168 results about "Crowd density" patented technology

The invention discloses an AI-based smart park multi-source data fusion method and system, and the method comprises the steps: generating a time-space aligned standardized data flow according to environment parameters, energy consumption waveforms, security signals and personnel trajectory data collected by a heterogeneous sensor network; generating a multi-modal fusion feature matrix based on the standardized data stream; according to the multi-modal fusion feature matrix, generating a three-dimensional twinborn body including the equipment state, the people flow density and the energy consumption hot spot in real time; inputting the three-dimensional twin into a multi-target constrained reinforcement learning algorithm, and fusing real-time data and prediction data to generate a Pareto optimal solution set; and based on the Pareto optimal solution set, generating a final instruction set for driving park equipment regulation and control, and triggering collaborative response of a security and protection system and an energy consumption system at the same time. According to the embodiment of the invention, intelligent upgrading of park management can be realized through cross-modal feature extraction, dynamic digital twin modeling and reinforcement learning optimization.

The invention discloses a video monitoring method and system, electronic equipment and a storage medium, and relates to the field of video monitoring. According to the method, a three-dimensional digital twinborn scene is constructed according to the space coordinates of each camera in a target area, and a node relation matrix is constructed according to the space relation between the cameras; according to the three-dimensional digital twinborn scene and the node relation matrix, a dynamic vision field splicing algorithm is adopted, the real-time position and the action path of the target object are determined, and the people flow density of the target area is displayed; determining a behavior mode of the target object through skeleton key point detection and interaction behavior analysis, and predicting an action track of the target object according to the behavior mode; and evaluating an initial risk level of the action track, adjusting the initial risk level in combination with the people flow density to obtain a final risk level, and generating a disposal suggestion according to the final risk level. By implementing the technical scheme provided by the invention, comprehensive and accurate video monitoring and risk management of the target area are realized.

The invention discloses an unmanned aerial vehicle and robot dog cooperative inspection system, and relates to the technical field of unmanned aerial vehicles, the unmanned aerial vehicle and robot dog cooperative inspection system comprises an unmanned aerial vehicle inspection module, a robot dog inspection module and a cooperative control module, the unmanned aerial vehicle inspection module is used for aerial aerial view of large-scale crowds, and real-time calculation of crowd density, velocity field and congestion hotspots; the robot dog inspection module is used for carrying out close inspection in a ground crack corridor, detecting gait stability and falling individuals in real time, forming a soft boundary to carry out differential diversion guidance and carrying out physical intervention on dangerous situations, and carrying out real-time inspection on the ground crack corridor. The cooperative control module is used for integrating the aerial view angle of the unmanned aerial vehicle and the ground detection information of the robot dog, dynamically updating a routing inspection path and triggering sound-light alarm and linkage guidance when a risk is identified, so that air-ground integrated risk prevention and control are realized, the unmanned aerial vehicle routing inspection module comprises a visual perception unit, and the unmanned aerial vehicle routing inspection system has the characteristic of near execution.

The invention relates to the technical field of Internet red scenic spot tourist crowd gathering risk monitoring, and discloses an Internet red scenic spot tourist crowd gathering risk intelligent monitoring and early warning system which comprises a central processing unit, a crowd density analysis module and the like. The crowd density analysis module generates basic density distribution based on region division and historical passenger flow data; the environment state acquisition module acquires environment and facility data in real time; the tourist behavior analysis module generates a behavior feature vector through the track and the stay duration; the central processing unit generates a risk early warning instruction through a spatial superposition algorithm; the risk early warning execution module adjusts monitoring parameters according to instructions and feeds back states, and triggers a dynamic adjustment algorithm when abnormity occurs. The system also improves the accuracy and the resource utilization rate through an optimization and adaptation module, achieves the intelligent monitoring and precise early warning of the crowd gathering risk, and guarantees the tourism safety.

The invention relates to the technical field of artificial intelligence, in particular to a video GIS intelligent analysis method based on deep learning, and the method comprises the steps: detecting a target in a video in real time through a predefined target detection model, and generating a space-time mark which comprises a bounding box and category information; thirdly, associating target tracks of different cameras by using a dynamic graph model and a dynamic graph neural network to form a space-time ID and a track chain; then, combining a visual inertial odometer and a geographic information system to calibrate a homography matrix, and mapping the trajectory chain to a geographic coordinate system to obtain space-time trajectory data; then, constructing a neural network model and a trajectory generation model, and respectively predicting crowd density distribution and pedestrian motion trajectories; and finally, carrying out real-time alarm according to the track and the multi-level geo-fencing rule. According to the invention, intelligent analysis of video data is realized, target tracking and alarm capabilities are improved, and the method is widely applicable to the fields of crowd management and safety monitoring.

The invention discloses an AI exhibition hall control method and system based on crowd thermal distribution monitoring, and the method comprises the steps: obtaining crowd density distribution data, behavior data and environment data through constructing a full-coverage sensing network, employing a thermal imaging camera, a WiFi probe and an infrared sensor, and generating a thermal distribution diagram; through converting discrete density point fusion and labeling into a data set of a continuous thermal field, crowd distribution characteristics are visually displayed, spatial-temporal correlation of crowd flow is effectively modeled by combining a convolutional neural network and a spatial-temporal diagram neural network, a prediction-adjustment-verification closed loop is realized based on a prediction result 6-8 minutes ahead of time, and the prediction efficiency is improved. The control strategy is dynamically adjusted according to the predicted crowd distribution trend and the business target, the guide route or the interaction form can be dynamically adjusted according to the crowd density, the exhibit layout can be adjusted in advance, the number of tourists going back and forth is reduced, the overall flow efficiency is improved, and therefore the display effect of the AI exhibition hall is improved.

The invention is applicable to the technical field of venue navigation, and provides an intelligent navigation method for venue digital service, which comprises the following steps: acquiring positioning information, behavior track and interaction record of a user; performing combined analysis on the user data and preset venue interest point attribute data to obtain a user feature vector containing a stay preference coefficient, movement speed analysis and a subject interest weight; extracting a topological relation between the current position and the target interest point according to the user feature vector, and calculating a constraint parameter according to the topological relation; based on the constraint parameters, constructing an initial path planning model taking the minimum expected passing time as a target function; determining a people flow density gradient map of each region of the stadium in a preset time period through the obtained historical people flow data and the user real-time positioning data; the initial path planning model is optimized by using the people flow density gradient map, and the optimal path is generated by dynamically adjusting navigation path nodes, so that the intelligence level and the user satisfaction of venue navigation are effectively improved.

The invention discloses a video crowd counting method based on a cascaded cross-domain feature interaction network. The method comprises the following steps: carrying out data enhancement processing of random cutting and horizontal flipping on a current frame and front and back frames of the current frame; and constructing a cross-domain feature interaction network composed of a spatial domain branch and a frequency domain branch. The frequency domain branch extracts frequency domain feature output of different stages through a high and low frequency signal aggregation module and a feature encoder based on adjacent frames; the spatial domain branch is based on a single-frame image, and static spatial semantic features are extracted through a feature encoder. Cascade fusion is carried out on the double-branch features on multiple scales, two-way channel cross attention is utilized to reconstruct time sequence correlation frequency domain features of a current frame, and fusion and reconstruction of the two domain features are achieved through a cross-domain feature mutual modulation module. And after the reconstructed double-branch features are processed by the fusion network, outputting a crowd density map of the current frame by a density regression head. And after training is completed, storing the optimal model for video crowd counting. According to the invention, through cross-domain feature cascade and bidirectional time sequence modeling, the accuracy and robustness of crowd counting in a video scene are effectively improved.

The invention discloses a multi-scale crowd counting method and system based on VSSM and mask reconstruction and a medium, and belongs to the field of computer vision and deep learning, and the method comprises the steps: carrying out the multi-scale transformation and segmentation operation of an input crowd image, so as to obtain an image block under each scale; analyzing each image block to obtain an information entropy graph, performing masking operation on each image block according to the information entropy graph, inputting the masked image block into a VSSM to perform feature extraction so as to obtain coding features, performing decoding reconstruction on the coding features through a Transform decoder, and finally obtaining a reconstructed feature image; fusing the reconstructed feature images of different scales by using a multi-scale fusion module to generate fused features; and generating a crowd density map based on the fusion features, and analyzing the crowd density map to obtain a crowd counting result. Counting errors caused by single-scale analysis are avoided, and the crowd counting precision in a full-scale range is remarkably improved.

The invention discloses a robot hierarchical path planning method and device in a complex environment, a medium and a product, and the method comprises the steps: responding to a path planning request of a robot in an airport terminal, dividing the airport terminal into a plurality of dynamic Voronoi regions according to an underlying environment grid map and people flow density information, a minimum path cost algorithm with people flow density weighting is adopted to construct a global path anchor point sequence, the global path anchor point sequence is further split into a plurality of local path planning requests, a double-heuristic cost function is constructed, an improved algorithm is adopted to generate local sub-paths, and according to surrounding environment information collected by a robot in real time, the local sub-paths are calculated. And optimizing each local sub-path by adopting a reinforcement learning algorithm, generating motion control instructions for the robot at different control time points, and realizing dynamic obstacle avoidance of the robot. The path planning efficiency and the motion safety of the mobile robot in a super-large-scale dynamic environment are remarkably improved, and the technical problems that a traditional method is high in calculation complexity and poor in real-time performance are effectively solved.

The invention discloses a hospital multi-scene transportation robot hybrid scheduling method based on dynamic priority, and belongs to the technical field of robot control and scheduling. The method comprises the following steps: acquiring hospital dynamic environment data; receiving and analyzing the multi-mode instruction to form task parameters; preliminarily grading according to task parameters and preset rules, and dynamically adjusting task priorities in combination with a dynamic map and the current state of the robot; based on the adjusted task priority and robot type, distributing robots and generating an initial path considering distance and people flow density; the robot is driven to track along the path trajectory, and obstacle behaviors are predicted in real time and dynamically avoided; decomposing a transportation task into task chains, and when the electric quantity is lower than a threshold value, deciding whether to insert a charging task in combination with the priority; and after the task is completed, prompting and transmitting feedback data. According to the invention, dynamic priority, behavior prediction and hybrid scheduling are adopted, intelligent distribution and path optimization of transportation tasks are realized, and the efficiency and safety of internal logistics of hospitals are improved.

The invention discloses an intelligent question and answer implementation method and system based on a large model and a semantic atlas, and relates to the technical field of supply chain intellectualization, and the method comprises the steps: obtaining a structured distribution data table and an unstructured text data stream, carrying out the data cleaning and normalization processing, and obtaining a structured distribution data table and an unstructured text data stream; constructing a unified knowledge base to perform semantic understanding and knowledge extraction on the unified knowledge base, extracting key entities and semantic relationships through named entity recognition and relationship extraction tasks, and fusing structured distribution data features to construct a preliminary semantic map; and integrating the preliminary semantic map with the spatial dimension features acquired by the data interface and the real-time task execution log of the shop patrol assistant, endowing nodes with space-time attributes through graph neural network training, and outputting a dynamic semantic map integrated with space-time dynamic mode features. According to the method, geofence coordinates and crowd density characteristics are injected by utilizing an Atde API, a store patrol assistant real-time replenishment state log is superposed, and the causal association strength modeling precision is improved through ST-GNN training.

The invention relates to the technical field of monitoring layout, in particular to a modeling camera layout method and system. The method comprises the following steps: carrying out geometric topology analysis on a venue to obtain a venue functional region model; performing fluid mechanics simulation on the venue functional area model to obtain people flow density distribution characteristic data; performing risk grade division on the venue according to the people flow density distribution characteristic data to obtain a venue key area evaluation matrix; performing dynamic density field modeling on the venue based on the crowd density distribution characteristic data to obtain a crowd density field mathematical model; performing monitoring demand analysis on the venue according to the crowd density field mathematical model and the venue key area evaluation matrix to obtain a monitoring coverage scheme; and performing density equalization configuration on the cameras according to the monitoring coverage range scheme to obtain a camera distribution density scheme. According to the invention, the camera layout is optimized, the resource waste is avoided, and the monitoring continuity and no dead angle are ensured.

The invention discloses a subway multi-line transfer station flood multi-target dynamic evacuation path planning method. The method comprises the following steps: establishing a three-dimensional space model by acquiring subway station structure information, and abstracting the three-dimensional space model into network representation; real-time water regimen information is obtained through a hydrological sensor and video monitoring, preprocessing and fusion are carried out, and water regimen sensing data under unified space-time reference are generated; in-station crowd information is obtained in real time through video target detection, the crowd density and the traffic capacity are calculated, and crowd situation perception data are formed; generating a plurality of group evacuation path candidate schemes for different types of passengers by adopting a real-time path search algorithm in combination with the water regimen, the people flow situation and the trafficability constraint; evacuation paths are classified according to passenger types, evacuation guidance is issued through a multi-terminal channel, and differentiated dynamic guidance of departure passengers, transfer passengers and mobility-disabled passengers is achieved. According to the method, flood disasters and people flow changes can be responded in real time, and the evacuation efficiency and safety of the subway transfer station are improved.

The embodiment of the invention discloses a camera arrangement evaluation method and device based on operation data and a medium. The method comprises the steps that a three-dimensional space model of a to-be-evaluated area is acquired and visually displayed, and a virtual monitoring scene is generated; in response to an adding operation of camera point locations, displaying a visible range of each camera in the virtual monitoring scene in an overlapping manner; in response to an import operation of historical operation data, superposing and displaying a thermodynamic diagram of historical people flow density and / or work order density in the virtual monitoring scene; according to a superposition display result, determining a coverage condition of the camera on the people flow density and / or the work order density; and evaluating the point location layout of the camera according to the coverage condition. According to the embodiment of the invention, intelligent and precise camera arrangement evaluation is realized.

The invention relates to a commercial district consumer population dynamic prediction method and system based on unmanned aerial vehicle identification, and the method comprises the steps: firstly obtaining a visible light image sequence which is continuously collected by a low-altitude unmanned aerial vehicle in a commercial district region and comprises a continuous timestamp mark, and then carrying out the end-to-end feature extraction of the image sequence through a pre-trained multi-task feature extraction network; generating a three-dimensional feature tensor containing crowd density distribution, individual movement tracks and crowd aggregation morphological features, then calling a space-time dynamic prediction model to carry out time sequence association and space mapping processing on the three-dimensional feature tensor, and generating consumer population distribution prediction results of the commercial district in a plurality of continuous time periods in the future. And performing historical trend matching analysis on the prediction result by using a confidence verification module, outputting verification data including a prediction confidence score and a key change time period, and finally generating a dynamic prediction report including a corresponding relationship between a time dimension and a space region based on the verification data. Therefore, the dynamic state of the consumer population in the business district can be comprehensively and accurately predicted in real time.

The invention discloses a crowd density detection method fusing optical flow and texture features, and relates to the technical field of computer vision, and the method comprises the following steps: collecting a real-time video stream of a camera, and carrying out graying, Gaussian filtering and perspective correction preprocessing; performing motion compensation by using image registration and offset transformation; modeling based on a Gaussian mixture model and extracting a foreground to generate a binary mask; analyzing a foreground coverage rate, an optical flow and texture features; pre-defining a multi-ROI and a density early warning standard; inputting the fusion features into a regression model and outputting initial density; dynamically calibrating and correcting the deviation; and generating a thermodynamic diagram superposition video to realize visualization. According to the invention, the optical flow and texture features are fused to improve density estimation precision, illumination resistance and dynamic background interference resistance; the dynamic calibration maintains long-term accuracy, and the dynamic ROI adapts to scene change; the thermodynamic diagram can quickly identify risks, is adaptive to multiple scenes, and meets real-time monitoring requirements.

The application discloses a fine-grained crowd analysis method based on passive WiFi sensing, which comprises the following steps: obtaining a coarse-grained crowd density map in a target monitoring area obtained by WiFi sensing at a continuous time; inputting the coarse-grained crowd density map into a trained deep convolutional autoencoder model to output a fine-grained global crowd density map at the continuous time; identifying the center pixel point coordinates of each local high-density crowd in the global crowd density map by using a density clustering method; cropping a local block from the corresponding position in the global crowd density map for each center pixel point coordinate, and combining the local blocks at the same position at several previous times to form a crowd density block sequence; inputting the crowd density block sequence into a trained bidirectional convolutional long short-term neural network model to output the velocity vector of each local high-density crowd. The method can improve the accuracy of crowd distribution estimation in a scene, and simultaneously realize the estimation of the velocity of local high-density crowds.

The invention provides a crowd intensity identification method based on a multi-modal data fusion and hybrid model, and the method comprises the steps: generating an optimal inspection path through the flight path planning of an unmanned plane, and capturing a target image; s2, realizing time synchronization of the camera and the Internet of Things equipment through an NTP protocol; s3, the image is divided into N * N grids, a thermodynamic diagram is constructed based on historical density data, a high-frequency crowded area is subdivided, complete CNN reasoning is started for high-density sub-blocks, and lightweight MobileNet acceleration is adopted for low-density sub-blocks; s4, estimating crowd density through a hybrid detection regression model; and S5, calculating a density baseline and a standard deviation based on a historical data sliding window, and setting a trigger threshold. Based on the technical scheme of the invention, the detection precision and robustness in a dense scene are effectively improved.

The invention belongs to the technical field of intelligent traffic and passenger flow monitoring, and discloses a passenger flow statistics fusion system and method based on multi-modal big data. The system comprises an infrared induction data acquisition module, a video identification data acquisition module, a WiFi probe data acquisition module, an entrance and exit environmental factor sensing module, a confidence coefficient calculation module and a data fusion module. The system calculates the confidence coefficient of various data sources by collecting various types of passenger flow data and the shielding intensity, crowd density and bandwidth state in the current environment, and performs weighted fusion according to the confidence coefficient to obtain a passenger flow statistical result with higher credibility. The system improves the accuracy and stability of passenger flow statistics in a complex environment, and is suitable for dynamic monitoring and management of a high-density passenger flow scene.

The invention discloses a large-scale subway group escape system based on panic emotion infection, and relates to the technical field of escape systems.The large-scale subway group escape system based on panic emotion infection comprises the steps that 1, a crowd evacuation scene is constructed according to subway related information; step 2, initializing a crowd (Crowd); each individual in the crowd Crowd comprises personality characteristics phi, an initial emotion value e0 and an initial movement speed v0; 3, performing an emotion infection simulation algorithm; step 4: first; the range between the pedestrian carrying the luggage and the luggage is divided to be less than or equal to 0.5 m; carrying out related weighting and improvement on the evacuation speed and behavior of pedestrians according to the luggage volume and the luggage weight when the luggage volume and the luggage weight exceed the individual bearing capacity; a discarding behavior will occur; 5, calculating the crowd density rho of the walking area at the t + 1 moment according to the crowd movement information; the crowd evacuation behavior is updated; and step 6, realizing crowd evacuation visualization in a graphical mode.

The invention relates to the technical field of fire monitoring, in particular to an intelligent fire monitoring and early warning method. A Gaussian distribution model is introduced to simulate the diffusion effect of a heat source, the adaptability of smoke flowing to airflow in a building is enhanced, limitation of a traditional smoke diffusion model is corrected and optimized according to local turbulence driven by differential pressure, especially the non-uniform airflow effect in areas such as narrow galleries and courtyards, and accurate monitoring and early warning of fire disasters are achieved. The expected speed and comfortable distance of the crowd are dynamically adjusted by combining light flow sensing with environment sensing (such as smoke concentration and temperature), and the problems of people flow and evacuation path optimization in a high-density scene can be effectively solved. Especially in a narrow space, interaction between crowds and obstacles can be fed back in real time, and secondary accidents caused by crowd density or high temperature and smoke influence are prevented.

The present invention relates to a method for counting the number of people in video images based on a multi-scale attention mechanism, which solves the defect that it is difficult to ensure the accuracy of people counting under the interference of complex scenes compared with the prior art. The present invention includes the following steps: acquisition and preprocessing of crowd images; generation of real crowd density maps; construction of a multi-scale attention mechanism module; construction of a crowd counting model; training of the crowd counting model; acquisition of video images to be detected; counting of the number of people in the video images. The present invention designs a multi-scale attention module, which embeds an attention mechanism in different scale branches to reduce the influence of irrelevant background noise of the model at different scales and increase the scale diversity of the model.

The invention provides a commercial complex crowd management system based on a real-time LoT sensor, and relates to the technical field of intelligent management. The management main system comprises a data acquisition module, a data processing module, a dynamic environment optimization module, a people flow guidance and excitation module, a resource scheduling module, a safety monitoring and response module, an external cooperation module, a space value optimization module, a user feedback and experience module and a control flow management module; the real-time LoT sensor is deployed to comprehensively monitor the people flow density, the environmental parameters and the equipment state in the commercial complex, the problems of crowded areas and uneven resource allocation in the peak period can be found in time, and user experience decline and potential safety hazards caused by delayed response are effectively avoided. The system achieves minute-level density monitoring in peak hours, and the real-time performance and response efficiency of crowd management are remarkably improved.

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 relates to the technical field of security and protection monitoring, in particular to a large-scale exhibition crowd density monitoring and abnormal behavior recognition method, which comprises the following steps: acquiring real-time video data acquired by a plurality of monitoring devices in an exhibition venue, and performing crowd density estimation on the real-time video data to generate a real-time crowd density distribution map; acquiring historical crowd flow data, acquiring a crowd dynamic evolution trend in a future preset time period according to the real-time crowd density distribution diagram and the historical crowd flow data, and identifying and acquiring a potential bottleneck region based on the crowd dynamic evolution trend; according to the potential bottleneck area and the real-time crowd density distribution diagram, a space attention thermodynamic diagram is generated, real-time mastering of the crowd state in the exhibition venue, risk pre-judgment and accurate abnormity disposal can be achieved, management and control measures in a large exhibition high-density crowd scene are more timely, and the response efficiency is higher.

The application discloses a kind of multi-modal crowd density prediction methods based on time convolution network, comprising the following steps: video information module obtains image from monitoring camera, the image obtained is carried out crowd counting by crowd counting model, obtains the crowd density of each camera every time, and is organized into time series data;The time series data of crowd density is respectively extracted into the current time hidden vector for each sub-region by time convolution network;Itinerary planning module extracts corresponding itinerary information from itinerary planning table for multi-modal prediction;The features of fusion module and video information module are fused, and the crowd density prediction value of each sub-region in the future is obtained.This application can improve the prediction accuracy of the model by fusing multi-modal information, and can give a smooth prediction result when facing low SNR data, and can also respond in time when the crowd density changes suddenly.

The application provides a building space energy consumption control method and system based on computer vision, comprising the following steps: S1: partitioning a public area of a building space and constructing a correspondence relationship between the partition and a camera and an energy consumption device; S2: mapping the partition to a digital plane grid and constructing a mapping relationship between the grid and a camera field of view; S3: collecting and processing video stream data of each camera in real time, inputting the video stream data into a lightweight crowd density estimation model, and calculating a crowd density value in the field of view of each camera; S4: based on the real-time value of the crowd density value in the field of view of each camera and the mapping relationship between the grid and the camera field of view, a weighted fusion algorithm is used to calculate a crowd density grade of each partition; S5: according to the real-time crowd density grade of the partition, combining preset upper and lower threshold values and a control strategy, corresponding device control instructions are dynamically generated; and S6: the control instructions are sent to terminal devices such as lighting and air conditioning for execution, so that dynamic and fine energy consumption control of the partition is achieved.

The application provides a crowd density estimation method and system based on feature-aware weighted contrast learning, relates to the technical field of crowd density estimation methods, and comprises the following steps: inputting a basic feature map into a constructed multi-level parallel hole convolution layer respectively, normalizing an importance score to obtain a fusion weight coefficient of each branch, and obtaining a final fusion feature map; constructing a regression network to generate a low-resolution density map, inputting the density map into a lightweight convolution network to generate a scaling mask, multiplying the density map after bilinear upsampling with the scaling mask element by element, and generating a predicted density map. The multi-level parallel hole convolution layer enables the network to simultaneously capture local details and wide-range context information, the channel attention automatically strengthens the feature channels related to the crowd, the spatial attention accurately locates the high-density area, the density map is calibrated to the actual number of people for each pixel through a loss function, and the number of people in the whole image can be directly obtained by summation.

The invention discloses a distribution method and system based on crowd density monitoring in disaster emergency hedging transfer. The method comprises the following steps: acquiring personnel position and moving speed data in real time through a sensor network deployed at a hedging channel and a temporary gathering point; identifying and quantifying a personnel gathering area, and positioning an excessive gathering area; the boundary, the people flow direction and the number of people of the excessive gathering area are extracted, and a plurality of alternative shunting paths leading to the standby gathering point are generated in combination with the topological structure of the peripheral channel, the available width and the obstacle information; simulating a shunting process to predict the future load of each path and the gathering point, and selecting a final shunting path from the alternative paths according to a load balancing principle to form a shunting scheme; and finally, integrating into a global transfer path diagram, generating an updated evacuation path, and executing guidance. According to the invention, real-time sensing, dynamic path planning and global load optimization of the crowd gathering risk are realized, so that the evacuation efficiency and the overall safety are improved.