KR20200085418A - Targeted automatic identification and traceable artificial intelligence devices and methods - Google Patents

Abstract

The present invention relates to a device and a method for automatically recognizing, identifying, and tracking a target and, more specifically, to an artificial intelligence device and an artificial intelligence method capable of automatically sensing distinct temperature of a target using two non-contact type multi-infrared temperature sensors corresponding to each of both eyes to accurately identify a size and a distance of a sensed target and track movement of the identified target.

Description

Targeted automatic identification and traceable artificial intelligence devices and methods}

The present invention relates to an apparatus and a method for automatically recognizing, identifying, and tracking a target. In particular, the present invention uses two non-contact multi-infrared temperature sensors (hereinafter referred to as "IR sensors") corresponding to both eyes. The present invention relates to an artificial intelligence device and method capable of automatically identifying and tracking a target in three dimensions.

In recent years, due to the development of the electronics and telecommunications industry, security and security systems can be easily deployed not only in major areas such as banks, museums, important cultural properties, national industrial institutions, etc., but also in businesses and homes, and real-time images of intruders and outside intruders are taken. However, there are conditions for monitoring. Accordingly, various apparatuses and methods for alerting an operator with a plurality of sensing means for sensing various abnormal conditions in the monitoring area and means for transmitting and receiving a situation sensed from the sensing means by wire or wireless have been proposed.

Briefly looking at the monitoring and tracking methods according to the prior art, a method of detecting the approach of an object into a certain space using an access sensor, a method of detecting the position and movement of an object using an image processing technology, and a position of a target by sensing the direction of sound Methods are used to detect, and more advanced technologies use radar, laser, and ultrasound to detect the appearance of a target and detect its position and movement.

In addition, this target detection method is applied to a surveillance robot, etc., and monitors a certain area according to the operation of a user terminal in an area requiring security and crime prevention. A robot has appeared. In addition, as the robot technology develops, the target detection method described above is expanding not only to the crime prevention field, but also to applications such as cleaning, security, animal care, and document transmission and reception.

However, in the case of the target detection method using the access sensor according to the prior art, it only informs that the object is located within the designated detection area and does not provide accurate information about where the detected object is located in the detection area. There is this.

On the other hand, in the case of the target detection method using the image processing technology, the frame data of the image screen captured by the camera is received, and the object motion vector that has appeared through comparison with the previously stored frame data is calculated, and this motion The object is tracked based on the motion vector information of the object area calculated by the vector calculation. However, the target detection and tracking method according to the image processing technology is a method of detecting color change in an image and tracking detection and movement of the appearance of an object by digital image processing such as edge detection. Calculation of a large amount of data is required, and accordingly there is a problem in that the time from shooting to detection is very delayed. In addition, Korean Patent Application Publication No. 2004-33986 (published on April 28, 2004) discloses a technique related to an "artificial intelligence video surveillance system that provides a distance and a moving direction of an animal". According to this technology, two integrated infrared light cameras are mounted in parallel to form a stereo vision system in an imaging device having the same conditions as both eyes of a human body, and the stored image is compared with the current image to create a threshold for making a difference image. By using an adaptive threshold value, it provides a method of minimizing errors in the extraction of a moving object and calculating information such as distance, volume, and direction of the moving object with images acquired from two cameras.

Looking at the techniques presented above, a surveillance camera is usually used to detect the position and direction of movement of the object to be monitored and use the detected result. Surveillance cameras are usually composed of a sensor capable of detecting an object to be monitored and a CCTV (Closed-Circuit Television) for notifying the monitor by capturing the motion of the object being monitored through the sensor. In addition, when there is movement in the object to be monitored, a tracking sensor for detecting movement of the object to be monitored and tracking it is configured separately or integrated with the sensor. In general, infrared sensors are used for the sensors, and the infrared sensors detect the temperature emitted by the monitored object and compare the detected temperature and the reference temperature to determine the appearance of the monitored object.

Monitoring devices according to the prior art are a sensor for monitoring the position and movement of the object to be monitored, a control unit that receives a signal from the sensor to calculate the position and movement direction of the object to be monitored, and generates a control signal according to the control signal of the controller. It consists of a driving unit that controls the direction of CCTV and a memory unit that records and stores information about the images and objects detected through the CCTV. However, in the monitoring apparatus according to the prior art, since the control unit that receives the detection signal of the first monitoring object must determine the moving direction of the monitoring object according to the sensor signal and transmit it to the driving unit to control the driving unit, the moving direction of the monitoring object is large. Or, if the movement speed is high, it is impossible to track it quickly and accurately.

In addition, even though the CCTV cannot accurately photograph the three-dimensional shape of the object to be monitored, unnecessary image data is included, so the processing capacity and storage capacity of the captured image are very large compared to the required data, and thus there is an inefficient problem in capacity management.

Accordingly, after installing at least a plurality of infrared sensors for detecting a monitoring object through a temperature difference in different directions at a certain place, in the installed infrared sensors, the detected infrared sensor detects the infrared sensor and detects the monitoring An apparatus for detecting an object position direction using an infrared sensor to detect a direction in which an object is located, and setting the detected direction to a direction in which the object is located, so that a control operation is performed, and a control method thereof are proposed.

In particular, Korean Patent Application Publication No. 2002-18515 (published on March 8, 2002) identifies the infrared sensor module that detects the object, and detects the direction in which the object is located by reading the light-receiving range of the identified infrared sensor module. Disclosed is an apparatus and method for measuring a distance from an object by adjusting a laser position of a laser range finder in a direction in which the detected object is located.

In addition, a method of providing a plurality of cameras, one camera to detect the appearance of an object, and the other camera to track the detected object movement is published in Korean Patent Publication No. 2006-69799 (2006.06.22 published), "Intelligent boundary robot system".

On the other hand, Korean Patent Publication No. 2004-63170 (published on February 16, 2006) discloses a technique related to "a robot having an intrusion detection function and a method for detecting the intrusion thereof". According to this technology, a robot having an intrusion detection function includes a speed sensor that measures a moving speed of a moving robot and at least first and second infrared sensors that measure and output infrared rays generated from an intruder in real time while the robot is moving. A plurality of infrared sensors are mounted, and after receiving distance information between the first and second infrared sensors, the first analog output signal measured from the first infrared sensor and the second measured from the second infrared sensor according to the movement of the robot The moving speed of the robot measured from the analog output signal and the speed sensor is received in real time. In addition, an intrusion is detected and notified by comparing the first and second analog output signals based on the distance information and the moving speed, so that the intrusion can be detected even while the robot is moving.

However, since the sensing device according to the prior art detects only an object and a plane in a direction when detecting an object, it detects whether an object appears or not and only tracks the movement of the detected object and cannot identify the object. There is this.

In addition, even though the CCTV cannot accurately photograph the three-dimensional shape of the object to be monitored, unnecessary image data is included, so the processing capacity and storage capacity of the captured image are very large compared to the required data, and thus there is an inefficient problem in capacity management. In addition, CCTV is not only shooting a surveillance object, but rather shooting a screen that includes the surveillance object, so it is not possible to provide enough information to accurately distinguish the surveillance object, or infrared rays are required because the operator's visual identification is required. Even if an arbitrary object is detected by the temperature sensor, there is a problem that the detected object cannot be automatically identified.

In addition, when the sensing and tracking device having the above-described problems is applied to the robot, not only the incompleteness of the sensing and tracking itself, but ultimately, it is impossible to elicit a natural response of the robot to the object to be detected and tracked.

Therefore, by integrating highly developed technologies for each field, such as the existing spiritual processing technology, speech recognition technology, and non-contact multi-infrared temperature sensor, it automatically detects the appearance of multiple objects and identifies them with natural reaction to the detected objects. And AI devices and methods capable of tracking.

Accordingly, an object of the present invention is to provide an artificial intelligence device and method for automatically detecting the appearance of multiple targets, grasping the size and position of the detected targets, and tracking the movement of the identified targets.

In addition, another object of the present invention is to provide an artificial intelligence device and method capable of accommodating a natural reaction occurring to a tracker when detecting, identifying, and tracking a plurality of targets.

In addition, another object of the present invention is to provide an artificial intelligence device and method capable of realizing the movement of the face and pupil of a robot that actively responds to various external changes occurring in the process of detecting, identifying and tracking a plurality of targets. Is doing.

The AI device capable of automatically identifying and tracking a target according to the present invention for achieving the above objects is a first non-contact multi-infrared ray that detects a position of an emerging target by observing a predetermined detection area while moving according to a predetermined pattern. Temperature sensor Position of targets detected according to the detection signals of targets of the second non-contact multi-infrared temperature sensor and the first non-contact multi-infrared temperature sensor detecting the size and distance of the targets detected by the first non-contact multi-infrared temperature sensor Control unit for calculating and moving the position of the calculated target by controlling the second non-contact multi-infrared temperature sensor, and calculating the size and distance of the detected targets according to the target detection signal of the second non-contact multi-infrared temperature sensor It is characterized by consisting of.

In addition, the artificial intelligence method capable of automatic target identification and tracking according to the present invention for achieving the above objects is to move the first non-contact multi-infrared temperature sensor according to a predetermined pattern to scan a predetermined detection area, and A process of receiving target detection signals generated when scanning a detection area. A process of calculating the maximum temperature and two-dimensional coordinates of targets detected from the received target detection signals. A second non-contact multi-infrared temperature sensor is coordinates of the calculated targets. Process of calculating the size and distance of the targets by receiving the detection signal from the second non-contact multi-infrared temperature sensor, if there is a change in the detection area where the targets are located, recalculating the coordinates of the changed targets; And calculating a moving direction of the targets from the calculated target coordinates and the recalculated target coordinates.

In addition, the AI device capable of automatic target identification and tracking according to the present invention for achieving the above objects is a first non-contact type sensing position of emerging targets by observing a predetermined detection area while moving according to a predetermined pattern Left and right eye-shaped sensors each having a multi-infrared temperature sensor and a second non-contact multi-infrared temperature sensor that senses the size and distance of targets sensed by the first non-contact multi-infrared temperature sensor. Sensor driving unit for driving the rotation of the pattern The driving unit for driving the rotation of the upper, lower, left and right and circular patterns of the head mounted with the eye sensor controls the sensor driving unit and the device driving unit to drive the eye sensor according to a predetermined pattern, It is characterized in that it consists of a control unit that scans a predetermined surveillance area and calculates the size and position of the detected targets according to the target detection signals received from the eyeball sensor. The artificial intelligence device capable of automatic target identification and tracking according to the present invention is a video camera that captures images of targets. It is provided in a cylindrical shape on the outer circumferential surface of the video camera. The sensor is provided in a cylindrical shape on the outer circumferential surface of the non-contact multi-infrared temperature sensor for tracking, and consists of a non-contact multi-infrared temperature sensor for identification that detects the size and distance of targets detected by the non-contact multi-infrared temperature sensor for tracking while moving in a circular pattern. It is characterized by.

As described above, the present invention has an effect of automatically detecting the appearance of multiple targets, grasping the size and position of the detected targets, and tracking the movement of the identified targets.

In addition, the present invention has an effect capable of realizing the movement of the face and pupil of the robot that actively responds to various external changes occurring in the process of detecting, identifying and tracking a plurality of targets.

In addition, the present invention has an effect that, when detecting, identifying, and tracking a plurality of targets, expresses a natural response to an artificial intelligence device, thereby giving a sense of bond to a visitor and a threat to an intruder.

1 is an internal structure diagram of a non-contact multi-infrared temperature sensor applied to the present invention,
Figure 2 is a view showing the detection range of the left / right pupil implemented with the non-contact multi-infrared temperature sensor of Figure 1,
3 is a view showing an artificial intelligence method capable of target detection, identification, and tracking according to a preferred embodiment of the present invention,
4 is a view for explaining a method for obtaining 2-D and 3-D coordinates of a monitored object by a trigonometric function;
5 is an exemplary diagram of an artificial intelligence device capable of target detection, identification, and tracking by applying the artificial intelligence method of FIG. 3;
FIG. 6 is another work of the AI device capable of target detection, identification, and tracking by applying the AI method of FIG. 3.
Illustration,
7 is a functional block configuration diagram of an AI device capable of target detection, identification, and tracking according to the present invention;
8 is a control flow diagram of an artificial intelligence method capable of target detection, identification and tracking according to the present invention.

Hereinafter, detailed descriptions of preferred embodiments of the present invention will be described with reference to the accompanying drawings. In the following description, specific specific matters are shown, which are provided to help a more comprehensive understanding of the present invention. And in the description of the present invention, if it is determined that a detailed description of related known functions or configurations may unnecessarily obscure the subject matter of the present invention, the detailed description will be omitted.

In the detailed description to be described later, representative embodiments of the present invention for achieving the above-described technical problems will be presented. In addition, in the above embodiment, for convenience of explanation of the present invention, an apparatus and method for monitoring a predetermined space using multiple IR sensors having a specific arrangement will be described, but these specific sensors and related names, and specific environmental conditions are described. The scope of the present invention does not limit the scope of the present invention, and of course, it can be applied to a surveillance system having a similar technical background, a humanoid robot, an insectoid robot, and the like.

1 is an internal structure diagram of a non-contact multi-infrared temperature sensor applied to the present invention, and FIG. 2 is a view showing a detection range of left/right pupils implemented with the non-contact multi-infrared temperature sensor of FIG. 1.

1 and 2, a non-contact multi-infrared temperature sensor (hereinafter referred to as "IR sensor") applied to the present invention is composed of two IR sensors that serve as both left and right eyes. The IR sensor R serving as the right eye (or the left eye) has an array of 1 * 8 to detect the position of the target to be detected by observing a wide range of areas. At this time,

The arrangement of the group IR sensor R is not necessarily limited to an arrangement of 1 * 8, and it is natural that other arrangements may be made as necessary. The IR sensor L, which plays the role of the left eye (or right eye), has an arrangement of 4 * 4 in order to further sense the position of the target detected by the IR sensor R. The arrangement of the IR sensor L is also not limited.

Alphabets (A to P) or Arabic numerals (1 to 8) corresponding to each subsensor constituting the IR sensors (L, R) respectively measure the temperature value of the magnetic sensing area at a spaced distance. Referring to FIG. 2, the IR sensor R recognizes the appearance of a target by scanning a wide range of areas up, down, left, and circular to detect a temperature different from a reference temperature. In addition, the IR sensor (L) detects a target by scanning a region of a relatively narrow range up, down, left, and circular to further segment and detect the corresponding region. At this time, the up and down and left and right movements of the IR sensors L and R are sensed by driving the sensor-equipped mounting portion (eg, the robot's eyeball) in a periodic or aperiodic pattern according to a pre-programmed process. The area can be observed. According to the current level of technology, such an eye type sensor can move beyond the movement of the human pupil. Since the mechanical action and optical mechanism of the eye-shaped sensor are well-known techniques, the description is omitted.

Hereinafter, an artificial intelligence method capable of target detection, identification, and tracking according to the present invention will be described in detail with reference to FIGS. 3 and 4. 3 is a diagram showing an artificial intelligence method capable of target detection, identification, and tracking according to a preferred embodiment of the present invention, and FIG. 4 is a view for explaining a method of obtaining 2D and 3D coordinates of a monitored object by a trigonometric function It is a drawing.

As shown in FIG. 3, the target detection, identification and tracking method according to the present invention monitors the appearance of the target while the IR sensor R moves up, down, left and right and scans the tracking section. At this time, the movement of the IR sensor R may be implemented in a case where the sensor is manufactured in the form of an eyeball or when the sensor is mounted on a circular driving device, the related driving device moves according to the scanning pattern. The IR sensor (R) can track a wide range of targets. In addition, when implemented as an eyeball sensor and mounted on the eyeball of a humanoid robot, the head of the robot moves according to the scanning pattern, so that the sensor can obtain the same movement as the scanning pattern necessary for monitoring the corresponding tracking section.

FIG. 3 shows an example of a case where the IR sensor R detects a temperature rise in a sensing area covered by the sub-sensors 6 and 7 while performing scanning for wide target tracking. I When the IR sensor R detects a temperature rise in the detection area, it calculates the maximum temperature and position (coordinates) of the detection area. At this time, the calculated position of the target is obtained as two-dimensional coordinates.

When the target detection of the IR sensor (R) and the calculation of the maximum temperature and position are complete, the head or left eye of the robot moves and the IR located in the detection area covered by the subsensors (4, 5) of the IR sensor (R) The detection area of the sensor L moves to the detection area of the subsensors 6 and 7 of the IR sensor R where the target is detected. When this is implemented in the form of an eyeball of a robot, the movement of the IR sensor (L) moves to the detection area of the subsensors (6, 7) of the IR sensor (R) so that the robot's pupil moves so that the IR sensor (L) moves. It can then be programmed to move the head to look at the target.

Subsequently, the IR sensor L moved to the area where the target is located calculates the size and distance of the target by using the sensed target and the angle formed by itself and the angle formed by the IR sensor R with the target and the distance from the target. . At this time, the calculated target size and position are obtained in three-dimensional coordinates.

4 is for explaining the mathematical basis for calculating the two-dimensional and three-dimensional coordinates of the target, using a trigonometric calculation method. As shown in Fig. 4, the distance (from Eye L to Eye R) is a value that is already known as a fixed value, and when the angles (Eye L and Eye R) are known, the distance to Target A is calculated. Can. Since the IR sensors L and R applied to the present invention are array sensors, since the Eye L and Eye R values are plural, it is possible to obtain a plurality of coordinates for the target A.

On the other hand, in the description of FIGS. 3 and 4, it has been described that the IR sensor R and the IR sensor L are sequentially moved in order to detect a target and calculate its temperature and position. , R), it should be noted that the scanning operation can be performed simultaneously for the detection of the target.

The target detection, identification, and tracking method of FIG. 3 may be applied even when there are multiple targets. Briefly, when two or more targets are detected by the IR sensor R, the temperature of each target is first measured. Then, the IR sensor L accurately measures the size and temperature of each target, and identifies the target based on the measured size and temperature.

In addition, tracking of the moving direction of the target according to the present invention is easily performed because the IR sensor applied to the present invention is an array sensor. When the identified target moves, the area of the sub-sensor where the target is sensed changes over time, so the movement of the target is easily tracked by this detection information. In addition, since the current position of the target is located at the center of the IR sensor, it is possible to predict the target's moving direction.

5 and 6 is an exemplary view of an AI device capable of target detection, identification, and tracking by applying the AI method of FIG. 3, with reference to FIGS. 5 and 6, target detection, identification, and Various embodiments of the AI device to which the AI method capable of tracking are applied will be described.

Figure 5 is an example of applying a single eye of an insect such as a dragonfly to the artificial intelligence device according to the present invention. As shown in Figure 5, the artificial intelligence device according to an embodiment of the present invention is a video camera (1), tracking IR sensor (2), identification IR sensor (3), near-far distance adjustment lens (4) It is composed of, and the front view and the side section view are shown together. 5, (A), (B) and

(C) shows the camera image range, the tracking range of the tracking IR sensor, and the identification range of the IR sensor for identification.

The video camera 1 is provided with its own zoom function and an optical zoom function using a lens 4 for near-far adjustment. That is, the near-far distance adjusting lens 4 or the image camera 1 moves back and forth to check the target image to a required size.

The movements of the IR sensors 2 and 3 can be adjusted in a circular pattern, respectively, to adjust the radiation angle of the sensor. The primary adjusted radiation angle enables a wide range of tracking and identification through the near-far lens 4. At this time, the radiation angles of the respective IR cells of the IR sensors 2 and 3 each have a unique value, and can be variously changed using the lens 4 for rotation and near-far adjustment.

6 is an embodiment in which the artificial intelligence device according to the present invention is applied to the eyes in the form of tentacles of an insect. As shown in FIG. 6, the identification IR sensor and the tracking IR sensor are provided in both right and left eyes, a camera is provided in the center, and a voice recognition sensor is provided in both left and right sides to detect sound with temperature in stereo. It was composed. According to the embodiment of FIG. 6, it is possible to support 3D detection of a target including a voice, and the installation position of the AI device may be installed before and after, up and down, as well as the shape of an eye of a dragonfly.

Hereinafter, an artificial intelligence device and method capable of automatically identifying and tracking a target according to the present invention including the above-described embodiments will be described with reference to FIGS. 7 and 8. 7 is a functional block diagram of an AI device capable of target detection, identification, and tracking according to the present invention, and FIG. 8 is a control flowchart of an AI method capable of target detection, identification and tracking according to the present invention.

Referring to FIG. 7, when the AI device according to the present invention is configured according to its functional unit, it includes a control unit 110, a left IR sensor 121, and a right IR sensor 123 for overall control of the AI device. The sensor unit 120, the sensor driving unit 130 for driving the sensor unit 130 under the control of the control unit 110, the sensor unit 120, a device for performing another function, such as a robot ( When mounted in 170), the device driving unit 170 drives the IR sensors, and includes a display unit 150 including a display device or a speaker for an operator, and a key input device or a microphone. It consists of an input unit 160. According to the above configuration, the artificial intelligence device according to the present invention performs target detection, identification, and tracking methods. In addition, although not illustrated in FIG. 7, it is preferable to display the detected target as an image to an operator, including an image capturing unit, as illustrated in FIGS. 5 and 6, showing embodiments of the present invention.

Referring to FIGS. 7 and 8, in the artificial intelligence method according to the present invention, the control unit 110 recognizes the target for the first time by receiving the target detection signal through the detection area scanning of the IR sensors R and 123. The initial target recognition is performed through 201 scanning. The scanning of step 201 is performed according to the driving of the sensor unit 120 of the sensor driving unit 130 under the control of the control unit 110. If the temperature of a specific range is detected by a specific sub-sensor from the IR sensors R and 123 in step 203, the controller 110 proceeds to step 205 to calculate the maximum temperature and two-dimensional coordinates of the target.

Subsequently, the control unit 110 proceeds to step 207, and controls the sensor driving unit 130 to move the IR sensors L and 121 to an area where the target is detected by the IR sensors R and 123. When the IR sensors (L, 121) move to the area where the target is detected, the control unit 110 receives the detection signals from the IR sensors (L, 121) in step 209 to 3D coordinate the size and distance of the target. Calculate exactly as.

The size, distance, and temperature of the target calculated in step 209 may be provided to the operator and the like through the display unit 150, and provided with statistical information on the size, distance, and temperature of the target in advance, and It can provide a prediction of the identity of a target based on it. Also, although not shown, a CCTV, a video camera, and the like are provided to accurately photograph the target based on the calculated target information, recognize the voice from the target, and provide the captured image and the recognized voice to the operator. It might be.

Subsequently, in step 213, if there is a change in the detection cell (the sensing area of the sub-sensor) of the target, in step 213, the controller 110 recognizes it from the signal input from the IR sensors, proceeds to step 215, and the sensor driving unit By controlling the 130, the IR sensors R and L are moved to the corresponding cell, and the next moving direction of the target may be predicted from the transition of the moving direction of the target.

Meanwhile, the control unit 110 controls the device driving unit 140 to move the device on which the sensor unit 120 is mounted, thereby moving the head of the robot when the IR sensor is mounted on a pupil such as a robot. By controlling this, the same result as the operation of the sensor driving unit 130 may be obtained.

In addition, when the IR sensor according to the present invention is mounted as a pupil on a robot or the like, the artificial intelligence device and method according to the present invention may cause the robot to react to the natural reactions that occur when the robot detects, identifies and tracks multiple targets. Be able to represent movement.

On the other hand, in the detailed description of the present invention, although specific embodiments have been described, various modifications are possible without departing from the scope of the present invention. Therefore, the scope of the present invention should not be limited to the described embodiments, but should be determined not only by the scope of the claims described below, but also by the scope and equivalents of the claims.

Claims (13)

An AI device capable of automatically detecting, identifying, and tracking targets, the first non-contact multi-infrared temperature sensor detecting a position of an emerging target by observing a predetermined detection area while moving according to a predetermined pattern. Calculate the positions of the detected targets according to the detection signals of the second non-contact multi-infrared temperature sensor and the first non-contact multi-infrared temperature sensor detecting the size and distance of the targets detected by the non-contact multi-infrared temperature sensor, 2 Targets composed of a control unit that calculates the size and distance of the detected targets according to the target detection signal of the second non-contact multi-infrared temperature sensor by controlling the non-contact multi-infrared temperature sensor to move to the position of the calculated targets AI device capable of automatic identification and tracking. According to claim 1, Image photographing unit for photographing the targets according to the size and distance of the targets calculated by the control unit Displaying an image photographed by the image photographing unit and a key input signal for controlling the control unit AI device capable of automatic identification and tracking of targets, further comprising an input. The target according to claim 2, further comprising a voice recognition sensor for recognizing the voices of the targets calculated by the controller and converting them into an audio signal, and a speaker for outputting the audio signal converted by the voice recognition sensor as voice. AI device capable of automatic identification and tracking. In an artificial intelligence method capable of automatically detecting, identifying, and tracking targets, the first non-contact multi-infrared temperature sensor is moved according to a predetermined pattern to scan a predetermined sensing area, and a target generated when scanning the sensing area The process of receiving a field detection signal The process of calculating the maximum temperature and two-dimensional coordinates of the targets detected from the received target detection signal The process of moving the second non-contact multi-infrared temperature sensor to the coordinates of the calculated targets The second The process of calculating the size and distance of the targets by receiving the detection signal from the non-contact multi-infrared temperature sensor. If there is a change in the detection area where the targets are located, the process of recalculating the coordinates of the changed targets and the coordinates of the calculated targets An artificial intelligence method capable of automatically identifying and tracking targets, including calculating the direction of movement of the targets from the coordinates of the recalculated targets. The method of claim 4, further comprising accumulating a result value for the calculated target movement direction and predicting a next movement direction of the targets from the accumulated result value.
Artificial intelligence method capable of automatic identification and tracking of targets, characterized by provision. The method according to claim 4, centered on the coordinates of the calculated targets, the calculated targets
Automatic identification of targets, characterized in that it further comprises a process to shoot according to the size and
AI method that can be traced. The method of claim 4, further comprising accumulating a result value for the calculated direction of movement of the targets and predicting a next movement direction of the targets from the accumulated result value.
Artificial intelligence method capable of automatic identification and tracking of targets, characterized by ships. According to claim 4, Recognizing the voice of the calculated target, the recognized voice
Automatic identification and tracking of targets characterized by further comprising the process of printing
Possible AI method. An artificial intelligence device capable of automatically detecting, identifying, and tracking targets, comprising: a first non-contact multi-infrared temperature sensor detecting a position of an emerging target by observing a predetermined sensing region while moving according to a predetermined pattern; and Left and right eyeball sensors each having a second non-contact multiple infrared temperature sensor that senses the size and distance of the targets detected by the first non-contact multi-infrared temperature sensor. Driving unit Device driving unit for driving the rotation of the upper, lower, left, and circular patterns of the head mounted with the eye-shaped sensor controls the sensor driving unit and the device driving unit to drive the eye-shaped sensor according to a predetermined pattern to scan a predetermined monitoring area. , An artificial intelligence device capable of automatically identifying and tracking targets comprising a control unit that calculates the size and position of the detected targets according to the target detection signals received from the eyeball sensor. 10. The method of claim 9, The control unit, The first contactless multi-infrared temperature sensor of the eye-shaped sensor is a predetermined for detecting the appearance of targets by observing the entire monitoring area
Control the sensor driving unit to provide movement according to a pattern, and the first non-contact
When the multiple infrared temperature sensor detects targets, the second non-contact of the eyeball sensor
Multi-infrared temperature sensor detected by the first non-contact multi-infrared temperature sensor
The eastern part of the sensor is controlled to move to the position of targets, and the eye-shaped sensor is mounted
Characterized in that the control unit to drive the device head to the sensed target head
AI device capable of automatic identification and tracking of targets. In the artificial intelligence device that can automatically detect, identify and track targets,
A video camera that takes images of targets. It is formed in a cylindrical shape on the outer circumferential surface of the video camera.
Non-contact type tracking for detecting the appearance of targets while moving in a circular pattern
On the outer peripheral surface of the middle infrared temperature sensor and the tracking non-contact multi-infrared temperature sensor
Cylindrical, non-contact multi-infrared for tracking while moving in a circular pattern
Non-contact multiple for identification to detect the size and distance of the targets detected by the line temperature sensor
An artificial intelligence device that can automatically identify and track targets composed of infrared temperature sensors. 12. The method of claim 11, wherein the imaging camera, the contactless multi-infrared temperature sensor for tracking
Standing in front of the non-contact multi-infrared temperature sensor for identification and movement
Automatic identification of targets, characterized by further comprising a lens for near-far adjustment
And an AI device capable of tracking. 12. The method of claim 11, wherein the imaging camera, the contactless multi-infrared temperature sensor for tracking
Standing and the front of the non-contact multi-infrared temperature sensor for identification, an artificial intelligence device capable of automatic identification and tracking of targets, further comprising a near-distant adjustment lens capable of moving back and forth.

Images