TWI796767B - Drug addict detection system amd method thereof - Google Patents

Abstract

A drug addict detection system is provided, which includes an image capturing device, a thermal imaging device and an analysis device. The image capturing device captures the images of a plurality of drug addicts. The thermal imaging device obtains the body temperatures of the heads and the necks of the drug addicts. The analysis device analyzes the images of the drug addicts to obtain the blood temperature changes of the arteries and veins of the heads and the necks of the drug addicts, and analyzes the blood temperature changes of the arteries and veins and the body temperatures of the heads and the necks of the drug addicts so as to generate a heart rate variability threshold and a head temperature threshold. The image capturing device captures the image of a subject and the thermal imaging device obtains the body temperatures of the head and the neck of the subject. The analysis device analyzes the image of the subject to obtain the blood temperature change of the arteries and veins of the subject and analyzes the blood temperature change of the arteries and veins and the body temperatures of the heads and the necks of the subject to obtain the heart rate variability and the head temperature of the subject, and compares the heart rate variability and the head temperature of the subject with the heart rate variability threshold and the head temperature threshold respectively in order to generate a determination result.

Description

Drug addict detection system and method thereof

The invention relates to a detection system for drug addicts, in particular to a non-contact detection system for drug addicts. The invention also relates to the drug addict detection method of the drug addict detection system.

The proliferation of drugs is very harmful to society, and drug addicts tend to be younger. It is difficult for drug addicts to restrain their demand for drugs, and they can only spend a lot of money to buy drugs continuously, so many drug addicts will inevitably become drug traffickers. Therefore, how to effectively identify drug addicts to prevent drug abuse is an important issue.

However, at present, most of the police can only conduct drug addiction tests through rapid screening reagents, and do not have an effective and rapid testing device, so they cannot efficiently find drug addicts.

According to an embodiment of the present invention, the present invention provides a drug addict detection system, which includes an image capture device, a thermal imaging device, and an analysis device. The image capture device is used for capturing multiple images of drug addicts. Thermal imaging devices are used to obtain the body temperature of the drug addicts' heads and necks. The analysis device is used to analyze the images of the drug addicts to obtain the temperature changes of the arterial and venous blood flow in the head and neck of the drug addicts, and analyze the head and neck of the drug addicts through the artificial intelligence algorithm. The temperature change of the arterial and venous blood flow in the neck and the body temperature of the head and the neck are used to obtain the heart rate variation threshold value and the head temperature threshold value. Wherein, the image capture device captures the subject's image and the thermal imaging device obtains the body temperature of the subject's head and neck, and the analysis device analyzes the subject's image to obtain the subject's head and neck temperature. The temperature change of the arteriovenous blood flow in the head and neck, and then analyze the temperature change of the arteriovenous blood flow in the head and neck of the subject and the body temperature of the head and neck to obtain the heart rate variation value of the subject and the head temperature, and compare the heart rate variation value and head temperature of the subject with the heart rate variation threshold value and the head temperature threshold value respectively to generate a judgment result.

According to another embodiment of the present invention, the present invention proposes a method for detecting drug addicts, which includes the following steps: capturing images of a plurality of drug addicts through an image capture device; obtaining images of these drug addicts through a thermal imaging device The body temperature of the head and neck of the drug addict; the analysis device analyzes the images of the drug addicts to obtain the temperature changes of the arterial and venous blood flow in the head and neck of the drug addict; the analysis device calculates through artificial intelligence The method analyzes the temperature changes of the arterial and venous blood flow in the head and neck of these drug addicts and the body temperature of the head and neck to obtain the threshold value of heart rate variation and the threshold value of head temperature; Take the image of the subject; obtain the body temperature of the subject's head and neck through the thermal imaging device; analyze the image of the subject by the analysis device to obtain the arterial and venous blood of the subject's head and neck Then analyze the temperature changes of the arterial and venous blood flow in the head and neck of the subject and the body temperature of the head and neck to obtain the heart rate variation and head temperature of the subject; and through analysis The device compares the heart rate variation value and head temperature of the subject with the threshold value of the heart rate variation value and the head temperature threshold value to generate a judgment result.

In one embodiment, the analysis algorithm may be principal component analysis, or other similar algorithms.

In one embodiment, the analysis device analyzes the images of the drug addicts to obtain the facial sag values of the drug addicts, and analyzes the facial sag values of the drug addicts through an artificial intelligence algorithm to obtain the facial sag values. The threshold value of depression, and the analysis device analyzes the image of the subject to obtain the value of depression of the face of the subject, and compares the value of depression of the face of the subject with the threshold value of depression of the face to generate a judgment result.

In one embodiment, the analysis device analyzes the images of the drug addicts to obtain the pupil dilation values of the drug addicts, and analyzes the pupil dilation values of the drug addicts through an artificial intelligence algorithm to obtain the pupil dilation threshold , and the analysis device analyzes the image of the subject to obtain the pupil dilation value of the subject, and compares the pupil dilation value of the subject with the pupil dilation threshold value to generate a judgment result.

In one embodiment, when any two items of the subject's heart rate variation value, the subject's head temperature, the subject's face depression value and the subject's pupil dilation value exceed the heart rate variation value threshold value, When the head temperature threshold value, facial depression threshold value and pupil dilation threshold value are determined, the judgment result of the analysis device shows that the subject is a suspected drug addict.

In one embodiment, the artificial intelligence algorithm may be a convolutional neural network, or other similar algorithms.

Based on the above, according to the drug addict detection system of the present invention, it may have one or more of the following advantages:

(1) In one embodiment of the present invention, the drug addict detection system uses an image capture device and a thermal imaging device to obtain the data to be analyzed, and then analyzes the data to be analyzed through the analysis device and generates a judgment result, so it can effectively realize Long-distance detection, and can achieve high efficiency.

(2) In one embodiment of the present invention, the drug addict detection system analyzes the temperature changes of the arterial and venous blood flow in the head and neck of the drug addict, and experiments have proved that it can more effectively represent heart rate changes, Therefore, better accuracy can be achieved to effectively identify suspected drug addicts.

(3) In one embodiment of the present invention, the drug addict detection system integrates artificial intelligence algorithm and special analysis technology, and analyzes multiple characteristic parameters of drug addicts, so the accuracy can be further improved, and Identify suspected drug addicts more effectively.

(4) In one embodiment of the present invention, the design of the drug addict detection system is ingenious and simple, so it can achieve the desired effect without greatly increasing the cost, which is of great commercial value.

The following will refer to the related drawings to illustrate the embodiment of the drug addict detection system according to the present invention. For the sake of clarity and convenience of illustration, the sizes and proportions of the components in the drawings may be exaggerated or reduced. presented. In the following description and/or claims, when it is mentioned that an element is "connected" or "coupled" to another element, it may be directly connected or coupled to the other element or there may be an intervening element; When "directly connected" or "directly coupled" to another element, there are no intervening elements present, and other words used to describe the relationship between elements or layers should be interpreted in the same manner. To facilitate understanding, the same components in the following embodiments are described with the same symbols.

Please refer to Fig. 1, which is a block diagram of the drug addict detection system according to the first embodiment of the present invention. As shown in the figure, the drug addict detection system 1 includes an image capture device 11 , a thermal imaging device 12 and an analysis device 13 .

The image capturing device 11 is used for capturing images of a plurality of drug addicts. In one embodiment, the image capture device 11 may be a video camera or other devices with the same function. Among them, the image capture device 11 can track the head and neck of each drug addict through machine vision technology, so as to facilitate the subsequent analysis by the analysis device 13 . In one embodiment, the image capture device 11 may be a camera with a thermal image function or a device with a similar function.

The thermal imaging device 12 is used to obtain the body temperature of the head and neck of the drug addicts. In one embodiment, the thermal imaging device 12 may be an infrared thermal imaging camera, a thermal sensing device or other similar devices.

The analysis device 13 is used to analyze the images of the drug addicts to obtain the temperature changes of the arterial and venous blood flow in the head and neck of the drug addicts, and analyze the head of the drug addicts through an artificial intelligence algorithm. The temperature changes of the arterial and venous blood flow in the neck and the body temperature of the head and neck are used for mechanical learning, and then the heart rate variability (Heart Rate Variability, HRV) threshold T1 and the head temperature threshold T2 are obtained. In one embodiment, the analysis device 13 may be a central processing unit (CPU), an application specific integrated circuit or other similar devices. In one embodiment, the aforementioned artificial intelligence algorithm can be but not limited to convolutional neural network (CNN); in another embodiment, the aforementioned artificial intelligence algorithm can also be other algorithms with machine learning functions . As mentioned above, the analysis device 13 analyzes the images of the drug addicts to obtain the temperature changes of the arterial and venous blood flow in the head and neck of the drug addicts, and the head of the drug addicts can be obtained through thermal images. The temperature change of the arteriovenous blood flow in the head and neck can be analyzed to obtain the corresponding heart rate variation value. Therefore, a heart rate variability threshold T1 can be obtained by analyzing the data of a large number of drug addicts. Similarly, the analysis device 13 analyzes the body temperature of the head and neck of these drug addicts to obtain the average head temperature of each drug addict, and then a head temperature can be obtained by analyzing the data of a large number of drug addicts Threshold T2.

The analysis device 13 analyzes the temperature changes of the arterial and venous blood flow in the head and neck of the drug addicts through an analysis algorithm to obtain visualized data, and then analyzes the visualized data through an artificial intelligence algorithm to obtain a heart rate variation threshold value T1. In one embodiment, the aforesaid analysis algorithm may be but not limited to principal component analysis (PCA); in another embodiment, the aforesaid analysis algorithm may also be other existing algorithms. Since the heart rate variability and head temperature of drug addicts are higher than those of normal people, their characteristics can be found out through the above-mentioned special analysis steps.

Through this mechanism and the above-mentioned filtering steps, the analysis device 13 can obtain the heart rate variation and head temperature of a large number of drug addicts, and perform machine learning through artificial intelligence algorithms to find out the threshold of heart rate variation that can screen drug addicts value T1 and head temperature threshold T2. In another embodiment, the analysis device 13 can also analyze the heart rate variation and head temperature of normal people through artificial intelligence algorithms, and integrate and analyze with the heart rate variation and head temperature of a large number of drug addicts to find out It can screen the heart rate variation threshold T1 and head temperature threshold T2 of drug addicts to increase accuracy.

When detecting drug addicts, the image capture device 11 captures the subject's image and the thermal imaging device 12 obtains the body temperature of the subject's head and neck, and the analysis device 13 analyzes the subject's image Obtain the temperature change of the arteriovenous blood flow in the head and neck of the subject, and then analyze the temperature change of the arteriovenous blood flow in the head and neck of the subject to obtain the heart rate variation value of the subject, and The heart rate variation value and head temperature of the subject are compared with the heart rate variation threshold value T1 and the head temperature threshold value T2 respectively to generate a judgment result R.

In this embodiment, when both the heart rate variation value and the head temperature of the subject exceed the heart rate variation threshold value T1 and the head temperature threshold value T2 (this condition can be adjusted according to the actual situation), the judgment result R of the analysis device 13 It shows that the subjects are suspected drug addicts. At this time, the police can quickly screen the subjects to confirm whether they are indeed drug addicts.

The drug addict detection system 1 of this embodiment can be installed at the entrances and exits of buildings, transportation facilities (such as subway stations, railway stations, high-speed rail stations, airports, various buildings, etc.) or other places where drug addicts may appear. Place. In this way, the drug addict detection system 1 can be used to quickly identify suspected drug addicts through long-distance detection, so that the police can take necessary measures more efficiently to prevent drug abuse.

From the above, it can be known that the drug addict detection system 1 of this embodiment can analyze the temperature changes of the arterial and venous blood flow in the head and neck of the drug addict, and it has been proved by experiments that it can more effectively represent the heart rate changes. In addition, the drug addict detection system 1 also integrates artificial intelligence algorithms and special analysis techniques, and analyzes multiple characteristic parameters of drug addicts, so the accuracy can be greatly improved to more effectively find suspicious drug addict.

In addition, the analysis process of the drug addict detection system 1 of this embodiment also includes a special filtering step, which can eliminate the temperature changes of the arterial and venous blood flow in the head and neck that do not correspond to the frequency range of the normal heart rate, Only the temperature changes of the arterial and venous blood flow in the head and neck corresponding to the frequency range of the normal heart rate are analyzed, so the accuracy can be further improved to more effectively identify suspected drug addicts.

Of course, the above is just an example, and the elements and functions of the drug addict detection system 1 of this embodiment can be changed according to actual needs, and the present invention is not limited thereto.

Please refer to Fig. 2, which is a flow chart of the drug addict detection method according to the first embodiment of the present invention. As shown in the figure, the drug addict detection method of this embodiment includes the following steps:

Step S21: Capture images of a plurality of drug addicts through an image capture device.

Step S22: The body temperature of the head and neck of the drug addicts is obtained by the thermal imaging device.

Step S23: Analyze the images of the drug addicts through the analysis device to obtain the temperature changes of the arterial and venous blood flow in the head and neck of the drug addicts, and analyze the drug addicts through artificial intelligence algorithms The temperature changes of the arterial and venous blood flow in the head and neck and the body temperature of the head and neck are used to obtain the heart rate variation threshold and the head temperature threshold.

Step S24: The image of the subject captured by the image capture device.

Step S25: The body temperature of the subject's head and neck is obtained by the thermal imaging device.

Step S26: Analyze the image of the subject through the analysis device to obtain the temperature change of the arteriovenous blood flow in the subject's head and neck, and then analyze the temperature of the arteriovenous blood flow in the subject's head and neck Change to obtain the heart rate variation value of the subject, and compare the heart rate variation value and head temperature of the subject with the heart rate variation value threshold value and the head temperature threshold value respectively to generate a judgment result.

Please refer to Fig. 3, which is a block diagram of the drug addict detection system according to the second embodiment of the present invention. As shown in the figure, the drug addict detection system 2 includes an image capturing device 21 , a thermal imaging device 22 and an analyzing device 23 .

The image capturing device 21 is used for capturing images of a plurality of drug addicts.

The thermal imaging device 22 is used to obtain the body temperature of the head and neck of the drug addicts.

The analysis device 23 is used to analyze the images of the drug addicts to obtain the temperature changes of the arterial and venous blood flow in the head and neck of the drug addicts, and analyze the head of the drug addicts through an artificial intelligence algorithm. The temperature changes of the arterial and venous blood flow in the neck and the body temperature of the head and neck are used for mechanical learning, and then the heart rate variation threshold T1 and the head temperature threshold T2 are obtained.

The above-mentioned analysis procedure is the same as the above-mentioned embodiment, so it will not be repeated here. Different from the foregoing embodiments, the drug addict detection system 2 of this embodiment further analyzes other characteristic parameters of drug addicts.

The analysis device 23 analyzes the images of the drug addicts to obtain the facial depression values of the drug addicts, and analyzes the facial depression values of the drug addicts through an artificial intelligence algorithm to generate the facial depression threshold value T3.

Then, the analysis device 23 analyzes the images of the drug addicts to obtain the pupil dilation values of the drug addicts, and analyzes the pupil dilation values of the drug addicts through an artificial intelligence algorithm to generate the pupil dilation threshold T4. Because drug addicts have higher facial depression values and pupil dilation values than normal people, their characteristics can also be found through the above-mentioned special analysis steps.

When detecting drug addicts, the image capture device 21 captures the subject's image and the thermal imaging device 12 obtains the body temperature of the subject's head and neck, and the analysis device 23 analyzes the subject's image Obtain the temperature change of the arteriovenous blood flow in the head and neck of the subject, the face sag value and the pupil dilation value, and then analyze the temperature change of the arteriovenous blood flow in the head and neck of the subject and the head The body temperature of the head and neck was obtained to obtain the heart rate variation value and head temperature of the subject, and the heart rate variation value, head temperature, face sunken value and pupil dilation value were respectively compared with the heart rate variation value threshold The value T1, the head temperature threshold T2, the sunken face threshold T3 and the pupil dilation threshold T4 are compared to generate a judgment result R.

When any two items of heart rate variation value, head temperature, facial depression value and pupil dilation value exceed the heart rate variation threshold T1, head temperature threshold T2, facial depression threshold T3 and pupil dilation threshold When the value is T4, the judgment result of the analysis device 23 shows that the subject is a suspected drug addict.

As mentioned above, the drug addict detection system 2 of this embodiment integrates artificial intelligence algorithm and special analysis technology, and analyzes more characteristic parameters of drug addicts, and among them two or more characteristic parameters ( This condition can be adjusted according to the actual situation) and the subject is judged as a suspected drug addict when there is a difference. This method can further improve the accuracy and find out the suspected drug addict more effectively.

Of course, the above is only an example, and the components and functions of the drug addict detection system 2 of this embodiment can be changed according to actual needs, and the present invention is not limited thereto.

Please refer to FIG. 4, which is a flow chart of the method for detecting drug addicts according to the second embodiment of the present invention. As shown in the figure, the drug addict detection method of this embodiment includes the following steps:

Step S41: Capture images of a plurality of drug addicts through an image capture device.

Step S42: The body temperature of the head and neck of the drug addicts is obtained by the thermal imaging device.

Step S43: Analyze the images of the drug addicts through the analysis device to obtain the temperature changes of the arterial and venous blood flow in the head and neck of the drug addicts, the sunken face value and the pupil dilation value, and manually The intelligent algorithm analyzes the temperature changes of the arterial and venous blood flow in the head and neck, the body temperature of the head and neck, the sunken face value and pupil dilation value of these drug addicts to obtain the threshold value of heart rate variation, head Body temperature threshold, face sunken threshold and pupil dilation threshold.

Step S44: The image of the subject captured by the image capture device.

Step S45: Obtain the body temperature of the subject's head and neck by the thermal imaging device.

Step S46: Analyze the image of the subject through the analysis device to obtain the temperature change of the arterial and venous blood flow of the subject's head and neck, the value of the depression of the face and the dilation value of the pupil, and then analyze the movement of the head and neck. The temperature change of the venous blood flow and the body temperature of the head and neck are used to obtain the heart rate variation value and head temperature of the subject, and the heart rate variation value, head temperature, face depression value and pupil The magnification value is compared with the heart rate variation threshold value, the head temperature threshold value, the sunken face threshold value and the pupil dilation threshold value respectively to generate a judgment result.

Step S47: When any two items of the subject's heart rate variation value, head temperature, facial depression value and subject's pupil dilation value exceed the threshold value of heart rate variation value, head temperature threshold value, and facial depression threshold value and pupil dilation threshold, the analysis device's judgment result shows that the subject is a suspected drug addict.

In summary, according to the embodiment of the present invention, the drug addict detection system uses an image capture device and a thermal imaging device to obtain the data to be analyzed, and then analyzes the data to be analyzed through the analysis device to generate a judgment result, so it can effectively Realize long-distance detection, and can achieve high efficiency.

In addition, according to the embodiment of the present invention, the drug addict detection system analyzes the arterial and venous blood flow in the head and neck of the drug addict, and experiments have proved that it can more effectively represent heart rate changes, so it can achieve better results. accuracy to effectively identify suspected drug addicts.

In addition, according to the embodiment of the present invention, the drug addict detection system integrates artificial intelligence algorithms and special analysis techniques, and analyzes multiple characteristic parameters of drug addicts, so that the accuracy can be further improved for more effective to identify suspected drug addicts.

Furthermore, according to the embodiment of the present invention, the design of the drug addict detection system is ingenious and simple, so the desired effect can be achieved without greatly increasing the cost, which is of great commercial value.

It can be seen that the present invention has indeed achieved the desired effect after breaking through the previous technology, and it is not easy for those who are familiar with this technology to think about it. Its progress and practicability obviously meet the requirements for patent application. ￠I filed a patent application in accordance with the law, and I sincerely ask your bureau to approve this invention patent application to encourage creation, and I am grateful for it.

The above descriptions are illustrative only, not restrictive. Any other equivalent modifications or changes made without departing from the spirit and scope of the present invention shall be included in the scope of the appended patent application.

1, 2: Drug addict detection system 11, 21: Image capture device 12, 22: thermal imaging device 13, 23: Analysis device T1: HRV threshold T2: head temperature threshold T3: Face sunken threshold T4: pupil dilation threshold R: Judgment result S21~S26, S41~S47: Step-by-step process

Fig. 1 is a block diagram of a drug addict detection system according to the first embodiment of the present invention. Fig. 2 is a flow chart of the method for detecting drug addicts according to the first embodiment of the present invention. Fig. 3 is a block diagram of a drug addict detection system according to the second embodiment of the present invention. Fig. 4 is a flow chart of the method for detecting drug addicts according to the second embodiment of the present invention.

1: Drug addict detection system 11: Image capture device 12: Thermal imaging device 13: Analysis device T1: HRV threshold T2: head temperature threshold R: Judgment result

Claims (16)

A drug addict detection system comprising: An image capture device is used to capture images of a plurality of drug addicts; A thermal imaging device is used to obtain the body temperature of the heads and necks of the drug addicts; An analysis device is used to analyze the images of the drug addicts to obtain the temperature changes of the arterial and venous blood flow in the head and neck of the drug addicts, and analyze the drug addicts through an artificial intelligence algorithm The temperature changes of the arterial and venous blood flow in the head and neck and the body temperature of the head and neck to obtain a heart rate variation threshold and a head temperature threshold; and Wherein, the image capture device captures an image of a subject and the thermal imaging device obtains the body temperature of the subject's head and neck, and the analysis device analyzes the image of the subject to obtain the subject The temperature change of the arteriovenous blood flow in the head and neck of the subject, and then analyze the temperature change of the arteriovenous blood flow in the head and neck of the subject and the body temperature of the head and neck to obtain the subject heart rate variation and head temperature of the subject, and compare the heart rate variation and head temperature with the heart rate variation threshold and the head temperature threshold respectively to generate a judgment result. The drug addict detection system as described in claim 1, wherein before the analysis device generates the heart rate variation threshold value, the analysis device is aimed at the head and heart rate of the drug addicts corresponding to a frequency range of a normal heart rate. The temperature changes of the arteriovenous blood flow in the neck were analyzed. The drug addict detection system as described in claim 1, wherein the analysis device analyzes the temperature changes of the arterial and venous blood flow in the head and neck of the drug addicts through an analysis algorithm to obtain a visualization data, and then The visualized data is analyzed by the artificial intelligence algorithm to obtain the heart rate variation threshold. The drug addict detection system as described in claim 3, wherein the analysis algorithm is principal component analysis. The drug addict detection system as described in Claim 1, wherein the analysis device analyzes the images of the drug addicts to obtain the facial sag values of the drug addicts, and analyzes the drug addicts through the artificial intelligence algorithm. The facial depression value of the addict is used to obtain a facial depression threshold value, and the analysis device analyzes the image of the subject to obtain the subject's facial depression value, and the subject's facial depression value Compared with the facial depression threshold value to generate the judgment result. The drug addict detection system as described in Claim 5, wherein the analysis device analyzes the images of the drug addicts to obtain the pupil dilation values of the drug addicts, and analyzes the drug addicts through the artificial intelligence algorithm The pupil dilation value of the subject is obtained to obtain a pupil dilation threshold value, and the analysis device analyzes the image of the subject to obtain the pupil dilation value of the subject, and compares the pupil dilation value of the subject with the pupil dilation threshold Value comparison to generate the judgment result. The drug addict detection system as described in claim 6, wherein when the subject's heart rate, the subject's head temperature, the subject's face depression value and the subject's pupil dilation value When any two items exceed the heart rate variation threshold, the head temperature threshold, the sunken face threshold and the pupil dilation threshold, the judgment result of the analysis device shows that the subject is a suspected drug addict . The drug addict detection system as described in claim 1, wherein the artificial intelligence algorithm is a convolutional neural network. A method for detecting drug addicts, comprising: Capture images of a plurality of drug addicts through an image capture device; Obtaining the body temperature of the drug addicts' heads and necks through a thermal imaging device; Analyzing the images of the drug addicts by an analysis device to obtain the temperature changes of the arterial and venous blood flow in the head and neck of the drug addicts; The analysis device uses an artificial intelligence algorithm to analyze the temperature changes of the arterial and venous blood flow in the head and neck of the drug addicts and the body temperature of the head and neck to obtain a threshold value of heart rate variation and a threshold value of head and neck. internal temperature threshold; capturing an image of a subject through the image capturing device; Obtaining the body temperature of the subject's head and neck through the thermal imaging device; The image of the subject is analyzed by the analysis device to obtain the temperature change of the arteriovenous blood flow in the head and neck of the subject, and then the temperature change of the arteriovenous blood flow in the head and neck of the subject is analyzed. Temperature variation and body temperature of the head and neck to obtain the subject's heart rate variability and head temperature; and The heart rate variation value and the head temperature of the subject are compared with the heart rate variation value threshold value and the head temperature threshold value respectively through the analysis device to generate a judgment result. The method for detecting drug addicts as described in Claim 9, wherein before the analysis device generates the threshold value of the heart rate variation value, the analysis device is aimed at the head and heart rate of the drug addicts corresponding to a frequency range of a normal heart rate The temperature changes of the arteriovenous blood flow in the neck were analyzed. The drug addict detection method as described in Claim 9, wherein the analysis device analyzes the temperature changes of the arterial and venous blood flow in the head and neck of the drug addicts through an analysis algorithm to generate a visualization data, and then The visualization data is analyzed by the artificial intelligence algorithm to generate the heart rate variation threshold value. The method for detecting drug addicts as described in Claim 11, wherein the analysis algorithm is principal component analysis. The method for detecting drug addicts as described in claim item 9 further comprises the following steps: Analyzing the images of the drug addicts through the analysis device to obtain the facial sag values of the drug addicts; Analyzing the facial depression values of the drug addicts through the artificial intelligence algorithm by the analysis device to generate a facial depression threshold value; and The analysis device analyzes the image of the subject to obtain the subject's facial depression value, and compares the subject's facial depression value with the facial depression threshold value to generate the judgment result. The method for detecting drug addicts as described in claim 13 further comprises the following steps: Analyzing the images of the drug addicts via the analysis device to obtain the pupil dilation values of the drug addicts; Analyzing the pupil dilation values of the drug addicts through the artificial intelligence algorithm by the analysis device to generate a pupil dilation threshold value; and The analysis device analyzes the image of the subject to obtain the pupil dilation value of the subject, and compares the pupil dilation value of the subject with the facial depression threshold value to generate the judgment result. The method for detecting drug addicts as described in claim 14 further comprises the following steps: When any two items of the subject's heart rate variation value, the subject's head temperature, the subject's face depression value and the subject's pupil dilation value exceed the heart rate variation value threshold value, the subject's When the head temperature threshold value, the facial depression threshold value and the pupil dilation threshold value are used, the judgment result of the analysis device shows that the subject is a suspected drug addict. The method for detecting drug addicts as described in Claim 9, wherein the artificial intelligence algorithm is a convolutional neural network.

Images