Radiation inspection method and system for moving target and storage medium

Abstract

The invention discloses a radiation inspection method and system for a moving target and a storage medium. The method comprises the following steps: acquiring an initial radiation image of the moving target in a preset first area; dividing the initial radiation image into a plurality of initial radiation sub-images; extracting image features and corresponding image feature values in the initial radiation sub-images; based on a preset image feature weight coefficient, determining a definition score value of the corresponding initial radiation sub-image according to the image feature in the initial radiation sub-image and the corresponding image feature value; if the definition score value of the initial radiation subimage is smaller than a preset score threshold value, identifying the initial radiation subimage, and extracting the initial radiation subimage position corresponding to the identification; and carrying out secondary radiation imaging on the identified initial radiation sub-image based on a preset second area. According to the invention, through twice radiation imaging, the accuracy of radiation inspection of the moving target is improved.

Description

Technical Field

[0001] The present application relates to the field of radiation inspection technology, and more specifically, to a method, system and storage medium for performing radiation detection on a mobile target. Background Art

[0002] By inspecting the target through radiation, it is possible to detect places inside the target that are not visible to the human eye, especially moving vehicles, luggage inspection at station entrances, etc., which can save a lot of time; however, when the target is moving, the speed of the target will affect the accuracy of radiation imaging. Summary of the invention

[0003] In view of the above problems, an object of the present invention is to provide a method, system and storage medium for radiation detection of mobile targets, which can further improve the accuracy of radiation inspection of mobile targets.

[0004] A first aspect of the present invention provides a method for detecting radiation from a mobile target, comprising:

[0005] Acquire an initial radiation image of the moving target within a preset first area;

[0006] dividing the initial radiation image into a plurality of initial radiation sub-images;

[0007] Extracting image features and corresponding image feature values ​​in the initial radiation sub-image;

[0008] Based on the preset image feature weight coefficient, according to the image features in the initial radiation sub-image and the corresponding image feature values, determine the clarity score value corresponding to the initial radiation sub-image;

[0009] If the clarity score value of the initial radiation sub-image is less than the preset score threshold, the initial radiation sub-image is marked, and the position of the initial radiation sub-image corresponding to the mark is extracted;

[0010] Based on the preset second area, secondary radiation imaging is performed on the marked initial radiation sub-image.

[0011] In this solution, the step of determining the clarity score value corresponding to the initial radiation sub-image according to the image features in the initial radiation sub-image and the corresponding image feature values ​​specifically includes:

[0012] Extract the continuous proportion value, layer contrast value and discrete value of the outer contour in the initial radiation sub-image;

[0013] The outer contour continuous proportion value in the initial radiation sub-image is multiplied by the preset outer contour weight coefficient to obtain the outer contour score value;

[0014] Multiplying the level contrast value in the initial radiation sub-image by a preset level contrast weight coefficient to obtain a level contrast score value;

[0015] Multiply the discrete value in the initial radiation sub-image by a preset discrete weight coefficient to obtain a discrete score value;

[0016] The outer contour score is added to the layer contrast score, and then the discrete score is subtracted to obtain the clarity score of the corresponding initial radiation sub-image;

[0017] The image feature values ​​in the initial radiation sub-image include an outer contour continuity ratio value, a layer contrast value and a discrete value.

[0018] In this solution, the step of obtaining the continuous proportion value of the outer contour in the initial radiation sub-image specifically includes:

[0019] Extracting the outer contour and the endpoints of the outer contour in the initial radiation sub-image;

[0020] If the endpoint of the outer contour is on the boundary of the initial radiation sub-image, the corresponding endpoint is set as a normal endpoint; if the endpoint of the outer contour is not on the boundary of the initial radiation sub-image, the corresponding endpoint is set as an abnormal endpoint;

[0021] When there are abnormal endpoints, the outer contour segments in the initial radiation sub-image are extracted and sorted in sequence to obtain the outer contour segment numbers;

[0022] Extract the abnormal endpoints on the outer contour line segment, and connect the abnormal endpoints on the outer contour line segments with adjacent numbers end to end to obtain the supplementary line segment length between the corresponding abnormal endpoints;

[0023] When there are two abnormal endpoints in the outer contour line segment with the first and last numbers, the shortest distances from the two abnormal endpoints to the boundary of the initial radiation sub-image are extracted and set as the complementary line segment length of the boundary of the corresponding outer contour line segment and the initial radiation sub-image;

[0024] The lengths of all supplementary line segments are accumulated to obtain the total length of the supplementary line segments;

[0025] Extract the total length of the outer contour line segments and add them to the total length of the supplementary line segments to obtain the total length of the outer contour in the corresponding initial radiation sub-image;

[0026] The total length of the outer contour line segments is divided by the total length of the outer contour in the corresponding initial radiation sub-image to obtain the outer contour continuity ratio value in the initial radiation sub-image.

[0027] In this solution, the step of obtaining the level comparison value specifically includes:

[0028] Based on the preset interval and position of the comparison calibration points, a calibration point is randomly selected on the outer contour line, and the corresponding comparison calibration point is outside the outer contour line;

[0029] Extract the brightness value of the calibration point and compare the brightness value of the calibration point;

[0030] Subtract the brightness value of the calibration point from the brightness value of the comparison calibration point to obtain the brightness difference;

[0031] Divide the brightness difference by the brightness value of the calibration point to obtain the brightness difference ratio of the corresponding group of calibration points;

[0032] The brightness difference ratios of different groups of calibration points are averaged to obtain the outer contour level contrast value in the corresponding initial radiation sub-image;

[0033] The group calibration points consist of a calibration point and a comparison calibration point, and no less than 2 group calibration points are set.

[0034] In this solution, the step of obtaining the discrete value specifically includes:

[0035] Get the pixel points that are not on the outer contour line;

[0036] Extract the color features of the pixels that are not on the outer contour line and the color features of the points closest to the outer contour line;

[0037] When the color features of the pixels not on the outer contour line are compared with the color features of the corresponding pixels closest to the outer contour line, a similarity value is obtained;

[0038] If the similarity value is greater than the preset similarity threshold, the distance value between the corresponding pixel point not on the outer contour line and the closest point of the corresponding pixel point to the outer contour line is extracted;

[0039] Calculate the average value of the distance values ​​to obtain the average distance value;

[0040] According to the preset distance range within which the average distance value falls, the outer contour discrete value in the corresponding initial radiation sub-image is determined.

[0041] In this solution, the step of determining the discrete value of the outer contour in the corresponding initial radiation sub-image according to the preset distance range within which the average distance value falls specifically includes:

[0042] When the average distance value is less than the preset distance range, the corresponding outer contour discrete value is set to 0;

[0043] When the average distance value is within the preset distance range, the average distance value is divided by the maximum value in the corresponding preset distance range to obtain the corresponding outer contour discrete value;

[0044] When the average distance value is greater than the preset distance range, the corresponding outer contour discrete value is set to 1.

[0045] A second aspect of the present invention provides a system for performing radiation inspection on a mobile target, comprising a memory and a processor, wherein the memory stores a method program for performing radiation inspection on a mobile target, and when the method program for performing radiation inspection on a mobile target is executed by the processor, the following steps are implemented:

[0046] Acquire an initial radiation image of the moving target within a preset first area;

[0047] dividing the initial radiation image into a plurality of initial radiation sub-images;

[0048] Extracting image features and corresponding image feature values ​​in the initial radiation sub-image;

[0049] Based on the preset image feature weight coefficient, according to the image features in the initial radiation sub-image and the corresponding image feature values, determine the clarity score value corresponding to the initial radiation sub-image;

[0050] If the clarity score value of the initial radiation sub-image is less than the preset score threshold, the initial radiation sub-image is marked, and the position of the initial radiation sub-image corresponding to the mark is extracted;

[0051] Based on the preset second area, secondary radiation imaging is performed on the marked initial radiation sub-image.

[0052] In this solution, the step of determining the clarity score value corresponding to the initial radiation sub-image according to the image features in the initial radiation sub-image and the corresponding image feature values ​​specifically includes:

[0053] Extract the continuous proportion value, layer contrast value and discrete value of the outer contour in the initial radiation sub-image;

[0054] The outer contour continuous proportion value in the initial radiation sub-image is multiplied by the preset outer contour weight coefficient to obtain the outer contour score value;

[0055] Multiplying the level contrast value in the initial radiation sub-image by a preset level contrast weight coefficient to obtain a level contrast score value;

[0056] Multiply the discrete value in the initial radiation sub-image by a preset discrete weight coefficient to obtain a discrete score value;

[0057] The outer contour score is added to the layer contrast score, and then the discrete score is subtracted to obtain the clarity score of the corresponding initial radiation sub-image;

[0058] The image feature values ​​in the initial radiation sub-image include an outer contour continuity ratio value, a layer contrast value and a discrete value.

[0059] In this solution, the step of obtaining the continuous proportion value of the outer contour in the initial radiation sub-image specifically includes:

[0060] Extracting the outer contour and the endpoints of the outer contour in the initial radiation sub-image;

[0061] If the endpoint of the outer contour is on the boundary of the initial radiation sub-image, the corresponding endpoint is set as a normal endpoint; if the endpoint of the outer contour is not on the boundary of the initial radiation sub-image, the corresponding endpoint is set as an abnormal endpoint;

[0062] When there are abnormal endpoints, the outer contour line segments in the initial radiation sub-image are extracted and sorted in sequence to obtain the outer contour line segment numbers;

[0063] Extract the abnormal endpoints on the outer contour line segment, and connect the abnormal endpoints on the outer contour line segments with adjacent numbers end to end to obtain the supplementary line segment length between the corresponding abnormal endpoints;

[0064] When there are two abnormal endpoints in the outer contour line segment with the first and last numbers, the shortest distances from the two abnormal endpoints to the boundary of the initial radiation sub-image are extracted and set as the complementary line segment length of the boundary of the corresponding outer contour line segment and the initial radiation sub-image;

[0065] The lengths of all supplementary line segments are accumulated to obtain the total length of the supplementary line segments;

[0066] Extract the total length of the outer contour line segments and add them to the total length of the supplementary line segments to obtain the total length of the outer contour in the corresponding initial radiation sub-image;

[0067] The total length of the outer contour line segments is divided by the total length of the outer contour in the corresponding initial radiation sub-image to obtain the outer contour continuity ratio value in the initial radiation sub-image.

[0068] A third aspect of the present invention provides a computer-readable storage medium, in which a program for a method for performing radiation inspection on a mobile target is stored. When the program for a method for performing radiation inspection on a mobile target is executed by a processor, the steps of the method for performing radiation inspection on a mobile target as described are implemented.

[0069] The present invention discloses a radiation inspection method, system and storage medium for a mobile target, which improves the accuracy of radiation inspection of the mobile target through two radiation imaging. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 A flow chart of a radiation inspection method for a mobile target according to the present invention is shown;

[0071] Figure 2A block diagram of a radiation inspection system for a mobile target according to the present invention is shown. DETAILED DESCRIPTION

[0072] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0073] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0074] Figure 1 A flow chart of a radiation inspection method for a mobile target according to the present invention is shown.

[0075] like Figure 1 As shown, the present invention discloses a radiation inspection method for a mobile target, comprising:

[0076] S101, acquiring an initial radiation image of a moving target within a preset first area;

[0077] S102, dividing the initial radiation image into a plurality of initial radiation sub-images;

[0078] S103, extracting image features and corresponding image feature values ​​in the initial radiation sub-image;

[0079] S104, determining a clarity score value corresponding to the initial radiation sub-image based on a preset image feature weight coefficient and image features in the initial radiation sub-image and corresponding image feature values;

[0080] S105, if the clarity score value of the initial radiation sub-image is less than a preset score threshold, the initial radiation sub-image is marked, and the position of the initial radiation sub-image corresponding to the mark is extracted;

[0081] S106: Based on the preset second area, perform secondary radiation imaging on the marked initial radiation sub-image.

[0082] According to an embodiment of the present invention, the moving target preferentially passes through a preset first area and then passes through a preset second area. When the moving target passes through the preset first area, a preset radiation imaging device is used to obtain a radiation imaging of the corresponding moving target, that is, an initial radiation image of the corresponding moving target. The preset image feature weight coefficient includes a preset outer contour weight coefficient, a preset level contrast weight coefficient and a preset discrete weight coefficient. The image features include outer contour features, level contrast features and discrete features. The corresponding image feature values ​​include outer contour continuous proportion values, level contrast values ​​and discrete values. When the clarity score value of the initial radiation sub-image is less than a preset score threshold, when the moving target passes through the preset second area, a preset radiation imaging device is used to perform secondary radiation imaging on the position of the initial radiation sub-image to improve the accuracy of the radiation image. Based on the secondary radiation imaging, a secondary radiation image is obtained, and the identified initial radiation sub-image at the corresponding position is replaced.

[0083] According to an embodiment of the present invention, the step of determining the clarity score value corresponding to the initial radiation sub-image according to the image features in the initial radiation sub-image and the corresponding image feature values ​​specifically includes:

[0084] Extract the continuous proportion value, layer contrast value and discrete value of the outer contour in the initial radiation sub-image;

[0085] The outer contour continuous proportion value in the initial radiation sub-image is multiplied by the preset outer contour weight coefficient to obtain the outer contour score value;

[0086] Multiplying the level contrast value in the initial radiation sub-image by a preset level contrast weight coefficient to obtain a level contrast score value;

[0087] Multiply the discrete value in the initial radiation sub-image by a preset discrete weight coefficient to obtain a discrete score value;

[0088] The outer contour score is added to the layer contrast score, and then the discrete score is subtracted to obtain the clarity score of the corresponding initial radiation sub-image;

[0089] The image feature values ​​in the initial radiation sub-image include an outer contour continuity ratio value, a layer contrast value and a discrete value.

[0090] It should be noted that the outer contour features, layer contrast features and discrete features in the initial radiation sub-image are numerically processed to obtain the clarity score value of the initial radiation sub-image.

[0091] According to an embodiment of the present invention, the step of obtaining the continuous proportion value of the outer contour in the initial radiation sub-image specifically includes:

[0092] Extracting the outer contour and the endpoints of the outer contour in the initial radiation sub-image;

[0093] If the endpoint of the outer contour is on the boundary of the initial radiation sub-image, the corresponding endpoint is set as a normal endpoint; if the endpoint of the outer contour is not on the boundary of the initial radiation sub-image, the corresponding endpoint is set as an abnormal endpoint;

[0094] When there are abnormal endpoints, the outer contour line segments in the initial radiation sub-image are extracted and sorted in sequence to obtain the outer contour line segment numbers;

[0095] Extract the abnormal endpoints on the outer contour line segment, and connect the abnormal endpoints on the outer contour line segments with adjacent numbers end to end to obtain the supplementary line segment length between the corresponding abnormal endpoints;

[0096] When there are two abnormal endpoints in the outer contour line segment with the first and last numbers, the shortest distances from the two abnormal endpoints to the boundary of the initial radiation sub-image are extracted and set as the complementary line segment length of the boundary of the corresponding outer contour line segment and the initial radiation sub-image;

[0097] The lengths of all supplementary line segments are accumulated to obtain the total length of the supplementary line segments;

[0098] Extract the total length of the outer contour line segments and add them to the total length of the supplementary line segments to obtain the total length of the outer contour in the corresponding initial radiation sub-image;

[0099] The total length of the outer contour line segments is divided by the total length of the outer contour in the corresponding initial radiation sub-image to obtain the outer contour continuity ratio value in the initial radiation sub-image.

[0100] It should be noted that when the initial radiation image is divided into multiple initial radiation sub-images, the outer contour of the target to be detected by radiation will also be segmented. When the initial radiation sub-image does not contain the outer contour, the corresponding initial radiation sub-image will be filtered; the places where the outer contour is interrupted are connected through abnormal endpoints to obtain the supplementary line segment length, and the supplementary line segment length is represented by the outer contour line of the corresponding detection target that is not displayed during the radiation imaging process.

[0101] According to an embodiment of the present invention, the step of obtaining the level contrast value specifically includes:

[0102] Based on the preset interval and position of the comparison calibration points, a calibration point is randomly selected on the outer contour line, and the corresponding comparison calibration point is outside the outer contour line;

[0103] Extract the brightness value of the calibration point and compare the brightness value of the calibration point;

[0104] Subtract the brightness value of the calibration point from the brightness value of the comparison calibration point to obtain the brightness difference;

[0105] Divide the brightness difference by the brightness value of the calibration point to obtain the brightness difference ratio of the corresponding group of calibration points;

[0106] The brightness difference ratios of different groups of calibration points are averaged to obtain the outer contour level contrast value in the corresponding initial radiation sub-image;

[0107] The group calibration points consist of a calibration point and a comparison calibration point, and no less than 2 group calibration points are set.

[0108] It should be noted that the calibration points are on the outer contour line, the comparison calibration points are on the non-outer contour line, and are set at blank positions of non-detection targets. The calibration points and comparison calibration points are relatively set according to preset comparison calibration point intervals and positions.

[0109] According to an embodiment of the present invention, the step of obtaining the discrete value specifically includes:

[0110] Get the pixel points that are not on the outer contour line;

[0111] Extract the color features of the pixels that are not on the outer contour line and the color features of the points closest to the outer contour line;

[0112] When the color features of the pixels not on the outer contour line are compared with the color features of the corresponding pixels closest to the outer contour line, a similarity value is obtained;

[0113] If the similarity value is greater than the preset similarity threshold, the distance value between the corresponding pixel point not on the outer contour line and the closest point of the corresponding pixel point to the outer contour line is extracted;

[0114] Calculate the average value of the distance values ​​to obtain the average distance value;

[0115] According to the preset distance range within which the average distance value falls, the outer contour discrete value in the corresponding initial radiation sub-image is determined.

[0116] It should be noted that the clarity score value of the radiation sub-image is inversely proportional to the discrete value, and the color feature of the pixel point is the RGB of the corresponding pixel point. The RGB between different pixels is compared and analyzed to determine the similarity value, and based on the preset similarity threshold, it is determined whether the corresponding pixel point not on the outer contour line is associated with the pixel point on the outer contour line. When there is an association, the distance value between the corresponding two pixels is calculated, and then the average distance value is determined.

[0117] According to an embodiment of the present invention, the step of determining the discrete value of the outer contour in the corresponding initial radiation sub-image according to the preset distance range within which the average distance value falls specifically includes:

[0118] When the average distance value is less than the preset distance range, the corresponding outer contour discrete value is set to 0;

[0119] When the average distance value is within the preset distance range, the average distance value is divided by the maximum value in the corresponding preset distance range to obtain the corresponding outer contour discrete value;

[0120] When the average distance value is greater than the preset distance range, the corresponding outer contour discrete value is set to 1.

[0121] It should be noted that the average distance value is converted into an outer contour discrete value ranging from 0 to 1 according to the preset distance range. When the average distance value is less than the preset distance range, it means that the corresponding outer contour is relatively clear and visible, and there are no messy pixels; when the average distance value is greater than the preset distance range, it means that the corresponding outer contour is relatively scattered and blurred, and the corresponding outer contour discrete value reaches the maximum.

[0122] According to an embodiment of the present invention, it also includes:

[0123] Perform difference calculation on the brightness difference ratio of the group calibration points and the outer contour level contrast value to obtain a first value;

[0124] If the first value is greater than a preset first threshold, the brightness difference ratio of the group calibration corresponding to the first value is deleted, and the number of brightness difference ratios of the remaining group calibration points is extracted;

[0125] If the number of the brightness difference ratios of the remaining group of calibration points is greater than or equal to the preset first number threshold, the brightness difference ratios of the remaining group of calibration points are averaged to obtain a revised outer contour level contrast value;

[0126] If the number of brightness difference ratios of the remaining group calibration points is less than the preset first number threshold, the brightness difference ratio data of the comparison calibration point and its group calibration points are added until the number of brightness difference ratios of the group calibration points is greater than or equal to the preset first number threshold.

[0127] It should be noted that by comparing and analyzing the brightness difference ratio of the group calibration points and the outer contour level contrast value, the brightness difference ratio of the group calibration points with large differences can be found to reduce errors and improve the accuracy of the outer contour level contrast value.

[0128] According to an embodiment of the present invention, it also includes:

[0129] The secondary radiation image of the secondary radiation imaging is fused with the initial radiation image to obtain a standard radiation image;

[0130] Extract the outer contour of the detection target in the standard radiation image;

[0131] Compare and analyze the outer contour of the detected target with the outer contour of the preset dangerous object to obtain an outer contour similarity value;

[0132] If the outer contour similarity value is greater than or equal to a preset second similarity threshold, a warning message is triggered;

[0133] The warning information is sent to a preset management terminal for prompting.

[0134] It should be noted that when secondary radiation imaging is not triggered, the initial radiation image is set as the standard radiation image. When secondary radiation imaging is triggered, the secondary radiation image of the secondary radiation imaging replaces the identified initial radiation sub-image at the corresponding position.

[0135] Figure 2 A block diagram of a radiation inspection system for a mobile target according to the present invention is shown.

[0136] like Figure 2 As shown, the second aspect of the present invention provides a system 2 for performing radiation inspection on a mobile target, comprising a memory 21 and a processor 22, wherein the memory stores a method program for performing radiation inspection on a mobile target, and when the method program for performing radiation inspection on a mobile target is executed by the processor, the following steps are implemented:

[0137] Acquire an initial radiation image of the moving target within a preset first area;

[0138] dividing the initial radiation image into a plurality of initial radiation sub-images;

[0139] Extracting image features and corresponding image feature values ​​in the initial radiation sub-image;

[0140] Based on the preset image feature weight coefficient, according to the image features in the initial radiation sub-image and the corresponding image feature values, determine the clarity score value corresponding to the initial radiation sub-image;

[0141] If the clarity score value of the initial radiation sub-image is less than the preset score threshold, the initial radiation sub-image is marked, and the position of the initial radiation sub-image corresponding to the mark is extracted;

[0142] Based on the preset second area, secondary radiation imaging is performed on the marked initial radiation sub-image.

[0143] According to an embodiment of the present invention, the moving target preferentially passes through a preset first area and then passes through a preset second area. When the moving target passes through the preset first area, a preset radiation imaging device is used to obtain a radiation imaging of the corresponding moving target, that is, an initial radiation image of the corresponding moving target. The preset image feature weight coefficient includes a preset outer contour weight coefficient, a preset level contrast weight coefficient and a preset discrete weight coefficient. The image features include outer contour features, level contrast features and discrete features. The corresponding image feature values ​​include outer contour continuous proportion values, level contrast values ​​and discrete values. When the clarity score value of the initial radiation sub-image is less than a preset score threshold, when the moving target passes through the preset second area, a preset radiation imaging device is used to perform secondary radiation imaging on the position of the initial radiation sub-image to improve the accuracy of the radiation image. Based on the secondary radiation imaging, a secondary radiation image is obtained, and the identified initial radiation sub-image at the corresponding position is replaced.

[0144] According to an embodiment of the present invention, the step of determining the clarity score value corresponding to the initial radiation sub-image according to the image features in the initial radiation sub-image and the corresponding image feature values ​​specifically includes:

[0145] Extract the continuous proportion value, layer contrast value and discrete value of the outer contour in the initial radiation sub-image;

[0146] The outer contour continuous proportion value in the initial radiation sub-image is multiplied by the preset outer contour weight coefficient to obtain the outer contour score value;

[0147] Multiplying the level contrast value in the initial radiation sub-image by a preset level contrast weight coefficient to obtain a level contrast score value;

[0148] Multiply the discrete value in the initial radiation sub-image by a preset discrete weight coefficient to obtain a discrete score value;

[0149] The outer contour score is added to the layer contrast score, and then the discrete score is subtracted to obtain the clarity score of the corresponding initial radiation sub-image;

[0150] The image feature values ​​in the initial radiation sub-image include an outer contour continuity ratio value, a layer contrast value and a discrete value.

[0151] It should be noted that the outer contour features, layer contrast features and discrete features in the initial radiation sub-image are numerically processed to obtain the clarity score value of the initial radiation sub-image.

[0152] According to an embodiment of the present invention, the step of obtaining the continuous proportion value of the outer contour in the initial radiation sub-image specifically includes:

[0153] Extracting the outer contour and the endpoints of the outer contour in the initial radiation sub-image;

[0154] If the endpoint of the outer contour is on the boundary of the initial radiation sub-image, the corresponding endpoint is set as a normal endpoint; if the endpoint of the outer contour is not on the boundary of the initial radiation sub-image, the corresponding endpoint is set as an abnormal endpoint;

[0155] When there are abnormal endpoints, the outer contour line segments in the initial radiation sub-image are extracted and sorted in sequence to obtain the outer contour line segment numbers;

[0156] Extract the abnormal endpoints on the outer contour line segment, and connect the abnormal endpoints on the outer contour line segments with adjacent numbers end to end to obtain the supplementary line segment length between the corresponding abnormal endpoints;

[0157] When there are two abnormal endpoints in the outer contour line segment with the first and last numbers, the shortest distances from the two abnormal endpoints to the boundary of the initial radiation sub-image are extracted and set as the complementary line segment length of the boundary of the corresponding outer contour line segment and the initial radiation sub-image;

[0158] The lengths of all supplementary line segments are accumulated to obtain the total length of the supplementary line segments;

[0159] Extract the total length of the outer contour line segments and add them to the total length of the supplementary line segments to obtain the total length of the outer contour in the corresponding initial radiation sub-image;

[0160] The total length of the outer contour line segments is divided by the total length of the outer contour in the corresponding initial radiation sub-image to obtain the outer contour continuity ratio value in the initial radiation sub-image.

[0161] It should be noted that when the initial radiation image is divided into multiple initial radiation sub-images, the outer contour of the target to be detected by radiation will also be segmented. When the initial radiation sub-image does not contain the outer contour, the corresponding initial radiation sub-image will be filtered; the places where the outer contour is interrupted are connected through abnormal endpoints to obtain the supplementary line segment length, and the supplementary line segment length is represented by the outer contour line of the corresponding detection target that is not displayed during the radiation imaging process.

[0162] According to an embodiment of the present invention, the step of obtaining the level contrast value specifically includes:

[0163] Based on the preset interval and position of the comparison calibration points, a calibration point is randomly selected on the outer contour line, and the corresponding comparison calibration point is outside the outer contour line;

[0164] Extract the brightness value of the calibration point and compare the brightness value of the calibration point;

[0165] Subtract the brightness value of the calibration point from the brightness value of the comparison calibration point to obtain the brightness difference;

[0166] Divide the brightness difference by the brightness value of the calibration point to obtain the brightness difference ratio of the corresponding group of calibration points;

[0167] The brightness difference ratios of different groups of calibration points are averaged to obtain the outer contour level contrast value in the corresponding initial radiation sub-image;

[0168] The group calibration points consist of a calibration point and a comparison calibration point, and no less than 2 group calibration points are set.

[0169] It should be noted that the calibration points are on the outer contour line, the comparison calibration points are on the non-outer contour line, and are set at blank positions of non-detection targets. The calibration points and comparison calibration points are relatively set according to preset comparison calibration point intervals and positions.

[0170] According to an embodiment of the present invention, the step of obtaining the discrete value specifically includes:

[0171] Get the pixel points that are not on the outer contour line;

[0172] Extract the color features of the pixels that are not on the outer contour line and the color features of the points closest to the outer contour line;

[0173] When the color features of the pixels not on the outer contour line are compared with the color features of the corresponding pixels closest to the outer contour line, a similarity value is obtained;

[0174] If the similarity value is greater than the preset similarity threshold, the distance value between the corresponding pixel point not on the outer contour line and the closest point of the corresponding pixel point to the outer contour line is extracted;

[0175] Calculate the average value of the distance values ​​to obtain the average distance value;

[0176] According to the preset distance range within which the average distance value falls, the outer contour discrete value in the corresponding initial radiation sub-image is determined.

[0177] It should be noted that the clarity score value of the radiation sub-image is inversely proportional to the discrete value, and the color feature of the pixel point is the RGB of the corresponding pixel point. The RGB between different pixels is compared and analyzed to determine the similarity value, and based on the preset similarity threshold, it is determined whether the corresponding pixel point not on the outer contour line is associated with the pixel point on the outer contour line. When there is an association, the distance value between the corresponding two pixels is calculated, and then the average distance value is determined.

[0178] According to an embodiment of the present invention, the step of determining the discrete value of the outer contour in the corresponding initial radiation sub-image according to the preset distance range within which the average distance value falls specifically includes:

[0179] When the average distance value is less than the preset distance range, the corresponding outer contour discrete value is set to 0;

[0180] When the average distance value is within the preset distance range, the average distance value is divided by the maximum value in the corresponding preset distance range to obtain the corresponding outer contour discrete value;

[0181] When the average distance value is greater than the preset distance range, the corresponding outer contour discrete value is set to 1.

[0182] It should be noted that the average distance value is converted into an outer contour discrete value ranging from 0 to 1 according to the preset distance range. When the average distance value is less than the preset distance range, it means that the corresponding outer contour is relatively clear and visible, and there are no messy pixels; when the average distance value is greater than the preset distance range, it means that the corresponding outer contour is relatively scattered and blurred, and the corresponding outer contour discrete value reaches the maximum.

[0183] According to an embodiment of the present invention, it also includes:

[0184] Perform difference calculation on the brightness difference ratio of the group calibration points and the outer contour level contrast value to obtain a first value;

[0185] If the first value is greater than a preset first threshold, the brightness difference ratio of the group calibration corresponding to the first value is deleted, and the number of brightness difference ratios of the remaining group calibration points is extracted;

[0186] If the number of the brightness difference ratios of the remaining group of calibration points is greater than or equal to the preset first number threshold, the brightness difference ratios of the remaining group of calibration points are averaged to obtain a revised outer contour level contrast value;

[0187] If the number of brightness difference ratios of the remaining group calibration points is less than the preset first number threshold, the brightness difference ratio data of the comparison calibration point and its group calibration points are added until the number of brightness difference ratios of the group calibration points is greater than or equal to the preset first number threshold.

[0188] It should be noted that by comparing and analyzing the brightness difference ratio of the group calibration points and the outer contour level contrast value, the brightness difference ratio of the group calibration points with large differences can be found to reduce errors and improve the accuracy of the outer contour level contrast value.

[0189] According to an embodiment of the present invention, it also includes:

[0190] The secondary radiation image of the secondary radiation imaging is fused with the initial radiation image to obtain a standard radiation image;

[0191] Extract the outer contour of the detection target in the standard radiation image;

[0192] Compare and analyze the outer contour of the detected target with the outer contour of the preset dangerous object to obtain an outer contour similarity value;

[0193] If the outer contour similarity value is greater than or equal to a preset second similarity threshold, a warning message is triggered;

[0194] The warning information is sent to a preset management terminal for prompting.

[0195] It should be noted that when secondary radiation imaging is not triggered, the initial radiation image is set as the standard radiation image. When secondary radiation imaging is triggered, the secondary radiation image of the secondary radiation imaging replaces the identified initial radiation sub-image at the corresponding position.

[0196] A third aspect of the present invention provides a computer-readable storage medium, in which a program for a method for performing radiation inspection on a mobile target is stored. When the program for a method for performing radiation inspection on a mobile target is executed by a processor, the steps of the method for performing radiation inspection on a mobile target as described are implemented.

[0197] The present invention discloses a radiation inspection method, system and storage medium for a mobile target, which improves the accuracy of the radiation inspection of the mobile target through two radiation imaging.

[0198] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0199] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0200] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0201] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks or optical disks, and other media that can store program codes.

[0202] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

Claims

1. A method for radiation inspection of a mobile target, characterized in that: include: Acquire an initial radiation image of the moving target within a preset first area; dividing the initial radiation image into a plurality of initial radiation sub-images; Extracting image features and corresponding image feature values ​​in the initial radiation sub-image; Based on the preset image feature weight coefficient, according to the image features in the initial radiation sub-image and the corresponding image feature values, determine the clarity score value corresponding to the initial radiation sub-image; If the clarity score value of the initial radiation sub-image is less than the preset score threshold, the initial radiation sub-image is marked, and the position of the initial radiation sub-image corresponding to the mark is extracted; Based on the preset second area, secondary radiation imaging is performed on the marked initial radiation sub-image.

2. A method for radiation inspection of a mobile target according to claim 1, characterized in that: The step of determining the clarity score value corresponding to the initial radiation sub-image according to the image features in the initial radiation sub-image and the corresponding image feature values ​​specifically includes: Extract the continuous proportion value, layer contrast value and discrete value of the outer contour in the initial radiation sub-image; The outer contour continuous proportion value in the initial radiation sub-image is multiplied by the preset outer contour weight coefficient to obtain the outer contour score value; Multiplying the level contrast value in the initial radiation sub-image by a preset level contrast weight coefficient to obtain a level contrast score value; Multiply the discrete value in the initial radiation sub-image by a preset discrete weight coefficient to obtain a discrete score value; The outer contour score is added to the layer contrast score, and then the discrete score is subtracted to obtain the clarity score of the corresponding initial radiation sub-image; The image feature values ​​in the initial radiation sub-image include an outer contour continuity ratio value, a layer contrast value and a discrete value.

3. A method for radiation inspection of a mobile target according to claim 2, characterized in that: The step of obtaining the continuous proportion value of the outer contour in the initial radiation sub-image specifically includes: Extracting the outer contour and the endpoints of the outer contour in the initial radiation sub-image; If the endpoint of the outer contour is on the boundary of the initial radiation sub-image, the corresponding endpoint is set as a normal endpoint; if the endpoint of the outer contour is not on the boundary of the initial radiation sub-image, the corresponding endpoint is set as an abnormal endpoint; When there are abnormal endpoints, the outer contour segments in the initial radiation sub-image are extracted and sorted in sequence to obtain the outer contour segment numbers; Extract the abnormal endpoints on the outer contour line segment, and connect the abnormal endpoints on the outer contour line segments with adjacent numbers end to end to obtain the supplementary line segment length between the corresponding abnormal endpoints; When there are two abnormal endpoints in the outer contour line segment with the first and last numbers, the shortest distances from the two abnormal endpoints to the boundary of the initial radiation sub-image are extracted and set as the complementary line segment length of the boundary of the corresponding outer contour line segment and the initial radiation sub-image; The lengths of all supplementary line segments are accumulated to obtain the total length of the supplementary line segments; Extract the total length of the outer contour line segments and add it to the total length of the supplementary line segments to obtain the total length of the outer contour in the corresponding initial radiation sub-image; The total length of the outer contour line segments is divided by the total length of the outer contour in the corresponding initial radiation sub-image to obtain the outer contour continuity ratio value in the initial radiation sub-image.

4. A method for radiation inspection of a mobile target according to claim 2, characterized in that: The step of obtaining the level comparison value specifically includes: Based on the preset interval and position of the comparison calibration points, a calibration point is randomly selected on the outer contour line, and the corresponding comparison calibration point is outside the outer contour line; Extract the brightness value of the calibration point and compare the brightness value of the calibration point; Subtract the brightness value of the calibration point from the brightness value of the comparison calibration point to obtain the brightness difference; Divide the brightness difference by the brightness value of the calibration point to obtain the brightness difference ratio of the corresponding group of calibration points; The brightness difference ratios of different groups of calibration points are averaged to obtain the outer contour level contrast value in the corresponding initial radiation sub-image; The group calibration points consist of a calibration point and a comparison calibration point, and no less than 2 group calibration points are set.

5. A method for radiation inspection of a mobile target according to claim 2, characterized in that: The step of obtaining the discrete value specifically includes: Get the pixel points that are not on the outer contour line; Extract the color features of the pixels that are not on the outer contour line and the color features of the points closest to the outer contour line; When the color features of the pixels not on the outer contour line are compared with the color features of the corresponding pixels closest to the outer contour line, a similarity value is obtained; If the similarity value is greater than the preset similarity threshold, the distance value between the corresponding pixel point not on the outer contour line and the closest point of the corresponding pixel point to the outer contour line is extracted; Calculate the average value of the distance values ​​to obtain the average distance value; According to the preset distance range within which the average distance value falls, the outer contour discrete value in the corresponding initial radiation sub-image is determined.

6. A method for radiation inspection of a mobile target according to claim 5, characterized in that: The step of determining the discrete value of the outer contour in the corresponding initial radiation sub-image according to the preset distance range within which the average distance value falls specifically includes: When the average distance value is less than the preset distance range, the corresponding outer contour discrete value is set to 0; When the average distance value is within the preset distance range, the average distance value is divided by the maximum value in the corresponding preset distance range to obtain the corresponding outer contour discrete value; When the average distance value is greater than the preset distance range, the corresponding outer contour discrete value is set to 1.

7. A radiation inspection system for a mobile target, characterized in that: The invention comprises a memory and a processor, wherein the memory stores a method program for performing radiation inspection on a mobile target, and when the method program for performing radiation inspection on a mobile target is executed by the processor, the following steps are implemented: Acquire an initial radiation image of the moving target within a preset first area; dividing the initial radiation image into a plurality of initial radiation sub-images; Extracting image features and corresponding image feature values ​​in the initial radiation sub-image; Based on the preset image feature weight coefficient, according to the image features in the initial radiation sub-image and the corresponding image feature values, determine the clarity score value corresponding to the initial radiation sub-image; If the clarity score value of the initial radiation sub-image is less than the preset score threshold, the initial radiation sub-image is marked, and the position of the initial radiation sub-image corresponding to the mark is extracted; Based on the preset second area, secondary radiation imaging is performed on the marked initial radiation sub-image.

8. A radiation inspection system for a mobile target according to claim 7, characterized in that: The step of determining the clarity score value corresponding to the initial radiation sub-image according to the image features in the initial radiation sub-image and the corresponding image feature values ​​specifically includes: Extract the continuous proportion value, layer contrast value and discrete value of the outer contour in the initial radiation sub-image; The outer contour continuous proportion value in the initial radiation sub-image is multiplied by the preset outer contour weight coefficient to obtain the outer contour score value; Multiplying the level contrast value in the initial radiation sub-image by a preset level contrast weight coefficient to obtain a level contrast score value; Multiply the discrete value in the initial radiation sub-image by a preset discrete weight coefficient to obtain a discrete score value; The outer contour score is added to the layer contrast score, and then the discrete score is subtracted to obtain the clarity score of the corresponding initial radiation sub-image; The image feature values ​​in the initial radiation sub-image include an outer contour continuity ratio value, a layer contrast value and a discrete value.

9. A radiation inspection system for a mobile target according to claim 8, characterized in that: The step of obtaining the continuous proportion value of the outer contour in the initial radiation sub-image specifically includes: Extracting the outer contour and the endpoints of the outer contour in the initial radiation sub-image; If the endpoint of the outer contour is on the boundary of the initial radiation sub-image, the corresponding endpoint is set as a normal endpoint; if the endpoint of the outer contour is not on the boundary of the initial radiation sub-image, the corresponding endpoint is set as an abnormal endpoint; When there are abnormal endpoints, the outer contour line segments in the initial radiation sub-image are extracted and sorted in sequence to obtain the outer contour line segment numbers; Extract the abnormal endpoints on the outer contour line segment, and connect the abnormal endpoints on the outer contour line segments with adjacent numbers end to end to obtain the supplementary line segment length between the corresponding abnormal endpoints; When there are two abnormal endpoints in the outer contour line segment with the first and last numbers, the shortest distances from the two abnormal endpoints to the boundary of the initial radiation sub-image are extracted and set as the complementary line segment length of the boundary of the corresponding outer contour line segment and the initial radiation sub-image; The lengths of all supplementary line segments are accumulated to obtain the total length of the supplementary line segments; Extract the total length of the outer contour line segments and add them to the total length of the supplementary line segments to obtain the total length of the outer contour in the corresponding initial radiation sub-image; The total length of the outer contour line segments is divided by the total length of the outer contour in the corresponding initial radiation sub-image to obtain the outer contour continuity ratio value in the initial radiation sub-image.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a method program for performing radiation inspection on a mobile target. When the method program for performing radiation inspection on a mobile target is executed by a processor, the steps of the method for performing radiation inspection on a mobile target as described in any one of claims 1 to 6 are implemented.

Images