468 results about "Crowd density" patented technology

The invention relates to a large scale crowd video analysis system and a method thereof. The system comprises a crowd density calculation module, a crowd prospect segmentation module, a crowd tracking module, a crowd state analysis module and an event determination module. The crowd density calculation module, the crowd prospect segmentation module and the crowd tracking module process video image data and then the crowd number, a crowd area, a crowd motion direction and a speed are acquired respectively. The crowd state analysis module carries out processing analysis based on the acquired crowd number, the crowd area, the crowd motion direction and the speed and sends an analysis result to the event determination module. The event determination module is used for determining whether a crowd event is abnormal. The crowd event means that the crowd reaching a certain scale carries out one group characteristic behavior in a monitoring area. By using the system and the method, monitoring personnel can complete intelligent trend prediction, characteristic event positioning and other tasks; and effective help is provided for prevention of emergency, suspicious clue tracking and the like.

The invention discloses a crowd density estimation method based on a cascaded multilevel convolution neural network. The method includes the steps that (1) the multilevel convolution neural network is adopted to extract characteristics from lower layers to high layers, and lower layer characteristics and high layer characteristics are combined to form multistage characteristics, so that separability of crowd density characteristics is enhanced; (2) according to similarity of a characteristic pattern in a downsampling layer of the multilevel convolution neural network, connections of redundant neurons in the convolution neural network are eliminated, and the characteristic extraction speed is increased; (3) two multilevel convolution neural networks of different structures are trained according to the difficulty level of the separability of crowd density samples, the two multilevel convolution neural networks are in cascade connection according to sequences from simpleness to complexity to form a crowd density estimation model of the cascaded multilevel convolution neural network, and crowd density level estimation is rapidly carried out on to-be-detected images obtained from a video terminal in real time. In the aspect of detection accuracy, a better real-time effect is achieved compared with previous schemes.

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 discloses a deep convolutional neural network-based abnormal crowd behavior visual detection and analysis early warning system. The system comprises a camera mounted at a monitoring target facility, a security prevention cloud server and an abnormal crowd behavior visual detection and analysis early warning system. In the system, various human body objects in the target facility areextracted through a deep convolutional neural network technology; then motion states of human bodies are calculated, identified and judged by using an optical flow method; different states of the human body objects are subjected to clustering and crowd modeling; further crowd objects are subjected to density calculation and danger index calculation; and finally according to different combinationsof crowd density, motion vector values and duration quantitative index data, various abnormal crowd behaviors are identified and judged, and according to the states of the abnormal crowd behaviors, corresponding crowd gathering management control policies are enabled. The deep convolutional neural network-based abnormal crowd behavior visual detection and analysis early warning system provided bythe invention is unlimited in scale, relatively high in precision and relatively good in robustness, and is based on a deep convolutional neural network.

The invention provides an intelligent dispatching system of automatic vending robots and a corresponding method. The intelligent dispatching system comprises at least one automatic vending robot which is configured as autonomously moving to a designated area position and vending goods according to a dispatching instruction from the designated area position of a dispatching control background server, at least one video monitoring system which is configured as collecting crowd images of multiple areas, and the dispatching control background server which is configured as allocating the automatic vending robots to the multiple areas according to crowd density information of the multiple areas, and sending the dispatching instruction assigned to the designated area position to the allocated automatic vending robots, wherein the crowd density information of the multiple areas can be acquired by processing the crowd images.

The invention discloses a crowd density estimation method based on video analysis and a pedestrian volume statistical method based on the video analysis. The crowd density estimation method includes the flowing steps of (1) off-line training: manually counting crowd density data, extracting characteristics and conducting training; and (2) on-line estimating: extracting the characteristics and conducting regression prediction by utilizing trained model parameters. The pedestrian volume statistical method includes the step of setting up a robust relationship between a scene and a line-passing number of people by combing the crowd density and a micro-region pedestrian flow speed before a line is passed. Characteristics such as foregrounds, edges and gray scale co-occurrence matrixes are extracted based on a whole area to conduct crowd density estimation, problems of dense crowds, sheltering and the like can be well solved through mixing of the characteristics, and real-time crowd density estimation is achieved. In addition, on the basis of area crowd density estimation, pedestrian volume estimation is conducted through combination of the pedestrian flow speed based on an optical flow, detection and tracking of a large number of individuals under a complex environment are avoided, and two-way pedestrian volume counting of accurate robust under dense crowds is achieved.

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 discloses a dynamic firefighting emergency evacuation indication system for a large-scale public building. The dynamic firefighting emergency evacuation indication system comprises an evacuation indication setting subsystem, a firefighting monitoring and predicating subsystem, a dynamic evacuation indication adjusting subsystem and a crowd evacuation predicating subsystem. Firstly, evacuation indication distribution in the large-scale public building is set according to the evacuation indication setting subsystem; secondly, firefighting accidents happening in the large-scale public building are considered, multiple fire detectors are used for obtaining information such as the position and the intensity of a fire, and a computer model is used for predicating the development of the fire; thirdly, the development of the fire is used for dynamically adjusting evacuation indication to ensure that the evacuation indication points to a safe area; finally, a built cellular automaton evacuation model considering the evacuation indication function is adopted to predict crowd evacuation and feeds back a predication result to the dynamic evacuation indication adjusting subsystem. The evacuation indication is corrected again according to the crowd density, the evacuation time and the like, and the evacuation efficiency is improved.

The invention provides a dense crowd security and protection monitoring management method based on artificial intelligence dynamic monitoring. The method comprises the following steps: screening and marking sensitive personnel based on dynamic face recognition at an entrance and an exit, Wherein the face recognition comprises rapid primary screening and accurate secondary screening; And if necessary, using the unmanned aerial vehicle monitoring system to assist in performing face tracking monitoring; performing Crowd density dynamic monitoring based on video analysis, Wherein the dynamic crowddensity is calculated by adopting a direction gradient histogram human body detection algorithm; Detecting and warning group abnormal behaviors of the dense crowd under video monitoring; And performing the unmanned aerial vehicle assisting monitoring in the video monitoring blind area. According to the method, a key monitoring area and comprehensive dynamic monitoring are combined, flow monitoring of an unmanned aerial vehicle system is assisted, and full monitoring coverage of dense crowd occasions is achieved.

The invention discloses an extraction method for dynamic crowd gathering characteristics and belongs to the technical field of intelligent monitoring of computers. According to the extraction method, a nuclear density spatial clustering algorithm is introduced into the 'external characteristics analysis process of crowd gathering', so that extraction and quantitative study and judgment of the crowd gathering characteristics for a mass disturbance are effectively achieved. As the crowd movement mode is recognized by the adoption of the method of crowd barycenter motion tracking, the current situation that at present, mass disturbance early warning is performed only according to crowd density grades, other external characteristics, such as the crowd gathering shape, the crowd movement speed and the crowd growth rate, of crowd gathering fail to be fully considered, and the false alarm rate and the missed alarm rate are high is changed. The extraction method can be applied to other safety-sensitive crowded places, thereby having broad popularization and application prospects.

The invention provides a method for estimating crowd density in a video image, which comprises the following steps: firstly, selecting an area of interest in a video image sample, and performing partitioning analysis of image blocks on the area of interest according to a perspective model; secondly, acquiring multi-scale grain characteristics by aiming at each image block; thirdly, performing cluster analysis on the video image sample to establish a classifier model of relation between the image block density level and the grain characteristics; fourthly, determining the density level of eachimage block in a target video image according to the classifier model; and fifthly, acquiring the overall density level of a target video area according to the density levels of all the image blocks in the area of interest. The method establishes a unified and definite partitioning standard of the image block density levels under the condition with different scenes, different camera angles and different positions, so the method can adapt to different scenes and provides a reliable density level estimation.

The invention discloses a method for counting the number of people based on a convolution neural network, which relates to the field of computer vision. Firstly, the image sample data is processed andthe actual crowd density map of the sample image is generated. Then, a hierarchical context and multi-scale feature fusion network is established by extracting and processing the feature maps in thebranch network to obtain the hierarchical context information and transferring it to the backbone network, which selectively fuses the low-level and high-level feature maps in the backbone network. The network is trained by using the processed sample data. Finally, the trained model is used to count the number of people in any image. The invention effectively solves the problem that the accuracy rate drops due to the inconsistent image scale in the number of people counting task, and improves the universality of the method in different scenes.

The invention relates to a method of measuring number of people based on geographic grids as well as a method and a system of monitoring crowd situation based on the geographic grids. The method of measuring the number of people based on the geographic grids comprises the following steps of establishing the geographic grids for one area; projecting communication cells (CELL) on the geographic grids, calculating an overlapping area of each cell and each related geographic grid unit, and calculating the proportion of the overlapping area in the area of each CELL; obtaining the current number of mobile communication devices in each CELL, and distributing the number of mobile communication devices in each CELL to each related geographic grid according to the proportion of the overlapping area of each CELL and the corresponding grid in the area of each CELL; and counting the number of people, which is distributed from different CELLs by each geographic grid, to obtain the number of people in each geographic grid unit. A monitoring area is determined, and the crowd situation of the monitoring area is analyzed according to the number of people of each geographic grid. According to the method and the system, the crowd situation, such as crowd density and crowd flow condition, can be effectively monitored.

The invention provides a dense crowd counting method and a device thereof. By obtaining an image to be detected including a portrait, the image to be detected is input into a convolution neural network model to obtain a crowd density map of the image to be detected, and the number of portraits in the image to be detected is determined according to the crowd density map. The process fully extractsthe feature information from the image to be detected, realizes good crowd counting and density estimation, and brings great convenience for subsequent safety monitoring, crowd control and other applications.

The invention discloses a crowd counting method based on a coding-decoding structure multi-scale convolutional neural network, and the method is characterized in that the method comprises the following steps: considering the visual angle distortion of an image, and employing an adaptive Gaussian filter to calculate a true value density map of the image; adopting an encoding-decoding structure, building a multi-scale convolutional neural network model, wherein a loss function of the multi-scale convolutional neural network model comprises pixel space loss and counting error description; training and testing the built multi-scale convolutional neural network model to obtain a trained multi-scale convolutional neural network model; inputting a to-be-estimated image into the trained multi-scale convolutional neural network model, and predicting to obtain a crowd density map; and performing regression estimation on the crowd density map to obtain the number of people in the to-be-estimatedimage. According to the method, scale features and contextual information of the image can be reserved, and the output quality of the density map can be improved.

The invention discloses an analysis method of a video-based crowd density and abnormal behavior detection system, and relates to the fields such as intelligent video surveillance and target detection. The analysis method comprises the steps of performing density grading by using an improved method based on pixel statistics and texture statistics; performing estimation on the number of people by using a method combining pixel statistics and foreground corner detection; introducing a local optical flow, proposing and implementing a crowd abnormal behavior detection algorithm based on the average kinetic energy change rate. The analysis method disclosed by the invention not only can be applicable to general surveillance video, but also can be more applicable to crowd gathering video in prominent large public places. The analysis method is less in system time consumption, has good effectiveness and practicability and meets actual requirements.

The invention discloses a crowd counting method based on a convolutional neural network. The method comprises the following steps of (1) after a training picture is marked, performing convolution operation with a Gaussian kernel to obtain a real crowd density diagram, and taking the real crowd density diagram as a label for model training; (2) inputting the training picture and the corresponding real crowd density diagram into a convolutional neural network model for performing training, and optimizing iterative updating parameters every time until the model is converged; (3) creating a new scene data set, and finely adjusting the obtained model by utilizing a model migration method, thereby finishing the model training; and (4) performing performance evaluation and testing on the trainedmodel. By utilizing the method, the number of parameters needed to be trained for the model is reduced; the model structure is simplified; the real-time performance of the model is improved on the premise that the accuracy is guaranteed; and the requirements of actual application are met.

Detecting crowds is provided. A location is selected in a set of locations a user of a client device wants to go to based on data within a profile associated with the user. A set of data inputs is monitored to determine a number of people currently at the selected location. Then, in response to determining that the number of people currently at the selected location is not greater than a user-defined threshold level of people for the selected location, a mapped route to the selected location is sent to the client device of the user.

The invention discloses a self-intended crowd density estimation method for a camera capable of straddling. The steps of the self-intended crowd density estimation method for the camera capable of straddling comprise capturing a video monitoring signal, obtaining a video monitoring population image and conducting space mapping processing toward the video monitoring population image, picking up a foreground image of population motion according to a geographical reference and conducting operation such as edge detection and morphological processing towards the foreground image. If a foreground edge pixel number is smaller than a threshold value being set, a crowd density is calculated through a low density population estimation model and is classified according to a crowd density degree standard. If the foreground edge pixel number is larger than the threshold value being set, a textual feature of the foreground image is picked up; the crowd density degree is estimated by using a camera capable of straddling support vector machine (SVM) crowd density classifier. The self-intended crowd density estimation method for the camera capable of straddling adopts a video data space mapping method to unify video data to the geographical reference so that the problem of various population image sizes of different monitoring devices is solved, scene dependency of a model is overcome and establishing efficiency of a crowd density estimation model is greatly improved.

The invention discloses a crowd counting method based on scene depth information, which comprises the following steps of: (10) image segmentation: extracting depth information of an input image by adopting a monocular image depth estimation algorithm, and segmenting the input image into a close-range region and a distant-range region according to the depth information; (20) close-range area crowdcounting: predicting a head boundary frame of the close-range area by adopting a crowd counting method based on target detection to obtain the number of people in the close-range area; (30) crowd counting in a distant view area: predicting a crowd density map in the distant view area by adopting a crowd counting method based on density estimation, and solving the product of the crowd density map in the distant view area to obtain the number of people in the distant view area; and (40) confirmation of the number of people in the input image: adding the number of people in the distant view areaand the number of people in the close view area to obtain the total number of people in the input image. The crowd counting method based on the scene depth information is good in multi-scale adaptability, low in overfitting degree and accurate in counting.

The embodiment of the invention discloses a crowd density statistics method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining a to-be-counted target image comprising crowd information; inputting the target image into a pre-trained target detection deep neural network to obtain a first crowd density distribution diagram corresponding to the target image; inputting the target image into a pre-trained crowd density regression deep neural network to obtain a second crowd density distribution map corresponding to the target image; and fusing the first crowd density distribution diagram and the second crowd density distribution diagram through a pre-trained fusion neural network to obtain a third crowd density distribution diagram. The problem that crowd density distribution in different crowd degree scenes cannot be well processed during crowd density statistics is solved, and the universality and accuracy of crowd density statistics application are improved.