Method and system for positioning gamma radioactive source carrier based on optical image

Abstract

The invention relates to a gamma radioactive source carrier positioning method and system based on an optical image, and the method comprises the steps: collecting an optical image in real time through an optical camera, employing an image detection algorithm to combine with a multi-target tracking algorithm, and positioning the pixel coordinates of a pedestrian position in the optical image; converting the pixel coordinates into actual coordinates according to a mapping relation between the pixel coordinates and the actual coordinates, and calculating an actual distance between the position of the pedestrian and the position of the radiation detector; the gamma radiation counting rate in the current environment is measured based on the radiation detector; correlation matching is carried out on the gamma radiation counting rate and the actual distance, and the pedestrian whose matching result is higher than a threshold value is determined as a suspected radioactive source carrier; and performing color marking and positioning on the suspected carrier of the radioactive source. Through the synchronous movement of the radioactive source carrier and the radioactive source, the pedestrian position and the radiation counting rate in the optical image can be matched based on the correlation between the radioactive source counting rate and the radioactive source distance, and the radioactive source carrier in the pedestrian is determined.

Description

Technical Field

[0001] This invention relates to the field of nuclear security monitoring technology, and in particular to a method and system for locating people carrying gamma radiation sources based on optical images. Background Technology

[0002] Locating and tracking mobile radioactive sources is crucial for the security of important locations such as national ports and transportation hubs. Current technologies using radiation detectors, such as gamma counters and gamma spectrometers, can only monitor the radioactivity intensity at their installation location and lack the ability to pinpoint the radioactive source. Radiation detectors capable of imaging radioactive sources, such as gamma cameras and Compton cameras, have the ability to directly locate radioactive sources, but they have high detection limits for mobile sources, small detection fields, and cannot effectively detect low-activity radioactive sources. Furthermore, they are expensive and unsuitable for widespread deployment.

[0003] The above problems urgently need to be addressed. Summary of the Invention

[0004] This invention discloses a method and system for locating a person carrying a gamma radiation source based on optical images, aiming to solve the technical problems existing in the prior art.

[0005] The present invention adopts the following technical solution: On one hand, the present invention provides a method for locating a person carrying a gamma radiation source based on optical images, comprising: placing a radiation detector and an optical camera at the same location; acquiring optical images in real time through the optical camera; locating the pixel coordinates of the pedestrian's position in the optical image using an image detection algorithm combined with a multi-target tracking algorithm; converting the pixel coordinates into actual coordinates according to the mapping relationship between pixel coordinates and actual coordinates; calculating the actual distance between the pedestrian's position and the position of the radiation detector, wherein the actual coordinates are used to indicate the pedestrian's two-dimensional coordinates on the ground plane; measuring the gamma radiation count rate in the current environment based on the radiation detector; performing correlation matching between the gamma radiation count rate and the actual distance to identify pedestrians whose matching results are higher than a threshold, wherein pedestrians whose matching results are higher than the threshold are suspected carriers of the radiation source; and color-coding the suspected carriers of the radiation source for location.

[0006] Optionally, by acquiring optical images through the optical camera and employing an image detection algorithm combined with a multi-target tracking algorithm to locate the pixel coordinates of the pedestrian's position in the optical image, the method includes: identifying the pedestrian's outline in the optical image based on the image detection algorithm and outputting a pedestrian identification box; locating the pixel coordinates of the pedestrian's feet at the bottom midpoint of the identification box based on the multi-target tracking algorithm; and determining the pixel coordinates of the pedestrian's position during the movement process using the moving identification box.

[0007] Optionally, based on the mapping relationship between pixel coordinates and actual coordinates, the pixel coordinates are converted into actual coordinates, and the actual distance between the pedestrian position and the position of the radiation detector is calculated. This includes: converting the pixel coordinates of the directly measured optical image into distorted pixel coordinates according to the camera distortion standard model; calibrating the intrinsic parameter coefficients of the optical camera and the extrinsic parameter coefficients corresponding to the ground plane using the Zhang Zhengyou calibration method to determine the mapping relationship between the camera imaging plane and the ground plane; converting the distorted pixel coordinates into actual coordinates on the ground plane according to the mapping relationship; and calculating the actual distance based on the actual coordinates and the position coordinates of the radiation detector.

[0008] Optionally, the actual distance is calculated based on the actual coordinates and the position coordinates of the radiation detector, including: calibrating the pedestrian's z-coordinate position based on the median of the functional height of an adult's hand, converting the two-dimensional coordinates of the actual coordinates into three-dimensional coordinates; and using the three-dimensional Euclidean distance formula to calculate the actual distance between the position coordinates of the radiation detector and the three-dimensional actual position coordinates, wherein the position coordinates of the radiation detector are three-dimensional coordinates.

[0009] Optionally, performing correlation matching between the gamma radiation count rate and the actual distance to determine pedestrians whose matching results are higher than a threshold includes: determining the correlation between the gamma radiation count rate and the actual distance; constructing radiation count rate sequences acquired at the current time and historical time; constructing a sequence of actual distances between pedestrians and radiation detectors; calculating the degree of conformity between the radiation count rate sequence and the actual distance sequence in the correlation; determining the correlation matching degree at the current time based on the degree of conformity, and determining pedestrians whose matching results are higher than a threshold.

[0010] Optionally, calculating the degree of agreement between the radiation count rate sequence and the actual distance sequence in the correlation includes: centering the radiation count rate sequence to obtain a net radiation count rate sequence; determining the correlation between the net radiation count rate sequence and the actual distance sequence; normalizing the net radiation count rate sequence to the same distance scale based on the correlation; using the Anderson-Darling test at the same distance scale to determine the AD statistic of the normalized net radiation count rate sequence's fit to a normal distribution; determining the normal distribution confidence and p-value of the normalized net radiation count rate sequence based on the AD statistic, wherein the p-value is an indicator of the normalized net radiation count rate sequence's fit to a normal distribution; and determining the degree of agreement between the radiation count rate sequence and the actual distance sequence in the correlation based on the confidence level and the p-value.

[0011] Optionally, a radiation count rate sequence acquired at the current time and historical times is constructed. The method for determining the start time in the historical times is as follows: determining the statistical mean and standard deviation of the background count rate, wherein the background count rate is used to represent the radiation count rate recorded by the radiation detector per unit time when no radiation source is present; determining the quantitative lower limit of the radiation count rate based on the statistical mean and the standard deviation; and determining the moment when the radiation count rate first exceeds the quantitative lower limit in the historical times as the start time of the radiation count rate sequence.

[0012] According to another aspect of the present invention, a positioning system for a person carrying a gamma radiation source based on optical images is also provided, comprising: a pixel coordinate module, which places a radiation detector and an optical camera at the same location, acquires optical images in real time through the optical camera, and uses an image detection algorithm combined with a multi-target tracking algorithm to locate the pixel coordinates of the pedestrian's position in the optical image; an actual coordinate module, which converts the pixel coordinates into actual coordinates according to the mapping relationship between pixel coordinates and actual coordinates, and calculates the actual distance between the pedestrian's position and the position of the radiation detector, wherein the actual coordinates are used to indicate the pedestrian's two-dimensional coordinates on the ground plane; a measurement module, which measures the gamma radiation count rate in the current environment based on the radiation detector; a matching module, which performs correlation matching between the gamma radiation count rate and the actual distance, and determines pedestrians whose matching results are higher than a threshold, wherein pedestrians whose matching results are higher than the threshold are suspected carriers of the radiation source; and a positioning and calibration module, which performs color marking to locate the suspected carriers of the radiation source.

[0013] According to another aspect of the present invention, a non-volatile storage medium is also provided, the non-volatile storage medium storing a plurality of instructions adapted for loading by a processor and executing any one of the methods for locating a gamma radiation source carrier based on optical images.

[0014] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements the steps of any one of the methods for locating a gamma radiation source carrier based on optical images.

[0015] The technical solution adopted in this invention can achieve at least one of the following beneficial effects: In this embodiment of the invention, by synchronously moving a person carrying a radioactive source with the radioactive source, and based on the correlation between the radioactive source count measurement and the distance to the radioactive source, the pedestrian's position in the optical image can be matched with the radioactive source count measured by the radiation detector to identify the person carrying the radioactive source among the pedestrians. This achieves the technical effect of monitoring and locating moving persons carrying radioactive sources while expanding the detection field of view. Simultaneously, the optical camera has a low cost, reducing operating costs and providing low detection limits, wide detection range, and low-cost mobile radioactive source monitoring technology support for nuclear security. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below, forming part of the present invention. The illustrative embodiments of the present invention and their descriptions explain the present invention and do not constitute an improper limitation of the present invention. In the accompanying drawings: Figure 1 This is a flowchart of a method for locating a person carrying a gamma radiation source based on optical images, according to Embodiment 1 of the present invention; Figure 2 This is a schematic diagram illustrating the principle of matching pedestrian data with radiation data in a method for locating a person carrying a gamma radiation source based on optical images, as described in Embodiment 1 of the present invention. Figure 3 This is a comparison diagram of the matching results between the suspected and non-suspects of the radiation source carrier in a method for locating a person carrying a gamma radiation source based on optical images in Embodiment 1 of the present invention. Figure 4 This is a flowchart of an optional method for locating a gamma radiation source carrier based on optical images in Embodiment 2 of the present invention; Figure 5 This is a schematic diagram of a positioning system for a gamma radiation source carrier based on optical images, according to Embodiment 3 of the present invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. In the description of this invention, it should be noted that the term "or" is generally used to include the meaning of "and / or," unless otherwise expressly indicated.

[0018] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or a magnetic connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal communication between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances. Furthermore, in the description of this application, the terms "first," "second," etc., are used only for distinguishing descriptions and should not be construed as indicating or implying relative importance. In the description of this invention, "a plurality of" means at least two, such as two, three, or more, unless otherwise explicitly specified.

[0019] Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0020] To address the problems existing in related technologies, this application provides a method and system for locating a person carrying a gamma radiation source based on optical images.

[0021] Example 1 This embodiment provides a method for locating a person carrying a gamma radiation source based on optical images, such as... Figure 1 As shown, Figure 1 This is a flowchart of a method for locating a person carrying a gamma radiation source based on optical images, according to Embodiment 1 of the present invention. The method includes: Step S102: Place the radiation detector and the optical camera at the same location, acquire optical images in real time through the optical camera, and use an image detection algorithm combined with a multi-target tracking algorithm to locate the pixel coordinates of the pedestrian's position in the optical image.

[0022] Optionally, pedestrian location information can be collected, i.e., capturing optical images of pedestrians passing by the optical camera, and using image detection algorithms combined with multi-object tracking algorithms to locate the pixel coordinates of the pedestrians in the optical images. ).

[0023] In some preferred embodiments, optical images are acquired by an optical camera, and the pixel coordinates of the pedestrian's position in the optical image are located by combining an image detection algorithm with a multi-target tracking algorithm. This includes: identifying the pedestrian's outline in the optical image based on the image detection algorithm and outputting the pedestrian's bounding box; locating the pixel coordinates of the pedestrian's feet at the bottom center of the bounding box based on the multi-target tracking algorithm; and determining the pixel coordinates of the pedestrian's position during the movement process using the moving bounding box.

[0024] Optional image detection algorithms include, but are not limited to: YOLO, SSD, RetinaNet, R-CNN, FPN, etc.; multi-object tracking algorithms include, but are not limited to: DeepSort, ByteTrack, BoT-SORT, CenterTrack, etc.

[0025] Optional, the pixel coordinates of the pedestrian in the optical image ( The coordinates of the pedestrian's feet are taken as the center point of the bottom edge of the pedestrian recognition box output by the image detection algorithm. At the same time, a multi-target tracking algorithm is used to identify pedestrians and move the recognition box according to the pedestrians to form a target tracking effect.

[0026] Step S104: Based on the mapping relationship between pixel coordinates and actual coordinates, convert the pixel coordinates into actual coordinates and calculate the actual distance between the pedestrian's position and the position of the radiation detector. The actual coordinates are used to indicate the pedestrian's two-dimensional coordinates on the ground plane.

[0027] Optionally, construct a pixel coordinate system for pixel coordinates and a real coordinate system for actual coordinates. Based on the mapping relationship between the pixel coordinate system and the real coordinate system of the optical image, the pixel coordinates of the pedestrian are... Convert the actual coordinates (x, y) of the pedestrian's location to the actual coordinates of the real location, and calculate the pedestrian's position and the position of the radiation detector. The Euclidean distance d between ) and .

[0028] In some preferred embodiments, the pixel coordinates are converted into actual coordinates based on the mapping relationship between pixel coordinates and actual coordinates, and the actual distance between the pedestrian's position and the position of the radiation detector is calculated. This includes: converting the pixel coordinates of the directly measured optical image into distorted pixel coordinates according to the camera distortion standard model; calibrating the intrinsic parameter coefficients of the optical camera and the extrinsic parameter coefficients corresponding to the ground plane using the Zhang Zhengyou calibration method to determine the mapping relationship between the camera imaging plane and the ground plane; converting the distorted pixel coordinates into actual coordinates on the ground plane according to the mapping relationship; and calculating the actual distance based on the actual coordinates and the position coordinates of the radiation detector.

[0029] Optionally, the coordinate transformation process includes: first, converting the pixel coordinates of the directly measured optical image into distorted pixel coordinates according to the camera distortion standard model; then, converting the distorted pixel coordinates into actual coordinates on the ground plane according to the mapping relationship between the camera imaging plane and the ground plane.

[0030] Specifically, the standard model for camera distortion is as follows: in, All are the radial distortion coefficients of the camera; All are the tangential distortion coefficients of the camera; ) represents the pixel coordinates of the optical image; r represents ( Distance from the origin of the coordinate system ; ( , () represents the pixel coordinates after distortion removal.

[0031] Optionally, the mapping relationship can be obtained by: calibrating the intrinsic parameter coefficients of the optical camera (including the camera focal length in the u direction) using the Zhang Zhengyou calibration method. Camera focal length in the v direction Coordinates ( , The corresponding pixel coordinates of the intersection of the optical axis of the optical camera and the imaging plane, and the extrinsic parameters of the ground plane (including the rotation matrix between the ground plane and the optical image plane) , , , , , Translation vector , , The homography matrix between the optical image plane and the ground plane is obtained as follows: The pixel coordinate system of the image after distortion correction ( , The relationship between (x, y) and the actual coordinate system (x, y) on the ground plane is as follows: In some preferred embodiments, the actual distance is calculated based on the actual coordinates and the position coordinates of the radiation detector, including: calibrating the pedestrian's z-coordinate position based on the median of the functional height of an adult's hand, and converting the two-dimensional coordinates of the actual coordinates into three-dimensional coordinates; and using the three-dimensional Euclidean distance formula to calculate the actual distance between the position coordinates of the radiation detector and the three-dimensional actual position coordinates, wherein the position coordinates of the radiation detector are three-dimensional coordinates.

[0032] Optionally, the pedestrian's actual position coordinates (x, y) are the pedestrian's two-dimensional coordinates on the ground plane. Radiation detector position ( )middle,( Let be the planar coordinates of the radiation detector in the actual coordinate system. This represents the height of the radiation detector above the ground plane.

[0033] Optionally, in the calculation of the Euclidean distance d, the pedestrian's two-dimensional actual coordinates are first converted into three-dimensional actual coordinates. Specifically, the pedestrian's three-dimensional actual coordinates are (x, y, 727.5), where (x, y) are the pedestrian's actual position coordinates on the ground plane, and 727.5 mm is the median of hand function height in Chinese adults as proposed in GB / T 10000-2023. The pedestrian's position coordinates are set as P( According to the requirements, =x、 =y、 =727.5mm. The position coordinates of the radiation detector are set to Q( ).

[0034] Optionally, the formula for three-dimensional Euclidean distance is as follows: Substituting the pedestrian's actual coordinates with the radiation detector's position coordinates, we can then fix the pedestrian's position. Substitute the coordinate 727.5mm into the formula.

[0035] Step S106: Measure the gamma radiation count rate in the current environment based on the radiation detector.

[0036] Optionally, the gamma radiation count rate c is measured using a gamma radiation detector. Specifically, the radiation detector and the optical camera are placed in the same position, with the optical camera shooting in the same direction as the radiation detector. That is, the radiation count rate detected by the radiation detector matches the pedestrian in the image captured by the optical camera.

[0037] Step S108: Perform correlation matching between gamma radiation count rate and actual distance to identify pedestrians whose matching results are higher than a threshold. Among them, pedestrians whose matching results are higher than the threshold are suspected carriers of radiation sources.

[0038] Optionally, based on the correlation between radiation count rate and distance to radiation source (pedestrians are considered radiation sources, and the distance d between pedestrians and radiation detectors is the distance to radiation source), the collected radiation count rate data and the distance data between pedestrians and radiation detectors are matched, and pedestrians whose matching results exceed the threshold are identified as suspected radiation source carriers.

[0039] In some preferred embodiments, correlation matching is performed between the gamma radiation count rate and the actual distance to identify pedestrians whose matching results are higher than a threshold. This includes: determining the correlation between the gamma radiation count rate and the actual distance; constructing radiation count rate sequences acquired at the current time and historical time; constructing a sequence of actual distances between pedestrians and radiation detectors; calculating the degree of agreement between the radiation count rate sequence and the actual distance sequence in the correlation; determining the correlation matching degree at the current time based on the degree of agreement, and identifying pedestrians whose matching results are higher than a threshold.

[0040] Optionally, a correlation exists between the radiation count rate c and the distance d from the radiation source, described by the following formula: in, The detection efficiency of the radiation detector; The activity of the radioactive source for pedestrians; denoted by , where is the linear attenuation coefficient of the medium between the pedestrian radiation source and the radiation detector; b is the background count rate. During the radiation detector measurement process, the detection efficiency... Radioactive source activity The background count rate b can be considered a constant. The medium between the pedestrian radiation source and the radiation detector is air, and the linear attenuation coefficient of air... Lower, within the measurement range The value of can be considered a constant.

[0041] The simplified formula for the correlation between radiation count rate c and distance d from the radiation source is as follows: in For unknown constants, This is the statistical mean of the background count rate.

[0042] Optional. Methods for obtaining matching results include: recording the radiation count rate sequences obtained at the current time i and historical time points. Distance sequence between pedestrians and radiation detectors In this context, the historical time refers to the time before the current time, and the degree of correlation between the two sets of sequences is calculated as the matching degree calculation result at the current time.

[0043] Specifically, the threshold setting standard for the matching results was obtained through multiple experiments or simulations. The matching result datasets of radiation data and radiation source carriers and radiation data and radiation source non-carriers were obtained respectively. The threshold was determined to minimize the false alarm rate (false positive) while ensuring that the false negative rate is 0.

[0044] In some preferred embodiments, calculating the degree of agreement between the radiation count rate sequence and the actual distance sequence in the correlation includes: centering the radiation count rate sequence to obtain a net radiation count rate sequence; determining the correlation between the net radiation count rate sequence and the actual distance sequence; based on the correlation, normalizing the net radiation count rate sequence to the same distance scale; at the same distance scale, using the Anderson-Darling test to determine the AD statistic of the normalized net radiation count rate sequence's fit to a normal distribution; based on the AD statistic, determining the normal distribution confidence and p-value of the normalized net radiation count rate sequence, where the p-value is an indicator of the normalized net radiation count rate sequence's fit to a normal distribution; and based on the confidence and p-value, determining the degree of agreement between the radiation count rate sequence and the actual distance sequence in the correlation. Figure 2 As shown, Figure 2 This is a schematic diagram illustrating the principle of matching pedestrian data with radiation data in a method for locating a person carrying a gamma radiation source based on optical images, as described in Embodiment 1 of the present invention.

[0045] Optionally, the p-value of the Anderson-Darling test (AD test) can be used as an indicator of conformity, and the net count rate can be calculated based on the correlation formula. Distance data between pedestrians and detectors The following relationship exists: At the maximum radiation count rate At the moment when the distance between the person carrying the radiation source and the radiation detector is minimal. ,therefore and The corresponding moments are theoretically the same.

[0046] Optionally, the net count rate can be normalized to the same distance scale according to the following formula: At the same distance scale, the statistical fluctuations of radioactive source decay approximate a normal distribution; therefore, the statistical fluctuations of the normalized net radiation count rate should also conform to a normal distribution. The p-value of the AD test output can be used to evaluate the rejection of the normalized net radiation count rate sequence. The confidence level is that the pedestrian conforms to a normal distribution, and the p-value ranges from [0,1]. The closer the p-value is to 0, the higher the confidence level that the pedestrian is a non-radioactive source carrier.

[0047] Optionally, the degree of compliance can be evaluated using other indicators instead of the Anderson-Darling test p-value, including but not limited to: normalized net count rate series. with normalized distance sequence Cosine distance, count rate sequence With distance sequence The goodness of fit of linear regression, count rate sequence With distance sequence Pearson correlation coefficient, etc.

[0048] Optionally, using the A / D test p-value as the evaluation index, a comparison chart of the matching results between the location data and radiation count rate data of suspected and unsuspected radioactive source carriers shows that, after accumulating a certain amount of statistical data over a period of time, the evaluation index for suspected radioactive source carriers is significantly higher than that for other pedestrians, while the evaluation indices for other pedestrians tend to approach 0 as the amount of statistical data increases. By comparing the evaluation indices of suspected and unsuspected radioactive source carriers, it is possible to effectively distinguish radioactive source carriers from other pedestrians, thus achieving the location of radioactive source carriers among pedestrians. Figure 3 As shown, Figure 3 This is a comparison diagram of the matching results between suspected and non-suspects of a radiation source carrier in a method for locating a person carrying a gamma radiation source based on optical images, as described in Embodiment 1 of the present invention.

[0049] In some preferred embodiments, a radiation count rate sequence acquired at the current time and historical time is constructed. The method for determining the start time in the historical time is as follows: the statistical mean and standard deviation of the background count rate are determined, wherein the background count rate is used to represent the radiation count rate recorded by the radiation detector per unit time when no radiation source is present; based on the statistical mean and standard deviation, the quantitative lower limit of the radiation count rate is determined; the moment when the radiation count rate first exceeds the quantitative lower limit in the historical time is determined as the start time of the radiation count rate sequence.

[0050] Optionally, the method for determining the start time of the sequence includes: based on the statistical mean of the background count rate. and standard deviation Calculate the lower limit of quantitation for radiation count rate, where the standard deviation is... The calculation is as follows: in, This is the data collected for the background count rate.

[0051] The lower limit of quantification L for radiation count rate is calculated as follows: Specifically, the start time of the sequence is the moment when the radiation count rate first exceeds the lower limit of quantification. The lower limit of quantification is the minimum value at which the radiation count rate can be accurately and reliably quantified; only count rate values ​​above the lower limit of quantification can ensure the reliability of the calculation and analysis, regardless of matching.

[0052] Step S110: Color-coded location of suspected carriers of the radiation source.

[0053] Through steps S102 to S110, by synchronously moving the person carrying the radioactive source with the radioactive source, and based on the correlation between the radioactive source count measurement and the distance to the radioactive source, the pedestrian's position in the optical image can be matched with the radioactive source count measured by the radiation detector to identify the person carrying the radioactive source among the pedestrians. This achieves the technical effect of monitoring and locating moving radioactive source carriers while broadening the detection field of view. Simultaneously, the low cost of the optical camera reduces operating costs, providing low detection limits, wide detection range, and low-cost technical support for monitoring moving radioactive sources in nuclear security.

[0054] Example 2 Based on the above embodiments and optional embodiments, the present invention also proposes an optional implementation method. Figure 4 This is a flowchart of an optional method for locating a gamma radiation source carrier based on optical images, as described in Embodiment 2 of the present invention. Figure 4 As shown, the method includes: The method for locating gamma radiation source carriers based on optical images integrates an optical camera and a radiation detector to locate gamma radiation source carriers. The optical camera can be any camera that can provide optical monitoring video, and the radiation detector can be any radiation detector that can provide gamma ray intensity information (including but not limited to count, count rate, energy spectrum, and dose rate).

[0055] Step S1: Use image detection algorithms combined with multi-target recognition algorithms to perform pedestrian recognition and tracking on optical images. Image detection algorithms include, but are not limited to: YOLO algorithm, SSD algorithm, RetinaNet algorithm, R-CNN algorithm, FPN algorithm, etc.; multi-target tracking algorithms include, but are not limited to: DeepSort algorithm, ByteTrack algorithm, BoT-SORT algorithm, CenterTrack algorithm, etc.

[0056] In step S2, the pixel coordinates of the pedestrian recognition image are obtained and converted into actual position coordinates through the two-dimensional mapping relationship between the optical camera's imaging plane and the ground plane. The two-dimensional mapping relationship is obtained by camera calibration methods, including but not limited to Zhang Zhengyou's calibration method.

[0057] Step S3: Based on the two-dimensional mapping relationship, calculate the Euclidean distance between the pedestrian and the radiation detector. The actual coordinates of the pedestrian's position are (x, y, 727.5), where (x, y) are the actual coordinates of the pedestrian's position on the ground plane, and 727.5 mm is the median of high hand function in Chinese adults proposed in GB / T 10000-2023. Step S3: Determine the correlation between the gamma radiation count rate c measured by the radiation detector and the distance d from the radiation source (the Euclidean distance d between the pedestrian and the radiation detector). The correlation is described in detail below: in, The detection efficiency of the radiation detector; The activity of the radioactive source; denoted by , where is the linear attenuation coefficient of the medium between the radiation source and the radiation detector; b is the background count rate. During the radiation detector measurement process, the detection efficiency... Radioactive source activity The background count rate b can be considered a constant. The medium between the radiation source and the radiation detector is air, and the linear attenuation coefficient of air... Lower, within the measurement range The value of can be considered a constant. It should be noted that the pedestrian is considered the radiation source here.

[0058] The simplified formula for the correlation between radiation count rate c and distance d from the radiation source is as follows: in, For unknown constants, This is the statistical mean of the background count rate.

[0059] Step S4: Based on the mathematical formula relating gamma radiation count rate to the distance to the radiation source, match the radiation count rate c with the Euclidean distance d between the pedestrian and the radiation detector. Specifically, record the radiation count rate sequences acquired at the current time i and historical times. Distance sequence between pedestrians and radiation detectors The correlation index between the two sets of sequences is calculated as the matching result at the current time. Pedestrians whose correlation index exceeds a threshold are identified as suspects carrying radioactive sources. The correlation index includes, but is not limited to, the Anderson-Darling test p-value and the normalized net count rate sequence. with normalized distance sequence Cosine distance, count rate sequence With distance sequence The goodness of fit of linear regression, count rate sequence With distance sequence Pearson correlation coefficient, etc.

[0060] The method for determining the start time of the sequence is as follows: based on the statistical mean of the background count rate. and standard deviation The lower limit of quantification for calculating radiation count rate: The start time of the sequence is the moment when the radiation count rate first exceeds the lower limit of quantitation. The threshold setting standard for the matching results is: to control the false alarm rate as low as possible while ensuring that the false alarm rate is 0%.

[0061] Step S5: Draw a target detection and identification box for suspected radioactive source carriers using a specific color to identify suspected radioactive source carriers among pedestrians.

[0062] Through steps S1 to S5 above, combining the data collected by the optical camera and the radiation detector, and based on the correlation between the detector count rate and the distance between the radiation source (pedestrian) and the radiation detector, it is determined whether the pedestrian is suspected of carrying a radiation source, thus achieving the location of the person carrying the gamma radiation source. This method first uses an optical camera to collect monitoring images, and simultaneously uses a radiation detector to collect gamma count rate data. For the monitoring images collected by the optical camera, an image detection algorithm is used to obtain the pixel coordinates of the pedestrian in the image, and a multi-target tracking algorithm is used to track the pedestrian's movement path in real time, obtaining the pedestrian's pixel position at each moment. Based on the mapping relationship between the image pixel plane and the actual ground plane, the pixel coordinates are transformed to obtain the pedestrian's two-dimensional position on the ground plane at each moment. Finally, based on the position coordinates of the radiation detector, the Euclidean distance between the pedestrian and the radiation detector is calculated. The calculation of the Euclidean distance requires the three-dimensional coordinates of the pedestrian and the radiation detector. The pedestrian's third-dimensional coordinate value is taken as the median of hand function of Chinese adults, 727.5 mm, as determined by GB / T 10000-2023. The third-dimensional coordinate of the radiation detector is the height of the radiation detector from the ground plane. Then, the correlation formula is calculated using the distance data between pedestrians and the radiation detector, and the gamma count rate data. The degree of conformity is used to identify pedestrians whose conformity exceeds a certain threshold as suspected carriers of radioactive sources.

[0063] Example 3 This embodiment also provides a positioning system for a person carrying a gamma radiation source based on optical images. This system is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the terms "module" and "system" can refer to a combination of software and / or hardware that performs a predetermined function. Although the system described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0064] According to embodiments of the present invention, a system embodiment for implementing the above-described method for locating a person carrying a gamma radiation source based on optical images is also provided. Figure 5 This is a schematic diagram of a positioning system for a person carrying a gamma radiation source based on optical images, as described in Embodiment 3 of the present invention. Figure 5As shown, the above system includes: a pixel coordinate module 301, an actual coordinate module 302, a measurement module 303, a matching module 304, and a positioning and calibration module 305, wherein: The pixel coordinate module 301 places the radiation detector and the optical camera at the same position, acquires optical images in real time through the optical camera, and uses an image detection algorithm combined with a multi-target tracking algorithm to locate the pixel coordinates of the pedestrian position in the optical image. The actual coordinate module 302 converts pixel coordinates into actual coordinates based on the mapping relationship between pixel coordinates and actual coordinates, and calculates the actual distance between the pedestrian's position and the position of the radiation detector. The actual coordinates are used to indicate the pedestrian's two-dimensional coordinates on the ground plane. Measurement module 303 measures the gamma radiation count rate under the current environment based on a radiation detector; Matching module 304 performs correlation matching between gamma radiation count rate and actual distance to identify pedestrians whose matching results are higher than a threshold. Among them, pedestrians whose matching results are higher than the threshold are suspected carriers of radiation sources. The positioning and calibration module 305 uses color marking to locate suspected carriers of radioactive sources.

[0065] It should be noted that the above modules can be implemented by software or hardware. For example, for the latter, it can be implemented in the following ways: the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0066] It should be noted that the pixel coordinate module 301, actual coordinate module 302, measurement module 303, matching module 304, and positioning calibration module 305 mentioned above correspond to steps S102 to S110 in the embodiments. The instances and application scenarios implemented by the above modules and their corresponding steps are the same, but are not limited to the content disclosed in the above embodiments. It should be noted that the above modules can run on a computer terminal as part of the system.

[0067] It should be noted that the optional or preferred implementation methods of this embodiment can be found in the relevant descriptions in the embodiments, and will not be repeated here.

[0068] The aforementioned positioning system for a person carrying a gamma radiation source based on optical images may further include a processor and a memory. The pixel coordinate module 301, actual coordinate module 302, measurement module 303, matching module 304, and positioning calibration module 305 are all stored in the memory as program modules. The processor executes the aforementioned program modules stored in the memory to achieve the corresponding functions.

[0069] The processor contains a core that retrieves the corresponding program modules from memory. One or more cores may be configured. Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory includes at least one memory chip.

[0070] According to an embodiment of this application, an embodiment of a non-volatile storage medium is also provided. Optionally, in this embodiment, the non-volatile storage medium includes a stored program, wherein, when the program is running, it controls the device containing the non-volatile storage medium to execute any of the aforementioned methods for locating a gamma radiation source carrier based on optical images.

[0071] Optionally, in this embodiment, the non-volatile storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals, and the non-volatile storage medium includes stored programs.

[0072] Optionally, during program execution, the device containing the non-volatile storage medium may be controlled to perform the following functions: Position the radiation detector and optical camera at the same location; acquire optical images in real time using the optical camera; employ an image detection algorithm combined with a multi-target tracking algorithm to locate the pixel coordinates of the pedestrian in the optical image; convert the pixel coordinates to actual coordinates based on the mapping relationship between pixel coordinates and actual coordinates; calculate the actual distance between the pedestrian's location and the radiation detector's location, where the actual coordinates indicate the pedestrian's two-dimensional coordinates on the ground plane; measure the gamma radiation count rate in the current environment based on the radiation detector; perform correlation matching between the gamma radiation count rate and the actual distance to identify pedestrians whose matching results are higher than a threshold, whereby pedestrians with matching results higher than the threshold are suspected carriers of the radiation source; and color-mark the suspected carriers of the radiation source for location.

[0073] According to an embodiment of this application, an embodiment of a processor is also provided. Optionally, in this embodiment, the processor is used to run a program, wherein the program executes any of the above-described methods for locating a gamma radiation source carrier based on optical images.

[0074] According to an embodiment of this application, an embodiment of a computer program product is also provided. Optionally, in this embodiment, the computer program product includes a computer program that, when executed by a processor, implements the steps of any of the above-described methods for locating a gamma radiation source carrier based on optical images.

[0075] Optionally, when the aforementioned computer program product is executed on a data processing device, it is suitable to execute an initialization program with the following steps: placing the radiation detector and optical camera at the same location, acquiring optical images in real time through the optical camera, and using an image detection algorithm combined with a multi-target tracking algorithm to locate the pixel coordinates of the pedestrian's position in the optical image; converting the pixel coordinates into actual coordinates according to the mapping relationship between pixel coordinates and actual coordinates, and calculating the actual distance between the pedestrian's position and the position of the radiation detector, wherein the actual coordinates are used to indicate the pedestrian's two-dimensional coordinates on the ground plane; measuring the gamma radiation count rate in the current environment based on the radiation detector; performing correlation matching between the gamma radiation count rate and the actual distance to identify pedestrians whose matching results are higher than a threshold, wherein pedestrians whose matching results are higher than the threshold are suspected carriers of the radiation source; and color-marking the suspected carriers of the radiation source for location.

[0076] This invention provides an electronic device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs the following steps: placing a radiation detector and an optical camera at the same location; acquiring optical images in real time using the optical camera; locating the pixel coordinates of a pedestrian in the optical image using an image detection algorithm combined with a multi-target tracking algorithm; converting the pixel coordinates to actual coordinates based on the mapping relationship between pixel coordinates and actual coordinates; calculating the actual distance between the pedestrian's location and the radiation detector's location, where the actual coordinates indicate the pedestrian's two-dimensional coordinates on the ground plane; measuring the gamma radiation count rate in the current environment based on the radiation detector; performing correlation matching between the gamma radiation count rate and the actual distance to identify pedestrians whose matching results are higher than a threshold, whereby pedestrians with matching results higher than the threshold are suspected carriers of the radiation source; and color-coding the suspected carriers of the radiation source for location.

[0077] The order of the above embodiments of the present invention is merely for description and does not represent the superiority or inferiority of the embodiments.

[0078] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0079] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The system embodiments described above are merely illustrative; for example, the division of modules described above can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between modules, and may be electrical or other forms.

[0080] The modules described above as separate components may or may not be physically separate. Similarly, the components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple modules. Some or all of the modules can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0081] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0082] If the aforementioned integrated modules are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable non-volatile storage medium. Based on this understanding, the technical solution of this invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a non-volatile storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned non-volatile storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0083] The above are merely preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for locating a person carrying a gamma radiation source based on optical images, characterized in that, include: The radiation detector and the optical camera are placed at the same location. The optical camera acquires optical images in real time. The image detection algorithm is combined with the multi-target tracking algorithm to locate the pixel coordinates of the pedestrian in the optical image. Based on the mapping relationship between pixel coordinates and actual coordinates, the pixel coordinates are converted into actual coordinates, and the actual distance between the pedestrian's position and the position of the radiation detector is calculated. The actual coordinates are used to indicate the pedestrian's two-dimensional coordinates on the ground plane. The gamma radiation count rate in the current environment is measured based on the radiation detector. The gamma radiation count rate is correlated with the actual distance to identify pedestrians whose matching results are higher than a threshold. Pedestrians whose matching results are higher than the threshold are suspected carriers of the radiation source. The suspected carriers of the radiation source were located using color-coded markers.

2. The method for locating a person carrying a gamma radiation source based on optical images according to claim 1, characterized in that, Optical images are acquired using the optical camera, and the pixel coordinates of the pedestrian's position in the optical image are located using an image detection algorithm combined with a multi-target tracking algorithm, including: Based on the image detection algorithm, pedestrian outlines in the optical image are identified, and pedestrian recognition boxes are output. Based on the multi-target tracking algorithm, the pixel coordinates of the pedestrian's feet are located at the bottom midpoint of the recognition box; The pixel coordinates of the pedestrian's position during the movement are determined using the moving recognition box.

3. The method for locating a person carrying a gamma radiation source based on optical images according to claim 1, characterized in that, Based on the mapping relationship between pixel coordinates and actual coordinates, the pixel coordinates are converted into actual coordinates, and the actual distance between the pedestrian position and the position of the radiation detector is calculated, including: Based on the standard model of camera distortion, the pixel coordinates of the directly measured optical image are converted into the distorted pixel coordinates; The intrinsic parameter coefficients of the optical camera and the extrinsic parameter coefficients corresponding to the ground plane were calibrated using the Zhang Zhengyou calibration method to determine the mapping relationship between the camera imaging plane and the ground plane. Based on the mapping relationship, the distorted pixel coordinates are converted into actual coordinates on the ground plane; The actual distance is calculated based on the actual coordinates and the position coordinates of the radiation detector.

4. The method for locating a person carrying a gamma radiation source based on optical images according to claim 3, characterized in that, Based on the actual coordinates and the position coordinates of the radiation detector, the actual distance is calculated, including: The z-coordinate position of a pedestrian is determined based on the median of the functional height of an adult's hand, and the two-dimensional coordinates of the actual coordinates are converted into three-dimensional coordinates. The actual distance between the position coordinates of the radiation detector and the actual three-dimensional position coordinates is calculated using the three-dimensional Euclidean distance formula, wherein the position coordinates of the radiation detector are three-dimensional coordinates.

5. The method for locating a person carrying a gamma radiation source based on optical images according to claim 1, characterized in that, Correlation matching is performed between the gamma radiation count rate and the actual distance to identify pedestrians whose matching results are higher than a threshold, including: Determine the correlation between the gamma radiation count rate and the actual distance; Construct radiation count rate sequences obtained at the current and historical moments; Construct a sequence of actual distances between pedestrians and radiation detectors; Calculate the degree of agreement between the radiation count rate sequence and the actual distance sequence in the correlation; Based on the degree of conformity, the relevance matching degree at the current moment is determined, and pedestrians whose matching results are higher than the threshold are identified.

6. The method for locating a person carrying a gamma radiation source based on optical images according to claim 5, characterized in that, Calculating the degree of agreement between the radiation count rate sequence and the actual distance sequence in the correlation includes: The radiation count rate sequence is centered to obtain the net radiation count rate sequence; Determine the correlation between the net radiation count rate sequence and the actual distance sequence; Based on the aforementioned correlation, the net radiation count rate sequence is normalized to the same distance scale; At the same distance scale, the Anderson-Darling test is used to determine the AD statistic of how well the normalized net radiation count rate sequence fits the normal distribution; Based on the AD statistic, the normal distribution reliability and p-value of the normalized net radiation count rate sequence are determined, wherein the p-value is an indicator that measures the degree of fit between the normalized net radiation count rate sequence and the normal distribution. Based on the confidence level and the p-value, determine the degree of agreement between the radiation count rate sequence and the actual distance sequence in the correlation.

7. The method for locating a person carrying a gamma radiation source based on optical images according to claim 5, characterized in that, Construct a radiation count rate sequence obtained at the current time and historical times, wherein the method for determining the start time in the historical times is as follows: Determine the statistical mean and standard deviation of the background count rate, wherein the background count rate is used to represent the radiation count rate recorded by the radiation detector per unit time when no radiation source is present; Based on the statistical mean and the standard deviation, the lower limit of the quantitative limit of the radiation count rate is determined; The moment when the radiation count rate first exceeds the lower limit of quantification in the historical time period is determined as the starting moment of the radiation count rate sequence.

8. A positioning system for a person carrying a gamma radiation source based on optical images, characterized in that, include: The pixel coordinate module places the radiation detector and the optical camera at the same position, acquires optical images in real time through the optical camera, and uses an image detection algorithm combined with a multi-target tracking algorithm to locate the pixel coordinates of the pedestrian position in the optical image. The actual coordinate module converts the pixel coordinates into actual coordinates according to the mapping relationship between pixel coordinates and actual coordinates, and calculates the actual distance between the pedestrian position and the position of the radiation detector. The actual coordinates are used to indicate the two-dimensional coordinates of the pedestrian on the ground plane. The measurement module measures the gamma radiation count rate under the current environment based on the radiation detector; The matching module performs correlation matching between the gamma radiation count rate and the actual distance to identify pedestrians whose matching results are higher than a threshold. Among them, pedestrians whose matching results are higher than the threshold are suspected carriers of the radiation source. The positioning and calibration module uses color marking to locate the suspected carriers of the radiation source.

9. A non-volatile storage medium, characterized in that, The non-volatile storage medium stores multiple instructions, which are adapted to be loaded by a processor and executed by a method for locating a gamma radiation source carrier based on optical images, as described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for locating a gamma radiation source carrier based on optical images as described in any one of claims 1 to 7.

Images