Remote patient monitoring system using camera, heat sensor, FMCW radar, AI based signal calibration

Abstract

A remote patient monitoring system utilizing a camera, a thermal sensor, an FMCW radar, and AI-based signal correction is disclosed. The remote patient monitoring system may include a thermal sensor that non-contactually measures the patient's body temperature and heat distribution to generate first biosignal data, an FMCW radar that detects the patient's minute movements to generate second biosignal data, a camera that captures the patient's appearance and behavior to generate image data, and an AI-based signal correction module that reads the patient's biosignal using the first biosignal data generated by the thermal sensor and the second biosignal data generated by the FMCW radar, and corrects the read biosignal by analyzing the image data generated by the camera using an object recognition algorithm and a behavior pattern analysis algorithm when an abnormal signal is detected in the read biosignal.

Description

Technology Field

[0001] The present invention relates to a remote patient monitoring system, and more specifically, to a system that accurately monitors a patient's condition in a non-contact manner by utilizing a camera, a thermal sensor, an FMCW (Frequency Modulated Continuous Wave) radar and an artificial intelligence (AI)-based signal correction technology. Background Technology

[0002] Conventional patient monitoring systems primarily measured patients' vital signs using contact sensors. However, this method not only caused discomfort to patients but also posed a risk of skin infection due to the sensors' contact with the skin. To address these issues, non-contact single sensors, such as cameras and radar, were introduced; however, these sensors were vulnerable to external noise and had low accuracy, limiting their practical clinical application. Furthermore, existing systems relied on local data processing, which restricted real-time analysis and remote access, and made it difficult to comprehensively assess the patient's condition.

[0003] Therefore, there has been a need for a new monitoring system that measures patients' vital signs non-contactually, offers high accuracy, enables real-time data analysis, and allows for an intuitive understanding of the patient's condition. The problem to be solved

[0004] The problem that the present invention aims to solve is to provide a remote patient monitoring system that combines a camera, a thermal sensor, and an FMCW (Frequency Modulated Continuous Wave) radar and applies AI-based signal correction technology to precisely measure a patient's vital signs in a non-contact manner, analyze their condition, and notify a user (e.g., medical staff or guardians) in real time. means of solving the problem

[0005] A remote patient monitoring system using a camera, a thermal sensor, a Frequency Modulated Continuous Wave (FMCW) radar, and AI-based signal correction according to an embodiment of the present invention for achieving the above objective may comprise: a thermal sensor that non-contactually measures the patient's body temperature and heat distribution to generate first biosignal data; an FMCW radar that detects the patient's minute movements to generate second biosignal data; a camera that captures the patient's appearance and behavior to generate image data; and an AI-based signal correction module that reads the patient's biosignal using the first biosignal data generated by the thermal sensor and the second biosignal data generated by the FMCW radar, and corrects the read biosignal by analyzing the image data generated by the camera using an object recognition algorithm and a behavior pattern analysis algorithm when an abnormal signal is detected in the read biosignal. Effects of the invention

[0006] A remote patient monitoring system using a camera, a thermal sensor, an FMCW radar, and AI-based signal correction according to one embodiment of the technical concept of the present invention has the advantage of being able to monitor a patient very accurately by using measurement values ​​from a multi-sensor including a camera, a thermal sensor, and an FMCW radar and correcting biosignals based on artificial intelligence.

[0007] In addition, a remote patient monitoring system using a camera, a thermal sensor, an FMCW radar, and AI-based signal correction according to one embodiment of the technical concept of the present invention can reduce the risk of infection and patient discomfort in a non-contact manner, and has the advantage of enabling medical staff to respond quickly through real-time data analysis and remote transmission.

[0008] A remote patient monitoring system using a camera, a thermal sensor, an FMCW radar, and AI-based signal correction according to one embodiment of the technical concept of the present invention has the advantage of being able to intuitively monitor the patient by comprehensively analyzing the patient's behavioral patterns and condition. Brief explanation of the drawing

[0009] A brief description of each drawing is provided to help to better understand the drawings cited in the detailed description of the invention. FIG. 1 is a block diagram of a remote patient monitoring system (100) using a camera, a thermal sensor, an FMCW (Frequency Modulated Continuous Wave) radar and AI-based signal correction according to one embodiment of the technical concept of the present invention. Specific details for implementing the invention

[0010] In order to fully understand the present invention, the operational advantages of the present invention, and the objectives achieved by the implementation of the present invention, reference should be made to the accompanying drawings illustrating preferred embodiments of the present invention and the contents described therein.

[0011] The present invention will be described in detail below by explaining preferred embodiments of the invention with reference to the attached drawings. Identical reference numerals in each drawing indicate identical components.

[0012] FIG. 1 is a block diagram of a remote patient monitoring system (100) using a camera, a thermal sensor, an FMCW (Frequency Modulated Continuous Wave) radar and AI-based signal correction according to one embodiment of the technical concept of the present invention.

[0013] Referring to FIG. 1, a remote patient monitoring system (100) using a camera, a thermal sensor, an FMCW radar, and an AI-based signal correction may be equipped with a thermal sensor (110), an FMCW radar (120), a camera (130), and an AI-based signal correction module (150).

[0014] The heat sensing sensor (110) can generate first biosignal data by non-contactually measuring the patient's body temperature and heat distribution. The first biosignal data generated by the heat sensing sensor (110) can be transmitted to an AI-based signal correction module (150).

[0015] The FMCW radar (120) can detect minute movements such as the patient's breathing pattern and heart rate to generate second biosignal data. The second biosignal data generated by the FMCW radar (120) can be transmitted to an AI-based signal correction module (150).

[0016] The camera (130) can capture the patient's appearance and behavior to generate image data. The image data generated by the camera (130) can be transmitted to an AI-based signal correction module (150).

[0017] The AI-based signal correction module (150) can analyze the first biosignal data and the second biosignal data to primarily read the patient's biosignal. Then, if the AI-based signal correction module (150) detects an abnormal signal in at least one of the patient's biosignal primarily read, the first biosignal data, and the second biosignal data, the AI-based signal correction module (150) controls the camera (130) to operate to generate image data, thereby receiving image data from the camera (130) or receiving image data generated by the camera (130) while it is operating from the camera (130). The image data may be an image in which the patient's external appearance, such as movement and posture, is captured.

[0018] The AI-based signal correction module (150) can correct the patient's biosignal, which is primarily read through the patient's behavioral pattern and patient shape recognition, by analyzing the image data. For example, the patient's behavioral pattern is information that detects a continuous change in the patient's shape, such as the patient having a seizure or the patient falling, and the patient shape recognition is information that detects a static shape of the patient, such as the patient's posture.

[0019] The AI-based signal correction module (150) may include an object recognition algorithm and a behavior pattern analysis algorithm. The object recognition algorithm can analyze the shape recognition information of the patient among the image data, and the behavior pattern analysis algorithm can analyze the behavior pattern information of the patient among the image data. In this way, the AI-based signal correction module (150) can correct the read biosignal using the shape recognition information analyzed by the object recognition algorithm and the behavior pattern information analyzed by the behavior pattern analysis algorithm. Through such correction, the biosignal generated using values ​​measured by the thermal sensor and FMCW radar is corrected more precisely, so that the patient's biosignal can be read non-contactually with high accuracy, thereby allowing the patient's condition to be accurately determined.

[0020] The patient's biosignal generated by the AI-based signal correction module (150) or the corrected patient's biosignal can be transmitted to a user terminal (170). The user terminal (170) may be a terminal used by a patient, guardian, or medical staff.

[0021] The operation process of a remote patient monitoring system (100) using a camera, a thermal sensor, an FMCW radar, and AI-based signal correction according to one embodiment of the technical concept of the present invention is as follows.

[0022] A heat sensing sensor (110) can generate first biosignal data by non-contactually measuring the patient's body temperature and heat distribution, and an FMCW radar (120) can generate second biosignal data by detecting minute movements such as the patient's breathing pattern and heart rate.

[0023] The AI-based signal correction module (150) can primarily read the patient's biosignal using the first biosignal data and the second biosignal data. If an abnormal signal or abnormal signs are detected in the patient's biosignal read from the above, the AI-based signal correction module (150) receives image data from the camera (130), analyzes the patient's behavioral pattern and the patient's shape, and corrects the biosignal read from the above to generate a more accurate patient's biosignal.

[0024] As described above, the best embodiments have been disclosed in the drawings and specification. Specific terms have been used herein, but they are used only for the purpose of describing the invention and are not intended to limit the meaning or the scope of the invention as described in the claims. Therefore, those skilled in the art will understand that various modifications and equivalent alternative embodiments are possible therefrom. Accordingly, the true technical scope of protection of the invention should be determined by the technical spirit of the appended claims.

Claims

Claim 1 A remote patient monitoring system using a camera, a thermal sensor, an FMCW radar, and AI-based signal correction, characterized by comprising: a thermal sensor that non-contactually measures the patient's body temperature and heat distribution to generate first biosignal data; a Frequency Modulated Continuous Wave (FMCW) radar that detects minute movements of the patient to generate second biosignal data; a camera that captures the patient's appearance and behavior to generate image data; and an AI-based signal correction module that reads the patient's biosignal using the first biosignal data generated by the thermal sensor and the second biosignal data generated by the FMCW radar, and corrects the read biosignal by analyzing the image data generated by the camera using an object recognition algorithm and a behavior pattern analysis algorithm when an abnormal signal is detected in the read biosignal.

Images