KR102307609B1 - Apparatus and method for detecting abnormal object and imaging device comprising the same - Google Patents

Abstract

According to an embodiment of the present invention, there is provided a data processing unit comprising: a data processing unit generating position distribution data representing a position distribution of a plurality of entities by using image data generated from an image including a plurality of entities; a motion detection unit generating motion data representing a motion of a motion object among the plurality of objects by using the generated image data; and a controller for generating abnormal entity data indicating an abnormal entity by comparing the position distribution data and the motion data, wherein the position distribution data is data in which the presence or absence of an entity is indicated as a probability for each pixel on the image data, and The motion data is data indicating whether motion exists for each pixel on the image data, and the controller accumulates the probability of the existence of the object from the location distribution data and applies it to the pixel value of the corresponding pixel, wherein motion is present in the motion data Provided is an anomaly detection apparatus for generating the abnormal entity data by initializing a pixel at the same position as a pixel.

Description

Apparatus and method for detecting anomaly, and imaging device including the same

Embodiments of the present invention relate to an apparatus and method for detecting an abnormal object, and an imaging device including the same.

As the consumption of livestock products increases, various measures are being proposed on how to efficiently manage livestock.

In the prior art, a person identified the state of each livestock, and the animals showing abnormal symptoms were treated or quarantined separately. However, when the number of 　 livestock is large, there is a problem that a large number of manpower is required to manage all 　 livestock.

In addition, if an infectious disease occurs in some 　 livestock, 　 most of the livestock may die, so a method that can quickly and accurately determine whether an animal is abnormal is required.

In addition, due to the development of transportation means, diseases that have occurred in a specific area are not limited to a specific place and are spread nationwide within a short period of time. In judging the disease 　 of livestock, the temperature measurement method according to the fever is used as a criterion for judging the presence or absence of disease. However, since uniform temperature measurements are made for many animals, there is a difficulty in judging diseases and diseases according to the state of each individual. In addition, this method of determining a disease by measuring temperature has difficulty in detecting an individual at an early stage of disease development.

An object of the present invention is to provide an apparatus and method for detecting an abnormal object capable of detecting an object with a high probability of having a disease on image data photographed inside a kennel, and an imaging apparatus including the same.

According to an embodiment of the present invention, there is provided a data processing unit comprising: a data processing unit generating position distribution data representing a position distribution of a plurality of entities by using image data generated from an image including a plurality of entities; a motion detection unit generating motion data representing a motion of a motion object among the plurality of objects by using the generated image data; and a controller for generating abnormal entity data indicating an abnormal entity by comparing the position distribution data and the motion data, wherein the position distribution data is data in which the presence or absence of an entity is indicated as a probability for each pixel on the image data, and The motion data is data indicating whether a motion exists for each pixel on the image data, and the controller additionally reflects data indicating the existence of an object as a probability for each pixel in the past probability of existence of the object, and the corresponding data on the location distribution data Provided is an anomaly detection apparatus that generates the abnormal entity data by initializing a pixel at the same position as a moving pixel in the motion data by applying it to a pixel value of a pixel.

The controller may display the initialized pixel as a primary color on the image data.

As the pixel values are accumulated, the controller may highlight and display the corresponding pixel.

The controller may generate the abnormal entity data according to Equation 1 below.

[Equation 1]

Pixel _t = Pixel _t-1 (1-μ) + μW _t - F _t

(In Equation 1, Pixel _t is the abnormal object data of the current frame, Pixel _{t -1} is the abnormal object data of the previous frame, μ is the update parameter, W _t is the position distribution data of the current frame _{, F t is the current frame} operation data of

According to an embodiment of the present invention, a photographing unit for generating image data by photographing an image including a plurality of objects; a data processing unit for generating position distribution data representing a position distribution of the plurality of objects by using the image data; a motion detection unit generating motion data representing a motion of a motion object among the plurality of objects by using the image data; and a controller for generating abnormal entity data indicating an abnormal entity by comparing the position distribution data and the motion data, wherein the position distribution data is data in which the presence or absence of an entity is indicated as a probability for each pixel on the image data, and The motion data is data indicating whether a motion exists for each pixel on the image data, and the controller additionally reflects data indicating the existence of an object as a probability for each pixel in the past probability of existence of the object, and the corresponding data on the location distribution data Provided is an imaging device that generates the abnormal object data by initializing a pixel at the same position as a pixel having motion in the motion data by applying it to a pixel value of a pixel.

The controller may display the initialized pixel as a primary color on the image data.

As the pixel values are accumulated, the controller may highlight and display the corresponding pixel.

According to an embodiment of the present invention, generating image data by photographing an image including a plurality of objects; generating position distribution data representing the position distribution of the plurality of objects by using the image data; generating motion data representing a motion of a motion object among the plurality of objects by using the image data; and generating abnormal entity data indicating an abnormal entity by comparing the position distribution data and the motion data, wherein the position distribution data is data in which the existence of an entity is indicated as a probability for each pixel on the image data, and the The motion data is data indicating whether a motion exists for each pixel on the image data, and the generating of the abnormal entity data includes additionally reflecting data indicating the existence of an entity as a probability for each pixel in the past probability of existence of the entity and applying to the pixel value of the corresponding pixel on the position distribution data, but initializing the pixel in the same position as the moving pixel in the motion data to generate the abnormal entity data.

The method may further include displaying the initialized pixels as primary colors on the image data.

The method may further include emphasizing and displaying a corresponding pixel as the pixel values are accumulated.

An apparatus and method for detecting an abnormal object according to the present invention, and an imaging device including the same, can detect an abnormal object having a high probability of contracting a disease from image data captured inside a kennel.

In addition, abnormal objects and normal objects can be visually distinguished and displayed.

In addition, abnormal objects can be tracked and monitored.

In addition, when an abnormal object occurs, a notification or warning can be sent to the administrator.

In addition, it is possible to reduce the amount of calculation of the analysis data and improve the calculation speed.

1 is a conceptual diagram of a kennel management system according to an embodiment of the present invention.
2 is a block diagram of an imaging device according to an embodiment of the present invention.
3 to 15 are diagrams for explaining the operation of the control unit according to an embodiment of the present invention.
16 to 17 are flowcharts of a method for detecting an anomaly according to an embodiment of the present invention.

Since the present invention can have various changes and can have various embodiments, specific embodiments are illustrated and described in the drawings. However, this is not intended to limit the present invention to specific embodiments, and it should be understood to include all modifications, equivalents and substitutes included in the spirit and scope of the present invention.

Terms including an ordinal number such as second, first, etc. may be used to describe various elements, but the elements are not limited by the terms. The above terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, the second component may be referred to as the first component, and similarly, the first component may also be referred to as the second component. and/or includes a combination of a plurality of related listed items or any of a plurality of related listed items.

When a component is referred to as being “connected” or “connected” to another component, it is understood that the other component may be directly connected or connected to the other component, but other components may exist in between. it should be On the other hand, when it is mentioned that a certain element is "directly connected" or "directly connected" to another element, it should be understood that the other element does not exist in the middle.

The terms used in the present application are only used to describe specific embodiments, and are not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly dictates otherwise. In the present application, terms such as “comprise” or “have” are intended to designate that a feature, number, step, operation, component, part, or combination thereof described in the specification exists, but one or more other features It should be understood that this does not preclude the existence or addition of numbers, steps, operations, components, parts, or combinations thereof.

Unless defined otherwise, all terms used herein, including technical and scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related art, and should not be interpreted in an ideal or excessively formal meaning unless explicitly defined in the present application. does not

Hereinafter, the embodiment will be described in detail with reference to the accompanying drawings, but regardless of the reference numerals, the same or corresponding components are given the same reference numerals, and the overlapping description thereof will be omitted.

1 is a conceptual diagram of a kennel according to an embodiment of the present invention, and FIG. 2 is a block diagram of an imaging device according to an embodiment of the present invention.

1 and 2 , first, the breeding house 10 means a barn for breeding livestock. Livestock may be various types of animals raised in a group in a barn, such as cattle and pigs, as well as poultry such as chickens and ducks.

The imaging device 100 may detect the environment in the breeding ground 10 and transmit it to at least one of the management server 200 and the air conditioner 300 . To this end, the imaging device 100 may communicate with the management server 200 and the air conditioner 300 by wire or wirelessly. Here, although the imaging device 100 is illustrated as communicating with the management server 200 and the air conditioner 300 respectively, it is not limited thereto, and the imaging device 100 communicates with the management server 200 , and the management server 200 may communicate with the air conditioner 300 .

A plurality of imaging devices may be disposed in the kennel 10 . The imaging device 100 may transmit image data captured by the photographing unit 111 to the management server 200 . Alternatively, a separate data collection device 150 may be disposed in the breeding ground 10 to collect image data from a plurality of imaging devices 100 and transmit it to the management server 200 . In order to precisely analyze the state of the inside of the kennel 10 , the image data of the imaging device 100 may have high-quality and high-capacity characteristics. Accordingly, a large bandwidth may be required to transmit the image data captured by the plurality of imaging devices 100 to the remote management server 200 in real time, and accordingly, the transmission speed may be reduced. Therefore, the separate data collection device 150 collects and encodes image data from the imaging device 100 in the kennel 10 and transmits it to the management server 200, thereby reducing the communication bandwidth and improving the transmission speed. have. Alternatively, the imaging device 100 may perform a primary analysis for analyzing the state of the breeding house 10 using the image data, and then transmit the processed data to the data collection device or the management server 200 . That is, the imaging device 100 can efficiently manage communication resources by selecting only data necessary for the state analysis of the breeding ground 10 and transmitting it to the data collection device 150 or the management server 200 . Alternatively, the imaging device 100 primarily analyzes the internal state of the kennel 10 using image data captured by the kennel 10 and transmits the result to the data collection device 150 or to the management server 200 . can be transmitted

The management server 200 may be a server including a personal computer (PC), a tablet PC, a portable terminal, and the like. When the imaging device 100 transmits the environment in the kennel 10 to the management server 200 , the manager may recognize the environment in the kennel 10 through a screen output to the management server 200 . For example, when the imaging device 100 captures an abnormal situation in the kennel 10 and transmits it to the management server 200 , the manager can detect the abnormal situation in the kennel 10 through the screen output to the management server 200 . It can recognize that a situation has occurred and can respond to an abnormal situation at an early stage. Here, the abnormal situation may be, for example, the occurrence of diseased livestock, the pregnancy of the livestock, the growth period of the livestock, the humidity in the breeding house 10 , the temperature, the concentration of a specific molecule or the like.

When the management server 200 is a central server that receives information from a plurality of breeding grounds 10 , the manager may not have easy access to the management server 200 . In this case, the management server 200 may transmit information about the abnormal situation in the breeding ground 10 through a separate manager's portable terminal.

Also, the management server 200 may analyze the state of the kennel using data transmitted from the imaging device 100 or the data collection device 150 . For example, the management server 100 may receive the data primarily processed from the plurality of imaging devices 100 or the data collection device 150 to perform a more precise analysis on the state of the kennel. The management server 200 may perform data communication with the communication unit 115 of the imaging device 100 or data communication with a communication module (not shown) mounted on the data collection device 150 . The management server 200 may receive the original image captured by the imaging device 100 and the processed image data primarily processed. In this case, the processed image data may refer to data obtained by performing primary analysis on the original image in the breeding house management apparatus 100 or the imaging apparatus 100 and encoding the same.

The air conditioning device 300 is a device for controlling the temperature of the breeding house (10). When the imaging device 100 captures the temperature abnormality in the breeding ground 10 and transmits it to the management server 200, the manager recognizes that the temperature abnormality in the breeding farm 10 has occurred through the screen output to the management server 200 It can be recognized, and the temperature in the breeding house 10 can be normalized by controlling the air conditioning device 300 . Alternatively, when the imaging device 100 detects an abnormal temperature in the breeding ground 10 and directly transmits it to the air conditioner 300 , the air conditioner 300 may directly normalize the temperature in the breeding ground 10 . For example, when the temperature in the breeding house 10 is lower or higher than a temperature suitable for livestock to live, the movement of the livestock tends to be slowed. Accordingly, the imaging device 100 , the management server 200 , or the air conditioner 300 may detect an abnormal temperature in the breeding ground 10 and normalize the temperature in the breeding station 10 .

The air conditioner 300 may adjust the humidity of the breeding house 10 . When an abnormality occurs in the humidity in the breeding ground 10 , the humidity in the breeding farm 10 may be normalized by controlling the air conditioner 300 .

The imaging device 100 includes a photographing unit 111 , a data processing unit 112 , a motion detection unit 113 , a control unit 114 , a communication unit 115 , a display unit 116 , a user interface unit 117 , and an encoding unit 118 . ), a database 119 , a light source unit 120 , and a pan tilt unit 121 . In the embodiment of the present invention, an abnormal object detection apparatus including a data processing unit 112 , a motion detection unit 113 , a control unit 114 , and a communication unit 115 is illustrated as being included in the imaging device 100 . However, the abnormal object detection apparatus may be manufactured in the form of a separate module and configured to be included in the data collection apparatus 150 or the management server 200 . Alternatively, the abnormal object detection apparatus may be implemented as an independent product in the form of a separate device. When the abnormal object detection apparatus is applied in the form of a module or device separate from the imaging apparatus 100 , the abnormal object detection apparatus may receive image data from the imaging apparatus 100 through the communication unit 115 . In addition, the data processing unit and the motion detection unit may be implemented as one processor by being included in the control unit. In the embodiment of the present invention, the functions of the data processing unit, the motion detection unit, and the control unit will be separately described for convenience of description.

Hereinafter, it will be described by taking as an example that the abnormal object detecting apparatus is included in the imaging apparatus 100 .

A plurality of imaging devices 100 may be installed in the kennel 10 . For example, the imaging device 100 may include at least one upper imaging device disposed on the top of the breeding ground 10 and at least one side imaging device disposed on the side of the breeding station 10 . Each of the upper imaging device and the side imaging device may be an IP camera capable of transmitting a real-time image because communication is possible by wire or wirelessly. In the present embodiment, an example in which one imaging device 100 is disposed above a breeding ground will be described.

The photographing unit 111 may generate image data by photographing an image including a plurality of objects. In an embodiment of the present invention, a plurality of individuals may refer to poultry raised inside a feedlot.

The photographing unit 111 may generate a plurality of image data using a plurality of sequentially photographed images. For example, the photographing unit 111 may generate first image data by photographing a first image including a plurality of objects, and may generate second image data by photographing a second image including a plurality of objects. have. Each of the first image and the second image may be images continuously photographed in time, and one image data may mean a single frame. The photographing unit 111 may generate the first image data and the second image data by using the first image and the second image that are sequentially photographed.

The photographing unit 111 may be an image sensor that photographs a subject using a complementary metal-oxide semiconductor (COMS) module or a charge coupled device (CCD) module. At this time, the input image frame is provided to the COMS module or CCD module in the photographing unit 111 through the lens, and the COMS module or CCD module converts the optical signal of the subject passing through the lens into an electrical signal (image data) and outputs it do.

The photographing unit 111 may include a fisheye lens or a wide-angle lens having a wide viewing angle. Accordingly, it is possible for one imaging device 100 to photograph the entire space inside the kennel 10 .

Also, the photographing unit 111 may be a depth camera. The photographing unit 111 may be driven by any one of various depth recognition methods, and depth information may be included in an image photographed through the photographing unit 111 . The photographing unit 111 may be, for example, a Kinect sensor. The Kinect sensor is a structured light projection type depth camera, and can acquire three-dimensional information of a scene by projecting a defined pattern image using a projector or a laser and acquiring an image on which the pattern is projected through the camera. The Kinect sensor includes an infrared emitter that irradiates a pattern using an infrared laser, and an infrared camera that captures an infrared image, and an RGB camera that functions like a general webcam is disposed between the infrared emitter and the infrared camera. In addition to this, the Kinect sensor may further include a pan/tilt unit 121 for adjusting the angle of the microphone arrangement and the camera.

The basic principle of the Kinect sensor is that when a laser pattern irradiated from an infrared emitter is projected onto an object and reflected, the distance to the surface of the object is obtained using the position and size of the pattern at the reflection point. According to this principle, the photographing unit 111 may generate image data including depth information for each object by irradiating a laser pattern into the space within the shed and sensing the laser pattern reflected from the object.

The data processing unit 112 may generate position distribution data indicating the position distribution of a plurality of objects by using the image data. The data processing unit 112 generates, for example, first position distribution data representing the position distribution of a plurality of entities by using the first image data generated including the plurality of entities, and generates a second image including the plurality of entities. The data may be used to generate second location distribution data indicating the location distribution of a plurality of objects.

In an embodiment of the present invention, location distribution data may mean a heat map of poultry detected on image data.

For example, the data processing unit 112 detects the outline of the object from the image data, compares the detected outline with the outline of the animal object stored in advance in the database 119 to obtain an outline matching the outline of the animal object stored in advance. It is possible to detect a subject with an animal as an animal subject. At this time, the appearance of the animal object stored in the database 119 may be the appearance of at least one or more animal objects, and the data processing unit 112 detects the object having the matching outline as the animal object as described above and simultaneously detects the corresponding object. It is also possible to determine the type of animal entity.

Also, for example, the data processing unit 112 extracts a feature point of an object in the image data, and when the extracted feature point matches the feature point of an animal object stored in advance in the database 119 with a proximity of more than a threshold, within the image data The subject may be detected as an animal subject. In this case, the data processing unit 112 extracts feature points from the images of two objects to be compared, and matches the extracted feature descriptors of the two objects using SIFT (Scale Invariant Feature Transform) or SURF (Speed Up Robust Features) algorithms can be used.

Also, for example, the data processing unit 112 may detect an animal object based on outlines of the objects in the image data. More specifically, the data processing unit 112 generates an edge image by detecting the contours of the objects in the image data, and detects the contour from the foreground image data that is a background image of the breeding house stored in advance in the database 119 to generate a background edge image. and the animal object may be detected from a different image obtained by subtracting the background edge image from the edge image. In this case, the data processing unit 112 generates an edge image by detecting the outline of an object appearing in the frame as an edge using gradient information of the image data frame. Here, the gradient information is a value generated from a difference value between adjacent pixels among predetermined pixels in a frame and means the sum of absolute values of the difference, and the edge means a boundary line between objects using the gradient information.

In addition, the data processing unit 112 may generate a background edge image by detecting an edge of an object corresponding to the background from the previously photographed image data of the foreground in the kennel. In this case, the background edge image may be an image in which the outlines of objects in a preset area are detected as background edges. It may be an image in which the outline of the appearing object is detected as a background edge.

Also, the data processing unit 112 may detect an animal object from the image data using an object detection classifier. In this case, the object detection classifier is learned by constructing a training DB from images of animal objects previously photographed with different postures or external environments of the animal object. It creates a DB of animal objects through various learning algorithms including Specifically, the data processing unit 112 detects an edge of an object corresponding to the foreground from the image data of the background in the previously photographed kennel, applies the edge of the foreground object detected from the image data, and an image to which the edge of the foreground object is applied. An entity detection classifier can be applied to an area of data to detect an animal entity.

In addition, the data processing unit 112 reduces noise in the image data photographed by the photographing unit 111 , and performs gamma correction, color filter array interpolation, color matrix, and color. Image signal processing for image quality improvement such as color correction and color enhancement may be performed. The data processing unit 112 may also perform color processing, blur processing, edge enhancement processing, image analysis processing, image recognition processing, image effect processing, and the like.

The motion detector 113 may generate motion data representing a motion of a motion object among a plurality of objects by using the image data. The motion detector 113 may detect a motion at a specific point, a specific object, or a specific pixel on a distribution map using single image data or a plurality of consecutive image data.

The motion detector 113 generates, for example, first motion data representing a motion of a motion object among a plurality of objects by using the first image data, and generates first motion data representing a motion of a motion object among the plurality of objects by using the second image data. Second motion data may be generated.

The motion detection unit 113 may detect the motion of the moving object using the dense optical flow method. The motion detector 113 may detect a motion of each pixel by calculating a motion vector for all pixels on the image data. In the case of the Dense Optical Flow method, since the motion vector is calculated for all pixels, the detection accuracy is improved, but the amount of computation is relatively increased. Therefore, the Dense Optical Flow method can be applied to a specific area requiring very high detection accuracy, such as a kennel suspected of having an abnormal situation or a kennel with a very large number of individuals.

Alternatively, the motion detection unit 113 may detect the motion of the moving object using a sparse optical flow method. The motion detector 113 may detect a motion by calculating a motion vector for only some characteristic pixels that are easy to track motion, such as an edge in an image. Although the sparse optical flow method reduces the amount of computation, it can only obtain results for a limited number of pixels. Therefore, the sparse optical flow method can be applied to a kennel with a small number of individuals or to a specific area in which overlapping individuals do not appear.

Alternatively, the motion detector 113 may detect the motion of the moving object using block matching. The motion detector 113 may divide the image equally or non-uniformly and calculate a motion vector for the divided region to detect the motion. Block Matching reduces the amount of computation because motion vectors are calculated for each segmented region, but the detection accuracy may be relatively low because it calculates the result for each region-specific motion vector. Therefore, the Block Matching method can be applied to a kennel with a small number of individuals or to a specific area in which overlapping individuals do not appear.

Alternatively, the motion detector 113 may detect the motion of the moving object using a continuous frame difference method. The motion detector 113 may compare successive image frames for each pixel and calculate a value corresponding to the difference to detect motion. Since the continuous frame difference method detects motion using the difference value between frames, the overall amount of computation is reduced, but the detection accuracy for a bulky object or an overlapping object may be relatively low. In addition, the continuous frame difference method cannot distinguish between a background image and a non-moving object, so accuracy may be relatively low. Therefore, the Continuous Frame Difference method can be applied to a kennel with a small number of individuals or to a specific area in which overlapping individuals do not appear.

Alternatively, the motion detection unit 113 may detect the motion of the moving object using a background subtraction method. The motion detector 113 may compare successive image frames for each pixel in a state in which the background image is initially learned, and may detect a motion by calculating a value corresponding to the difference. Since the background subtraction method learns the background image in advance, it is possible to distinguish the background image from the non-moving object. Accordingly, a separate process of filtering the background image is required, which increases the amount of computation but improves accuracy. Therefore, the background subtraction method can be applied to a specific area requiring very high detection accuracy, such as a breeding ground suspected of having an abnormal situation or a breeding ground having a very large number of individuals. In the background subtraction method, the background image can be continuously updated.

The motion detection unit 113 detects a motion on the distribution map using an appropriate method according to the environment in the breeding ground and external settings.

The controller 114 may generate abnormal entity data indicating an abnormal entity by comparing the position distribution data and motion data of the image data. For example, the controller 114 may generate first abnormal entity data indicating an abnormal entity by comparing the first location distribution data and the first motion data. The control unit 114 may compare the first location distribution data with the first motion data to generate first or more object data indicating information about an object for which a motion is not detected on the first location distribution data. That is, the controller 114 may estimate that an individual whose motion is not detected on the first position distribution data indicating the position of the entity is afflicted with a disease, and generate the first abnormal entity data. That is, the first or more object data may refer to data as a result of determining whether an object has a disease by using the location distribution and motion detection information of the object with respect to single image data. Alternatively, the controller 114 may By comparing the position distribution data and the motion data, the cumulative number of motion detection and non-motion detection of a plurality of entities may be calculated, and abnormal entity data may be generated according to the cumulative number of motion detection and the cumulative number of motion non-detection. For example, the controller may generate the second abnormal entity data by comparing the first abnormal entity data, the second position distribution data, and the second motion data. The control unit compares the first or more object data with the second location distribution data and the second motion data to calculate the cumulative number of motion detections of the plurality of entities and the cumulative number of motion non-detections of the plurality of entities, and the cumulative number of motion detections and the cumulative number of motion detections According to the number of times, the second or more entity data may be generated. That is, the second or higher entity data may refer to data as a result of determining whether an entity has a disease by using the position information and motion detection information of the entity accumulated with respect to a plurality of image data.

The controller 114 may control pixel display of a plurality of objects on the image data according to the cumulative number of motion detection and non-motion detection of the abnormal entity data. For example, the controller may control pixel display of the plurality of entities on image data according to the second or more entity data. Here, the pixel display may include all concepts for displaying a pixel corresponding to an arbitrary point, such as pixel saturation, pixel contrast, pixel color, pixel outline, and mark display, separately from other pixels. In an embodiment of the present invention, display of pixels may be controlled by adjusting pixel values. The pixel value may be adjusted in stages, and a pixel having a high pixel value may be visually emphasized and displayed compared to a pixel having a low pixel value. However, the present invention is not limited thereto, and a pixel having a low pixel value may be displayed with more emphasis than a pixel having a high pixel value.

Hereinafter, in order to describe a pixel in which motion is detected and an object as the same, it is assumed that one pixel represents one object. This is for convenience of explanation, and in reality, a plurality of pixels represent one object. That is, in order to determine an abnormal situation by detecting only the movement of a part of the body region of the poultry, a method of detecting the movement of each pixel and controlling the display of the pixel will be used.

The controller 114 may classify the object as an abnormal object as the movement of a specific object is not detected, and classify the object as a normal object as the movement is detected to display pixel values differently.

Hereinafter, image data captured by an imaging device installed on an upper part of a breeding ground will be described with reference to FIGS. 3 to 16 as an example. 3 to 11, nk (k is a natural number between -1 and 3) frames means consecutive frames in time, "0" is when motion is detected in each frame, and "X" is when motion is non-moving. case is detected. Also, in FIGS. 3 to 6 , the pixel value of each object of the image data is set to “0”, and in FIGS. 7 to 11 , the pixel value of each object of the image data is set to “5”. 3 to 16 , one image data may mean a single frame. For example, when the n-1 th frame is the first image data, the n th frame may mean the second image data. Also, when the nth frame is the first image data, the n+1th frame may mean the second image data. 3 is a view for explaining the operation of the control unit according to the embodiment of the present invention. Referring to FIG. 3 , the controller may increase the pixel value corresponding to an arbitrary point or object in stages according to the accumulated number of motion non-detection. In FIG. 3 , the cumulative number of motion non-detection of entity A is 5 times. Accordingly, the control unit increases the pixel value of the object A by 5 steps. The cumulative number of motion non-detection of object B is 3 times. Accordingly, the control unit increases the pixel value of the object B by three steps. The cumulative number of motion non-detection of object C is 2 times. Accordingly, the control unit increases the pixel value of the object C by two steps. According to the embodiment of FIG. 3 , as the total accumulated number of the number of times of non-detection of an object's motion increases, the pixel value may be increased and displayed with emphasis. That is, as the pixel value is higher on the distribution map, it may be displayed with emphasis in red, and as the pixel value is lower, it may be displayed closer to the original data value. According to this, even if a motion is detected during a certain frame, the control unit highlights even an object with a low probability of a disease by highlighting it to be close to an abnormal object if the cumulative number of total motion non-detection is large. .

4 is a diagram for explaining an operation of a control unit according to an embodiment of the present invention. Referring to FIG. 4 , the controller may increase the pixel value of the corresponding object in stages according to the cumulative number of consecutive motion non-detection. In Fig. 4, the cumulative number of consecutive motion non-detection of the entity A is 5 times. Accordingly, the control unit increases the pixel value of the object A by 5 steps. The cumulative number of consecutive motion non-detection of object B is 2 times. Accordingly, the control unit increases the pixel value of the object B by two steps. The cumulative number of consecutive motion non-detection of entity C is 1. Accordingly, the control unit increases the pixel value of the object C by one step. According to the embodiment of FIG. 4 , as the total accumulated number of the number of consecutive motion non-detection of the object increases, the pixel value may be increased and displayed with emphasis. According to this, even if the accumulated number of motion non-detection is large, the controller may display it close to a normal object if the accumulated number of consecutive motion non-detection is not large.

5 is a diagram for explaining an operation of a control unit according to an embodiment of the present invention. Referring to FIG. 5 , when the cumulative number of non-motion detection exceeds a first threshold value, the controller may control a pixel value of a corresponding object as a first set value. Here, the first threshold value and the first set value may be set through the user interface unit. Alternatively, it may be set through a control command of the management server. In Fig. 5, the first threshold is set to two times. The first set value may mean a maximum value of a pixel value. In FIG. 5 , the first set value may mean the maximum red value of the pixel. In FIG. 5 , the cumulative number of motion non-detection of entity A is 5 times, which exceeds the first threshold. Accordingly, the controller controls the pixel value of the object A as the maximum red value. The cumulative number of motion non-detection of entity B exceeds the first threshold value 3 times. Accordingly, the controller controls the pixel value of the object B as the maximum red value. The cumulative number of consecutive motion non-detection of object C is 1, and does not exceed the first threshold. Accordingly, the control unit maintains the pixel value of the object C in the current state. According to the embodiment of FIG. 5 , when the total accumulated number of times of non-detection of an object's motion exceeds a specific number, the pixel value may be displayed with maximum emphasis.

6 is a diagram for explaining an operation of a control unit according to an embodiment of the present invention. Referring to FIG. 6 , when the cumulative number of consecutive motion non-detection exceeds a first threshold value, the controller may control a pixel value of a corresponding object as a first set value. Here, the first threshold value and the first set value may be set through the user interface unit. Alternatively, it may be set through a control command of the management server. In Fig. 6, the first threshold is set to two times. The first set value may mean a maximum value of a pixel value. In FIG. 6 , the first set value may mean the maximum red value of the pixel. The cumulative number of consecutive motion non-detection of object A is 5, which exceeds the first threshold. Accordingly, the controller controls the pixel value of the object A as the maximum red value. The cumulative number of consecutive motion non-detection of object B is 2, and does not exceed the first threshold. Accordingly, the control unit maintains the pixel value of the object B in the current state. The cumulative number of consecutive motion non-detection of object C is 1, and does not exceed the first threshold. Accordingly, the control unit maintains the pixel value of the object C in the current state. According to the embodiment of FIG. 6 , only when the number of frames in which the object does not continuously move exceeds the first threshold value, the pixel value is displayed with maximum emphasis, thereby making it possible to discriminate anomalies according to stricter standards.

7 is a diagram for explaining an operation of a control unit according to an embodiment of the present invention. Referring to FIG. 7 , the controller may gradually decrease the pixel value of the corresponding object according to the accumulated number of motion detection. The cumulative number of motion detections of entity A is 5. Accordingly, the control unit decreases the pixel value of the object A by 5 steps. The cumulative number of motion detection of entity B is 3 times. Accordingly, the control unit decreases the pixel value of the object B by three steps. The cumulative number of motion detections of entity C is two. Accordingly, the control unit decreases the pixel value of the object C by two steps. According to the embodiment of FIG. 7 , as the total accumulated number of the number of detections of an object's motion increases, the pixel value decreases, so that the display may be displayed without emphasis. That is, the lower the pixel value on the distribution map, the closer to the original data value or the fainter it may be displayed. According to this, even if a motion is not detected during a predetermined frame, the controller can display a non-emphasized object close to a normal object if the total number of accumulated motion detections is large.

8 is a diagram for explaining an operation of a control unit according to an embodiment of the present invention. Referring to FIG. 8 , the controller may gradually decrease the pixel value of the corresponding object according to the number of consecutive motion detection accumulations. In Fig. 8, the cumulative number of consecutive motion detection of the entity A is 5 times. Accordingly, the control unit decreases the pixel value of the object A by 5 steps. The cumulative number of consecutive motion detection of entity B is 2 times. Accordingly, the control unit decreases the pixel value of the object B by two steps. The cumulative number of consecutive motion detection of entity C is 1. Accordingly, the control unit decreases the pixel value of the object C by one step. According to the embodiment of FIG. 8 , as the cumulative number of the number of consecutive motion detection of an object increases, a pixel value may decrease and display non-emphasis. According to this, even if the accumulated number of motion detection is large, the controller can display the object to be close to the abnormal object if the accumulated number of consecutive motion detection is not large.

9 is a diagram for explaining an operation of a control unit according to an embodiment of the present invention. Referring to FIG. 9 , the controller may control a pixel value of an object whose motion is detected as a second set value. Here, the second setting value may be set through the user interface unit. Alternatively, it may be set through a control command of the management server. 9 , the second setting value is a pixel value of the original image data. In Fig. 9, in each of the objects A to C, motion was detected at least once during the image frames of n-1 to n+3. Accordingly, the controller sets the pixel values of the objects A to C as the pixel values of the original image data. Accordingly, an object whose motion is detected at least once during the analysis image frame period may be classified as a normal object and displayed as pixel values of the original image data.

10 is a diagram for explaining an operation of a control unit according to an embodiment of the present invention. Referring to FIG. 10 , when the accumulated number of motion detection exceeds the second threshold value, the controller may control the pixel value of the corresponding object as the second set value. Here, the second threshold value and the second setting value may be set through the user interface unit. Alternatively, it may be set through a control command of the management server. In Fig. 10, the second threshold is set to two times. The second setting value is a pixel value of the original image data. In Fig. 10, the cumulative number of motion detections of the entity A is 5, which exceeds the second threshold. Accordingly, the controller controls the pixel value of the object A as the pixel value of the original image data. The cumulative number of motion detections of entity B exceeds the second threshold value 3 times. Accordingly, the controller controls the pixel value of the object B as the pixel value of the original image data. The cumulative number of consecutive motion detection of entity C is 1, and does not exceed the second threshold. Accordingly, the control unit maintains the pixel value of the object C in the current state. According to the embodiment of FIG. 10 , when the total accumulated number of times of detecting the motion of an object exceeds a specific number, the pixel value may be displayed as the pixel value of the original image data.

11 is a diagram for explaining an operation of a control unit according to an embodiment of the present invention. Referring to FIG. 11 , when the cumulative number of consecutive motion detection exceeds the second threshold value, the controller may control the pixel value of the corresponding object as the second set value. Here, the second threshold value and the second setting value may be set through the user interface unit. Alternatively, it may be set through a control command of the management server. In Fig. 11, the second threshold is set to two times. The second setting value is a pixel value of the original image data. In Fig. 11, the cumulative number of motion detection of the entity A is 5, which exceeds the second threshold. Accordingly, the controller controls the pixel value of the object A as the pixel value of the original image data. The cumulative number of motion detections of entity B is 2 and does not exceed the second threshold. Accordingly, the control unit maintains the pixel value of the object B in the current state. The cumulative number of consecutive motion detection of entity C is 1, and does not exceed the second threshold. Accordingly, the control unit maintains the pixel value of the object C in the current state. According to the embodiment of FIG. 11 , the pixel value may be displayed as the pixel value of the original image data only when the total accumulated number of the number of consecutive motion detections of the object exceeds a specific number.

12 is a diagram for explaining an operation of a control unit according to an embodiment of the present invention. Referring to FIG. 12 , the controller may control a pixel value corresponding to a motion-detected object as a second set value and exclude it from the analysis target later by excluding it from the abnormal object data. Here, the second setting value may be set through the user interface unit. Alternatively, it may be set through a control command of the management server. 12 , the second setting value is a pixel value of the original image data. 12 , in the case of the object A, the controller sets the pixel value of the object A as the original image data pixel value in the n-1 frame in which the motion is detected, and then excludes it from the analysis target for the period of n to n+3 frames. In the case of the object B, the controller sets the pixel value of the object B as the original image data pixel value in the n frames in which the motion is detected, and then excludes the object from analysis for the period of n+1 to n+3 frames. In the case of the object C, the controller sets the pixel value of the object C as the original image data pixel value in the n+2 frames in which the motion is detected, and excludes it from the analysis target for the n+3 frame period thereafter.

13 is a diagram for explaining an operation of a control unit according to an embodiment of the present invention. Referring to FIG. 13 , the control unit may control a pixel value corresponding to an entity whose accumulated number of motion detection exceeds a second threshold value as a second set value and exclude it from the analysis target by excluding it from the abnormal entity data. Here, the second threshold value and the second setting value may be set through the user interface unit. Alternatively, it may be set through a control command of the management server. In Fig. 13, the second threshold is set to one time. The second setting value is a pixel value of the original image data. In Fig. 13, in the case of entity A, the number of cumulative motion detections in n frames is shown twice. Accordingly, the controller sets the pixel value of the object A as the pixel value of the original image data in n frames, and excludes it from the analysis target for a period of n+1 to n+3 frames thereafter. In the case of object B, the cumulative motion detection count appears twice in n+2 frames. Accordingly, the controller sets the pixel value of the object B as the original image data pixel value in n+2 frames, and excludes it from the analysis target for the n+3 frame period thereafter. In the case of entity C, since the cumulative number of motion detections during the analysis frame period was less than 2, the controller controls the pixel values by continuously performing analysis in subsequent frames.

14 is a diagram for explaining an operation of a control unit according to an embodiment of the present invention. Referring to FIG. 14 , the controller controls a pixel value corresponding to an object whose cumulative number of consecutive motion detection exceeds the second threshold value as a second set value, and excludes it from the analysis target later by excluding it from the abnormal object data. have. Here, the second threshold value and the second setting value may be set through the user interface unit. Alternatively, it may be set through a control command of the management server. In Fig. 14, the second threshold is set to one time. The second setting value is a pixel value of the original image data. 14 , in the case of entity A, the number of consecutive motion accumulation detections in n frames is shown twice. Accordingly, the controller sets the pixel value of the object A as the pixel value of the original image data in n frames, and excludes it from the analysis target for a period of n+1 to n+3 frames thereafter. In the case of entities B and C, since the cumulative number of consecutive motion detections during the analysis frame period was less than 2, the controller continuously performs analysis in subsequent frames to control the pixel values.

In the case of FIGS. 12 to 14 , an entity satisfying a specific condition according to the number of motion detections is determined as a normal entity, and the amount of data calculation for analysis can be reduced by excluding from the analysis target after the time point at which the entity is determined to be a normal entity. Accordingly, it is possible to greatly improve the analysis speed, accuracy, and efficiency of video data captured inside a kennel where as few as hundreds and as many as tens of thousands of poultry live.

15 is a diagram for explaining an operation of a control unit according to an embodiment of the present invention. Referring to FIG. 15 , the controller may control a pixel value corresponding to an entity having a cumulative number of motion detections equal to or greater than a second threshold value as a second set value and exclude it from analysis. Here, the second threshold value and the second setting value may be set through the user interface unit. Alternatively, it may be set through a control command of the management server. In Fig. 15, the second threshold is set to two times. The second setting value may be implemented by any means for not visually displaying the corresponding object or the corresponding pixel. The second setting value may be implemented by, for example, masking processing, mosaic processing, or transparent pixel processing for a corresponding object or corresponding pixel. Accordingly, when classified as a normal object, it is not visually displayed on the image data, so there is an advantage in that an abnormal object can be more accurately identified.

Referring back to FIGS. 1 and 2 , the controller 114 may perform various commands for the operation of the imaging device 100 .

The control unit 114 may perform an operation of the imaging device 100 by, for example, executing a command stored in the user interface unit 117 or the database 119 .

Alternatively, the controller 114 may control various operations of the imaging device 100 using a command received from the management server 200 .

The controller 114 may control the photographing unit 11 to track and photograph a point or an object in which the cumulative number of motion non-detection is equal to or greater than the third set value. The third setting value may be set through the user interface unit 117 or may be set through a control command of the management server 200 . The control unit 114 controls the photographing unit 111 to track and photograph a specific area with an abnormal object to generate image data, so that continuous monitoring can be performed.

In this case, the controller 114 may control the pan/tilt unit 121 of the imaging device 100 to perform tracking imaging. The pan/tilt unit 121 may control the photographing area of the photographing unit 111 by driving two motors: Pan (horizontal direction) and tilt (Tilt, vertical direction). The pan/tilt unit 121 may adjust the orientation direction of the photographing unit 111 in order to photograph a specific area under the control of the control unit 114 . Also, the pan/tilt unit 121 may adjust the orientation direction of the photographing unit 111 in order to track a specific object under the control of the control unit 114 .

The communication unit 115 may perform data communication with another imaging device, the data collection device 150 , or the management server 200 . For example, the communication unit 115 is a wireless LAN (Wireless LAN: WLAN), Wi-Fi (Wi-Fi), Wi-Bro (Wireless Broadband: Wibro), WiMAX (World Interoperability for Microwave Access: Wimax), HSDPA (High Speed Downlink) Packet Access), IEEE 802.16, Long Term Evolution (LTE), and data communication may be performed using a telecommunication technology such as Wireless Mobile Broadband Service (WMBS).

Alternatively, the communication unit 115 may include Bluetooth, Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Ultra Wideband (UWB), ZigBee, and Neighboring Field Communication (NFC). In addition, as the wired communication technology, data communication may be performed using a short-distance communication technology such as USB communication, Ethernet, serial communication, or an optical/coaxial cable.

For example, the communication unit 115 may perform data communication with another imaging device or data collection device 150 using a short-distance communication technology, and may perform data communication with the management server 200 using a long-distance communication technology. Yes, but is not limited thereto, and various communication technologies may be used in consideration of all matters of the breeding ground 10 and the like.

The communication unit 115 may transmit the original image data captured by the photographing unit 111 to the data collection device 150 or the management server 200 .

Alternatively, the communication unit 115 may transmit at least one of image data whose pixel values are adjusted, position distribution data, motion data, and coordinate information to at least one of the data collection device 150 or the remote management server 200 . In this case, the coordinate information may mean coordinates of a point or object suspected of being an anomaly.

Data transmitted through the communication unit 115 may be compressed data encoded through the encoding unit 118 .

The display unit 116 includes a liquid crystal display (LCD), a thin film transistor-liquid crystal display (TFT LCD), an organic light-emitting diode (OLED), and a flexible display (Flexible Display). ), a three-dimensional display (3D display), may include at least one of an e-ink display (e-ink display).

The display unit 116 may display at least one of image data and distribution data whose pixel values are adjusted through the control unit 114 .

Also, the display unit 116 may output the original image data captured by the photographing unit 111 on the screen.

Also, the display unit 116 may output various user interfaces or graphic user interfaces on the screen.

The user interface unit 117 generates input data for controlling the operation of the imaging apparatus 100 . The user interface unit 117 may include a key pad, a dome switch, a touch pad, a jog wheel, a jog switch, and the like. When the display unit 116 and the touchpad form a layered structure to form a touch screen, the display unit 116 may be used as an input device in addition to an output device.

The user interface unit 117 may receive various commands for operating the imaging device.

The encoding unit 118 encodes the original image data photographed by the photographing unit 111 or the processed image data processed through the data processing unit 112 , the motion detection unit 113 , and the control unit 114 into a digital signal. For example, the encoding unit 118 may encode image data according to H.264, H.265, Moving Picture Experts Group (MPEG), and Motion Joint Photographic Experts Group (M-JPEG) standards.

The database 119 is a flash memory type (Flash Memory Type), a hard disk type (Hard Disk Type), a multimedia card micro type (Multimedia Card Micro Type), a card type memory (eg, SD or XD memory, etc.) ), magnetic memory, magnetic disk, optical disk, random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), PROM ( Programmable Read-Only Memory) may include at least one storage medium. Also, the imaging device 100 may operate a web storage that performs a storage function of the database 119 on the Internet, or may operate in connection with the web storage.

The database 119 may store image data captured by the photographing unit 111 , and may store image data for a predetermined period in the past.

Also, the database 119 may store data and programs necessary for the imaging apparatus 100 to operate.

Also, the database 119 may store various user interfaces (UIs) or graphic user interfaces (GUIs).

The light source unit 120 may irradiate light in a direction directed under the control of the control unit 114 . For example, the light source unit 120 may include at least one laser diode LD and a light emitting diode LED. The light source unit may emit light in various wavelength bands under the control of the controller.

For example, the light source unit 120 may irradiate light in an infrared wavelength band for night photography. Alternatively, the light source unit 120 may irradiate light in the ultraviolet wavelength band for photochemotherapy of livestock in the breeding grounds.

16 is a flowchart of a method for detecting an anomaly according to an embodiment of the present invention.

Referring to FIG. 16 , first, the photographing unit captures an image including a plurality of objects. The photographing unit is disposed inside the kennel to photograph a plurality of objects including poultry (S1601).

Next, the photographing unit generates image data by using an image including a plurality of objects. One image data may mean a single frame. The data processing unit generates a plurality of image data by using the sequentially photographed images (S1602).

Next, the data processing unit generates position distribution data indicating the position distribution of a plurality of objects by using the image data. The data processing unit generates position distribution data for a plurality of time-series generated image data (S1603).

Next, the motion detector generates motion data representing the motion of the motion object among the plurality of objects by using the image data. The data processing unit generates motion data for a plurality of time-series generated image data (S1604).

The steps of generating the location distribution data and generating the motion data may be performed simultaneously, or any one data generating process may be performed first. However, the data generation step of any one of the location distribution data generation and the motion data does not necessarily precede the other data generation step.

Next, the controller compares the position distribution data and the motion data of the image data to generate abnormal entity data indicating the abnormal entity. The control unit compares the position distribution data and motion data of the plurality of image data to calculate the cumulative number of motion detection and non-motion detection of the plurality of objects, and collect abnormal object data according to the cumulative number of motion detection and non-motion detection. can be generated (S1605).

Next, the controller controls pixel display of a plurality of objects on the image data according to the cumulative number of motion detection and non-motion detection of the abnormal entity data. The control unit classifies the object into normal and abnormal objects according to the number of times the movement of a specific object is not detected and the number of times the movement is detected, and displays pixel values corresponding to the normal object and the abnormal object differently on the image data (S1606).

The following Equation 1 may be applied to the abnormal object detection method according to the embodiment.

[Equation 1]

Pixel _t = Pixel _{t -1} (1-μ) + ㎼ _t - F _t

In Equation 1, μ is an update parameter and may be changed according to setting.

In Equation 1, Pixel _t and Pixelt-1 are abnormal object data, which is a value for indicating whether an abnormal object exists in a pixel, and may mean the density of a pixel. The pixel with a high probability of having an anomaly is displayed in a darker color. For example, if there is no probability that an anomaly exists, the primary color (white) is displayed. The higher the probability of an anomaly, the closer it is expressed to red. will make it Therefore, Pixel _t and Pixelt-1 can be set to have a value between 0 and 1, and the closer to 0, the closer to the primary color (white), and the closer to 1, the more red.

In Equation 1, Pixel _t-1 is abnormal entity data of the immediately preceding frame in which position distribution data and motion data are continuously reflected. In Equation 1, Pixel _t is abnormal object data updated by applying the position distribution data and motion data of the current frame.

In Equation 1, Wt may be position distribution data of the current frame. The location distribution data may have a value between 0 and 1 as a probability that an object exists in the corresponding pixel. The update parameter μ may be applied to the location distribution data. μ is a very small value, for example 0.001. That is, the position distribution data must be continuously reflected for a long time to be controlled so that it is gradually displayed in the pixel.

In Equation 1, F _t may be motion data of the current frame. The motion data is obtained by calculating the absolute value of the motion vector and may have a value of 0 or more. Since the size of the motion vector corresponds to the speed of the object, it can have a value of 1 or more. Since a separate parameter is not reflected in the motion data, when motion is detected in the corresponding pixel, the display of the corresponding pixel is controlled to be initialized.

Alternatively, the following Equation 2 may be applied to the abnormal object detection method according to the embodiment.

[Equation 2]

Pixel _t = Pixel _{t -1} (1-μ+ ε) + ㎼ _t - F _t

※μ: update parameter, ε: offset parameter

In Equation 2, the offset parameter ε is added in Equation 1, and the same description as in Equation 1 is omitted. The offset parameter ε is a parameter that adjusts the accumulation of position distribution data and may have a value of 1/10 to 1/100 compared to μ.

Alternatively, the following Equation 3 or Equation 4 may be applied to the abnormal object detection method according to the embodiment.

[Equation 3]

Pixelt = Pixelt-1 (1-μ) + μWt - κFt

[Equation 4]

_{Pixel t = Pixel t -1 (1} -μ + ε) + ㎼ t - κF t

※μ: update parameter, ε: offset parameter, κ: update parameter

Equation 3 or Equation 4 is _{obtained by multiplying motion data F t} by the update parameter κ, and the same contents as Equations 1 and 2 are omitted. The constant κ is a parameter that adjusts the accumulation of motion data.

Equation 5 below may be additionally applied to the abnormal entity detection method according to Equations 1 to 4.

[Equation 5]

max(Equation 1,2,3 or 4, 0)

Equation 5 is an equation for preventing the value of Equation 1, 2, 3 or 4 from falling below zero. For example, when _{the size of the motion data F t} becomes larger than the sum of other parameter values, and the value of Equation 1, 2, 3 or 4 becomes a negative number smaller than 0, it is corrected so that it can be displayed as 0. control method to correct it.

17 is a flowchart of a method for detecting an anomaly according to an embodiment of the present invention.

Referring to FIG. 17 , first, the photographing unit captures a first image including a plurality of objects. The photographing unit is disposed inside the kennel to photograph a plurality of objects including poultry (S1701).

Next, the photographing unit generates the first image data by using the first image including the plurality of objects. The first image data may mean a single frame (S1702).

Next, the data processing unit generates first position distribution data representing the position distribution of a plurality of objects by using the first image data (S1703).

Next, the motion detector generates first motion data representing the motion of the motion object among the plurality of objects by using the first image data (S1704).

The steps of generating the first location distribution data and generating the first motion data may be performed simultaneously, or any one data generation process may be performed first. However, the step of generating any one of the first position distribution data generation and the first motion data does not necessarily precede the other data generation step.

Next, the controller compares the first location distribution data and the first motion data to generate first abnormal entity data indicating the abnormal entity. The controller may compare the first position distribution data and the first motion data with respect to the first image data to generate the first or more object data according to the movement of the plurality of objects ( S1705 ).

Next, the photographing unit captures a second image including a plurality of objects ( S1706 ).

Next, the photographing unit generates second image data by using the second image including the plurality of objects. The second image data may mean a single frame (S1707).

Next, the data processing unit generates second position distribution data representing the position distribution of a plurality of objects by using the second image data (S1708).

Next, the motion detector generates second motion data representing the motion of the motion object among the plurality of objects by using the second image data (S1709).

The steps of generating the second location distribution data and generating the second motion data may be performed simultaneously, or any one data generation process may be performed first. However, the data generation step of any one of the second position distribution data generation and the second motion data does not necessarily precede the other data generation step.

Next, the control unit generates second abnormal entity data by comparing the first abnormal entity data, the second location distribution data, and the second motion data. The control unit compares the first or more entity data with the second location distribution data and the second motion data to calculate the cumulative number of motion detections of the plurality of entities and the cumulative number of motion non-detections of the plurality of entities, and the cumulative number of motion detections and the cumulative number of motion non-detections The second or more entity data is generated according to the number of times (S1710).

Next, the controller controls display of pixels for a plurality of objects on the image data according to the second or more object data. The control unit classifies the specific object into normal and abnormal objects according to the number of times the movement of a specific object is not detected and the number of times that the movement is detected, and displays pixel values corresponding to the normal object and the abnormal object differently on the image data (S1711).

Although the steps S1701 to S1711 are briefly illustrated as generating the first abnormal entity data and the second abnormal entity data, the abnormal entity data is continuously generated and updated as image data is continuously generated through image capturing, so that the pixel act to control the display.

The term '~ unit' used in this embodiment means software or a hardware component such as a field-programmable gate array (FPGA) or ASIC, and '~ unit' performs certain roles. However, '-part' is not limited to software or hardware. The '~ unit' may be configured to reside on an addressable storage medium or may be configured to refresh one or more processors. Thus, as an example, '~part' refers to components such as software components, object-oriented software components, class components, and task components, and processes, functions, properties, and procedures. , subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables. The functions provided in the components and '~ units' may be combined into a smaller number of components and '~ units' or further separated into additional components and '~ units'. In addition, components and '~ units' may be implemented to play one or more CPUs in a device or secure multimedia card.

Although the above has been described with reference to the preferred embodiments of the present invention, those skilled in the art can variously modify and change the present invention within the scope without departing from the spirit and scope of the present invention as set forth in the claims below. You will understand that it can be done.

100: imaging device
111: shooting department
112: data processing unit
113: motion detection unit
114: control unit
115: communication department
116: display unit
117: user interface unit
118: encoding unit
119: database
120: light source unit
121: pan tilt part

Claims (10)

a data processing unit configured to generate position distribution data representing a position distribution of the plurality of entities by using image data generated from an image including a plurality of entities;
a motion detection unit generating motion data representing a motion of a motion object among the plurality of objects by using the generated image data; and
Comprising a control unit for generating abnormal entity data representing the abnormal entity by comparing the position distribution data and the motion data,
The position distribution data is data in which the presence or absence of an object is displayed as a probability for each pixel on the image data,
The motion data is data indicating whether a motion exists for each pixel on the image data,
The control unit further reflects data indicating the existence of an object as a probability for each pixel to the probability of the existence of an object in the past, and applies it to the pixel value of the corresponding pixel on the location distribution data, wherein a motion is present in the motion data. The abnormal object detection device generates the abnormal object data by initializing the pixels located at the same position as the
According to claim 1,
The control unit displays an initialized pixel as a primary color on the image data.
According to claim 1,
The control unit emphasizing and displaying the corresponding pixel as the pixel value increases.
According to claim 1,
The control unit generates the abnormal entity data according to Equation 1 below.
[Equation 1]
Pixel _t = Pixel _t-1 (1-μ) + μW _t - F _t
(In Equation 1, Pixel _t is the abnormal object data of the current frame, Pixel _t-1 is the abnormal object data of the previous frame, μ is the update parameter, W _t is the position distribution data of the current frame _{, F t is the current frame} is the operation data of , and F _t has a value of 1 or more, but Pixel _t , Pixel _t-1 and Wt are set to have a value between 0 and 1)
a photographing unit generating image data by photographing an image including a plurality of objects;
a data processing unit for generating position distribution data representing a position distribution of the plurality of objects by using the image data;
a motion detection unit generating motion data representing a motion of a motion object among the plurality of objects by using the image data; and
Comprising a control unit for generating abnormal entity data representing the abnormal entity by comparing the position distribution data and the motion data,
The position distribution data is data in which the presence or absence of an object is displayed as a probability for each pixel on the image data,
The motion data is data indicating whether a motion exists for each pixel on the image data,
The control unit further reflects data indicating the existence of an object as a probability for each pixel to the probability of the existence of an object in the past, and applies it to the pixel value of the corresponding pixel on the location distribution data, wherein a motion is present in the motion data. An imaging device for generating the abnormal object data by initializing pixels located at the same position as .
6. The method of claim 5,
The control unit displays the initialized pixel as a primary color on the image data.
6. The method of claim 5,
The control unit emphasizing the corresponding pixel as the pixel value increases.
generating image data by photographing an image including a plurality of objects;
generating position distribution data representing the position distribution of the plurality of objects by using the image data;
generating motion data representing a motion of a motion object among the plurality of objects by using the image data; and
Comprising the step of generating abnormal entity data representing the abnormal entity by comparing the position distribution data and the motion data,
The position distribution data is data in which the presence or absence of an object is displayed as a probability for each pixel on the image data,
The motion data is data indicating whether a motion exists for each pixel on the image data,
In the generating of the abnormal entity data, data indicating the existence of an entity for each pixel as a probability is additionally reflected in the probability of the existence of an entity in the past and applied to the pixel value of the corresponding pixel on the location distribution data, A method for detecting anomalies in data, wherein pixels at the same position as pixels in motion are initialized to generate the abnormal entity data.
9. The method of claim 8,
and displaying the initialized pixels as primary colors on the image data.
9. The method of claim 8,
and emphasizing and displaying the corresponding pixel as the pixel value is larger.

Images