System and method for providing crowd flow information

Abstract

The present invention relates to a system for providing crowd flow information and a method thereof. The method includes the steps of: collecting image data from a CCTV and a drone; analyzing and predicting a crowd flow in a predetermined area by using the image data as an input; and generating a dense display UI indicating the crowd flow and displaying the dense display UI on a map, wherein the dense display UI indicates at least three of a direction, a speed, a dense range, and a density of the crowd flow. Accordingly, a crowd flow can be analyzed and predicted using CCTV and drone images. In addition, a UI for visualizing the direction, speed, dense range, or density of the crowd flow is provided so that the crowd flow can be intuitively identified.

Description

Crowd flow information provision system and method thereof

[0001] The present invention relates to a method and system for providing crowd flow information, and more specifically, to a technology for analyzing crowd flow in a certain area or in India and visualizing the analyzed information.

[0002] As populations and population densities increase worldwide, festivals and events are growing in scale. In particular, the proliferation of social media has led to a rise in events with difficult-to-identify organizers and events that draw unspecified crowds, such as flash mobs.

[0003] Crowd-related incidents are a constant occurrence at these large-scale events, where large numbers of people gather. In the case of crowd-related incidents, control personnel have difficulty predicting crowd density and flow in densely packed spaces, making it impossible to respond appropriately in advance.

[0004] To address the aforementioned issues, the present invention provides a system and method for analyzing and predicting crowd flow using CCTV and drone footage. Furthermore, the present invention provides a system and method capable of providing a user interface (UI) that visualizes the direction, speed, concentration, or density of crowd flow. Furthermore, the present invention provides a system and method capable of providing a UI that forecasts the hourly density of crowd flow.

[0005] The above object can be achieved by a method for providing crowd flow information, comprising the steps of: collecting video data from CCTV and drones; analyzing and predicting crowd flow in a certain area using the video data as input; and generating a crowd display UI representing the crowd flow and displaying it on a map, wherein the crowd display UI is characterized in that it represents at least three of the direction, speed, crowd range, and density of the crowd flow.

[0006] Here, the dense display UI includes an arrow, the direction is expressed by the direction of the arrow, the speed is expressed by the length of the arrow and the animation speed, the dense range is expressed by the number of arrows, and the density can be expressed by at least one of the size, thickness, and color of the arrow.

[0007] Meanwhile, the above object can also be achieved by a crowd flow information providing system, comprising: a server for collecting video data from CCTV and drones, analyzing the crowd flow in a sidewalk and a certain area using the video data as input, and generating a crowd display UI indicating the crowd flow to provide crowd density information; and a user terminal for displaying the crowd density information received from the server on a display, wherein the crowd display UI is characterized in that it indicates at least three of the direction, speed, crowd density range, and density of the crowd flow.

[0008] The above dense display UI includes an arrow, the direction is expressed by the direction of the arrow, the speed is expressed by the length of the arrow and the animation speed, the dense range is expressed by the number of arrows, and the density can be expressed by at least one of the size, thickness, and color of the arrow.

[0009] Here, the density display UI may include a density forecast UI that forecasts the density by hour.

[0010] As described above, the crowd flow information system and method according to the present invention can analyze and predict crowd flow using CCTV and drone footage. Furthermore, it provides a UI that visualizes the direction, speed, concentration, and density of crowd flow, allowing for intuitive understanding of crowd flow. Furthermore, it provides a UI that forecasts the hourly crowd flow density, allowing for time-based crowd flow analysis.

[0011] Figure 1 is a schematic diagram of a crowd flow information providing system according to one embodiment of the present invention.

[0012] Figure 2 is a flowchart of a method for providing crowd flow information according to one embodiment of the present invention.

[0013] FIG. 3 illustrates an example of a web page providing crowd flow information according to one embodiment of the present invention.

[0014] Figure 4 is an enlarged view of a portion of Figure 3. Figure 4 (a) is an enlarged view of area A of Figure 3, and Figure 4 (b) is an enlarged view of area B of Figure 3.

[0015] Hereinafter, specific embodiments of the present invention will be described with reference to the drawings.

[0016] Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. However, detailed descriptions of well-known functions or components that may obscure the gist of the present invention will be omitted in the following description and the accompanying drawings. It should also be noted that, where possible, identical components are indicated with the same reference numerals throughout the drawings.

[0017] The terms and words used in this specification and claims described below should not be interpreted as limited to their conventional or dictionary meanings, but should be interpreted with meanings and concepts that conform to the technical idea of ​​the present invention based on the principle that the inventor can appropriately define the concept of the term to best describe his or her invention. Therefore, the embodiments described in this specification and the configurations illustrated in the drawings are merely the most preferred embodiments of the present invention and do not represent all of the technical idea of ​​the present invention. Therefore, it should be understood that there may be various equivalents and modified examples that can replace them at the time of filing this application.

[0018] FIG. 1 is a schematic diagram of a crowd flow information providing system according to one embodiment of the present invention. Referring to FIG. 1, the crowd flow information providing system according to the first embodiment of the present invention includes a server (100) and a user terminal (200).

[0019] The server (100) collects video data from CCTV (10) and a drone (20), analyzes the crowd flow based on the collected video data, and provides the data to a user terminal (200). The server (100), CCTV (10), drone (20), and user terminal (200) are connected via a network (30).

[0020] CCTV (10) may include both public and private CCTV (10) installed in each region and building. Drone (20) may include public and private drones (20) that capture images of each region. The server (100) can estimate indoor as well as outdoor crowd density through image data collected from CCTV (10), and furthermore, can determine the influence of people indoors or in vehicles on outdoor crowd flow. The server (100) builds a database of information regarding CCTV (10) and drone (20), and can determine the crowd flow by region by building and analyzing the DB of image data collected from CCTV (10) and drone (20).

[0021] Referring to FIG. 1, the server (100) can be implemented as a computing device and computing system including a memory (110), a processor (120), a DB (130), a user interface (140), and a communication interface (150).

[0022] The memory (110) is a recording medium readable by a computing device, and may be configured to include a non-volatile memory such as a ROM (Read Only Memory), an EPROM (Erasable Programmable ROM), an EEPROM (Electrically Erasable Programmable ROM), a flash memory, a HDD (Hard Disk Drive), an SSD (Solid State Disk), a removable disk, or any type of computer-readable recording medium well known in the art to which the present invention pertains. The memory (110) may store at least one computer program code executed by the processor (120). Such computer program code may be loaded into the memory (110) from a floppy drive, disk, memory card, etc. separate from the memory (110) built into the device. The memory (110) may store software for analyzing crowd flow, various data, etc.

[0023] The processor (120) is configured to execute and process computer program instructions by performing basic logic, calculations, operations, etc., and may include at least one of a CPU (Central Processing Unit), an MPU (Micro Processor Unit), an MCU (Micro Controller Unit), a GPU (Graphics Processing Unit), or any other type of processor well known in the technical field of the present invention. The computer program code stored in the memory (110) is loaded into the processor (120) and executed. The processor (120) executes the algorithm stored in the memory (110) to analyze image data collected from CCTV (10) and drones (20) to analyze crowd flow.

[0024] DB (130) includes various DBs, such as, for example, information about CCTV (10), drone (20), DB about image data collected from CCTV (10) and drone (20), and previous analysis data.

[0025] The user interface (140) is for receiving user input or displaying data, and may include, for example, an input device such as a microphone, keyboard, or mouse, and a display that displays images and data.

[0026] The communication interface (150) is for communicating with other devices through a network (30), and may include any one or more networks (30) among, for example, a personal area network (PAN), a local area network (LAN), a campus area network (CAN), a metropolitan area network (MAN), a wide area network (WAN), a broadband network (BBN), and the Internet.

[0027] The server (100) includes a crowd analysis model for identifying crowds and analyzing the flow of crowds from video data collected from CCTV (10) and drones (20). The crowd analysis model is stored in a memory (110) and executed by a processor (120). The crowd analysis model is a model that recognizes people from video data collected for a certain area, extracts movement directions, etc., and simulates the flow of crowds. The model can be created through learning using deep learning.

[0028] The server (100) generates crowd flow information that displays a crowd flow indicator UI on a map based on the analysis results and provides the information to the user terminal (200). In addition, the server generates a crowd forecast UI that forecasts crowd flow and provides the information to the user terminal (200).

[0029] The user terminal (200) may include a smartphone, tablet PC, PC, etc., on which a dedicated app for receiving crowd flow information is installed or executed, or on which a web server providing crowd flow information is accessed to obtain crowd flow information. The dedicated app for receiving crowd flow information according to one embodiment of the present invention may be configured to display crowd flow information within a certain radius of the area where the terminal is located based on the terminal's GPS information.

[0030] Hereinafter, a method for providing crowd flow information according to one embodiment of the present invention will be described with reference to FIGS. 2 and 3.

[0031] Figure 2 is a flowchart illustrating a method for providing crowd flow information according to one embodiment of the present invention. A server (100) collects video data from CCTV (10) and a drone (20) (S10). The server (100) analyzes video data in the same location or range based on location information to analyze and predict crowd flow in a certain area (S11). Since CCTV video data and drone video data are set to be transmitted including device location information, the server (100) can analyze crowd flow in the same location or range. The server (100) can recognize overlapping locations in the video data for a certain area through object recognition, and can analyze crowd flow by focusing on videos with high definition or a large number of people among multiple video data for the same location or range. In addition, the server (100) can estimate crowd flow from multiple CCTV (10) or drone video data in a certain area by considering the direction of movement of crowds in the video data. The server (100) calculates by adding up the vectors of the crowd flow corresponding to the same location based on the results of the image data analysis, and calculates the dense range in units of arbitrary cells.

[0032] Furthermore, the server (100) can accumulate analysis data to predict crowd flow by day of the week and time of day. Furthermore, the server (100) can collect SNS data to extract information on regional festivals and events, which can be used to forecast crowd flow. The server (100) can extract text data, such as store or building signs or notices, included in video data to extract information on regional events or store events. The information extracted from such SNS and video data is used to predict and forecast crowd flow.

[0033] The server (100) generates a crowd display UI indicating the flow of people and provides it to the user terminal (200) so that it can be superimposed on a map, and the user terminal (200) displays the received crowd flow information on the display (S13). The crowd display UI is expressed so as to indicate at least three of the direction, speed, crowd range, and density of the crowd flow. In one embodiment of the present invention, an example of expressing it using arrows is described.

[0034] In an example where the crowd display UI is expressed as an arrow, the direction of movement of the crowd is expressed by the direction of the arrow, the speed of movement of the crowd is expressed by the length of the arrow and the animation speed, the range of the crowd density is expressed by the number of arrows, and the density of the crowd can be expressed by at least one of the size, thickness, and color of the arrow.

[0035] FIG. 3 illustrates an example of a web page providing crowd flow information according to an embodiment of the present invention, and FIG. 4 is an enlarged view of a portion of FIG. 3 . FIG. 4 (a) is an enlarged view of area A of FIG. 3 , and FIG. 4 (b) is an enlarged view of area B of FIG. 3 . Referring to FIGS. 3 and 4 , the crowd display UI is represented by arrows on the map, and the direction of crowd movement is indicated by the direction of the arrows. Users can determine where crowds are moving by looking at the direction of the arrows displayed on the map. The movement speed of the crowd is expressed by the length of the arrows and the animation speed. A longer arrow indicates a faster speed, and a shorter arrow indicates a slower speed. In addition, the server (100) animates the arrows according to the movement direction and movement speed. The faster the speed, the faster the animation, and the slower the speed, the slower the animation. Through these animation effects, users can intuitively understand the direction and speed of crowd flow. The server (100) expresses the density range by the number of arrows. The wider the density range, the more arrows there are, and the narrower the density range, the fewer arrows there are.

[0036] The server (100) expresses the crowd density by the size and color of the arrow. The higher the crowd density, the larger the arrow size. The color representing the crowd density can be expressed by changing the color of the arrow from blue > green > orange > red as the density increases from low to high.

[0037] In Figures 3 and 4, when the crowd density is low and the flow is smooth, the arrows are expressed in blue, small, and long. When the crowd density is high and the flow is stagnant, the arrows are expressed in red, large, and short. The number of arrows increases as the crowd density increases. Although Figure 3 is a captured screen and it is difficult to represent the animation effect of the crowd display UI in a drawing, the crowd display UI displays animation effects indicating the direction and speed of movement, so the user can intuitively understand the flow of the crowd.

[0038] Meanwhile, the crowd display UI further includes a crowd forecast UI that forecasts crowd density by hour. Based on the collected image data, the server (100) can predict not only the current crowd flow but also the future crowd flow by hour, and provides the predicted information through a crowd forecast UI in forecast form (S15).

[0039] Referring to FIGS. 3 and 4, the density forecast UI displays items indicating the time, '15, 18, 21', along with icons indicating the density below them, and 'smooth, normal, caution, crowded', etc., to describe the density. At this time, the icons express the density with color and expression. In FIGS. 3 and 4, a forecast for 9 hours at 3-hour intervals is described as an example, but a forecast for a longer interval or a longer period of time can be displayed as needed. As in FIG. 4 (a), you can check a forecast for a period longer than 9 hours by clicking the display expansion and reduction icons on the right. In addition, the density forecast UI can express the range differently depending on the scale of the map. For example, the server (100) can display the density forecast UI in a large area unit when the map scale is large, and can display the density forecast UI in a small area unit when the map scale is small. Accordingly, the user can check the flow of people in the area he or she wants by adjusting the size of the map.

[0040] The invention can also be implemented in various computer-readable recording media, such as magnetic storage media, optical readable media, and digital storage media, which store computer programs for performing the methods according to the present invention when executed on a computer. Furthermore, the description expressed as steps in the claims is not limited to the order of the steps.

[0041] While several embodiments of the present invention have been described so far, those skilled in the art will appreciate that modifications or substitutions of certain embodiments may be made without departing from the technical spirit of the present invention. Therefore, the scope of protection of the present invention should be deemed to encompass the inventions described in the claims and their equivalents.

Claims

1. Step of collecting video data from CCTV and drones; A step of analyzing and predicting the flow of people in a certain area by inputting the above image data; and Including a step of creating a density display UI that represents the above crowd flow and displaying it on a map, A method for providing crowd flow information, characterized in that the above crowd display UI indicates at least three of the direction, speed, crowd range, and density of the crowd flow.

2. In paragraph 1, The above dense display UI includes arrows, A method for providing crowd flow information, characterized in that the direction is expressed by the direction of the arrow, the speed is expressed by the length of the arrow and the animation speed, the dense range is expressed by the number of arrows, and the density is expressed by at least one of the size, thickness, and color of the arrow.

3. In the system providing crowd flow information, A server that collects video data from CCTV and drones, analyzes the flow of people in a certain area and a certain area using the video data as input, and generates a crowd display UI that indicates the flow of people to provide crowd density information; and Includes a user terminal that displays the crowd density information received from the server on a display; A crowd flow information providing system, characterized in that the above crowd display UI indicates at least three of the direction, speed, crowd range, and density of the crowd flow.

4. In paragraph 3, The above dense display UI includes arrows, A system for providing crowd flow information, characterized in that the direction is expressed by the direction of the arrow, the speed is expressed by the length of the arrow and the animation speed, the dense range is expressed by the number of arrows, and the density is expressed by at least one of the size, thickness, and color of the arrow.

5. In paragraph 4, A system for providing crowd flow information, characterized in that the above-mentioned crowd display UI includes a crowd forecast UI that forecasts crowding by hour.

Images