Method for predicting risky situation by generating virtual object simulation from image

Abstract

According to an embodiment of the present disclosure, disclosed is a method, performed by a computing device, for predicting a risky situation by analyzing an image. The method may comprise the steps of: acquiring an image; transforming an object included in the image into a virtual object to generate a transformation image; and predicting a risky situation on the basis of the transformation image including the transformed virtual object by utilizing a risk prediction model.

Description

A method for predicting hazardous situations by generating virtual object simulations from images.

[0001] The present invention relates to a method for predicting a dangerous situation, and more specifically, to a technology for predicting a dangerous situation through simulation in a virtual space by augmenting data while considering the characteristics of an object.

[0002] With the recent increase in Closed Circuit Television (CCTV) installations, interest in intelligent video analytics technology is growing for efficient monitoring. Intelligent video analytics analyzes video information to automatically detect abnormal behavior and send alerts to managers, enabling proactive prevention of accidents and rapid response to minimize damage when they occur. Furthermore, intelligent video analytics technology analyzes video information to automatically detect abnormal behavior. Its capabilities include object identification, object tracking, and event detection based on predefined rules.

[0003] However, there is a problem that images (videos) acquired through CCTV, etc. have different characteristics (e.g., shape, age, volume, etc.) for each object, making it difficult to augment learning data and using a lot of resources.

[0004] Korean Patent Publication No. 10-2022-0063280 (May 17, 2022) discloses a method and device for predicting crowding.

[0005] The present disclosure aims to provide a method for converting an object included in an image into a virtual object and augmenting learning data through simulation of the simplified virtual object.

[0006] Meanwhile, the technical task to be achieved by the present disclosure is not limited to the technical task mentioned above, and may include various technical tasks within a scope obvious to a person skilled in the art from the contents described below.

[0007] According to one embodiment of the present disclosure for achieving the aforementioned task, a method for predicting a hazardous situation by analyzing an image performed by a computing device is disclosed. The method may include the steps of: acquiring an image; converting an object included in the image into a virtual object to generate a converted image; and utilizing a risk prediction model to predict a hazardous situation based on the converted image including the converted virtual object.

[0008] In one embodiment, the step of converting an object included in the image into the virtual object and generating the converted image may include the steps of: recognizing an object included in the image; extracting key points of the recognized object; predicting a skeleton of the recognized object based on the key points; and converting the object into the virtual object based on the predicted skeleton.

[0009] In one embodiment, the step of converting an object included in the image into the virtual object and generating the converted image may include the steps of: recognizing an object included in the image; extracting feature information of the recognized object; and utilizing a virtual object conversion model, converting the recognized object into a virtual object including volume information based on the feature information of the recognized object.

[0010] In one embodiment, the virtual object including the volume information may include a skeleton element representing the physical movement of the recognized object; and a virtual body element representing the volume of the recognized object.

[0011] In one embodiment, the risk prediction model may be a model learned based on an operation of acquiring behavioral information corresponding to a risk situation; an operation of simulating the behavioral information corresponding to the risk situation based on a virtual object to acquire a virtual object-based simulation image; and an operation of augmenting the learning data by including the virtual object-based simulation image in the learning data of the risk prediction model.

[0012] In one embodiment, the operation of obtaining behavioral information corresponding to the risk situation may include an operation of extracting a target keyword from text-type information; an operation of extracting a target keyword from image-type information using a multimodal model; or an operation of extracting a target keyword from voice-type information using a STT (Speech-To-Text) model.

[0013] In one embodiment, the target keyword is included in a prompt for a language model, the prompt includes a combination of a plurality of target keywords extracted from different types of information, and the operation of obtaining behavioral information corresponding to the risk situation may include an operation of inputting the prompt to the language model and obtaining a scenario for behavioral information corresponding to the risk situation based on the input prompt.

[0014] In one embodiment, the operation of obtaining the virtual object-based simulation image may include an operation of simulating a virtual object based on the obtained scenario in a virtual space; and an operation of generating the virtual object-based simulation image based on movement information of the virtual object obtained in the simulating operation.

[0015] In one embodiment, the target keyword is included in a prompt for a generative model, the prompt includes a combination of a plurality of keywords extracted from different types of information, and the operation of obtaining the virtual object-based simulation image may include an operation of generating the virtual object-based simulation image based on the prompt by utilizing the generative model.

[0016] In one embodiment, the operation of generating the virtual object-based simulation image based on the prompt by utilizing the generative model may include an operation of applying information about the type of the generated virtual object as condition information to the generative model.

[0017] According to one embodiment of the present disclosure for achieving the above-described task, a computer program stored in a computer-readable storage medium is disclosed. When the computer program is executed on one or more processors, the computer program causes the one or more processors to perform the following operations for analyzing an image to predict a dangerous situation, wherein the operations may include: an operation of acquiring an image; an operation of converting an object included in the image into a virtual object to generate a converted image; and an operation of predicting a dangerous situation based on the converted image including the converted virtual object by utilizing a danger prediction model.

[0018] In one embodiment, the operation of converting an object included in the image into the virtual object and generating the converted image may include an operation of recognizing an object included in the image; an operation of extracting key points of the recognized object; an operation of predicting a skeleton of the recognized object based on the key points; and an operation of converting the object into the virtual object based on the predicted skeleton.

[0019] In one embodiment, the operation of converting an object included in the image into the virtual object and generating the converted image may include: an operation of recognizing an object included in the image; an operation of extracting feature information of the recognized object; and an operation of converting the recognized object into a virtual object including volume information based on the feature information of the recognized object by utilizing a virtual object conversion model.

[0020] In one embodiment, the risk prediction model may be a model learned based on an operation of acquiring behavioral information corresponding to a risk situation; an operation of simulating the behavioral information corresponding to the risk situation based on a virtual object to acquire a virtual object-based simulation image; and an operation of augmenting the learning data by including the virtual object-based simulation image in the learning data of the risk prediction model.

[0021] In one embodiment, the operation of obtaining behavioral information corresponding to the risk situation may include an operation of extracting a target keyword from text-type information; an operation of extracting a target keyword from image-type information using a multimodal model; or an operation of extracting a target keyword from voice-type information using a STT (Speech-To-Text) model.

[0022] In one embodiment, the target keyword is included in a prompt for a language model, the prompt includes a combination of a plurality of target keywords extracted from different types of information, and the operation of obtaining behavioral information corresponding to the risk situation may include an operation of inputting the prompt to the language model and obtaining a scenario for behavioral information corresponding to the risk situation based on the input prompt.

[0023] In one embodiment, the target keyword is included in a prompt for a generative model, the prompt includes a combination of a plurality of keywords extracted from different types of information, and the operation of obtaining the virtual object-based simulation image may include an operation of generating the virtual object-based simulation image based on the prompt by utilizing the generative model.

[0024] In one embodiment, the operation of generating the virtual object-based simulation image based on the prompt by utilizing the generative model may include an operation of applying information about the type of the generated virtual object as condition information to the generative model.

[0025] A computing device according to one embodiment of the present disclosure for achieving the aforementioned task is disclosed. The device comprises a computing device, at least one processor; and a memory, wherein the at least one processor is configured to acquire an image; convert an object included in the image into a virtual object to generate a converted image; and utilize a risk prediction model to predict a risk situation based on the converted image including the converted virtual object.

[0026] In one embodiment, the at least one processor may be configured to recognize an object included in the image; extract key points of the recognized object; predict a skeleton of the recognized object based on the key points; and transform the object into the virtual object based on the predicted skeleton.

[0027] In one embodiment, the at least one processor may be configured to recognize an object included in the image; extract feature information of the recognized object; and, using a virtual object transformation model, transform the recognized object into a virtual object including volume information based on the feature information of the recognized object.

[0028] In one embodiment, the virtual object including the volume information may include a skeleton element representing the physical movement of the recognized object; and a virtual body element representing the volume of the recognized object.

[0029] In one embodiment, the risk prediction model may be a model learned based on an operation of acquiring behavioral information corresponding to a risk situation; an operation of simulating the behavioral information corresponding to the risk situation based on a virtual object to acquire a virtual object-based simulation image; and an operation of augmenting the learning data by including the virtual object-based simulation image in the learning data of the risk prediction model.

[0030] In one embodiment, the at least one processor may be configured to extract a target keyword from text type information; extract a target keyword from image type information using a multimodal model; and extract a target keyword from voice type information using a speech-to-text (STT) model.

[0031] In one embodiment, the target keyword is included in a prompt for a language model, the prompt includes a combination of a plurality of target keywords extracted from different types of information, and the at least one processor is configured to input the prompt to the language model and obtain a scenario for behavioral information corresponding to the risk situation based on the input prompt.

[0032] In one embodiment, the target keyword is included in a prompt for a generative model, the prompt includes a combination of a plurality of keywords extracted from different types of information, and the at least one processor can be configured to generate the simulation image based on the virtual object based on the prompt by utilizing the generative model.

[0033] In one embodiment, the at least one processor may be configured to apply information about the type of the generated virtual object as condition information to the generative model.

[0034] The present disclosure can save resources in the process of predicting a risk situation in a risk prediction model by converting an object included in an image into a virtual object.

[0035] In addition, the present disclosure can predict more diverse risk situations and more accurate risk situations by augmenting learning data through virtual object-based simulation.

[0036] Meanwhile, the effects of the present disclosure are not limited to the effects mentioned above, and various effects may be included within a range apparent to those skilled in the art from the contents described below.

[0037] FIG. 1 is a block diagram of a computing device for analyzing an image to predict a dangerous situation according to one embodiment of the present disclosure.

[0038] FIG. 2 is a conceptual diagram illustrating a neural network according to one embodiment of the present disclosure.

[0039] FIG. 3 is a flowchart illustrating a method for predicting a dangerous situation by analyzing an image according to one embodiment of the present disclosure.

[0040] FIG. 4 is a schematic diagram illustrating a virtual object for predicting a dangerous situation by analyzing an image according to one embodiment of the present disclosure.

[0041] FIG. 5 is a schematic diagram illustrating an operation for augmenting learning data of a risk prediction model according to one embodiment of the present disclosure.

[0042] FIG. 6 is a simplified, general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented.

[0043] Various embodiments are now described with reference to the drawings. In this specification, various descriptions are provided to facilitate understanding of the present disclosure. However, it will be apparent that these embodiments may be practiced without these specific details.

[0044] As used herein, the terms "component," "module," "system," and the like refer to computer-related entities, hardware, firmware, software, a combination of software and hardware, or an execution of software. For example, a component may be, but is not limited to, a procedure running on a processor, a processor, an object, a thread of execution, a program, and / or a computer. For example, both an application running on a computing device and the computing device may be a component. One or more components may reside within a processor and / or a thread of execution. A component may be localized within a single computer. A component may be distributed between two or more computers. Furthermore, these components may execute from various computer-readable media having various data structures stored therein. Components may communicate via local and / or remote processes, for example, by signals comprising one or more data packets (e.g., data from one component interacting with another component in a local system, a distributed system, and / or data transmitted to another system via a network such as the Internet via signals).

[0045] Furthermore, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or." That is, unless otherwise specified or clear from context, "X employs A or B" is intended to mean either of the natural inclusive permutations. That is, if X employs A; X employs B; or X employs both A and B, "X employs A or B" can apply to any of these cases. Furthermore, the term "and / or" as used herein should be understood to refer to and include all possible combinations of one or more of the associated items listed.

[0046] Additionally, the terms "comprises" and / or "comprising" should be understood to imply the presence of the features and / or components in question. However, it should be understood that the terms "comprises" and / or "comprising" do not exclude the presence or addition of one or more other features, components, and / or groups thereof. Furthermore, unless otherwise specified or clear from the context to refer to the singular form, the singular in the specification and claims should generally be construed to mean "one or more."

[0047] And, the term "at least one of A or B" should be interpreted to mean "if it includes only A", "if it includes only B", or "if it is combined in the composition of A and B".

[0048] Those skilled in the art should further appreciate that the various illustrative logical blocks, configurations, modules, circuits, means, logics, and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate the interchangeability of hardware and software, various illustrative components, blocks, configurations, means, logics, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application. However, such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

[0049] The description of the disclosed embodiments is provided to enable a person skilled in the art to make or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art. The general principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Therefore, the present invention is not limited to the embodiments disclosed herein. The present invention is to be construed in the widest scope consistent with the principles and novel features disclosed herein.

[0050] In the present disclosure, network function, artificial neural network and neural network can be used interchangeably.

[0051]

[0052] FIG. 1 is a block diagram of a computing device for analyzing an image to predict a dangerous situation according to one embodiment of the present disclosure.

[0053] The configuration of the computing device (100) illustrated in FIG. 1 is merely a simplified example. In one embodiment of the present disclosure, the computing device (100) may include other configurations for performing the computing environment of the computing device (100), and only some of the disclosed configurations may constitute the computing device (100).

[0054] A computing device (100) may include a processor (110), memory (130), and network unit (150).

[0055] The processor (110) may be configured with one or more cores, and may include a processor for data analysis and deep learning, such as a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU) of a computing device. The processor (110) may read a computer program stored in the memory (130) to perform data processing for machine learning according to an embodiment of the present disclosure. According to an embodiment of the present disclosure, the processor (110) may perform operations for learning a neural network. The processor (110) may perform calculations for learning a neural network, such as processing input data for learning in deep learning (DL), extracting features from input data, calculating errors, and updating weights of a neural network using backpropagation. At least one of the CPU, GPGPU, and TPU of the processor (110) may process learning of a network function. For example, a CPU and a GPGPU can jointly process network function learning and data classification using network functions. Furthermore, in one embodiment of the present disclosure, processors of multiple computing devices can be jointly used to process network function learning and data classification using network functions. Furthermore, a computer program executed on a computing device according to one embodiment of the present disclosure may be a CPU, GPGPU, or TPU executable program.

[0056] According to one embodiment of the present disclosure, the memory (130) can store any form of information generated or determined by the processor (110) and any form of information received by the network unit (150).

[0057] According to one embodiment of the present disclosure, the memory (130) may include at least one type of storage medium among a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (e.g., SD or XD memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, and an optical disk. The computing device (100) may also operate in relation to web storage that performs the storage function of the memory (130) on the internet. The description of the above-described memory is merely an example, and the present disclosure is not limited thereto.

[0058] The network unit (150) according to one embodiment of the present disclosure can use various wired communication systems such as a public switched telephone network (PSTN), xDSL (x Digital Subscriber Line), RADSL (Rate Adaptive DSL), MDSL (Multi Rate DSL), VDSL (Very High Speed ​​DSL), UADSL (Universal Asymmetric DSL), HDSL (High Bit Rate DSL), and a local area network (LAN).

[0059] In addition, the network unit (150) presented in this specification can use various wireless communication systems such as CDMA (Code Division Multi Access), TDMA (Time Division Multi Access), FDMA (Frequency Division Multi Access), OFDMA (Orthogonal Frequency Division Multi Access), SC-FDMA (Single Carrier-FDMA) and other systems.

[0060] In the present disclosure, the network unit (150) may be configured regardless of the communication mode, such as wired or wireless, and may be configured as various communication networks, such as a local area network (LAN), a personal area network (PAN), and a wide area network (WAN). In addition, the network may be the well-known World Wide Web (WWW), and may also utilize a wireless transmission technology used for short-distance communication, such as infrared (IrDA: Infrared Data Association) or Bluetooth.

[0061] The techniques described in this specification can be used in other networks as well as the networks mentioned above.

[0062]

[0063] FIG. 2 illustrates an exemplary structure of an artificial intelligence-based model according to one embodiment of the present disclosure.

[0064] Throughout this specification, the terms artificial intelligence model, artificial intelligence-based model, computational model, neural network, network function, and neural network may be used interchangeably.

[0065] A neural network can be composed of a set of interconnected computational units, generally referred to as nodes. These nodes can also be referred to as neurons. A neural network consists of at least one node. The nodes (or neurons) that make up a neural network can be interconnected by one or more links.

[0066] Within a neural network, one or more nodes connected via links can form a relationship between input nodes and output nodes. The concept of input nodes and output nodes is relative, meaning that any node that is in an output node relationship with one node can also be in an input node relationship with another node, and vice versa. As described above, the relationship between input nodes and output nodes can be created based on links. One input node can be connected to one or more output nodes via links, and vice versa.

[0067] In a relationship between input nodes and output nodes connected through a single link, the data of the output node can have its value determined based on the data input to the input node. Here, the link interconnecting the input nodes and output nodes can have a weight. The weight can be variable and can be varied by the user or an algorithm so that the neural network can perform a desired function. For example, when one or more input nodes are interconnected to one output node through each link, the output node can determine the output node value based on the values ​​input to the input nodes connected to the output node and the weight set on the link corresponding to each input node.

[0068] As described above, a neural network is a network in which one or more nodes are interconnected through one or more links, forming input and output node relationships within the network. The characteristics of a neural network can be determined based on the number of nodes and links within the network, the relationships between the nodes and links, and the weights assigned to each link. For example, if two neural networks have the same number of nodes and links but different weight values ​​for the links, the two neural networks can be perceived as different from each other.

[0069] A neural network can be composed of a set of one or more nodes. A subset of the nodes comprising the neural network can form a layer. Some of the nodes comprising the neural network can form a layer based on their distances from the initial input node. For example, a set of nodes that are n distances from the initial input node can form n layers. The distance from the initial input node can be defined by the minimum number of links required to reach the node from the initial input node. However, this definition of a layer is arbitrary for illustrative purposes, and the degree of a layer within a neural network can be defined in a different way than described above. For example, a layer of nodes can be defined by its distance from the final output node.

[0070] In one embodiment of the present disclosure, a set of neurons or nodes may be defined as a layer.

[0071] An initial input node may refer to one or more nodes within a neural network into which data is directly input without going through links with other nodes. Alternatively, within a neural network, it may refer to nodes that do not have other input nodes connected by links in the relationship between nodes based on links. Similarly, a final output node may refer to one or more nodes within a neural network that do not have output nodes in their relationship with other nodes. Furthermore, a hidden node may refer to nodes that constitute a neural network other than the initial input node and the final output node.

[0072] A neural network according to one embodiment of the present disclosure may be a neural network in which the number of nodes in an input layer may be the same as the number of nodes in an output layer, and the number of nodes decreases and then increases as it progresses from the input layer to the hidden layer. In addition, a neural network according to another embodiment of the present disclosure may be a neural network in which the number of nodes in an input layer may be less than the number of nodes in an output layer, and the number of nodes decreases as it progresses from the input layer to the hidden layer. In addition, a neural network according to another embodiment of the present disclosure may be a neural network in which the number of nodes in an input layer may be greater than the number of nodes in an output layer, and the number of nodes increases as it progresses from the input layer to the hidden layer. A neural network according to another embodiment of the present disclosure may be a neural network in a combined form of the neural networks described above.

[0073] A deep neural network (DNN) can refer to a neural network that includes multiple hidden layers in addition to input and output layers. Using a DNN, one can identify latent structures in data. This can include images, text, videos, audio, protein sequence structures, gene sequence structures, peptide sequence structures, the latent structure of music (e.g., what objects are in the image, what the content and emotion of the text are, what the content and emotion of the audio are, etc.), and / or the binding affinity between peptides and MHC. A DNN can include a convolutional neural network (CNN), a recurrent neural network (RNN), an autoencoder, a restricted Boltzmann machine (RBM), a deep belief network (DBN), a Q-network, a U-network, a Siamese network, a generative adversarial network (GAN), a transformer, and more. The description of the deep neural network described above is only an example and the present disclosure is not limited thereto.

[0074] The artificial intelligence-based model of the present disclosure can be represented by a network structure of any structure described above, including an input layer, a hidden layer, and an output layer.

[0075] The neural network that can be used in the artificial intelligence-based model of the present disclosure may be trained using at least one of supervised learning, unsupervised learning, semi-supervised learning, transfer learning, active learning, or reinforcement learning. Training of the neural network may be a process of applying knowledge to the neural network to perform a specific action.

[0076] Neural networks can be trained to minimize output errors. This process involves repeatedly inputting training data into the neural network, calculating the neural network output and target error for the training data, and backpropagating the neural network error from the output layer to the input layer to update the weights of each node in the neural network to reduce the error. In supervised learning, training data with the correct answer for each training data is used (i.e., labeled training data). In unsupervised learning, the correct answer may not be labeled for each training data. For example, in supervised learning for data classification, the training data may be data with each category labeled. Labeled training data is input to the neural network, and the error can be calculated by comparing the output (category) of the neural network with the training data labels. Alternatively, in unsupervised learning for data classification, the error can be calculated by comparing the input training data with the neural network output. The calculated error is backpropagated in the neural network in the backward direction (i.e., from the output layer to the input layer), and the connection weights of each node in each layer of the neural network can be updated according to the backpropagation. The amount of change in the connection weights of each node to be updated can be determined by the learning rate. The neural network's calculation of the input data and the backpropagation of the error can constitute a learning cycle (epoch). The learning rate can be applied differently depending on the number of iterations of the neural network's learning cycle. For example, a high learning rate can be used in the early stages of neural network training to quickly achieve a certain level of performance, thereby increasing efficiency. A lower learning rate can be used in the later stages of training to increase accuracy.

[0077] In neural network training, training data can typically be a subset of real-world data (i.e., the data to be processed using the trained neural network). Therefore, there can be a learning cycle where errors on the training data decrease but errors on the real-world data increase. Overfitting is a phenomenon where excessive training on the training data leads to increased errors on the real-world data. For example, a neural network trained on yellow cats may fail to recognize cats when shown non-yellow colors, a type of overfitting. Overfitting can increase errors in machine learning algorithms. Various optimization methods can be used to prevent overfitting. These methods include increasing the training data, regularization, dropout, which disables some nodes in the network during the learning process, and the use of batch normalization layers.

[0078]

[0079] FIG. 3 is a flowchart illustrating a method for predicting a dangerous situation by analyzing an image according to one embodiment of the present disclosure.

[0080] The method of predicting a dangerous situation by analyzing the image shown in FIG. 3 can be performed by a computing device (100).

[0081]

[0082] According to one embodiment of the present disclosure, a computing device (100) can acquire an image (S110). For example, the computing device (100) can acquire an image through a closed circuit television (CCTV) installed indoors or outdoors. The image may be a dynamic image (video) acquired through the CCTV. Additionally, the computing device (100) may acquire an image from a smartphone, drone, security camera, or the like. In this case, the acquired image may be an image collected in real time.

[0083]

[0084] FIG. 4 is a schematic diagram illustrating a virtual object for predicting a dangerous situation by analyzing an image according to one embodiment of the present disclosure.

[0085] According to one embodiment of the present disclosure, the computing device (100) can convert an object included in an image into a virtual object to generate a converted image (S120). For example, the object included in the image may be a person. Referring to FIG. 4, the computing device (100) can convert an object included in the image into a virtual object. For example, the virtual object may include at least one of a skeleton-based first virtual object as illustrated in (a) of FIG. 4, a planar second virtual object as illustrated in (d) of FIG. 4, or a third virtual object including volumetric information as illustrated in (c) of FIG. 4. However, the present invention is not limited thereto, and the object included in the image may be converted into a virtual object through various methods that can be implemented in a virtual environment.

[0086] First, the computing device (100) can generate a converted image by converting an object included in the image into a skeleton-based first virtual object as shown in (a) of FIG. 4. For example, the computing device (100) can recognize an object included in the image. For example, the computing device (100) can perform object recognition on the image through various methods such as classification, object detection, and instance segmentation. In addition, the computing device (100) can recognize an object included in the image by using at least one of a plurality of classification algorithms. In addition, the computing device (100) can recognize an object included in the image through image retrieval, image annotation, face detection, image classification, etc. performed in object detection. In addition, the computing device (100) can perform object identification included in environmental information through computer vision, image processing, machine learning models, etc. For example, computer vision can recognize objects included in an image by including technologies such as object classification, object detection and localization, object segmentation, image captioning, object tracking, and action classification.For example, the computing device (100) may perform object recognition (identification) by utilizing a deep learning-based convolutional neural network (CNN), YOLO (You Only Look Once), Faster R-CNN, SSD (Single Shot MultiBox Detector), semantic segmentation, instance segmentation, SIFT (Scale-Invariant Feature Transform), SURF (Speeded-Up Robust Features), HOG (Histogram of Oriented Gradients), etc. In addition, the computing device (100) may extract key points of the recognized object. For example, the key points may include the head, neck, both shoulders, elbows, wrists, both hips, knees, ankles, and torso in the recognized object. However, the present invention is not limited thereto, and more diverse key points may be included. For example, the computing device (100) can extract key points of the recognized object based on key point detection, pose estimation, deep learning, and neural network. In addition, the computing device (100) can predict a skeleton of the recognized object based on the key points. The computing device (100) can predict a skeleton of the recognized object by connecting the key points. In addition, the computing device (100) can convert the object into the virtual object based on the predicted skeleton. For example, referring to (a) of FIG. 4, the computing device (100) can convert the object into a first virtual object based on a skeleton-based object based on the predicted skeleton.

[0087] Alternatively, the computing device (100) can recognize an object included in an image. The computing device (100) can recognize an object included in an image in a manner identical or similar to the method described above. In addition, the computing device (100) can extract feature information of the recognized object and, based on the feature information of the recognized object, convert the recognized object into a second virtual object including volume information by utilizing a contour-based model. A planar model is a model used to express the shape or appearance of a human body, and can express body parts using a plurality of rectangles.

[0088] According to one embodiment, the computing device (100) may generate a converted image by converting an object included in an image into a third virtual object ((c) of FIG. 4) including volume information. For example, the virtual object including volume information may include a skeleton element expressing the physical movement of the recognized object and a virtual body element indicating the volume of the recognized object. First, the computing device (100) may recognize an object included in an image. For example, the computing device (100) may perform object recognition on the image through various methods such as classification, object detection, and instance segmentation. In addition, the computing device (100) may recognize an object included in the image using at least one of a plurality of classification algorithms. In addition, the computing device (100) may recognize an object included in an image through image retrieval, image annotation, face detection, image classification, and the like performed in object detection. In addition, the computing device (100) can perform object identification included in environmental information through computer vision, image processing, machine learning models, etc. For example, computer vision can recognize objects included in an image by including technologies such as object classification, object detection and localization, object segmentation, image captioning, object tracking, and action classification.For example, the computing device (100) may perform object recognition (identification) by utilizing a deep learning-based convolutional neural network (CNN), YOLO (You Only Look Once), Faster R-CNN, SSD (Single Shot MultiBox Detector), semantic segmentation, instance segmentation, SIFT (Scale-Invariant Feature Transform), SURF (Speeded-Up Robust Features), HOG (Histogram of Oriented Gradients), etc.

[0089] In addition, the computing device (100) can extract feature information of the recognized object. For example, the feature information may include shape information such as outline, appearance, and boundary. The computing device (100) can extract feature information of the recognized object by utilizing geometric features such as outlines, vertices, and curves from the recognized object. In addition, the computing device (100) can utilize a virtual object conversion model to convert the recognized object into a virtual object (third virtual object) including volume information based on the feature information of the recognized object. For example, the computing device (100) can utilize a volumetric model to convert the recognized object into a virtual object (third virtual object) including volume information based on the feature information of the recognized object. For reference, a volumetric model is a technology or method for modeling an object or space in the form of volume (three dimensions), and a volumetric model includes volume information of an object to express a three-dimensional space and may include the shape, structure, volume, etc. of the object. For example, virtual object transformation models may include voxel-based models, mesh-based models, or implicit surface models, but the object transformation models are not limited thereto.

[0090] Meanwhile, the computing device (100) can save resources in the process of predicting a risk situation by utilizing a risk prediction model by converting an object included in an image into a virtual object and generating a converted image.

[0091]

[0092] According to one embodiment of the present disclosure, the computing device (100) can predict a risk situation based on a converted image including a converted virtual object by utilizing a risk prediction model (S130). For example, the computing device (100) can convert an object included in an acquired image into a virtual object and input the converted image into the risk prediction model. For example, the risk prediction model can predict a risk situation of an object included in an acquired image in real time based on a converted image including a converted virtual object. For reference, the risk prediction model is a model learned based on learning data including a virtual object-based simulation image. The risk prediction model will be described in more detail with reference to FIG. 5 below.

[0093]

[0094] FIG. 5 is a schematic diagram illustrating an operation for augmenting learning data of a risk prediction model according to one embodiment of the present disclosure.

[0095] For example, the risk prediction model may be a model learned based on an operation that performs augmentation of learning data by i) acquiring behavioral information corresponding to a risk situation, ii) simulating the behavioral information corresponding to the risk situation based on a virtual object to acquire a virtual object-based simulation image, and iii) including the virtual object-based simulation image in the learning data of the risk prediction model.

[0096] First, i) the computing device (100) can acquire behavioral information corresponding to a risk situation to augment the learning data of the risk prediction model. For example, the computing device (100) can acquire behavioral information from multiple types of information. For example, the multiple types of information may include text type, image type, and voice type. For reference, the target keyword may include one or more intention keywords related to the risk situation. For example, the target keyword may include an action keyword, a time keyword, a context keyword, a name keyword, etc. For reference, the target keyword extracted from different types of information may be included in the prompt of the language model or generative model described below.

[0097] According to one embodiment, the computing device (100) can extract target keywords from text-type information. For example, referring to FIG. 5, the computing device (100) can extract target keywords such as “alley” as a name keyword, “movement” as an activity keyword, and “people,” “difficult,” and “situation” as context keywords from text-type information (11) corresponding to “It is difficult to move in the alley due to many people.” However, the target keywords extracted from the text-type information are not limited thereto, and may include one or more intention keywords related to a dangerous situation.

[0098] In addition, the computing device (100) can extract target keywords from image type information by utilizing a multimodal model. For reference, the multimodal model may include a CLIP (Contrastive Language-Image Pre-training), a BLIP (Bootstrapping Language-Image Pre-training), a GLIP (Grounded Language-Image Pre-training), and a VLP (Vision-Language Pre-training) model. For example, referring to FIG. 5, the computing device (100) can extract target keywords such as “crowd,” “dense,” and “narrow space” from image type information (12) in which crowds are densely packed in a limited space. However, the target keywords extracted from the image type information are not limited thereto, and may include one or more intention keywords related to a dangerous situation.

[0099] In addition, the computing device (100) can extract target keywords from voice-type information by utilizing the STT (Speech-To-Text) model. For reference, speech recognition (STT or ASR; Speech To Text, or Automatic Speech Recognition) is a dictation technology that converts voice into text. The input of the speech recognition (STT) may include at least one of a voice signal, a spectrogram converted from a voice signal, or a voice feature. In addition, the output of the speech recognition (STT) is text in the form of a string. The computing device (100) can extract target keywords based on real-time conversation text, which is a result of performing speech recognition. According to one embodiment, the computing device (100) can obtain voice-type information in real time from a mobile device associated with an object included in the image. For example, referring to FIG. 5, the computing device (100) can extract target keywords such as “here” as a name keyword, “fall” and “crush” as activity keywords, and “people”, “too”, and “many” as context keywords from text type information (11) corresponding to “There are too many people here. I think I’ll get crushed if I fall.” However, the target keywords extracted from the text type information are not limited thereto, and may include one or more intention keywords related to a dangerous situation.

[0100] According to one embodiment, the computing device (100) may input a prompt to a “language model” (20) and obtain a scenario for behavioral information corresponding to the risk situation based on the input prompt. Here, the prompt may include a combination of multiple target keywords extracted from different types of information. At this time, the language model (20) may use a pre-trained transformer (GPT series) model, and examples thereof include Google’s Bard and Chat-GPT, but are not limited thereto and various language models may be used. For example, referring to FIG. 5, the computing device (100) can generate a prompt by combining target keywords “alleyway,” “movement,” “person,” “difficult,” “situation” obtained from text type information (11), target keywords “crowd,” “dense,” “narrow space” obtained from image type information (12), and target keywords “here,” “fall,” “crush,” “person,” “too,” “many” obtained from voice type information (13). For example, the language model (20) can generate a scenario (21) for behavioral information in response to a dangerous situation based on the input prompt, such as “an accident in a narrow alleyway with a dense crowd,” situation introduction: “A large number of people are moving in a complex and crowded alleyway of a certain market. Suddenly, someone in front falls down, and as a result, people around them also fall down, and a situation occurred where the crowd was crushed.” A scenario (21) such as the above can be created. However, the scenario described above is only an example and is not limited thereto, and various embodiments may exist.

[0101] Next, ii) the computing device (100) can obtain a virtual object-based simulation image by simulating behavioral information corresponding to the risk situation based on a virtual object in order to augment the learning data of the risk prediction model. For example, the computing device (100) can obtain a virtual object-based simulation image by simulating behavioral information corresponding to the risk situation based on a virtual object based on at least one of computer graphics, physical simulation, and system simulation. The computing device (100) can obtain a virtual object-based simulation image by simulating behavioral information corresponding to the risk situation by programming the shape, surface properties, movement, etc. of the object.

[0102] According to one embodiment, the computing device (100) can simulate a virtual object in a virtual space based on the acquired “scenario” (21). In addition, the computing device (100) can generate the simulation image based on the virtual object based on the movement information of the virtual object acquired in the simulated operation. For example, the computing device (100) can simulate a virtual object based on a scenario (21), such as “A large number of people are moving in a complex and crowded alleyway of a certain market. Suddenly, someone in front falls down, and as a result, people around them also fall down and the crowd is crushed.”, and can generate a first simulation image (22) based on the virtual object based on the movement information of the virtual object acquired in the simulated operation. For example, the first simulation image (22) can include information about the environment of a crowded alleyway of a market, images related to a large number of people moving, someone falling down, and a movement in which people around them fall and the crowd is crushed.

[0103] According to one embodiment, the computing device (100) can generate the simulation image based on the virtual object based on the prompt by utilizing a “generative model” (30). Here, the prompt may include a combination of multiple target keywords extracted from different types of information. For reference, the generative model may include a generative model that converts text into an image, such as stable diffusion, Midjourney, GAN (Conditional Generative Adversarial Network), DALLE-2, CLIP+VQ-VAE, and AttnGAN. For example, the computing device (!00) can generate a prompt by combining target keywords “crowd”, “dense”, “narrow space” obtained from image type information (12), “alleyway”, “movement”, “person”, “difficult”, “situation”, target keywords “here”, “fall”, “crush”, “person”, “too”, “many” obtained from voice type information (13). The computing device (100) can input the generated prompt into the generative model (30). In addition, the computing device (100) can obtain a second simulation image (31) based on virtual objects generated for behavioral information corresponding to a dangerous situation in the generative model (30) based on the input prompt. For example, the second simulation image (31) may include an image of people moving closely together in a narrow and crowded alleyway, an image of people falling down or being pushed and crushed by others due to a dangerous situation, a dense crowd of people, and a image of people representing a difficult situation. This may include facial expressions, tense atmosphere, etc.

[0104] According to one embodiment, the computing device (100) can apply information about the type of the generated virtual object as condition information to the generative model. For example, information about at least one of i) a type consisting of only a skeleton, ii) a 3D human type consisting of a skeleton + volume, and iii) a 3D human type of another type can be applied as condition information to the generative model. For example, when the computing device (100) generates a virtual object-based simulation image using the generative model, the computing device (100) can apply information about the first virtual object, the second virtual object, the third virtual object, the mixed type of the first virtual object and the third virtual object, or other virtual objects as condition information of the generative model. For example, the computing device (100) may apply information about a mixed type of the first virtual object and the third virtual object as condition information to a generative model, and the generative model may generate a simulation image by utilizing a virtual object of a mixed type of the first virtual object and the third virtual object based on a prompt.

[0105] Next, iii) the computing device (100) may perform learning data augmentation by including the virtual object-based simulation image in the learning data of the risk prediction model to augment learning data of the risk prediction model. For example, the computing device (100) may include a first virtual object-based simulation image (22) generated based on movement information of a virtual object acquired in an operation of simulating a virtual object based on a scenario acquired using a language model, and a second virtual object-based simulation image (31) generated based on a prompt using a generative model, as learning data of the risk prediction model.

[0106] Meanwhile, the computing device (100) can more easily augment the learning data of the risk prediction model by including a virtual object-based simulation image in the learning data of the risk prediction model. In addition, the computing device (100) can help improve the performance and generalization ability of the learning model and solve the problem of data insufficiency by augmenting the learning data by including a virtual object-based simulation image in the learning data of the risk prediction model. In addition, the computing device (100) can utilize behavioral information corresponding to a risk situation for which there is no existing data as learning data of the risk prediction model by generating a virtual object-based simulation image.

[0107]

[0108] The steps described in the above description may be further divided into additional steps or combined into fewer steps, depending on the implementation of the present disclosure. Furthermore, some steps may be omitted as needed, and the order of the steps may be changed.

[0109]

[0110] Meanwhile, a computer-readable medium storing a data structure according to an embodiment of the present disclosure is disclosed.

[0111] A data structure can refer to the organization, management, and storage of data to enable efficient access and modification. A data structure can refer to the organization of data to solve a specific problem (e.g., data retrieval, data storage, or data modification in the shortest possible time). A data structure can also be defined as the physical or logical relationships between data elements designed to support specific data processing functions. Logical relationships between data elements can include connections between user-defined data elements. Physical relationships between data elements can include actual relationships between data elements physically stored on a computer-readable storage medium (e.g., persistent storage). Specifically, a data structure can include a collection of data, relationships between data, and functions or commands applicable to the data. An effectively designed data structure allows a computing device to perform operations while minimizing the use of its resources. Specifically, a computing device can improve the efficiency of operations, reading, inserting, deleting, comparing, exchanging, and searching through an effectively designed data structure.

[0112] Data structures can be categorized as linear or nonlinear, depending on their form. A linear data structure can be a structure in which only one data item is linked to the next. Linear data structures can include lists, stacks, queues, and deques. A list can refer to a series of data sets with an internal order. Lists can also include linked lists. A linked list is a data structure in which data is linked in a single line, each item having a pointer. In a linked list, a pointer can contain information about the next or previous item. Linked lists can be expressed as singly linked lists, doubly linked lists, or circular linked lists, depending on their form. A stack can be a data listing structure with limited data access. A stack can be a linear data structure in which data operations (e.g., insertion or deletion) can only be performed at one end of the data structure. Data stored in a stack can be a Last-in-First-out (LIFO) data structure. A queue is a data structure with limited access to data. Unlike a stack, it can be a first-in, first-out (FIFO) data structure, with later data being retrieved later. A deck can be a data structure that can process data at both ends.

[0113] A nonlinear data structure can be a structure in which multiple pieces of data are connected behind a single piece of data. Nonlinear data structures can include graph data structures. A graph data structure can be defined by vertices and edges, and an edge can include a line connecting two different vertices. Graph data structures can include tree data structures. A tree data structure can be a data structure in which there is only one path connecting two different vertices among multiple vertices included in the tree. In other words, it can be a data structure that does not form a loop in a graph data structure.

[0114] Throughout this specification, the terms computational model, neural network, network function, and neural network may be used interchangeably. Hereinafter, they are collectively referred to as neural networks. The data structure may include a neural network. And the data structure including the neural network may be stored on a computer-readable medium. The data structure including the neural network may also include preprocessed data for processing by the neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data obtained from the neural network, activation functions associated with each node or layer of the neural network, loss functions for learning the neural network, etc. The data structure including the neural network may include any of the components disclosed above. That is, the data structure including the neural network may be configured to include all or any combination of preprocessed data for processing by the neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data obtained from the neural network, activation functions associated with each node or layer of the neural network, loss functions for learning the neural network, etc. In addition to the aforementioned configurations, a data structure including a neural network may include any other information that determines the characteristics of the neural network. Furthermore, the data structure may include any form of data used or generated in the computational process of the neural network, and is not limited to the aforementioned. The computer-readable medium may include a computer-readable recording medium and / or a computer-readable transmission medium. A neural network may be composed of a set of interconnected computational units, which may generally be referred to as nodes. These nodes may also be referred to as neurons. A neural network is composed of at least one node.

[0115] The data structure may include data input to a neural network. The data structure including the data input to the neural network may be stored on a computer-readable medium. The data input to the neural network may include training data input during the neural network training process and / or input data input to the neural network after training has been completed. The data input to the neural network may include data that has undergone preprocessing and / or data that is the target of preprocessing. Preprocessing may include a data processing process for inputting data to the neural network. Accordingly, the data structure may include data that is the target of preprocessing and data generated by the preprocessing. The above-described data structure is merely an example, and the present disclosure is not limited thereto.

[0116] The data structure may include weights of the neural network. (In this specification, the terms "weight" and "parameter" may be used interchangeably.) The data structure including the weights of the neural network may be stored in a computer-readable medium. The neural network may include a plurality of weights. The weights may be variable and may be varied by a user or an algorithm so that the neural network can perform a desired function. For example, when one or more input nodes are interconnected to one output node by respective links, the output node may determine a data value output from the output node based on values ​​input to the input nodes connected to the output node and weights set for links corresponding to each input node. The above-described data structure is merely an example, and the present disclosure is not limited thereto.

[0117] By way of example and not limitation, the weights may include weights that vary during the neural network training process and / or weights that have completed neural network training. The weights that vary during the neural network training process may include weights at the start of the training cycle and / or weights that vary during the training cycle. The weights that have completed neural network training may include weights that have completed the training cycle. Accordingly, a data structure including the weights of a neural network may include a data structure including weights that vary during the neural network training process and / or weights that have completed neural network training. Therefore, the above-described weights and / or combinations of each weight are included in the data structure including the weights of a neural network. The above-described data structures are merely examples and the present disclosure is not limited thereto.

[0118] A data structure including neural network weights can be stored in a computer-readable storage medium (e.g., memory, hard disk) after going through a serialization process. Serialization can be a process of converting a data structure into a form that can be stored on the same or different computing devices and later reconstructed and used. A computing device can serialize the data structure to transmit and receive data over a network. The serialized data structure including neural network weights can be reconstructed on the same or different computing devices through deserialization. The data structure including neural network weights is not limited to serialization. Furthermore, the data structure including neural network weights can include a data structure that increases computational efficiency while minimizing the use of computing device resources (e.g., a B-Tree, a Trie, an m-way search tree, an AVL tree, a Red-Black Tree in nonlinear data structures). The foregoing is merely an example, and the present disclosure is not limited thereto.

[0119] The data structure may include hyperparameters of a neural network. Furthermore, the data structure including the hyperparameters of the neural network may be stored on a computer-readable medium. The hyperparameters may be variables that can be varied by the user. The hyperparameters may include, for example, a learning rate, a cost function, the number of learning cycle repetitions, weight initialization (e.g., setting a range of weight values ​​to be subject to weight initialization), and the number of hidden units (e.g., the number of hidden layers, the number of nodes in the hidden layer). The above-described data structure is merely an example, and the present disclosure is not limited thereto.

[0120]

[0121] FIG. 6 is a simplified, general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented.

[0122] Although the present disclosure has been described above as being generally implemented by a computing device, those skilled in the art will appreciate that the present disclosure may also be implemented in combination with computer-executable instructions and / or other program modules that may be executed on one or more computers and / or as a combination of hardware and software.

[0123] Generally, program modules include routines, programs, components, data structures, and the like that perform specific tasks or implement specific abstract data types. Furthermore, those skilled in the art will appreciate that the methods of the present disclosure can be implemented with other computer system configurations, including single-processor or multiprocessor computer systems, minicomputers, mainframe computers, as well as personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, and the like, each of which may be operatively connected to one or more associated devices.

[0124] The described embodiments of the present disclosure can also be practiced in distributed computing environments, where certain tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

[0125] Computers typically include a variety of computer-readable media. Computer-readable media can be any media that can be accessed by a computer, and includes both volatile and nonvolatile media, transitory and non-transitory media, removable and non-removable media. By way of example, and not limitation, computer-readable media can include computer-readable storage media and computer-readable transmission media. Computer-readable storage media includes both volatile and nonvolatile media, transitory and non-transitory media, removable and non-removable media implemented in any method or technology for storing information such as computer-readable instructions, data structures, program modules, or other data. Computer-readable storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital video disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be accessed by a computer and used to store the desired information.

[0126] Computer-readable transmission media typically includes any information delivery media that embodies computer-readable instructions, data structures, program modules, or other data in a modulated data signal, such as a carrier wave or other transport mechanism. The term modulated data signal means a signal that has one or more of its characteristics set or changed so as to encode information in the signal. By way of example, and not limitation, computer-readable transmission media includes wired media, such as a wired network or direct-wired connection, and wireless media, such as acoustic, RF, infrared, or other wireless media. Combinations of any of the above are also intended to be included within the scope of computer-readable transmission media.

[0127] An exemplary environment for implementing various aspects of the present disclosure is illustrated, including a computer (1102), which includes a processing unit (1104), system memory (1106), and a system bus (1108). The system bus (1108) connects system components, including but not limited to the system memory (1106), to the processing unit (1104). The processing unit (1104) may be any of a variety of commercially available processors. Dual processors and other multiprocessor architectures may also be utilized as the processing unit (1104).

[0128] The system bus (1108) may be any of several types of bus structures that may be additionally interconnected to a memory bus, a peripheral bus, and a local bus using any of a variety of commercial bus architectures. The system memory (1106) includes read-only memory (ROM) (1110) and random access memory (RAM) (1112). A basic input / output system (BIOS) is stored in non-volatile memory (1110), such as ROM, EPROM, or EEPROM, and includes basic routines that help transfer information between components within the computer (1102), such as during start-up. The RAM (1112) may also include high-speed RAM, such as static RAM, for caching data.

[0129] The computer (1102) also includes an internal hard disk drive (HDD) (1114) (e.g., EIDE, SATA) - which may also be configured for external use within a suitable chassis (not shown), a magnetic floppy disk drive (FDD) (1116) (e.g., for reading from or writing to a removable diskette (1118)), and an optical disk drive (1120) (e.g., for reading from or writing to a CD-ROM disk (1122) or other high-capacity optical media such as a DVD). The hard disk drive (1114), the magnetic disk drive (1116), and the optical disk drive (1120) may be connected to the system bus (1108) by a hard disk drive interface (1124), a magnetic disk drive interface (1126), and an optical drive interface (1128), respectively. The interface (1124) for implementing an external drive includes at least one or both of Universal Serial Bus (USB) and IEEE 1394 interface technologies.

[0130] These drives and their associated computer-readable media provide non-volatile storage of data, data structures, computer-executable instructions, and the like. In the case of the computer (1102), the drives and media correspond to storing any data in a suitable digital format. While the description of computer-readable media above refers to HDDs, removable magnetic disks, and removable optical media such as CDs or DVDs, those of ordinary skill in the art will appreciate that other types of computer-readable media, such as zip drives, magnetic cassettes, flash memory cards, cartridges, and the like, may also be used in the exemplary operating environment, and that any such media may contain computer-executable instructions for performing the methods of the present disclosure.

[0131] A number of program modules, including an operating system (1130), one or more application programs (1132), other program modules (1134), and program data (1136), may be stored in the drive and RAM (1112). All or portions of the operating system, applications, modules, and / or data may also be cached in RAM (1112). It will be appreciated that the present disclosure may be implemented in various commercially available operating systems or combinations of operating systems.

[0132] A user may enter commands and information into the computer (1102) via one or more wired / wireless input devices, such as a keyboard (1138) and a pointing device such as a mouse (1140). Other input devices (not shown) may include a microphone, an IR remote control, a joystick, a game pad, a stylus pen, a touch screen, and the like. These and other input devices are often connected to the processing unit (1104) via an input device interface (1142) that is connected to the system bus (1108), but may be connected by other interfaces such as a parallel port, an IEEE 1394 serial port, a game port, a USB port, an IR interface, and the like.

[0133] A monitor (1144) or other type of display device is also connected to the system bus (1108) via an interface, such as a video adapter (1146). In addition to the monitor (1144), the computer typically includes other peripheral output devices (not shown), such as speakers, a printer, and so on.

[0134] The computer (1102) may operate in a networked environment using logical connections to one or more remote computers, such as remote computer(s) (1148), via wired and / or wireless communications. The remote computer(s) (1148) may be a workstation, a computing device computer, a router, a personal computer, a portable computer, a microprocessor-based entertainment device, a peer device, or other conventional network node, and generally include many or all of the components described for the computer (1102), although for simplicity, only the memory storage device (1150) is shown. The logical connections shown include wired / wireless connections to a local area network (LAN) (1152) and / or a larger network, such as a wide area network (WAN) (1154). Such LAN and WAN networking environments are common in offices and companies and facilitate enterprise-wide computer networks, such as intranets, all of which may be connected to a worldwide computer network, such as the Internet.

[0135] When used in a LAN networking environment, the computer (1102) is connected to a local network (1152) via a wired and / or wireless communication network interface or adapter (1156). The adapter (1156) may facilitate wired or wireless communications to the LAN (1152), which may also include a wireless access point installed therein for communicating with the wireless adapter (1156). When used in a WAN networking environment, the computer (1102) may include a modem (1158), be connected to a communications computing device on the WAN (1154), or have other means of establishing communications over the WAN (1154), such as via the Internet. The modem (1158), which may be internal or external and wired or wireless, is connected to the system bus (1108) via a serial port interface (1142). In a networked environment, program modules or portions thereof described for the computer (1102) may be stored in a remote memory / storage device (1150). It will be appreciated that the network connections depicted are exemplary and other means of establishing a communications link between the computers may be used.

[0136] The computer (1102) operates to communicate with any wireless device or object that is arranged and operates via wireless communication, such as a printer, a scanner, a desktop and / or portable computer, a portable data assistant (PDA), a communication satellite, any equipment or location associated with a radio-detectable tag, and a telephone. This includes at least Wi-Fi and Bluetooth wireless technologies. Accordingly, the communication may be a predefined structure as in a conventional network, or may simply be an ad hoc communication between at least two devices.

[0137] Wi-Fi (Wireless Fidelity) enables connections to the Internet and other devices without wires. Wi-Fi is a wireless technology that allows devices, such as computers, to send and receive data anywhere within the coverage area of ​​a base station, both indoors and outdoors, similar to cell phones. Wi-Fi networks use wireless technologies called IEEE 802.11 (a, b, g, etc.) to provide secure, reliable, and high-speed wireless connections. Wi-Fi can be used to connect computers to each other, to the Internet, and to wired networks (using IEEE 802.3 or Ethernet). Wi-Fi networks can operate in the unlicensed 2.4 and 5 GHz radio bands, at data rates of, for example, 11 Mbps (802.11a) or 54 Mbps (802.11b), or in products that include both bands (dual-band).

[0138] Those skilled in the art will appreciate that information and signals may be represented using any of a variety of different technologies and techniques. For example, the data, instructions, commands, information, signals, bits, symbols, and chips referenced in the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof.

[0139] Those skilled in the art will appreciate that the various illustrative logical blocks, modules, processors, means, circuits, and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, various forms of programs or design code (referred to herein, for convenience, as software), or a combination of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Those skilled in the art may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

[0140] The various embodiments presented herein can be implemented as a method, apparatus, or article of manufacture using standard programming and / or engineering techniques. The term article of manufacture includes a computer program, carrier, or media accessible from any computer-readable storage device. For example, computer-readable storage media include, but are not limited to, magnetic storage devices (e.g., hard disks, floppy disks, magnetic strips, etc.), optical disks (e.g., CDs, DVDs, etc.), smart cards, and flash memory devices (e.g., EEPROMs, cards, sticks, key drives, etc.). Furthermore, various storage media presented herein include one or more devices and / or other machine-readable media for storing information.

[0141] It should be understood that the specific order or hierarchy of steps in the presented processes is merely an example of exemplary approaches. It should be understood that the specific order or hierarchy of steps in the processes may be rearranged within the scope of the present disclosure based on design priorities. The appended method claims provide elements of various steps in a sample order, but are not intended to be limited to the specific order or hierarchy presented.

[0142] The description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the embodiments disclosed herein, but is to be construed in the broadest scope consistent with the principles and novel features disclosed herein.

[0143] As described above, the relevant contents have been described in the best form for carrying out the invention.

Claims

1. A method for predicting a dangerous situation by analyzing an image, performed by a computing device. Step of acquiring an image; A step of generating a converted image by converting an object included in the image into a virtual object; and A step of predicting a risk situation based on the converted image including the converted virtual object by utilizing a risk prediction model. Including, method.

2. In paragraph 1, The step of generating the converted image by converting the object included in the image into the virtual object is as follows: A step of recognizing an object included in the above image; A step of extracting key points of the above recognized object; A step of predicting a skeleton of the recognized object based on the above feature points; and A step of converting the object into the virtual object based on the predicted skeleton. Including, method.

3. In paragraph 1 The step of generating the converted image by converting the object included in the image into the virtual object is as follows: A step of recognizing an object included in the above image; A step of extracting feature information of the above recognized object; and A step of converting a recognized object into a virtual object including volume information based on feature information of the recognized object by utilizing a virtual object conversion model. Including, method.

4. In paragraph 3, A virtual object containing the above volume information, A skeleton element representing the physical movements of the above recognized object; and A virtual body element that represents the volume of the above recognized object. Including, method.

5. In paragraph 1, The above risk prediction model is, Actions to obtain behavioral information in response to a risk situation; An operation of simulating action information corresponding to the above-mentioned risk situation based on a virtual object and obtaining a simulation image based on a virtual object; and An operation of augmenting learning data by including the above virtual object-based simulation image in the learning data of the risk prediction model. A model learned based on, method.

6. In paragraph 5, The action of obtaining behavioral information in response to the above risk situation is: The action of extracting target keywords from text type information; An operation to extract target keywords from image type information by utilizing a multimodal model; or An operation that extracts target keywords from voice type information by utilizing the STT (Speech-To-Text) model. Including, method.

7. In paragraph 6, The above target keywords are included in the prompt for the language model, The above prompt includes a combination of multiple target keywords extracted from different types of information, The action of obtaining behavioral information in response to the above risk situation is: An action of inputting the above prompt into the above language model and obtaining a scenario for action information corresponding to the risk situation based on the input prompt. Including, method.

8. In paragraph 7, The operation of obtaining the above virtual object-based simulation image is as follows: An action of simulating a virtual object based on the acquired scenario in a virtual space; and An operation of generating a simulation image based on the virtual object based on the movement information of the virtual object obtained from the above-mentioned simulated operation. Including, method.

9. In paragraph 6, The above target keywords are included in the prompt for the generative model, The above prompt contains a combination of multiple keywords extracted from different types of information, The operation of obtaining the above virtual object-based simulation image is as follows: An operation of generating a simulation image based on the virtual object based on the prompt by utilizing the generative model. Including, method.

10. In paragraph 9, The operation of generating the simulation image based on the virtual object based on the prompt by utilizing the generative model is as follows. Including an operation of applying information about the type of the generated virtual object as condition information to the generative model. method.

11. A computer program stored in a computer-readable storage medium, wherein the computer program, when executed on one or more processors, causes the one or more processors to perform the following operations to analyze an image and predict a dangerous situation, the operations being: The act of acquiring an image; An operation of converting an object included in the above image into a virtual object and generating a converted image; and An operation for predicting a risk situation based on the converted image including the converted virtual object by utilizing a risk prediction model. Including, A computer program stored on a computer-readable storage medium.

12. As a computing device, at least one processor; and Memory Including, At least one processor of the above, Acquire the image; Converting an object included in the above image into a virtual object to generate a converted image; and By utilizing a risk prediction model, a risk situation is predicted based on the converted image including the converted virtual object. device.

Images