KR-20260064293-A - FACIAL IMAGE ANALYSIS BASED THREAT DETECTION METHOD AND APPARATUS

Abstract

A threat detection method based on face image analysis according to the first aspect of the present invention comprises the steps of: identifying a face from a face image obtained from a camera; inferring an emotion corresponding to the face and obtaining an emotion-based threat score based on the emotion; obtaining an eye-based threat score based on the blinking frequency of the eyes and the number of pupil movements within the face; and detecting whether a person corresponding to the face is in a threat situation based on a total threat score calculated by combining the emotion-based threat score and the eye-based threat score.

Inventors

• 정철희
• 김경아
• 송봉섭
• 이현창

Assignees

• 주식회사 슈프리마

Dates

Publication Date

20260507

Application Date

20241031

Claims (20)

1. In a face image analysis-based threat detection method performed by a face image analysis-based threat detection device, A step of identifying a face from a face image acquired from a camera; A step of inferring an emotion corresponding to the above face and obtaining an emotion-based threat score based on the said emotion; A step of obtaining an eye-based threat score based on the blinking frequency and the number of pupil movements of the eyes within the face; and A step of detecting whether a person corresponding to the face is in a threat situation based on a total threat score calculated by combining the emotion-based threat score and the eye-based threat score. Face image analysis-based threat detection method.
2. In paragraph 1, The above camera is a near-infrared (NIR) camera, and The above face image is acquired from the above near-infrared camera. Face image analysis-based threat detection method.
3. In paragraph 1, The above emotion is inferred to belong to one of the pre-established threat emotion classes, and The above emotion-based threat score is determined dependently on the reliability of the inference regarding the emotion. Face image analysis-based threat detection method.
4. In paragraph 1, The above emotion is inferred not to belong to any of the pre-established threat emotion classes, and The above emotion-based threat score is determined to be 0 Face image analysis-based threat detection method.
5. In paragraph 1, The above eye-based threat score is, Calculated by applying a first reliability for the blinking frequency to the blinking frequency of the eye and a second reliability for the number of pupil movements to the number of pupil movements of the pupil Face image analysis-based threat detection method.
6. In paragraph 1, The above method is, It further includes the step of acquiring the above-mentioned facial movement, The above eye-based threat score is, Calculated by identifying the movement of the pupil within the face by considering the movement of the face above Face image analysis-based threat detection method.
7. In paragraph 1, The above total threat score is, Calculated by reflecting the result of applying a first weight to the above emotion-based threat score and the result of applying a second weight to the above eye-based threat score Face image analysis-based threat detection method.
8. In Paragraph 7, The first weight and the second weight mentioned above are, Determined based on the reliability of the above emotion, the reliability of the above blinking frequency, and the reliability of the above pupil movement count Face image analysis-based threat detection method.
9. In paragraph 1, The above total threat score is greater than or equal to a preset threshold, and In the step of detecting whether there is the above threat situation, When the above person is detected to be in a threatening situation Face image analysis-based threat detection method.
10. Memory capable of storing computer-executable instructions; and By executing the above command, a face is identified from a face image acquired from a camera, and Inferring the emotion corresponding to the above face, and obtaining an emotion-based threat score based on the above emotion, Obtain an eye-based threat score based on the blinking frequency and number of pupil movements within the face above, and A processor comprising a total threat score calculated by combining the emotion-based threat score and the eye-based threat score to detect whether a person corresponding to the face is in a threat situation. Face image analysis-based threat detection device.
11. In Paragraph 10, The above camera is a near-infrared (NIR) camera, and The above face image is acquired from the above near-infrared camera. Face image analysis-based threat detection device.
12. In Paragraph 10, The above emotion is inferred to belong to one of the pre-established threat emotion classes, and The above emotion-based threat score is determined dependently on the reliability of the inference regarding the emotion. Face image analysis-based threat detection device.
13. In Paragraph 10, The above emotion is inferred not to belong to any of the pre-established threat emotion classes, and The above emotion-based threat score is determined to be 0 Face image analysis-based threat detection device.
14. In Paragraph 10, The above eye-based threat score is, Calculated by applying a first reliability for the blinking frequency to the blinking frequency of the eye and a second reliability for the number of pupil movements to the number of pupil movements of the pupil Face image analysis-based threat detection device.
15. In Paragraph 10, The above processor is, Acquire the above facial movements, The above eye-based threat score is, Calculated by identifying the movement of the pupil within the face by considering the movement of the face above Face image analysis-based threat detection device.
16. In Paragraph 10, The above total threat score is, Calculated by reflecting the result of applying a first weight to the above emotion-based threat score and the result of applying a second weight to the above eye-based threat score Face image analysis-based threat detection device.
17. In Paragraph 16, The first weight and the second weight mentioned above are, Determined based on the reliability of the above emotion, the reliability of the above blinking frequency, and the reliability of the above pupil movement count Face image analysis-based threat detection device.
18. In Paragraph 10, The above total threat score is greater than or equal to a preset threshold, and The above processor is, The person above detects that they are in a threatening situation Face image analysis-based threat detection device.
19. A computer-readable recording medium storing computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, A step of identifying a face from a face image acquired from a camera; A step of inferring an emotion corresponding to the above face and obtaining an emotion-based threat score based on the said emotion; A step of obtaining an eye-based threat score based on the blinking frequency and the number of pupil movements of the eyes within the face; and A method in which the processor performs a step of detecting whether a person corresponding to the face is in a threat situation based on a total threat score calculated by combining the emotion-based threat score and the eye-based threat score. Computer-readable recording medium.
20. As a computer program stored on a computer-readable recording medium, When the above computer program is executed by a processor, A step of identifying a face from a face image acquired from a camera; A step of inferring an emotion corresponding to the above face and obtaining an emotion-based threat score based on the said emotion; A step of obtaining an eye-based threat score based on the blinking frequency and the number of pupil movements of the eyes within the face; and Instructions for the processor to perform a method including the step of detecting whether a person corresponding to the face is in a threat situation based on a total threat score calculated by combining the emotion-based threat score and the eye-based threat score. A computer program stored on a computer-readable recording medium.

Description

Facial Image Analysis-Based Threat Detection Method and Apparatus The present invention relates to a threat detection method and device based on facial image analysis. Threat situations can occur in dark environments with little light, in which case it may be difficult to acquire clear images for threat detection using conventional RGB cameras. Near-infrared (NIR) imaging generally utilizes near-infrared wavelengths in the range of 700 nm to 1000 nm. Since near-infrared wavelengths fall outside the visible light range, they cannot be perceived by the human eye; however, NIR imaging can identify areas that are difficult or impossible to detect with visible light cameras (RGB), making it useful in low-light or nighttime environments. Accordingly, there is a need for technology that acquires facial information from NIR images and utilizes it to determine threat situations when a threat occurs in the aforementioned dark environment with almost no light. FIG. 1 is a block diagram exemplarily illustrating a face image analysis-based threat detection device according to one embodiment. Figure 2 is a block diagram exemplifying the functions of a face image analysis-based threat detection program. FIG. 3 is a flowchart exemplarily illustrating a face image analysis-based threat detection method according to one embodiment. FIGS. 4 and 5 are exemplary diagrams specifically illustrating the process of detecting a threat situation according to a face image analysis-based threat detection method according to one embodiment. The advantages and features of the present invention and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below but can be implemented in various different forms. These embodiments are provided merely to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the invention, and the present invention is defined only by the scope of the claims. In describing the embodiments of the present invention, specific descriptions of known functions or configurations will be omitted if it is determined that such detailed descriptions could unnecessarily obscure the essence of the invention. Furthermore, the terms described below are defined in consideration of their functions in the embodiments of the present invention, and these definitions may vary depending on the intentions or practices of the user or operator. Therefore, such definitions should be based on the content throughout this specification. The terms used in this specification will be briefly explained, and the invention will be described in detail. The terms used in this specification have been selected to be as widely used as possible, taking into account the functions of the present invention; however, these terms may vary depending on the intent of those skilled in the art, case law, the emergence of new technologies, etc. Additionally, in specific cases, terms have been arbitrarily selected by the applicant, and in such cases, their meanings will be described in detail in the relevant description of the invention. Therefore, the terms used in this invention should be defined not merely by their names, but based on their meanings and the overall content of the invention. When a part of a specification is described as 'comprising' a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components. Additionally, the term "part" as used in the specification refers to software or hardware components, such as FPGAs or ASICs, and the "part" performs certain roles. However, the meaning of "part" is not limited to software or hardware. The "part" may be configured to reside in an addressable storage medium or configured to run one or more processors. Thus, by example, the "part" includes components such as software components, object-oriented software components, class components, and task components, as well as processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and "parts" may be combined into a smaller number of components and "parts" or further separated into additional components and "parts." Below, embodiments of the present invention are described in detail with reference to the attached drawings so that those skilled in the art can easily implement the present invention. FIG. 1 is a block diagram exemplarily illustrating a face image analysis-based threat detection device according to one embodiment. As shown in FIG. 1, the face image analysis-based threat detection device (100) may include an input unit (110), an output unit (120), a processor