AI-based risk prediction method and system

Abstract

To provide AI-based dangerous situation prediction methods and systems therefor.SOLUTION: The present invention relates to an AI-based dangerous situation prediction method and a system therefor. According to an embodiment of the present invention, a dangerous situation prediction method using a dangerous situation prediction system based on AI includes a step of inputting video from a camera installed in a monitoring region, a step of recognizing one or more objects from the inputted video, a step of extracting movement information or motion information on the recognized object, a step of applying the movement information or motion information on the object to a pre-trained, first learning model, and predicting a probability of occurrence of a dangerous situation, a step of obtaining object congestion degree information, meteorological information, and environmental information concerning the monitoring region, a step of applying the object congestion degree information, meteorological information, and environmental information to a pre-trained, second learning model, and determining a critical value, a step of comparing the dangerous situation occurrence probability, which is predicted from the first learning model, with the critical value, and determining the occurrence of a dangerous situation, and a step of, when the predicted dangerous situation occurrence probability is higher than the critical value, generates an alarm signal.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to an AI-based method and system for predicting a dangerous situation, and more particularly, to a method and system for predicting a probability of a dangerous situation occurring by determining a critical value according to a surrounding situation. [Background technology]

[0002] As not only crime but also safety accidents are increasing, CCTVs are being installed in various places to prevent crime and safety accidents in advance or to respond quickly to them.

[0003] Currently, the use of CCTV in crime prevention and response generally involves searching CCTV footage (stored on a server or in a specific storage space) of the scene after a dangerous situation has occurred, and identifying the area where the dangerous situation occurred.

[0004] Therefore, the current method has a limitation in that it is not possible to grasp the occurrence of a dangerous situation in real time using CCTV images.

[0005] In addition, in order to store CCTV videos for a certain period of time, the CCTV videos themselves must be transmitted to a server, occupying a relatively high bandwidth, and the server must also require a high amount of calculation.

[0006] In addition, because CCTV footage is stored directly on the server, personal information (such as faces) is exposed when reviewing the CCTV footage, which can lead to privacy violations.

[0007] This allows the occurrence of dangerous situations to be identified in real time using real-time CCTV footage, but there is a demand for new methods that are less burdensome not only in terms of protecting personal information but also in terms of data transmission and storage.

[0008] In addition, a technical plan is needed that can adaptively notify the occurrence of dangerous situations depending on the environment in which the CCTV is installed.

[0009] The background technology of the present invention is disclosed in Korean Patent Publication No. 10-2490062 (announced on January 12, 2023). Summary of the Invention [Problem to be solved by the invention]

[0010] The present invention aims to provide an AI-based method and system for predicting a dangerous situation by extracting information from an image, predicting the probability of a dangerous situation occurring using the information, and determining a critical value that can recognize and judge a dangerous situation using information obtained in real time, thereby predicting the dangerous situation. [Means for solving the problem]

[0011] According to an embodiment of the present invention for achieving this technical objective, a method for predicting a dangerous situation using an AI-based dangerous situation prediction system includes the steps of: inputting an image from a camera installed in a monitored area; recognizing one or more objects from the input image; extracting movement information or movement information of the recognized object; predicting a probability of a dangerous situation occurring by applying the movement information or movement information of the object to a pre-trained first learning model; acquiring object density information, meteorological information and environmental information about the monitored area; applying the object density information, meteorological information and environmental information to a pre-trained second learning model to determine a critical value; comparing the probability of a dangerous situation occurring predicted from the first learning model with the critical value to determine the occurrence of a dangerous situation; and generating an alarm signal if the probability of a dangerous situation occurring is higher than the critical value.

[0012] The method may further include a step of setting movement information and motion information of the object as input data, and setting a dangerous situation including at least one of an outsider's intrusion, abduction, wandering, falling, a fight, arson, and drowning as output data, and training the first learning model.

[0013] The step of acquiring object density information, meteorological information, and environmental information for the monitored area may include: acquiring object density information including traffic volume information and detected object density from the image; acquiring meteorological information including sunrise and sunset times, difference between minimum and maximum temperatures, weather, and wind speed; and acquiring environmental information including illuminance information, time, and camera installation position.

[0014] The method may further include setting the acquired object density information, meteorological information, and environmental information as input data, setting a danger situation grade as output data, and training the second learning model.

[0015] The step of training the second learning model may train the threshold value for generating an alarm signal to be lower the lower the object density, the closer it is to sunset, the greater the temperature difference, the worse the weather conditions, the faster the wind speed, the lower the illuminance, the closer the camera is installed to the periphery, and the closer it is to night.

[0016] According to another embodiment of the present invention, an AI-based dangerous situation prediction system includes an image acquisition unit that receives an image from a camera installed in a monitored area; an object recognition unit that recognizes one or more objects from the received image; a pre-processing unit that extracts movement information or movement information of the recognized object; a learning unit that predicts a probability of a dangerous situation occurring by applying the object movement information or movement information to a pre-trained first learning model; an information acquisition unit that acquires object density information, weather information, and environmental information about the monitored area; a control unit that applies the object density information, weather information, and environmental information to a pre-trained second learning model to determine a critical value; a judgment unit that compares the probability of a dangerous situation occurring predicted from the first learning model with the critical value to determine the occurrence of a dangerous situation; and an alarm unit that generates an alarm signal if the probability of a dangerous situation occurring is higher than the critical value. Effect of the Invention

[0017] In this way, according to the present invention, a critical value is determined according to the surrounding conditions, and a dangerous situation is recognized and an alarm is provided, thereby reducing false alarms and enabling a rapid response to emergency situations.

[0018] In addition, by minimizing random errors in various information received through CCTV footage and various sensors, the system can predict and prevent current and future dangerous situations for users in various industries and classes in society, thereby reliably ensuring the protection of users. [Brief description of the drawings]

[0019] [Figure 1] 1 is a configuration diagram of an AI-based dangerous situation prediction system according to an embodiment of the present invention. FIG.

[0020] [Diagram 2] 1 is a flowchart of an AI-based dangerous situation prediction method using a dangerous situation prediction system according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0021] Hereinafter, the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily carry out the present invention. However, the present invention may be embodied in various different forms and is not limited to the embodiments described herein. In order to clearly explain the present invention in the drawings, parts that are not related to the description will be omitted, and similar parts will be denoted by similar reference numerals throughout the specification.

[0022] Throughout the specification, when a part is described as being "connected" to another part, this includes not only when it is "directly connected" to another part, but also when it is "electrically connected" to another part via another element in between. Furthermore, when a part is described as "including" a certain component, this does not mean that it excludes the other component, but that it can further include the other component, unless otherwise specified.

[0023] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily carry out the present invention.

[0024] Hereinafter, a dangerous situation prediction system according to an embodiment of the present invention will be described with reference to FIG.

[0025] FIG. 1 is a configuration diagram of an AI-based dangerous situation prediction system according to an embodiment of the present invention.

[0026] As shown in FIG. 1, a dangerous situation prediction system 100 according to an embodiment of the present invention includes an image acquisition unit 110, an object recognition unit 120, a pre-processing unit 130, a learning unit 140, an information acquisition unit 150, a control unit 160, a judgment unit 170 and an alarm unit 180.

[0027] First, an image acquiring unit 110 receives images in real time from a camera installed in a monitored area.

[0028] At this time, the image capture unit 110 can capture a two-dimensional RGB image in real time.

[0029] The object recognition unit 120 recognizes one or more objects from the input image.

[0030] The object recognition unit 120 recognizes and separates a person's area from an object area held by the person from the image input through the image acquisition unit 110 .

[0031] That is, the object recognition unit 120 can improve the accuracy of feature information extracted through recognition of people and objects, and accurately distinguish between people and objects.

[0032] The pre-processing unit 130 then extracts movement or motion information of the recognized object.

[0033] The pre-processing unit 130 extracts object movement information (wandering, entering, exiting, etc.) including the movement path of the object from the image, and extracts motion information including behavior recognition information of a person or animal (walking, running, falling, etc.).

[0034] The learning unit 140 applies the object movement information or motion information to the first learning model that has already been learned to predict the probability of a dangerous situation occurring.

[0035] The learning unit 140 applies the movement information or motion information of the recognized object to a previously learned first learning model to predict the probability of a dangerous situation occurring.

[0036] In this case, the first learning model is trained by setting the object's movement information and motion information as input data and setting dangerous situations including at least one of an outsider's intrusion, abduction, wandering, falling, fighting, arson, and drowning as output data.

[0037] The information acquiring unit 150 acquires object density information, meteorological information, and environmental information about the monitored area.

[0038] The information acquiring unit 150 can acquire object density information, weather information, and environmental information in real time from a meteorological agency server, a camera, a plurality of sensors, and a user terminal.

[0039] The control unit 160 then applies the object density information, the weather information, and the environment information to the second learning model that has already been learned, to determine the threshold value.

[0040] That is, the control unit 160 determines an appropriate threshold value in consideration of information on the monitored area acquired in real time.

[0041] The determination unit 170 compares the risky situation occurrence probability predicted from the first learning model with a threshold value to determine whether a risky situation has occurred.

[0042] The alarm unit 180 generates an alarm signal when the probability of occurrence of a dangerous situation is higher than a critical value.

[0043] The alarm unit 180 can generate an alarm signal to notify a user of a danger through the user terminal.

[0044] The user terminals include terminals that can be connected to a network, such as a personal computer (PC), a notebook computer, and a smart phone.

[0045] Hereinafter, a method for predicting a dangerous situation using an AI-based dangerous situation prediction system according to an embodiment of the present invention will be described with reference to FIG.

[0046] FIG. 2 is a flowchart of an AI-based dangerous situation prediction method according to an embodiment of the present invention.

[0047] First, as shown in FIG. 2, the image acquiring unit 110 receives an image from a camera installed in a monitored area (step S210).

[0048] Then, the object recognition unit 120 recognizes one or more objects from the input image (step S220).

[0049] When learning using deep learning, the object recognition unit 120 can segment a person region and an individual region using semantic segmentation and semantic segmentation for Region of Interest, respectively.

[0050] The pre-processing unit 130 extracts movement information or motion information of the object recognized by the object recognition unit 120 (step S230).

[0051] For example, if an image is input from a security camera installed on a mountain trail, the object recognition unit 120 can recognize the background of the mountain trail (trees, stones, etc.) and the person. The pre-processing unit 130 can extract the person's movement direction and speed information as movement information, and can extract movement information (sitting, walking, running, falling, etc.).

[0052] The learning unit 140 then applies the object movement information or motion information extracted from the pre-processing unit 130 to the previously learned first learning model to predict the probability of a dangerous situation occurring (step S240).

[0053] The information acquiring unit 150 acquires object density information, weather information, and environmental information (step S250).

[0054] The information acquisition unit 150 can acquire environmental information including traffic volume information, object density information, illuminance information, time, and camera installation location (residential area, downtown, park, etc.) from at least one of a camera, a plurality of sensors, and a user terminal.

[0055] The information acquiring unit 150 can acquire meteorological information including sunrise and sunset times, the difference between the minimum and maximum temperatures, the weather (sunny, cloudy, rainy, snowy, etc.) and wind speed from a meteorological agency server.

[0056] The control unit 160 then applies object density information, meteorological information, and environmental information about the monitored area to the second learning model that has already been learned, and determines a threshold value (step S260).

[0057] The control unit 160 sets object density information, weather information, and environmental information as input data, sets the danger situation level as output data, and trains a second learning model.

[0058] The second learning model is trained to determine a lower threshold for generating an alarm signal the lower the object density, the closer it is to sunset, the greater the temperature difference, the worse the weather conditions, the faster the wind speed, the lower the illuminance, the closer the camera is installed to the periphery, and the closer it is to night.

[0059] The determination unit 170 then compares the risky situation occurrence probability with the threshold value to determine whether or not a risky situation has occurred (step S270).

[0060] The determination unit 170 may determine that a dangerous situation has occurred if the probability of occurrence of the dangerous situation is higher than a threshold value, and may determine that a dangerous situation has not occurred if the probability of occurrence of the dangerous situation is lower than the threshold value.

[0061] If the determination unit 170 determines that no dangerous situation has occurred, step S210 is repeated to determine whether or not a dangerous situation has occurred.

[0062] If the determining unit 170 determines that a dangerous situation has occurred in the monitored area, the alarm unit 180 generates an alarm signal (step S280).

[0063] The alarm unit 180 can generate an alarm signal to notify the user through the user terminal of the occurrence of a dangerous situation.

[0064] In this way, according to the present invention, a critical value is determined according to the surrounding conditions, and a dangerous situation is recognized and an alarm is provided, thereby reducing false alarms and enabling a rapid response to emergency situations.

[0065] In addition, by minimizing random errors in various information received through CCTV footage and various sensors, the system can predict and prevent current and future dangerous situations for users in various industries and classes in society, thereby reliably ensuring the protection of users.

[0066] The present invention has been described with reference to the embodiments shown in the drawings, but these are merely illustrative, and those skilled in the art will understand that various modifications and equivalent embodiments are possible. Therefore, the true technical scope of the present invention should be determined by the technical spirit of the claims. [Explanation of symbols]

[0067] 100: Danger situation prediction system 110: Video Acquisition Department 120:Object recognition section 130: Pre-processing section 140: Learning Department 150: Information acquisition department 160: Control unit 170: Judgment Department 180: Alarm section

Claims

1. A method for predicting a dangerous situation using an AI-based dangerous situation prediction system, receiving an image from a camera installed in a surveillance area; recognizing one or more objects from the input image; extracting movement information or motion information of the recognized object; applying the movement information or motion information of the object to a first learning model that has been trained to predict a probability of occurrence of a dangerous situation; acquiring object density information, meteorological information, and environmental information about the monitoring area; determining a threshold value by applying the object density information, meteorological information, and environmental information to a second learning model that has already been learned; determining whether a dangerous situation occurs by comparing the probability of occurrence of the dangerous situation predicted from the first learning model with the threshold value; generating an alarm signal if the probability of the dangerous situation occurring is higher than the critical value; A method for predicting a dangerous situation, comprising:

2. 2. The method of claim 1, further comprising the step of setting movement information and motion information of the object as input data, and setting a danger situation including at least one of an outsider's intrusion, abduction, wandering, falling, a fight, arson, and drowning as output data, and training the first learning model.

3. The step of acquiring object density information, meteorological information, and environmental information about the monitoring area includes: acquiring object density information including traffic information and detected object density from the image; obtaining meteorological information including sunrise and sunset times, minimum and maximum temperature differences, weather and wind speed; acquiring environmental information including illuminance information, time, and a camera installation position; The method for predicting a dangerous situation according to claim 1 ,

4. 2. The method of claim 1, further comprising: setting the acquired object density information, meteorological information, and environmental information as input data, setting a danger situation grade as output data, and training the second learning model.

5. The step of training the second learning model includes:

5. The method of claim 4, further comprising learning to lower the threshold value for generating an alarm signal as the object density is lower, the closer to sunset, the greater the temperature difference, the worse the weather conditions are, the faster the wind speed is, the lower the illuminance is, the closer the camera is installed to the periphery, and the closer it is to night.

6. In an AI-based danger situation prediction system, an image acquisition unit that receives images from a camera installed in a surveillance area; an object recognition unit for recognizing one or more objects from the input image; a pre-processing unit for extracting movement information or motion information of the recognized object; a learning unit that predicts a probability of occurrence of a dangerous situation by applying the movement information or motion information of the object to a first learning model that has already been learned; an information acquisition unit for acquiring object density information, meteorological information, and environmental information about the monitoring area; a control unit for determining a threshold value by applying the object density information, the meteorological information, and the environmental information to a second learning model that has already been learned; a determination unit that determines whether a dangerous situation occurs by comparing the probability of occurrence of the dangerous situation predicted from the first learning model with the threshold value; an alarm unit for generating an alarm signal when the risk occurrence probability is higher than the critical value; A dangerous situation prediction system including:

7. The learning unit is The danger situation prediction system of claim 6, wherein the object's movement information and motion information are set as input data, and danger situations including at least one of an outsider's intrusion, abduction, wandering, falling, fighting, arson, and drowning are set as output data to train the first learning model.

8. The information acquisition unit is Acquiring object density information including traffic volume information and detected object density from the image; Obtaining meteorological information including sunrise and sunset times, minimum and maximum temperature differences, weather and wind speed; The dangerous situation prediction system according to claim 6, further comprising: acquiring environmental information including illuminance information, time, and a camera installation position.

9. The control unit is The system for predicting a dangerous situation according to claim 6, wherein the acquired object density information, meteorological information and environmental information are set as input data, and a danger situation grade is set as output data to train the second learning model.

10. The second learning model is 10. The system of claim 9, further learning to lower the threshold value for generating an alarm signal as the object density is lower, as it is closer to sunset, as the temperature difference is larger, as the weather condition is worse, as the wind speed is higher, as the illuminance is lower, as the camera is installed in the peripheral area, and as it is closer to night.

Images