KR20160103844A - Method and Apparatus for counting the number of person - Google Patents

Abstract

According to an embodiment of the present invention, a system for counting the number of people and a method thereof are disclosed. According to the embodiment of the present invention, a device for counting the number of people comprises: a correction unit configured to calculate a correlation between a distance camera and a thermal imaging camera which obtain images with respect to the same scene in different directions; a detection unit configured to detect at least one candidate area in a thermal image, obtained by the thermal imaging camera, by using the correlation wherein the at least one candidate area corresponds to an object, detected in a distance image obtained by the distance camera; and a counting unit configured to determine whether the object is a person based on a temperature of the at least one candidate area.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention [0001]

An embodiment of the present invention relates to a human counting system and method, and to a human counting system and method based on a heterogeneous camera.

Due to large and small casualties, there is an increasing demand for safety. If an accident occurs, the number of people who have stayed in a specific space for the purpose of identifying the rescue or victim is an important factor in understanding the situation.

However, the conventional human counting system has many false positives due to false positives or undetected people. Therefore, for accurate person counting, it is important to increase the counting accuracy.

Korean Patent Publication No. 2014-0040527

Embodiments of the present invention are intended to provide a system and method that can accurately count persons even at gates with many cargoes.

According to an aspect of the present invention, there is provided a human counting apparatus including: an interpolator for calculating a correlation between a distance camera and a thermal camera that acquire images in different directions with respect to the same scene; A detector for detecting at least one candidate region corresponding to an object detected in the distance image acquired by the distance camera, from a thermal image acquired by the thermal imaging camera using the correlation; And a coefficient unit for determining whether the object is a person based on the temperature of the at least one candidate region.

The distance camera may acquire a top-view distance image, and the thermal camera may acquire a side-view thermal image.

The detecting unit may extract at least one local feature region of the object from the distance image and detect at least one candidate region corresponding to the at least one local feature region in the thermal image using the correlation have.

The counting unit may select at least one temperature sensing region in the at least one candidate region and may determine the object as a person when the temperature of the selected temperature sensing region falls within a reference temperature range.

The counting unit may determine that the object is a person if the ratio of the region belonging to the reference temperature range in the selected temperature sensing region is equal to or greater than a reference ratio.

The detection unit may detect skeleton information for at least a part of the object in the distance image, and may detect at least one local feature region of the object from the skeleton information.

The detecting unit may model a shape by reconstructing at least a part of the object in the distance image in a slice manner and detect a candidate region corresponding to the modeled shape in the thermal image using the correlation.

The counting unit may determine the object as a person if the ratio of the region belonging to the reference temperature range in the candidate region is not less than the reference ratio.

A human factor system according to an embodiment of the present invention includes a distance camera and a thermal image camera that acquire images in different directions with respect to the same scene; And detecting at least one candidate region corresponding to an object detected in the distance image acquired by the distance camera from the thermal image acquired by the thermal image camera using the correlation between the distance camera and the thermal image camera, And a person counting device for determining whether the object is a person based on the temperature of the candidate region.

Wherein the system further comprises a calibration tool including a body of a cube structure and a heating element disposed at a vertex and emitting heat, wherein the human counting device comprises: And the correlation between the thermal image and the thermal image can be calculated.

The distance camera may acquire a top-view distance image, and the thermal camera may acquire a side-view thermal image.

Wherein the human counting device selects at least one temperature sensing region in the at least one candidate region and determines that the object is a person if the ratio of the region belonging to the reference temperature range in the selected temperature sensing region is equal to or greater than a reference ratio .

According to an aspect of the present invention, there is provided a human counting method using a human counting apparatus, comprising: calculating a correlation between a distance camera and a thermal camera that acquire images in different directions with respect to the same scene; Detecting at least one candidate region corresponding to an object detected in the distance image acquired by the distance camera from the thermal image acquired by the thermal image camera using the correlation; And determining whether the object is a person based on the temperature of the at least one candidate region.

The distance camera may acquire a top-view distance image, and the thermal camera may acquire a side-view thermal image.

Wherein the detecting comprises: extracting at least one local feature region of the object from the distance image; And detecting at least one candidate region corresponding to the at least one local feature region in the thermal image using the correlation.

Wherein the human determining step comprises: selecting at least one temperature sensing region in the at least one candidate region; And determining the object as a person if the temperature of the selected temperature sensing area belongs to the reference temperature range.

The person determining step may include determining that the object is a person if the ratio of the region within the reference temperature range in the selected temperature sensing region is equal to or greater than a reference ratio.

Wherein the detecting step comprises the steps of: detecting skeleton information for at least a part of the object in the distance image; And detecting at least one local feature region of the object from the skeleton information.

Wherein the detecting step includes: reconstructing at least a part of the object in the distance image in a sliced manner to model the shape; And detecting a candidate region corresponding to the modeled shape in the thermal image using the correlation.

The person determining step may include determining that the object is a person if the ratio of the region belonging to the reference temperature range in the candidate region is equal to or greater than a reference ratio.

The human counting system and method according to the embodiment of the present invention can accurately count persons even at the gates having many cargoes.

1 is a block diagram that schematically illustrates a human factor system in accordance with an embodiment of the present invention.
2 is a diagram illustrating a photographing method of a camera according to an embodiment of the present invention.
3 is a view for explaining candidate region detection using a distance camera and a thermal image camera according to an embodiment of the present invention.
4 is a view for explaining candidate region detection using a distance camera according to another embodiment of the present invention.
5 is a diagram for explaining a method of calculating a correlation between a distance camera and a thermal image camera according to an embodiment of the present invention.
6 is a flowchart illustrating a method of counting persons according to an embodiment of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS The present invention is capable of various modifications and various embodiments, and specific embodiments are illustrated in the drawings and described in detail in the detailed description. It is to be understood, however, that the invention is not to be limited to the specific embodiments, but includes all modifications, equivalents, and alternatives falling within the spirit and scope of the invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, the present invention will be described in detail with reference to the accompanying drawings.

In the following embodiments, the terms first, second, etc. may be used to describe various elements, but the elements should not be limited by terms. Terms are used only for the purpose of distinguishing one component from another.

The terms used in the following examples are used only to illustrate specific embodiments and are not intended to limit the invention. The singular expressions include plural expressions unless the context clearly dictates otherwise. In the following description, the terms "comprises" or "having ", and the like, specify that the presence of stated features, integers, steps, operations, elements, But do not preclude the presence or addition of other features, numbers, steps, operations, components, parts, or combinations thereof.

Embodiments of the present invention may be represented by functional block configurations and various processing steps. These functional blocks may be implemented in a wide variety of hardware and / or software configurations that perform particular functions. For example, embodiments of the invention may be embodied directly in hardware, such as memory, processing, logic, look-up tables, etc., that can perform various functions by control of one or more microprocessors or by other control devices Circuit configurations can be employed. Similar to the components of an embodiment of the present invention that may be implemented with software programming or software components, embodiments of the present invention include various algorithms implemented with a combination of data structures, processes, routines, or other programming constructs , C, C ++, Java, assembler, and the like. Functional aspects may be implemented with algorithms running on one or more processors. Embodiments of the present invention may also employ conventional techniques for electronic configuration, signal processing, and / or data processing. Terms such as mechanisms, elements, means, and configurations are widely used and are not limited to mechanical and physical configurations. The term may include the meaning of a series of routines of software in conjunction with a processor or the like.

1 is a block diagram that schematically illustrates a human factor system in accordance with an embodiment of the present invention. 2 is a diagram illustrating a photographing method of a camera according to an embodiment of the present invention.

Referring to FIG. 1, a human factor system 1 according to an embodiment of the present invention is a system for counting people using a plurality of different types of cameras. The human factor system 1 includes a first camera 10, a second camera 20 and a human counting device 50.

The first camera 10 and the second camera 20 may be cameras having different characteristics, which capture the same scene in different directions and provide image information. The first camera 10 and the second camera 20 have a PTZ function and can acquire images at the same point at respective zoom magnifications while being panned and tilted together. The first camera 10 and the second camera 20 are integrally installed inside and outside the offices, houses, hospitals, banks and public buildings requiring security, and are used for access control and crime prevention. Depending on the purpose of use, it can have various shapes such as straight shape and dome shape. The first camera 10 and the second camera 20 may be installed on a ceiling, a wall, or the like.

The first camera 10 is a distance camera (hereinafter, referred to as a 'distance camera'), and is a distance camera for providing distance information between each object in the shot scene and / or distance information from the camera to each object Image) can be generated. The first camera 10 photographs the surrounding environment or a scene (space), and includes various objects (for example, static objects such as walls and obstacles, dynamic objects such as people and animals) It can be realized as a depth camera that acquires depth information in real time.

The second camera 20 is a thermal image camera (or infrared light camera) that detects radiant energy (thermal energy) emitted by an object and detects it in the form of an infrared ray, which is a type of electromagnetic wave, measures the intensity of thermal energy, It is possible to generate a second image which is a column image representing another color.

Referring to FIG. 2, the first camera 10 is a distance camera that is arranged to look from top to bottom in a direct-down manner (top-view mode) to obtain a top-view image. The second camera 20 is a laminating camera arranged to photograph the angle of view area of the first camera 10 obliquely to obtain a side-view image.

In the conventional human factor system, direct-type cameras are mainly used. It is easy to measure the distance to the head of a person by using a direct-type stereo camera or distance sensor information, but it is difficult to classify objects similar to human, so that false detection that can not distinguish a cargo or a person from a gate at frequent cargo access It can occur frequently. For example, maneuvers, dolls, gas tanks, drums and other objects with similar shapes or heights are also counted as people.

The direct-type thermal camera can detect the presence of a person because it can sense the temperature of a person. However, when the heat is not uniform on a person's head and the head is covered by a helmet, a cap, a hood, etc., a problem arises that a person can not be detected when wearing thick clothes.

In the embodiment of the present invention, whether or not the detected object is a person is judged by appropriately using mutual pros and cons of the direct-view distance camera and the side-view type thermal camera, and then counted as a person.

The human-counting apparatus 50 can process a video signal such as a noise elimination for a distance image from the distance camera and a thermal image from the thermal image camera.

The human counting device 50 detects at least a part of a human or human like object in the distance image. The human counting device 50 extracts a region corresponding to a part of the body (for example, face, neck, hand, foot, etc.) in a region predicted by a person. The distance camera and the thermal image camera are calibrated, and the human counting device 50 detects a candidate region corresponding to the regions detected in the distance image from the thermal image, detects the temperature of the candidate region through the thermal image camera, It is possible to determine whether the object is a person or something similar to a person.

The human-counting apparatus 50 includes an ac- cording unit 501, a detecting unit 503, and a counting unit 505. [

The calibration unit 501 calculates the correlation between the distance camera and the thermal camera by performing calibration. The calibration unit 501 calculates a correlation indicating the positional relationship between the distance camera and the thermal image camera. The calibration unit 501 calculates a conversion matrix related to the translation (t) and the rotation amount (R) between the distance camera and the thermal camera by matching the correspondence between the distance image acquired by the distance camera and the thermal image acquired by the thermal camera, A projection matrix (P) can be calculated as a correlation.

The detection unit 503 detects an object in the distance image acquired by the distance camera using the correlation, and detects at least one candidate region corresponding to the detected object in the thermal image acquired by the thermal camera.

For example, if [X, Y, Z, 1] ^T is the position of the points in the head region obtained from the distance image, the transformation matrix ([R | t] The relative 3D coordinates [X ', Y', Z ', 1] ^T of the 3D coordinates can be obtained.

[X ', Y', Z ', 1] ^T = [R | t] [X, Y, Z, 1] T ... formula (1)

(2) by using [X '/ Z', Y / Z ', 1] and P ([f, 0, cx; 0, f, cy; 0,0,1] The coordinates [x, y, 1] in the image can be obtained.

[x, y, 1] ^T = [f, 0, cx; 0, f, cy; 0, 1] [X '/ Z', Y / Z ', 1]

As a method of detecting an object in a distance image, a skeleton technique or a slice technique described later can be utilized. However, it is needless to say that the embodiment of the present invention is not limited thereto, and various techniques capable of detecting the shape or body of a person can be utilized.

The detection unit 503 can detect an area estimated to have a person or a person in the distance image, and detect the head area and other body parts in the detected area. The detection unit 503 can detect a candidate region corresponding to the region detected in the range image in the column image.

The counting unit 505 determines whether the object detected in the distance image is a person based on the temperature of at least one candidate region. The counting unit 505 judges the person as a person when the body temperature is sensed in the candidate region, and judges it as an object if not. The counting unit 505 can increase the counting accuracy by counting only for a person.

The counting unit 505 may select at least one temperature sensing region in at least one candidate region and may determine the object as a person if the temperature of the selected temperature sensing region falls within the reference temperature range. The counting unit 505 may select at least one temperature sensing region among a plurality of candidate regions, and may determine the object as a human when at least a part of the at least one candidate region falls within a reference temperature range. The counting unit 505 can judge the object as a person if the ratio of the region belonging to the reference temperature range in the selected temperature sensing region is equal to or greater than the reference ratio. The reference temperature range can be set at 25 to 41 degrees in consideration of the heat loss due to clothes and hair and the error range of the thermal camera at a temperature range of 35 to 41 degrees, which is a normal human body temperature. The reference ratio is set to 50% or more, and if the area satisfying the reference temperature range in the entire temperature sensing area is 50% or more, the object can be judged as a human. The reference temperature range and the reference ratio can be variably set by the user in consideration of the installation position of the camera.

In addition, since the embodiment of the present invention can receive the high and low temperature information of the body temperature from the heat information of the human-determined area, the body temperature of the gate entrance can be detected to provide the body health state.

The human counting device 50 can display a distance image, a column image, and the number of people counted on the screen in real time.

In one embodiment, it is possible to display the number of incoming persons and the number of outgoing persons.

3 is a view for explaining candidate region detection using a distance camera and a thermal image camera according to an embodiment of the present invention.

FIG. 3 (a) is a distance image acquired by the distance camera, and FIG. 3 (b) is a thermal image acquired by the thermal image camera. In the distance image, different colors are displayed according to the distance from the camera to the object. In the thermal image, different colors are shown according to the intensity of heat energy.

The detection unit 503 acquires skeleton information from a distance image by a skeleton technique. The detection unit 503 can detect at least one local feature region corresponding to a body part such as a head, a hand, a leg, and a foot using skeleton information. FIG. 3 (a) shows an example in which a head, a left hand, and a right hand region are detected as local feature regions.

The detection unit 503 may detect at least one candidate region corresponding to at least one local feature region in the thermal image using the correlation between the distance camera and the thermal image camera. 3B shows an example in which candidate regions corresponding to the local feature regions of the head, the left hand, and the right hand are detected, respectively.

In the embodiment of FIG. 3, skeleton information including a head, an arm, a leg, and the like is obtained from a distance image obtained by a direct-type distance camera, and the skeleton information including the head, A skeleton technique for detecting the positions of the face, arms, and legs is illustrated. Here, it is assumed that the position of face, arm, leg, etc. is utilized because it is estimated that the body temperature detection is the best. However, such a place may not be exposed directly to the skin, but may be masked by a mask or glove. An explanation thereof will be described later. Since human body temperature is copied through clothes or work clothes, it is possible to analyze the whole person's thermal image using the skeleton information as it is, rather than the thermal image analysis of a part of the body.

Further, not only skeleton information including arms, legs and the like but skeleton information of the head and shoulders can be extracted, and the corresponding thermal images can be analyzed.

4 is a view for explaining candidate region detection using a distance camera according to another embodiment of the present invention.

(A) from the head to the shoulder detected in the distance image is divided into a slice method as shown in Fig. 4 (b) to model the shape of a person (b). The candidate region c corresponding to the shape of the person modeled as shown in Fig. 4 (c) can be detected from the thermal image.

5 is a diagram for explaining a method of calculating a correlation between a distance camera and a thermal image camera according to an embodiment of the present invention.

To calibrate the distance camera and the thermal camera, location information of the distance camera and the thermal camera is needed. To do this, the transformation matrix by calculating the corresponding points between the distance image and the thermal image should be calculated. Since the characteristics of the distance camera and the thermal image camera are different, it is difficult to detect the corresponding point only by the image.

In the embodiment of the present invention, as shown in FIG. 5 (a), a dedicated calibration tool for calibrating the distance camera and the thermal camera is used.

The calibration tool 70 includes a main body 701 having a box-like cube structure, a heating element 703 for dissipating heat at each vertex of the main body 701, and a handle 705 connected to the main body 701. The heating element 703 may be implemented as an object that radiates heat that can be sensed by a thermal imaging camera, such as a heat ray or a lamp. The handle 705 may be cylindrical as shown in Fig. 5 (a), but is not limited thereto, and it may suffice that the handle 705 is capable of holding a calibration tool 70 by a person.

While the user grips the grip 705 of the calibration tool 70, the distance camera and the thermal camera acquire the top-view distance image and the side-view column image, respectively. In the distance image, the position of the vertex of the cube can be detected because the distance variation of the surface of the cube comes out. In a thermal image, a vertex, which is a heating part of a cube, can be detected. The translation and rotation relationships between the distance camera and the thermal camera and the projection matrix can be calculated by using a plurality of vertexes detected from the distance image and the thermal image as corresponding points. At this time, the Least Mean Square method can be used. 5 (b) shows the correspondence of the vertexes detected by the photographing of the distance image and the thermal image correcting tool 70.

When the correlation between the distance camera and the thermal image camera is calculated as shown in FIG. 5, the coordinates of the object area detected in the distance image are converted into three-dimensional coordinates based on the thermal camera using Equation (1) The three-dimensional coordinates can be converted into the projected coordinates on the thermal image using the above-described equation (2).

6 is a flowchart illustrating a method of counting persons according to an embodiment of the present invention.

Hereinafter, detailed description of the contents overlapping with those described in Figs. 1 to 5 will be omitted.

Referring to FIG. 6, the human-counting system calculates the correlation between the distance camera and the thermal camera (S61). The human factor system correlates the translation matrix (P) and the projection matrix (P) related to the translation (t) and the rotation amount (R) between the distance camera and the thermal camera through the calibration of the distance camera and the thermal camera Can be calculated. In order to calculate the correlation, a distance image and a thermal image may be obtained by using a calibration tool as shown in FIG. 5, and correlation may be calculated by tracking the corresponding point.

The human-counting system detects an object in the distance image acquired by the distance camera (S62). The human counting system can detect a human or human-like object in a distance image, and can detect a head region and a region of the body region outside the head. At this time, a skeleton technique or a slice technique can be used.

The human factor system detects at least one candidate region corresponding to the object detected in the distance image using the correlation in a thermal image acquired by the thermal camera (S63). The human factor system extracts at least one local feature region of the object and uses the correlation to detect at least one candidate region corresponding to at least one local feature region in the thermal image.

The human factor system selects at least one temperature sensing region in at least one candidate region (S64). A human wearing a hat, a glove, shoes, and the like can be considered, so that the human-counting system can select a temperature sensing region in which an optimal body temperature can be sensed in at least one candidate region. One or more temperature sensing areas may be selected.

The human factor system determines whether the object detected in the distance image is a person based on the temperature of at least one temperature sensing area (S65). The human factor system determines if at least a portion of at least one temperature sensing zone belongs to a reference temperature range. The reference temperature range can be set in consideration of the heat loss due to clothes and hair and the error range of the thermal camera in a normal body temperature range of a person. The reference temperature range can be variably set by the user. The human factor system can judge a human if the region corresponding to the reference temperature range in one or more temperature sensing regions is equal to or greater than a reference ratio.

The human factor system counts a person if the object is judged to be a person (S66). The person counting system can count the persons who are detected in the time zone designated by the user.

The distance image and the thermal image and the count result can be displayed on the screen in real time.

In the conventional method of counting people only with a top-view image, even though a human-like shape is determined as a person, the accuracy of counting is reduced. However, in the embodiment of the present invention, A thermal camera capable of extracting the image of the person is further used to determine whether the person is an actual person through a side-view thermal image. With the information thus determined, the cargo is not counted as a person at the gates where frequent cargo accesses are frequent, so that the accuracy of the counting can be drastically improved.

In addition, since the embodiment of the present invention can provide the high and low temperature information of the body temperature from the human heat information, it is possible to detect the body temperature of the gate entrance and transmit the health state of the body.

Embodiments of the present invention can be usefully used in various places that require accurate human factor. Embodiments of the present invention can be utilized in infrastructure such as airports, ports, and commercial facilities such as shops and casinos. It can also be used in transportation, such as airplanes, ships, trains, etc., where facts need to be identified, as well as in factories and workplaces, in order to prepare for accidents. For example, entrance and exit of a person can be applied to a sorting function of a person / object, such as pushing a cart at a mart or carrying an object at a workplace. In recent years, the demand for disaster / disaster evacuation has been particularly strong. Therefore, the embodiment of the present invention can be usefully applied to a system for grasping the remaining personnel in a limited space such as a workplace or a plane / ship when a fire or a disaster occurs.

The human-counting system and method based on a heterogeneous camera according to an embodiment of the present invention can be implemented as a computer-readable code on a computer-readable recording medium. A computer-readable recording medium includes all kinds of recording apparatuses in which data that can be read by a computer system is stored. Examples of the computer-readable recording medium include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage, and the like. In addition, the computer-readable recording medium may be distributed over network-connected computer systems so that computer readable codes can be stored and executed in a distributed manner. In addition, functional programs, codes, and code segments for implementing the present invention can be easily inferred by programmers of the technical field to which the present invention belongs.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is clearly understood that the same is by way of illustration and example only and is not to be taken by way of limitation, You will understand.

Claims (20)

A calibration unit for calculating a correlation between a distance camera and a thermal camera that acquire images in different directions with respect to the same scene;
A detector for detecting at least one candidate region corresponding to an object detected in the distance image acquired by the distance camera, from a thermal image acquired by the thermal imaging camera using the correlation; And
And a coefficient unit for determining whether the object is a person based on the temperature of the at least one candidate region. The method according to claim 1,
Wherein the distance camera acquires a top-view distance image and the thermal camera acquires a side-view thermal image. The apparatus according to claim 1,
Extract at least one local feature region of the object from the distance image and use the correlation to detect at least one candidate region corresponding to the at least one local feature region in the thermal image. The apparatus as claimed in claim 3,
Select at least one temperature sensing region in the at least one candidate region and determine the object as a person if the temperature of the selected temperature sensing region falls within a reference temperature range. 5. The image processing apparatus according to claim 4,
And judges the object as a person if the ratio of the region belonging to the reference temperature range in the selected temperature sensing region is equal to or greater than a reference ratio. 4. The apparatus according to claim 3,
Detect skeleton information for at least a portion of the object in the distance image and detect at least one local feature region of the object from the skeleton information. The apparatus according to claim 1,
And reconstructs at least a part of the object in the distance image in a sliced manner to model the shape and detects the candidate region corresponding to the modeled shape in the thermal image using the correlation. The apparatus as claimed in claim 7,
And judges the object as a person if the ratio of the region belonging to the reference temperature range in the candidate region is not less than the reference ratio. A distance camera and a thermal camera to acquire images in different directions for the same scene; And
Detecting at least one candidate region corresponding to an object detected in the distance image acquired by the distance camera from the thermal image acquired by the thermal image camera using the correlation between the distance camera and the thermal image camera, And a person counting device for determining whether the object is a person based on the temperature of the area. 10. The method of claim 9,
A calibration tool including a body of a cube structure and a heat generating element disposed at a vertex to emit heat,
Wherein the person counting apparatus calculates a correlation between the distance camera and the thermal image obtained by the distance camera and the thermal image with respect to the calibration tool to calculate the correlation. 10. The method of claim 9,
Wherein the distance camera acquires a top-view distance image and the thermal camera acquires a side-view thermal image. 10. The apparatus according to claim 9,
Select at least one temperature sensing region in the at least one candidate region and determine that the object is a person if the ratio of regions within the reference temperature range in the selected temperature sensing region is greater than or equal to a reference ratio. Calculating a correlation between a distance camera and a thermal camera that acquires images in different directions for the same scene;
Detecting at least one candidate region corresponding to an object detected in the distance image acquired by the distance camera from the thermal image acquired by the thermal image camera using the correlation; And
And determining whether the object is a person based on the temperature of the at least one candidate region. 14. The method of claim 13,
Wherein the distance camera obtains a top-view distance image and the thermal camera obtains a side-view thermal image. 14. The method according to claim 13,
Extracting at least one local feature region of the object from the distance image; And
And detecting at least one candidate region corresponding to the at least one local feature region in the thermal image using the correlation. 16. The method according to claim 15,
Selecting at least one temperature sensing region in the at least one candidate region; And
And determining that the object is a human when the temperature of the selected temperature sensing area belongs to a reference temperature range. 17. The method according to claim 16,
And determining that the object is a person if the ratio of the region within the reference temperature range to the selected temperature sensing region is equal to or greater than a reference ratio. 16. The method according to claim 15,
Detecting skeleton information for at least a portion of the object in the distance image; And
And detecting at least one local feature region of the object from the skeleton information. 14. The method according to claim 13,
Modeling a shape by reconstructing at least a part of the object in a slice manner in the distance image; And
And detecting a candidate region corresponding to the modeled shape in the thermal image using the correlation. 20. The method according to claim 19,
And judging the object as a person if the ratio of the region belonging to the reference temperature range in the candidate region is not less than the reference ratio.

Images