KR20230050762A - Apparatus for disseminating an emergency situation based on network separation and method therefor - Google Patents

Abstract

A device for disseminating emergency situations is configured to perform a plurality of operations in which weights between a plurality of layers are applied to a field image through a detection network including a plurality of layers connected with learned weights to calculate an output value which indicates with probability whether a situation in the field image is a normal situation or an emergency situation, and includes a detection unit which detects a scene video as the emergency situation video, if the probability indicates that the situation in the scene video is the emergency situation.

Description

Apparatus for disseminating an emergency situation based on network separation and method therefor}

The present invention relates to emergency propagation technology, and more particularly, to an apparatus and method for propagating an emergency situation based on network separation.

Various disasters such as typhoons, floods, fires, and infectious diseases occur frequently. Although the on-site situation for such a disaster is collected through various CCTVs, the network is separated for security management of the internal network, so it cannot be provided to the response team responding to such a disaster.

Korean Patent Publication No. 2015-0018975 (published on February 25, 2015)

An object of the present invention is to provide a device and method for propagating an emergency situation based on network separation.

An apparatus for propagating an emergency situation according to a preferred embodiment of the present invention for achieving the above object is a detection network including a plurality of layers connected to learned weights when receiving an on-site image from a surveillance video device. Through this, a plurality of operations are performed to which a plurality of inter-layer weights are applied to the field image to calculate an output value indicating whether the situation of the field image is a normal situation or an emergency situation with a probability, and the probability is the situation of the field image If it indicates an emergency situation, it includes a detection unit for detecting the scene image as an emergency situation image.

When the device receives authentication information including an encryption code for authentication, the number of authentication terminals, and an authentication period from any one representative terminal representing a plurality of terminals, the authentication is performed by comparing it with pre-stored authentication confirmation information. include more wealth Here, the authentication is characterized in that the representative terminal authenticates the qualification to receive the emergency situation video and the qualification to transmit the emergency situation video to other terminals of the number of the authenticated terminals during the authentication period.

The apparatus further includes an image processing unit for detecting an additional image corresponding to the emergency situation image. Here, the additional video is characterized in that it includes a field image of a normal situation and a field image of an emergency situation among past field images corresponding to the emergency situation image.

The detection network includes an input layer, a convolutional layer, a pooling layer, a first fully connected layer, a second fully connected layer, and an output layer. The input layer receives a field image, and the convolution layer receives an input field image. At least one first feature map is derived by performing a convolution operation using a first filter and an operation using an activation function, and the pooling layer applies a second filter to the at least one first feature map of the convolution layer. At least one second feature map is derived by performing a pooling operation using a pooling operation, and a plurality of first nodes of the first completed connection layer are operated by an activation function for at least one second feature map of the pooling layer to derive a plurality of first nodes. Calculate a first node value of , and the plurality of second nodes of the second fully connected layer are a plurality of second node values through an operation by an activation function for the plurality of first node values of the first fully connected layer. , and the output node of the output layer determines whether the situation of the scene image input to the input layer is normal through operation by an activation function to which weights are applied to a plurality of second node values of the second complete connection layer. Alternatively, it is characterized in that an output value indicating whether or not it is an emergency is calculated with a probability.

After preparing a field image for learning with a label set, the device inputs the field image for learning to a detection network in which learning is not completed, and the detection network performs a plurality of calculations to which weights between a plurality of layers are applied to the field image for learning Learning to perform optimization to modify the parameters of the detection network so that the loss, which is the difference between the output value and the label, is minimized through a loss function when an output value representing the probability of whether the situation of the field image is a normal situation or an emergency situation is calculated include more wealth

에 따라 손실을 산출하며, 상기 E는 손실을 나타내며, 상기 xi는 출력층의 출력값에 대응하는 레이블이고, 상기 yi는 출력층의 출력값인 것을 특징으로 한다. The learning part is a loss function

The loss is calculated according to , wherein E represents the loss, xi is a label corresponding to the output value of the output layer, and yi is the output value of the output layer.

A method for propagating an emergency situation according to a preferred embodiment of the present invention for achieving the above object includes the step of receiving a field image from a surveillance video device by a detection unit, and a plurality of Calculating an output value indicating whether the situation of the field image is a normal situation or an emergency situation by performing a plurality of operations to which weights between a plurality of layers are applied to the field image through a detection network including layers; , If the detection unit indicates that the situation of the field image is an emergency situation, detecting the corresponding field image as an emergency situation image.

According to the present invention, it is possible to diagnose whether a field image is normal or abnormal based on a deep neural network.

1 is a diagram for explaining the configuration of a system for propagating an emergency situation based on network separation according to an embodiment of the present invention.
2 is a diagram for explaining the configuration of an apparatus for propagating an emergency situation based on network separation according to an embodiment of the present invention.
3 to 5 are diagrams for explaining the configuration of a detection network for propagating an emergency situation based on network separation according to an embodiment of the present invention.
6 is a flowchart illustrating a method of training a detection network to diagnose the state of an on-site image according to an embodiment of the present invention.
7 is a flowchart illustrating a method for disseminating an emergency situation based on network separation according to an embodiment of the present invention.
8 is a flowchart illustrating a method of detecting an emergency situation image representing an emergency situation from an on-site image using a detection network according to an embodiment of the present invention.

Prior to the detailed description of the present invention, the terms or words used in this specification and claims described below should not be construed as being limited to a common or dictionary meaning, and the inventors should use their own invention in the best way. It should be interpreted as a meaning and concept corresponding to the technical idea of the present invention based on the principle that it can be properly defined as a concept of a term for explanation. Therefore, the embodiments described in this specification and the configurations shown in the drawings are only the most preferred embodiments of the present invention, and do not represent all of the technical ideas of the present invention, so various equivalents that can replace them at the time of the present application. It should be understood that there may be water and variations.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. At this time, it should be noted that the same components in the accompanying drawings are indicated by the same reference numerals as much as possible. In addition, detailed descriptions of well-known functions and configurations that may obscure the gist of the present invention will be omitted. For the same reason, some components in the accompanying drawings are exaggerated, omitted, or schematically illustrated, and the size of each component does not entirely reflect the actual size.

First, a system for propagating an emergency situation based on network separation according to an embodiment of the present invention will be described. 1 is a diagram for explaining the configuration of a system for propagating an emergency situation based on network separation according to an embodiment of the present invention. Referring to FIG. 1 , an emergency situation propagation system according to an embodiment of the present invention includes a control server 10, a plurality of surveillance video devices 20, and a plurality of terminals 30.

The terminal 30 is a device used by an agent dispatched to a site where an emergency situation occurs (eg, a firefighter when the emergency situation is a fire).

The surveillance imaging device 20 is for continuously photographing a field situation and generating a field image. The monitoring video device 20 provides the generated field video to the control server 10 . This monitoring video device 20 may be a closed-circuit television (CCTV).

The control server 10 is connected to the monitoring video device 20 through an intra-network, and is connected to the terminal 30 through an inter-network. The control server 10 may determine whether or not an emergency situation has occurred from the field image received from the monitoring video device 20, and may provide the field image to the terminal 30 when an emergency situation occurs.

Next, an apparatus for propagating an emergency situation based on network separation according to an embodiment of the present invention will be described. 2 is a diagram for explaining the configuration of an apparatus for propagating an emergency situation based on network separation according to an embodiment of the present invention. 3 to 5 are diagrams for explaining the configuration of a detection network for propagating an emergency situation based on network separation according to an embodiment of the present invention. Referring to FIG. 2 , the control server 10 includes a communication unit 11 , an input unit 12 , a display unit 13 , a storage unit 14 and a control unit 15 .

The communication unit 11 is for receiving an on-site image from the monitoring video device 20 and transmitting an emergency situation image, which is an image of a site where an emergency situation occurs among the on-site images, to the terminal 30 . The communication unit 11 may be connected to the monitoring video device 20 through wireless communication, wired communication, etc. as necessary to receive on-site images.

The input unit 12 receives a user's key manipulation for controlling various functions and operations of the control server 10, generates an input signal, and transmits it to the control unit 15. The input unit 12 may exemplify a keyboard, a mouse, and the like. The input unit 12 may include a power key for power on/off, character keys, number keys, direction keys, and the like. The function of the input unit 12 may be performed on the display unit 13 when the display unit 13 is implemented as a touch screen, and when all functions can be performed only by the display unit 13, the input unit 12 may be omitted. there is.

The display unit 13 visually provides the menu of the control server 10, input data, function setting information, and other various information to the user. In particular, according to an embodiment of the present invention, the control unit 15 may perform analysis on the field image to detect the field image in which an emergency situation has occurred. In this case, the display unit 13 may be displayed through the display unit 13 by distinguishing the site image where the emergency situation occurs from other site images under the control of the control unit 15 . The display unit 13 performs a function of outputting screens such as a booting screen, a standby screen, a menu screen, and the like of the control server 10 . The display unit 13 may be formed of a Liquid Crystal Display (LCD), Organic Light Emitting Diodes (OLED), Active Matrix Organic Light Emitting Diodes (AMOLED), or the like.

The storage unit 14 serves to store various types of data, applications, and various data configured according to the operation of the control server 10 necessary for the operation of the control server 10. This storage unit 14 may largely include a program area and a data area. The program area may store an operating system (OS) for booting and operation of the control server 10, an application according to an embodiment of the present invention, and the like. The data area may store an on-site image according to an embodiment of the present invention. Various types of data stored in the storage unit 14 may be deleted, changed, or added according to user manipulation.

The control unit 15 may control the overall operation of the control server 10 and the signal flow between internal blocks of the control server 10, and perform a data processing function of processing data. The control unit 15 may be a central processing unit (CPU), a digital signal processor (DSP), or the like. In addition, the controller 15 may further include an image processor or a graphic processing unit (GPU). The control unit 15 includes a learning unit 100, a detection unit 200, an image processing unit 300 and an authentication unit 400.

The learning unit 100 performs a series of processes for learning a detection network (DN), which is a deep neural network (DNN) according to an embodiment of the present invention. When learning of the detection network DN is completed, the learning unit 100 provides the detection network DN for which learning has been completed to the detection unit 200 . The learning process of the learning unit 100 will be described in more detail below.

The detection unit 200 includes a detection network DN, and the detection network DN may be a deep convolutional neural network (DCNN). The detection network (DN) of the present invention includes a plurality of layers. That is, the detection network DN includes an input layer IL, at least one pair of convolutional layers CL and a pooling layer PL, at least one fully connected layer FL1 and FL2, and an output layer OL. includes

Upon receiving the field image, the detection unit 200 performs a plurality of calculations to which a plurality of inter-layer weights are applied to the field image through the detection network DN to determine whether the situation occurring in the field image is a normal situation or an emergency situation. Calculate the output value representing the probability.

According to an embodiment, as shown in FIG. 3, the detection network DN sequentially includes an input layer IL, a convolution layer GCL, a pooling layer GPL, a first fully connected layer GFL1, It includes a second fully connected layer (GFL2) and an output layer (GOL).

The convolution layer (CL) and the pooling layer (PL) are composed of at least one feature map (FM). The feature map (FM) is generated as a result of performing an operation with weights applied to the values of the previous layer. These weights are applied through a filter or kernel (W). In an embodiment of the present invention, the first filter W1 is used for the convolution operation of the convolution layer CL, and the second filter W2 is used for the pooling operation of the pooling layer PL.

The input layer IL serves as a buffer for receiving field images. The input layer IL may receive an on-site image in units of pixels.

The convolution layer (GCL) derives at least one first feature map (FM1) by performing a convolution operation using a first filter (W1) and an operation by an activation function on the input field image.

Next, the pooling layer PL performs a pooling (or sub-sampling) operation using the second filter W2 on at least one first feature map FM1 of the convolution layer CL to obtain at least one feature map FM1. A second feature map (FM2) is derived.

The first completed connection layer FL1 includes a plurality of first nodes f1 to fm. The plurality of first nodes f1 to fm of the first fully connected layer FL1 are operated by an activation function with respect to at least one second feature map FM2 of the pooling layer PL. Calculate the value.

The second completed connection layer FL2 includes a plurality of second nodes g1 to gn. The plurality of second nodes f1 to fm of the second fully-connected layer FL2 generate a plurality of second node values through an activation function operation with respect to the plurality of first node values of the first fully-connected layer GFL1. yields

Activation functions used in the aforementioned convolutional layer (CL) and the first and second fully connected layers (FL1, FL2) are sigmoid, hyperbolic tangent (tanh), and exponential linear unit (ELU). , Rectified Linear Unit (ReLU), Leakly ReLU, Maxout, Minout, Softmax, etc. may be exemplified. Any one of these activation functions can be selected and used.

Referring to FIGS. 4 and 5 , the output layer OL includes two output nodes N and A. Each of the plurality of second nodes g1 to gn of the second complete connection layer FL2 is a channel (indicated by a dotted line) having a weight (W) and is connected to the output nodes N and A of the output layer OL. do. In other words, a plurality of second node values of the plurality of second nodes g1 to gn are input to the output nodes N and A, respectively, with weights applied thereto. Accordingly, the output nodes N and A of the output layer OL are applied to the input layer IL through an activation function operation for a plurality of second node values to which the weights of the second complete connection layer FL2 are applied. A probability indicating whether a situation occurring in the input site image is normal or abnormal is calculated.

Meanwhile, a node N according to an embodiment of the present invention is shown in FIG. 5 . This node (N) will be described assuming that it is one of the output nodes (N, A) of the detection network (DN), but the description of this node (N) is the first node (f1) included in the detection network (DN). to fm), second nodes (f1 to fm) and output nodes (N, A) and all other nodes of the present invention.

Node N is an input signal x = [x1, x2, ... , xn] with weights w=[w1, w2, … , wn], take the function F as the result. Here, function F is an activation function. At this time, even when the input is the same, the output becomes a different value according to the weight (W). That is, the output of each node is as shown in Equation 1 below.

의 값이 임계치 보다 작을 때 해당 노드가 활성화되지 않도록 하는 역할을 한다. 예를 들면, 노드(N)의 이전 계층의 노드가 3개라고 가정한다. 이에 따라, 해당 노드에 대해 3개의 입력(n=3) X1, X2, X3과 3개의 가중치 W1, W2, W3이 존재한다. 노드(N)는 3개의 입력 X1, X2, X3에 대응하는 가중치 W1, W2, W3을 곱한 값을 입력받고, 모두 합산한 후, 합산된 값을 전달 함수에 대입하여 출력을 산출한다. 구체적으로, 입력 [X1, X2, X3] = 0.5, -0.3, 0이라고 가정하고, 가중치 w=[W1, W2, W3] = 4, 5, 2라고 가정한다. 또한, 설명의 편의를 위하여 전달 함수는 'sgn()'이라고 가정하면, 다음과 같이 출력값이 산출된다. Among the unexplained parameters, b is a threshold, and this threshold is

It serves to prevent the corresponding node from being activated when the value of is smaller than the threshold. For example, it is assumed that there are 3 nodes in the hierarchy prior to the node N. Accordingly, there are three inputs (n=3) X1, X2, and X3 and three weights W1, W2, and W3 for the corresponding node. The node N receives a value obtained by multiplying three inputs X1, X2, and X3 by weights W1, W2, and W3, sums them all, and substitutes the summed value into a transfer function to calculate an output. Specifically, assume that inputs [X1, X2, X3] = 0.5, -0.3, 0, and weights w = [W1, W2, W3] = 4, 5, 2. In addition, assuming that the transfer function is 'sgn()' for convenience of explanation, the output value is calculated as follows.

x1 × w1 = 0.5 × 4 = 2

x2 × w2 = -0.3 × 5 = -1.5

x3 × w3 = 0 × 2 = 0

2 + (-1.5) + 0 = 0.5

sgn(0.5) = 1

In this way, any one node of the detection network (DN) of the present invention receives a value obtained by applying a weight to the node value of the previous layer, sums them, performs an operation according to an activation function, and transmits the result as an input to the next layer. forward to

Again, referring to FIG. 4 , each of the two output nodes N and A of the output layer OL corresponds to whether a situation occurring in the field image is a normal situation or an abnormal situation. That is, the first output node N corresponds to a normal situation, and the second output node A corresponds to an abnormal situation. Accordingly, the output value of the first output node N is the probability that a situation occurring in the field image input to the input layer IL is a normal situation, and the output value of the second output node A is the input layer IL ) represents the probability that a situation occurring in the field image input is an abnormal situation.

Each of the output nodes N and A is a plurality of second node values input from a plurality of second nodes g1 to gn x = [x1, x2, . , xn] with weights w=[w1, w2, … , wn] is applied, and an activation function F is applied to the result to calculate an output value. For example, if the output values of the first and second output nodes N and A are 0.201 and 0.799, respectively, the probability that the situation of the field image is normal is 20%, and the situation of the field image is abnormal. ) indicates an 80% probability. In this way, if the detection network DN outputs probabilities (0.201, 0.799), the detection unit 200 may determine that the situation of the field image is an emergency situation (abnormal) according to these probabilities (0.201, 0.799). That is, if the probability (0.201, 0.799) output by the detection network DN indicates that the situation of the field image is an emergency situation, the detection unit 200 may detect the corresponding field image as an emergency situation image.

Referring back to FIG. 2 , the image processor 300 detects an additional image corresponding to an emergency situation image among a plurality of field images stored in the storage unit 14 . The additional video includes an on-site video in a normal situation and an on-site video in an emergency situation among past on-site images corresponding to the emergency video. The image processing unit 300 may detect additional video from the storage unit 14 and provide the additional video detected through the communication unit 11 to the terminal 30 together with the emergency situation video. Accordingly, a user of the terminal 30, for example, a firefighter, can easily determine the current level of danger, identification of a shadow area, and the like.

The authentication unit 400 is for authenticating the target terminal 30 to provide an emergency situation image. In particular, the authentication unit 400 may provide authentication on behalf of a plurality of other terminals 30 to any one terminal 30, that is, a representative terminal. In the case of such authentication, authentication may be performed by applying an encryption code for authentication, the number of authentication terminals 30, and an authentication period. The authentication unit 400 stores authentication confirmation information in the storage unit 14, and the authentication confirmation information includes an encryption code, the number of authentication terminals 30 corresponding to the encryption code, and an authentication period. Authentication by the authentication unit 400 means that the representative terminal certifies the qualification to receive the emergency situation video and the qualification to transmit the emergency situation video to other terminals of the number of certified terminals during the authentication period.

Next, a method for propagating an emergency situation based on network separation according to an embodiment of the present invention will be described. Learning of the detection network (DN) is required to diagnose the state of the field image. These methods will be described. First, a method for learning the detection network DN will be described. 6 is a flowchart illustrating a method of training a detection network to diagnose the state of an on-site image according to an embodiment of the present invention.

Referring to FIG. 6 , the learning unit 100 prepares a field image for learning in step S110. The field image for learning is an image that can be used to know whether the situation of the field image is a normal situation or an emergency situation.

Then, the learning unit 100 sets a label for the field image for learning in step S120. Here, the label may be a one-hot encoding vector indicating whether it is a normal situation or an emergency situation. At this time, a classification label [1, 0] is assigned to the training field image known as a normal situation in response to the output nodes (N, A), and the training field image known as an emergency situation is classified in response to the output node (N, A) Label [0, 1].

Next, the learning unit 100 inputs the corresponding field image for learning to the detection network DN in which learning is not completed in step S130. Then, the detection network DN performs a plurality of calculations to which weights between a plurality of layers are applied in step S140 to calculate an output value indicating whether the situation of the field image is a normal situation or an emergency situation with a probability.

Then, the learning unit 100 modifies the parameters of the detection network (DN), that is, the weight (w), the threshold (b), etc., so that the loss, which is the difference between the output value and the label, is minimized through the loss function in step S150. optimization can be performed. At this time, the learning unit 100 may obtain a loss through a loss function such as Equation 2 below.

Here, E represents loss. In addition, xi is a label corresponding to the output value of the output layer, and yi represents the output value of the output layer.

Steps S120 to S150 described above are repeatedly performed using a plurality of different learning data, and such repetition may be performed until a preset accuracy is reached through an evaluation index.

Next, a method of diagnosing the state of an on-site image using the detection network (DN) for which learning has been completed in the above-described method will be described. 7 is a flowchart illustrating a method for disseminating an emergency situation based on network separation according to an embodiment of the present invention.

Referring to FIG. 7 , the plurality of monitoring video devices 20 continuously captures on-site images in step S210 and provides them to the control server 10 through the internal network. Then, the control server 10

Meanwhile, in FIG. 7 , a first terminal 31 and a plurality of second terminals 32 are one terminal group, and the first terminal 31 is a terminal 30 that performs authentication on behalf of one authentication group. am.

The authentication unit 400 of the control server 10 may receive authentication information from the first terminal 31 in step S220. This authentication information may include an encryption code for authentication, the number of authentication terminals 30, and an authentication period.

The authentication unit 400 may perform authentication by checking the authentication confirmation information stored in the storage unit 14, the encryption code for authentication, the number of authentication terminals 30, and the authentication period in step S230. The authentication confirmation information includes an encryption code, the number of authentication terminals 30 corresponding to the encryption code, and an authentication period, and the authentication unit 400 performs authentication through whether the authentication information and the authentication confirmation information are the same.

If authentication is successful, the detection unit 200 of the control server 10 detects an abnormal situation image, which is an image of an abnormal situation, among a plurality of on-site images using the detection network (DN) in step S240.

Then, the image processing unit 300 detects an additional image corresponding to the emergency situation image among the plurality of field images stored in the storage unit 14 in step S250. The additional video includes an on-site video in a normal situation and an on-site video in an emergency situation among past on-site images corresponding to the emergency video. This step S250 may optionally not be performed. Subsequently, the image processing unit 300 transmits the emergency situation image to the first terminal 31 through the communication unit 11 in step S260. At this time, the image processing unit 300 may transmit the detected additional video along with the emergency situation video to the first terminal 31 . For example, by delivering not only the current real-time video of the emergency situation to the terminal 30 of the firefighter dispatched to the scene, but also the site video of the abnormal situation and the scene video of the normal situation among the corresponding past field images. , the current risk level, identification of shaded areas, etc. can be easily determined.

Since the first terminal 31 has previously been authenticated with the number of verifiable terminals 30 and the authentication period in step S230, another terminal of the number of authentication terminals 30 during the authentication period in step S270, that is, the second terminal Emergency situation video can be transmitted to (32). At this time, the first terminal 31 may transmit the detected additional video along with the emergency situation video to the plurality of second terminals 32 . For example, among a plurality of firefighters, only the representative firefighter's terminal 30, that is, the first terminal 31, performs authentication with the control server 10 to receive an emergency video, and another firefighter's terminal in the vicinity s, that is, the plurality of second terminals 32 can connect to the first terminal 31 of the representative firefighter to receive an emergency situation image without an additional authentication procedure.

Next, the above-described step S240 will be described in more detail. 8 is a flowchart illustrating a method of detecting an emergency situation image representing an emergency situation from an on-site image using a detection network according to an embodiment of the present invention.

Referring to FIG. 8 , field images are continuously received from the surveillance video device 20 of the control server 10 through the communication unit 11 . Accordingly, the detection unit 200 receives an input field image in step S310.

In step S320, the detection unit 200 performs a plurality of operations in which a plurality of inter-layer weights are applied to the field image through the detection network (DN) to determine whether there is an abnormality in the field image included in the field image. Calculates an output value expressed as a probability.

The operation of the detection network (DN) in step S320 will be described in more detail as follows.

When the input layer (IL) receives a field image, the convolution layer (GCL) performs a convolution operation using the first filter (W1) and an operation by an activation function on the input field image to obtain at least one A first feature map FM1 is derived.

Next, the pooling layer PL performs a pooling (or sub-sampling) operation using the second filter W2 on at least one first feature map FM1 of the convolution layer CL to obtain at least one feature map FM1. A second feature map (FM2) is derived.

Next, the plurality of first nodes f1 to fm of the first complete connection layer FL1 are operated by an activation function with respect to at least one second feature map FM2 of the pooling layer PL. 1 Calculate the node value.

Subsequently, the plurality of second nodes f1 to fm of the second fully-connected layer FL2 are operated by an activation function on the plurality of first node values of the first fully-connected layer GFL1, so that a plurality of second nodes f1 to fm are generated. Calculate the node value.

The output nodes (N, A) of the output layer (OL) are input to the input layer (IL) through an operation by an activation function to which weights are applied to a plurality of second node values of the second complete connection layer (FL2). An output value, which is a probability indicating whether the video situation is normal or abnormal, is calculated.

As described above, when the output value is calculated, the detection unit 200 determines whether the situation of the field image is normal or abnormal according to the probability of the output value of the detection network DN in step S340. When it is determined that it is an emergency situation (abnormal), the scene image is detected as an emergency situation image. For example, if the detection network DN outputs probabilities (0.211, 0.789), the detection unit 200 determines that the situation of the corresponding site image is an emergency situation (abnormal) according to these probabilities (0.211, 0.789), and the corresponding site The video is detected as an emergency situation video.

On the other hand, the method according to the embodiment of the present invention described above may be implemented in the form of a program readable by various computer means and recorded on a computer-readable recording medium. Here, the recording medium may include program commands, data files, data structures, etc. alone or in combination. Program instructions recorded on the recording medium may be those specially designed and configured for the present invention, or those known and usable to those skilled in computer software. For example, recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magneto-optical media such as floptical disks ( It includes hardware devices specially configured to store and execute program instructions, such as magneto-optical media and ROM, RAM, flash memory, etc. Examples of program commands may include high-level language wires that can be executed by a computer using an interpreter, as well as machine language wires such as those produced by a compiler. These hardware devices may be configured to act as one or more software modules to perform the operations of the present invention, and vice versa.

The present invention has been described above using several preferred examples, but these examples are illustrative and not limiting. As such, those skilled in the art to which the present invention belongs will understand that various changes and modifications can be made according to the doctrine of equivalents without departing from the spirit of the present invention and the scope of rights set forth in the appended claims.

10: control server 11: communication department
12: input unit 13: display unit
14: storage unit 15: control unit
20: surveillance video device 30: terminal
100: learning unit 200: detection unit
300: image processing unit 400: authentication unit

Claims (7)

In the apparatus for disseminating an emergency situation,
When a field image is received from a surveillance video device, a plurality of calculations are performed to apply weights between a plurality of layers to the field image through a detection network including a plurality of layers connected to the learned weights, so that the situation of the field image is changed. Calculate an output value representing the probability of whether it is a normal situation or an emergency situation,
If the probability indicates that the situation of the field image is an emergency situation, a detection unit for detecting the corresponding field image as an emergency situation image;
characterized in that it includes
A device for disseminating emergency situations. According to claim 1,
When receiving authentication information including an encryption code for authentication, the number of authentication terminals, and an authentication period from any one representative terminal representing a plurality of terminals, an authentication unit that performs authentication by comparing with pre-stored authentication confirmation information;
Including more,
Characterized in that the authentication authenticates the representative terminal's qualification for receiving an emergency situation image and the qualification for transmitting an emergency situation image to other terminals of the number of the authenticated terminals during the authentication period.
A device for disseminating emergency situations. According to claim 1,
an image processing unit detecting an additional image corresponding to the emergency situation image;
Including more,
The additional video
Characterized in that it includes a field image of a normal situation and a field image of an emergency situation among past field images corresponding to the emergency situation image
A device for disseminating emergency situations. According to claim 1,
The detection network
It includes an input layer, a convolution layer, a pooling layer, a first fully connected layer, a second fully connected layer, and an output layer,
The input layer receives an on-site image,
The convolution layer derives at least one first feature map by performing a convolution operation using a first filter and an operation by an activation function on the input field image,
The pooling layer derives at least one second feature map by performing a pooling operation using a second filter on at least one first feature map of the convolution layer;
The plurality of first nodes of the first complete connection layer calculates a plurality of first node values through an operation by an activation function for at least one second feature map of the pooling layer,
The plurality of second nodes of the second fully connected layer calculates a plurality of second node values through an activation function operation for the plurality of first node values of the first fully connected layer;
The output node of the output layer determines whether the situation of the field image input to the input layer is a normal situation or an emergency situation through an operation by an activation function to which weights are applied to a plurality of second node values of the second complete connection layer. Characterized in that for calculating an output value indicating whether or not
A device for disseminating emergency situations. According to claim 1,
The device
After preparing a field video for learning with a label set,
Input the field image for learning to the detection network where learning is not completed,
When the detection network performs a plurality of calculations to which weights between a plurality of layers are applied to the learning site image, and calculates an output value indicating whether the situation of the site image is a normal situation or an emergency situation with a probability,
Performing optimization to modify the parameters of the detection network so that the loss, which is the difference between the output value and the label, is minimized through a loss function
learning department;
characterized in that it further comprises
A device for disseminating emergency situations. According to claim 5,
The learning department
loss function

Calculate the loss according to
wherein E represents the loss,
xi is a label corresponding to an output value of an output layer,
Characterized in that the yi is the output value of the output layer
A device for disseminating emergency situations. In a method for disseminating an emergency,
Receiving an on-site image from a surveillance imaging device by a detection unit;
The detection unit performs a plurality of calculations in which weights between a plurality of layers are applied to the field image through a detection network including a plurality of layers connected to the learned weights to determine whether the situation of the field image is a normal situation or an emergency situation. Calculating an output value representing whether or not with probability; and
detecting, by the detection unit, the scene image as an emergency situation image when the probability indicates that the situation of the scene image is an emergency situation;
characterized in that it includes
How to disseminate an emergency.

Images