dimensional twin static scene structure and two-dimensional simulation scene structure;Real-time acquisition of the dynamic changes of the crowd in dynamic scene structure in multiple time windows Video data;Obtain the macroscopic crowd movement flow and crowd density distribution of each time window;Macroscopic crowd movement flow and crowd density distribution are distributed to each unit area, obtain the movement flow set and cumulative density error of each unit area;Obtain the migration adjustment demand and migration adjustment amount of the agent in each unit area;The preferred speed of the agent in each unit area is obtained, the obstacle avoidance speed is obtained, and the three-dimensional dynamic crowd corresponding to the dynamic scene structure time is generated in three-dimensional twin static scene structure.The application can fully meet the application demand of digital twinning scene, with high fidelity, high restoration characteristics.

The invention discloses a multivariate paradigm decoupling crowd counting method and system based on density level segmentation, and belongs to the technical field of crowd counting. The method comprises the steps that a target image is acquired, the target image is input into a segmentation mask generator generated through training of a Gaussian distribution mask generator, a density level mask is obtained, and the segmentation mask generator comprises an image encoder and a density level segmentation module; inputting the target image into a multivariate paradigm counting module to obtain a frame position information graph, a point position information graph and a density position information graph; inputting the density level mask, the frame position information graph, the point position information graph and the density position information graph into a result fusion module to obtain a composite result graph; and performing summation based on the composite result image to obtain the total number of crowds in the target image. The method improves the accuracy of crowd counting.

The present application is directed to the problem of dense crowd face detection in complex environments, and designs the field of face detection in computer vision. The method provides a model named deep and compact face detection (DCFD), which is referred to as DCFD for short. The method comprises: building an input layer of the DCFD model; building a main feature extraction network of the DCFD model, using an EfficientNetV2 network to replace the original main network module, and using a large core attention mechanism to replace a traditional convolution block to give the network long end support and realize the ability of global receptive field; building the connection between the main network of the DCFD model and the feature module, introducing an ECA attention mechanism to strengthen the feature extraction capability of the model, so that the model pays more attention to the detected target; building a feature fusion module of the DCFD model: using an improved NAS-FPN image pyramid to replace the original FPN structure. The pedestrian dataset is sent into the improved RetinaFcae model, and the Adam optimizer is used for training to obtain the DCFD model and apply it to dense crowd face detection in complex environments.

The application is suitable for the technical field of crowd simulation, and provides a crowd evacuation simulation method, device and terminal equipment, which comprises the following steps: constructing a scene model; constructing a pedestrian model and an attacker model based on the scene model, wherein the pedestrian model comprises a pedestrian motion rule, and the attacker model comprises an attacker motion rule; constructing an interaction model based on the pedestrian model and the attacker model, wherein the interaction model comprises multiple interaction modes, and the multiple interaction modes can be converted to each other; and performing crowd evacuation simulation based on the scene model, the pedestrian model, the attacker model and the interaction model. The application can more realistically simulate the crowd evacuation movement in a terrorist attack, and provides data support and scientific basis for the construction and management of public places, so as to reduce the casualties of the crowd in a terrorist attack.

The application provides a kind of urban crowd trajectory generation method and device based on generative adversarial network, the method comprises: obtaining the time label of the generated trajectory of urban crowd, and determining the trajectory starting point of the generated trajectory;The time label and trajectory starting point are input into the generative adversarial network model that has been trained to obtain the moving trajectory of urban crowd that meets the time label;The trained generative adversarial network model includes the trained conditional generator and the trained discriminator, the conditional generator is obtained by training based on the feedback of the discriminator, and the discriminator is obtained by training based on real trajectory data set and the generated trajectory data set output by the conditional generator.The application can generate the moving trajectory of urban crowd in a specific time and in a moving state by combining time label with generative adversarial network model.

The invention provides an image-based crowd abnormal behavior recognition method, and belongs to the technical field of crowd abnormal behavior recognition. The method comprises the following steps: acquiring a to-be-identified crowd video stream; detecting the crowd in the video frame through a target detection network to obtain a target frame and a person category label of each person; extracting human body key point skeleton coordinates in each target frame through a posture estimation model; generating a group distribution thermodynamic diagram for the whole view; performing multi-modal coding on the target frame, the personnel category labels, the skeleton key point coordinates and the thermodynamic diagram to obtain crowd feature codes; and inputting the crowd feature codes into a large language model for sequence modeling and context reasoning, and outputting a crowd behavior category. According to the method, the target frame, the personnel category, the skeleton information and the thermodynamic diagram are jointly coded through the multi-modal fusion technology, and the extraction precision and robustness of the crowd behavior characteristics in a complex scene are remarkably improved.

The application provides a kind of smart city service method and system based on cloud computing and big data, it is related to the technical field of smart city, method includes: according to first traffic flow and first crowd, respectively predict the second traffic flow and second crowd in the second preset time length of target area;According to historical traffic flow data and historical crowd data, respectively determine the third traffic flow and third crowd in the second preset time length of target area;Second traffic flow and third traffic flow are combined to determine target traffic flow, and calculate first congestion index;Second crowd, third crowd and appointment outpatient volume data are combined to determine target crowd, and calculate second congestion index;First congestion index and second congestion index are combined to determine target congestion index, when target congestion index exceeds preset index, generate adjustment scheme.The application has the technical effect that: accurately predict the traffic condition of hospital surrounding area, timely formulate effective preventive adjustment scheme.

The application discloses a crowd subscription method and system based on kafka, a terminal and a storage medium. The method comprises the following steps: acquiring crowd data of different crowds, controlling a crowd production program to send the crowd data to kafka, receiving state data returned by the kafka, and storing the state data into a relational database management system; when a request sent by a subscription page is received, the state data is displayed on the subscription page, and a crowd is subscribed in the subscription page; based on the crowd, target state data corresponding to the crowd in the relational database management system is acquired, and the target state data is sent to the kafka for consumption, so as to complete the subscription of the crowd. When each team uses the user portrait system, the required crowd can be acquired for data extraction in a subscription mode, and the subscription can be performed before or after the crowd is executed.

The application discloses a real-time crowd counting method combined with scale perception, mainly comprising the following steps: firstly, local features are extracted from an image, and multi-scale information is learned by using a scale module (SFEM) according to the extracted results to adapt to the scale change of the crowd in the scene. Then, a scale fusion module (SFFM) is used to fuse the feature maps with different scale information together to enhance the scale expression ability of the network, and the final output feature map is sent to a regression module (DMR) to predict the output crowd density map. In addition, the application also proposes a multi-level intersection-over-union joint loss function (MIoU) to further reduce the background misrecognition rate and prediction error of the network model. Experimental results show that the method can effectively reduce the parameter quantity and reasoning time of the network model, meet the real-time demand of edge devices, and achieve a better balance in accuracy and complexity.

An embodiment of the present application provides a method and a device for calculating a building-related load. The method for calculating a building-related load comprises the steps of: acquiring simulation activity features of a plurality of virtual persons on the basis of simulation activity in a virtual building environment simulating an environment in a building, performed by the plurality of virtual persons simulating a crowd in the building, the simulation activity features including heat generation amounts of the plurality of virtual persons; and calculating a building-related load on the basis of at least the heat generation amounts of the plurality of virtual persons. Due to this configuration, it is possible, by a simple and efficient method, to simulate crowd activity features that are more realistic and accurate than preset fixed values, i.e., crowd simulation activity features. Given the above, it is possible, by a simple and efficient method, to simulate crowd activity features that are more realistic and accurate than preset fixed values, i.e., crowd simulation activity features, thereby improving the calculation accuracy of the building-related load on the basis of the simulation activity features.

The invention discloses an intelligent agent-based in-city crowd movement simulation method and device, and relates to the technical field of crowd movement simulation. The intelligent agent-based in-city crowd movement simulation method comprises the following steps: obtaining population data of a to-be-simulated region and city underlying surface land use index data; according to the population data of the to-be-simulated region and the urban underlying surface land use index data, obtaining urban gridded residential population and opportunity distribution of the to-be-simulated region; establishing a departure-destination matrix of crowds in the city according to the urban gridded resident population and opportunity distribution of the to-be-simulated region; obtaining basic travel information; and performing crowd movement track simulation according to the travel basic information and the departure-destination matrix. According to the method, the dynamic process simulation of crowd activities is realized, the data dependence is relatively low, and the portability is relatively high.

A process for identifying relationships between individuals in a crowd. In operating, an electronic computing device detects questions presented to a crowd with an instruction directing the crowd to answer each question in the form of non-verbal responses rather than in the form of verbal responses. The computing device enables at least one camera to record videos capturing activities of the crowd in response to each presented question. The activities of the crowd captured in the videos are analyzed using a video analytics engine to identify a pattern of non-verbal responses that would indicate a leader-follower relationship between individuals identified from the crowd. The electronic computing device then generates a visual and / or audio output identifying the leader-follower relationship between the individuals identified from the crowd.

The application discloses a crowd density estimation method based on sparse support base estimation, and proposes a target perception attention mechanism enhanced by sparse support base estimation of head features of a monitoring area based on crowd congestion, density, and mutual occlusion; proposes a target scale perception attention mechanism of sparse support base estimation based on the change of head scale caused by the distance of people in a scene, generates a head scale perception rate, controls an adaptive sampling mechanism of convolution, further improves the distinguishability of heads, performs crowd density prediction on the enhanced multi-scale features, obtains a crowd density map, and statistically obtains the number of crowds in the monitoring area; solves the problem that heads are difficult to distinguish due to crowd congestion, different density, and mutual occlusion in a monitoring area where a large number of people gather and appear, and the problem that the scale of heads in an image changes due to the distance of people in a scene, and a crowd density map with good quality can be obtained, and the accuracy of crowd density estimation is improved.