Foreign matter detection system

Abstract

The invention belongs to the technical field of detection equipment, and particularly relates to a foreign matter detection system. The foreign matter detection system comprises a first ray source, a first detector, a second ray source and a second detector, and ray light paths of the first ray source and the second ray source intersect; the first detector is used for collecting first detection image data of a to-be-detected object, and the second detector is used for collecting second detection image data of the to-be-detected object; the processing assembly is used for recording a first time period when the first detector collects the first detection image data and recording a second time period when the second detector collects the second detection image data; and determining whether a binding relationship exists between the first detection image data and the second detection image data or not by using an overlapping relationship between the first time period and the second time period. Whether the first detection image data and the second detection image data can be bound or not can be determined based on the binding relation, so that the problem of false detection caused by target image output errors of the foreign matter detection system is solved.

Description

Technical Field

[0001] This application belongs to the technical field of detection devices, and particularly relates to a foreign object detection system. Background Art

[0002] Compared with a single-view foreign object detection system, a dual-view foreign object detection system can generate target images at two different angles, which can prevent missed detection of foreign objects caused by the special angle of the object to be inspected and effectively eliminate the negative impact of occluders on foreign object recognition.

[0003] The dual-view foreign object detection system includes a first detection device and a second detection device. During the detection of the object to be inspected, the first detection device can generate multiple first detection images, and the second detection device can generate a second detection image. By binding each first detection image to the corresponding second detection image one by one, multiple target images can be obtained; during the detection process, if one of the first detection images is lost or the second detection image is lost, it will cause all subsequent first detection images to be unable to be bound to the corresponding second detection images, resulting in incorrect output of the target images and causing false detection. Summary of the Invention

[0004] The purpose of the embodiments of this application is to provide a foreign object detection system that can at least solve the problem of incorrect output of target images in the foreign object detection system and causing false detection.

[0005] To solve the above technical problems, this application is implemented as follows:

[0006] In a first aspect, the embodiments of this application provide a foreign object detection system, which includes:

[0007] A first radiation source and a first detector for detecting the x-rays emitted by the first radiation source at a first viewing angle;

[0008] A second radiation source and a second detector for detecting the x-rays emitted by the second radiation source at a second viewing angle; wherein, the radiation optical paths of the first radiation source and the second radiation source intersect;

[0009] During the process of detecting the object to be inspected using x-rays, the first detector is used to collect the first detection image data of the object to be inspected, and the second detector is used to collect the second detection image data of the object to be inspected;

[0010] A processing component for:

[0011] Recording the first time period when the first detector collects the first detection image data, and recording the second time period when the second detector collects the second detection image data;

[0012] Determine whether there is a binding relationship between the first detection image data and the second detection image data by using the overlapping relationship between the first time period and the second time period; wherein, the binding relationship is used to indicate that the first detection image data and the second detection image data belong to image data of different perspectives for the same object to be detected.

[0013] In an embodiment of the present application, the processing component can determine whether there is a binding relationship between the first detection image data and the second detection image data according to the overlapping relationship between the first time period when the first detector collects the first detection image data and the second time period when the second detector collects the second detection image data. Based on this binding relationship, it can be determined whether the first detection image data and the second detection image data can be bound. That is to say, only when there is a binding relationship between the first detection image data and the second detection image data, the first detection image data and the second detection image data are bound. In this way, the problem of incorrect output of the target image and false detection can be solved.

[0014] In a second aspect, an embodiment of the present application provides a foreign object detection system, which includes:

[0015] A first radiation source and a first detector for detecting the first radiation emitted by the first radiation source from a first perspective;

[0016] A second radiation source and a second detector for detecting the second radiation emitted by the second radiation source from a second perspective; wherein, the first radiation emitted by the first radiation source and the second radiation emitted by the second radiation source intersect;

[0017] During the operation of the foreign object detection system, the same object to be detected first enters the irradiation range of one of the first radiation and the second radiation, and then enters the irradiation range of the other of the first radiation and the second radiation. And within the first detection time period, the same object to be detected is simultaneously located within the irradiation ranges of the first radiation and the second radiation.

[0018] In an embodiment of the present application, one of the first detector and the second detector will first detect the object to be detected, and the other of the first detector and the second detector will then detect the object to be detected. And within the first time period, the same object to be detected is simultaneously located within the irradiation ranges of the first radiation and the second radiation. That is to say, during the process of one of the first detector and the second detector detecting and outputting an image for the object to be detected, that is, when the detection and output of the image have not ended, the other of the first detector and the second detector has already started to detect and output an image for the object to be detected. In this way, when the total number of the uploaded first detection image data and the uploaded second detection image data is inconsistent, it is convenient to process the first detection image data or the second detection image data, so that each processed first detection image data and each processed second detection image data are bound and output one by one, thereby solving the problem of false detection. Description of the Drawings

[0019] Figure 1 A schematic structural diagram of the foreign object detection system disclosed in the embodiments of the present application;

[0020] Figures 2 to 10 A schematic diagram of the relationship between the first detection image data and the second detection image data disclosed in the embodiments of the present application;

[0021] Figure 11 A schematic structural diagram of the process of the foreign object detection method disclosed in the embodiments of the present application.

[0022] Explanation of reference numerals:

[0023] 110 - First ray source, 120 - First detector, 210 - Second ray source, 220 - Second detector, 300 - First detection image data, L1 - First data length, 400 - Second detection image data, L2 - Second data length, 510 - First position detection sensor, 520 - Second position detection sensor, 530 - Third position detection sensor, 600 - Conveyor device, 700 - Object to be inspected. Detailed implementation manners

[0024] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0025] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects and are not used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. generally belong to the same category, and the number of objects is not limited. For example, the first object can be one or multiple. In addition, "and / or" in the specification and claims means at least one of the connected objects, and the character " / " generally indicates an "or" relationship between the associated objects before and after.

[0026] Next, a foreign object detection system provided in the embodiments of the present application will be described in detail in conjunction with the accompanying drawings through specific embodiments and their application scenarios.

[0027] As Figures 1 to 10 shown, the embodiments of the present application disclose a foreign object detection system, and the foreign object detection system includes:

[0028] A first radiation source 110, and a first detector 120 for detecting X-rays emitted by the first radiation source 110 at a first viewing angle; a second radiation source 210, and a second detector 220 for detecting X-rays emitted by the second radiation source 210 at a second viewing angle; wherein, the radiation optical paths of the first radiation source 110 and the second radiation source 210 intersect, and during the process of detecting the object to be inspected 700 using X-rays, the first detector 120 is used to collect first detection image data 300 of the object to be inspected 700, and the second detector 220 is used to collect second detection image data 400 of the object to be inspected 700. Specifically, the first detection image data 300 is image data of the object to be inspected 700 obtained by the first detector 120 at the first viewing angle, and the second detection image data 400 is image data of the object to be inspected 700 obtained by the second detector 220 at the second viewing angle. Binding the first detection image data 300 and the second detection image data 400 can obtain the target image data.

[0029] A processing component, configured to:

[0030] Record a first time period when the first detector 120 collects the first detection image data 300, and record a second time period when the second detector 220 collects the second detection image data 400, and use the overlapping relationship between the first time period and the second time period to determine whether there is a binding relationship between the first detection image data 300 and the second detection image data 400; wherein, the binding relationship is used to indicate that the first detection image data 300 and the second detection image data 400 are image data of different viewing angles of the same object to be inspected 700.

[0031] In an embodiment of the present application, the processing component can determine whether there is a binding relationship between the first detection image data 300 and the second detection image data 400 according to the overlapping relationship between the first time period when the first detector 120 collects the first detection image data 300 and the second time period when the second detector 220 collects the second detection image data 400. Based on this binding relationship, it can be determined whether the first detection image data 300 and the second detection image data 400 can be bound. That is to say, only when there is a binding relationship between the first detection image data 300 and the second detection image data 400, the first detection image data 300 and the second detection image data 400 are bound. In this way, the problem of incorrect target image output and false detection can be solved.

[0032] In an optional embodiment, the processing component is specifically configured to:

[0033] Record the start point and end point of the first time period when the first detector 120 acquires the first detection image data 300, record the start point and end point of the second time period when the second detector 220 acquires the second detection image data 400, and determine the overlapping relationship between the first time period and the second time period by using the time sequence relationship between the start point of the first time period, the end point of the first time period, the start point of the second time period, and the end point of the second time period. In this embodiment, the following method can be used to determine the overlapping relationship between the first time period and the second time period. If the end point of the first time period of the first time period is later than the start point of the second time period of the second time period, or the end point of the second time period of the second time period is later than the start point of the first time period of the first time period, it proves that there is an overlapping relationship between the two; if the end point of the first time period of the first time period is earlier than the start point of the second time period of the second time period, or the end point of the second time period of the second time period is earlier than the start point of the first time period of the first time period, it proves that there is no overlapping relationship between the two. And it is relatively easy to determine the magnitude relationship between the start point and the end point of each time period, so as to improve the accuracy and convenience of judging the overlapping relationship between the first time period and the second time period. Of course, in addition to this embodiment, the first time period and the second time period can also be converted into line segments, and the overlapping relationship between the first time period and the second time period can be judged according to the overlapping relationship between the two line segments.

[0034] In order to further improve the accuracy of judging the overlapping relationship between the first time period and the second time period, in an alternative embodiment, the processing component is further configured to:

[0035] Record the first data length L1 of the first detection image and the second data length L2 of the second detection image. Specifically, the processing component is configured to determine whether there is a binding relationship between the first detection image data 300 and the second detection image data 400 by using the length relationship between the first data length L1 and the second data length L2, and the time sequence relationship between the start point of the first time period, the end point of the first time period, the start point of the second time period, and the end point of the second time period. On the basis of the previous embodiment, this embodiment further introduces the first data length L1 and the second data length L2. The first data length L1 can represent the integrity of the first detection image data 300, and the second data length L2 can represent the integrity of the second detection image data 400. In this embodiment, the length relationship between the first data length L1 and the second data length L2, and the above time sequence relationship are jointly used to determine whether there is a binding relationship between the first detection image data 300 and the second detection image data 400. Compared with the previous embodiment, this embodiment uses more parameters to determine whether there is a binding relationship between the first detection image data 300 and the second detection image data 400, so as to further improve the accuracy of judging the overlapping relationship between the first time period and the second time period.

[0036] It should be noted that considering that data frame loss is an extremely rare event, the situation where the first detection image data 300 and the second detection image data 400 of the same object to be detected are both lost can be ignored and not considered. That is to say, the first detection image data 300 and the second detection image data 400 of the same object to be detected will not be lost simultaneously. The first detection image data 300 and the second detection image data 400 of the same object to be detected are either both not lost, or only one of the first detection image data 300 and the second detection image data 400 of the same object to be detected is lost.

[0037] Please refer to Figure 2 , in an optional embodiment, the processing component is specifically configured to:

[0038] When the first data length L1 is equal to the second data length L2, and the start point of the second time period is between the start point and the end point of the first time period, it is determined that there is a binding relationship between the first detection image data 300 and the second detection image data 400, and the first detection image data 300 is bound to the second detection image data 400. In this embodiment, since the first detection image data 300 and the second detection image data 400 of the same object to be detected will not be lost simultaneously, and the first data length L1 and the second data length L2 are respectively used to represent the integrity of the first detection image data 300 and the second detection image data 400, when the first data length L1 is equal to the second data length L2, it means that the first detection image data 300 and the second detection image data 400 are both complete. And when the start point of the second time period is between the start point and the end point of the first time period, it proves that either the first detection image data 300 or the second detection image data 400 of the same object to be detected is not completely lost. In this way, it can be determined that the first detection image data 300 and the second detection image data 400 of the same object to be detected are both not lost, and thus it can be determined that there is a binding relationship between the first detection image data 300 and the second detection image data 400.

[0039] It should be noted that in some special cases, for example, when the first detection image data 300 of the current object to be detected is completely lost and the second detection image data 400 is not lost, the processing component will regard the first detection image data 300 of the next object to be detected as the first detection image data 300 of the current object to be detected. At this time, the processing component will also determine that the first data length L1 is equal to the second data length L2. Therefore, in this embodiment, further judging whether the start point of the second time period is between the start point and the end point of the first time period can determine whether the first detection image data 300 and the second detection image data 400 of the same object to be detected are both not completely lost.

[0040] In the case where there is no binding relationship between the first detection image data 300 and the second detection image data 400, the first detection image data 300 and the second detection image data 400 cannot be directly bound. Therefore, in an alternative embodiment, the processing component is further configured to:

[0041] In the case where there is no binding relationship between the first detection image data 300 and the second detection image data 400, process the first detection image data 300 or the second detection image data 400, and then bind the first detection image data 300 and the processed second detection image data 400, or bind the second detection image data 400 and the processed first detection image data 300. In this embodiment, the first detection image data 300 or the second detection image data 400 is processed to make there be a binding relationship between the second detection image data 400 and the processed first detection image data 300, or make there be a binding relationship between the first detection image data 300 and the processed second detection image data 400, and then the two are bound to obtain a target image, thereby solving the problem of incorrect output of the target image and causing false detection. Further, in the case where there is no binding relationship between the first detection image data 300 and the second detection image data 400, the processing component is further configured to send an alarm message for the maintenance personnel to process in a timely manner.

[0042] Among them, the purpose of processing the first detection image data 300 or the second detection image data 400 is to rationalize the binding correspondence relationship between the first detection image data 300 and the second detection image data 400. The processing strategy can be determined according to the length relationship between the first data length L1 of the first detection image and the second data length L2 of the second detection image, and the time sequence relationship between the start point and the end point of the first time period when the first detector collects the first detection image data 300 and the start point and the end point of the second time period when the second detector collects the second detection image data 400.

[0043] Please refer to Figure 3 In an alternative embodiment, the processing component is specifically configured to:

[0044] When the first data length L1 is equal to the second data length L2 and the starting point of the first time period is greater than the starting point of the second time period, it is determined that there is no binding relationship between the first detected image data 300 and the second detected image data 400, and the blank image data is used as the processed first detected image data 300. In this embodiment, since there is no binding relationship between the first detected image data 300 and the second detected image data 400, and the first data length L1 is equal to the second data length L2, only when the first detected image data 300 is completely lost or the second detected image data 400 is completely lost. Since the starting point of the first time period in this embodiment is greater than the starting point of the second time period, it can be determined that the first detected image data 300 of the current object to be detected is completely lost, and the blank image data can be used as the processed first detected image data 300 to bind the blank image data and the second detected image data 400 to obtain the target image.

[0045] Please refer to Figure 7 , in an alternative embodiment, the processing component is specifically configured to:

[0046] When the first data length L1 is equal to the second data length L2 and the starting point of the first time period is less than the starting point of the second time period, there is no binding relationship between the first detected image data 300 and the second detected image data 400, and the blank image data is used as the processed second detected image data 400. In this embodiment, since there is no binding relationship between the first detected image data 300 and the second detected image data 400, and the first data length L1 is equal to the second data length L2, only when the first detected image data 300 is completely lost or the second detected image data 400 is completely lost. Since the starting point of the first time period in this embodiment is less than the starting point of the second time period, it can be determined that the second detected image data 400 of the current object to be detected is completely lost, and the blank image data can be used as the processed second detected image data 400 to bind the blank image data and the first detected image data 300 to obtain the target image.

[0047] Please refer to Figure 9 , in an alternative embodiment, the processing component is specifically configured to:

[0048] When the first data length L1 is greater than the second data length L2, and the difference between the starting point of the first time period of the current first detected image data 300 and the starting point of the second time period of the current second detected image data 400 is equal to the difference between the ending point of the first time period of the current first detected image data 300 and the ending point of the second time period of the next second detected image data 400, it is determined that there is no binding relationship between the first detected image data 300 and the second detected image data 400, and the current second detected image data 400 and the next second detected image data 400 are spliced, and the spliced second detected image data 400 is used as the processed second detected image data 400.

[0049] In this embodiment, since there is no binding relationship between the first detected image data 300 and the second detected image data 400, and the first data length L1 is greater than the second data length L2, it can be determined that there is a partial loss of the second detected image data 400. The partial loss of the second detected image data 400 includes the following three cases: the front - half image data of the second detected image data 400 is lost (please refer to Figure 6 ), the rear - half image data of the second detected image data 400 is lost (please refer to Figure 10 ) or the middle - segment image data of the second detected image data 400 is lost. The loss of the front - half image data or the rear - half image data of the second detected image data 400 will not cause false detection, so these two cases need to be excluded. In this embodiment, it is judged whether the difference between the starting point of the first time period of the current first detected image data 300 and the starting point of the second time period of the current second detected image data 400 is equal to the difference between the ending point of the first time period of the current first detected image data 300 and the ending point of the second time period of the next second detected image data 400. If so, it can be determined that the middle - segment image data of the second detected image data 400 is lost. At this time, the second detected image data 400 is split into two parts. The processing component will regard the second detected image data 400 located behind as the second detected image data 400 of the next object to be detected. Therefore, the current second detected image data 400 and the next second detected image data 400 are spliced, and then the spliced second detected image data 400 is used as the processed second detected image data 400, so as to bind the spliced second detected image data 400 and the first detected image data 300 to obtain the target image.

[0050] Please refer to Figure 8 , in an alternative embodiment, the processing component is specifically configured to:

[0051] When the first data length L1 is less than the second data length L2, and the difference between the start point of the first time period of the current first detection image data 300 and the start point of the second time period of the current second detection image data 400 is equal to the difference between the end point of the first time period of the next first detection image data 300 and the end point of the second time period of the current second detection image data 400, it is determined that there is no binding relationship between the first detection image data 300 and the second detection image data 400, and the current first detection image data 300 and the next first detection image data 300 are spliced, and the spliced first detection image data 300 is used as the processed first detection image data 300.

[0052] In this embodiment, since there is no binding relationship between the first detection image data 300 and the second detection image data 400, and the first data length L1 is less than the second data length L2, it can be determined that there is a partial loss of the first detection image data 300. The partial loss of the first detection image data 300 includes the following three cases: the front half of the first detection image data 300 is lost (please refer to Figure 5 ), the second half of the first detection image data 300 is lost (please refer to Figure 4 ) or the middle section of the first detection image data 300 is lost. The loss of the front half or the second half of the first detection image data 300 will not cause false detection, so these two cases need to be excluded. In this embodiment, it is judged whether the difference between the start point of the first time period of the current first detection image data 300 and the start point of the second time period of the current second detection image data 400 is equal to the difference between the end point of the first time period of the next first detection image data 300 and the end point of the second time period of the current second detection image data 400. If so, it can be determined that the middle section of the first detection image data 300 is lost. At this time, the first detection image data 300 is divided into two parts, and the processing component will regard the first detection image data 300 at the back as the first detection image data 300 of the next object to be detected. Therefore, the current first detection image data 300 and the next first detection image data 300 are spliced, and then the spliced first detection image data 300 is used as the processed first detection image data 300, so as to bind the spliced first detection image data 300 and the second detection image data 400 to obtain the target image.

[0053] As can be seen from the above analysis, the non - binding relationship between the first detection image data 300 and the second detection image data 400 includes the following situations: all of the first detection image data 300 or the second detection image data 400 is lost, and the middle - segment image data of the first detection image data 300 or the second detection image data 400 is lost. In the above - mentioned situations, the total number of the first detection image data 300 and the total number of the second detection image data 400 are not equal, and the position of the first detection image data 300 after the processed first detection image data 300 or the position of the second detection image data 400 after the processed second detection image data 400 is not the preset position. That is to say, there is no binding relationship between the first detection image data 300 after the processed first detection image data 300 and the second detection image data 400 at the corresponding position, or there is no binding relationship between the second detection image data 400 after the processed second detection image data 400 and the first detection image data 300 at the corresponding position, which will also lead to false detection. Of course, if there is no first detection image data 300 after the processed first detection image data 300, or no second detection image data 400 after the processed second detection image data 400, the above - mentioned problem does not exist.

[0054] In an alternative embodiment, the processing component is further configured to:

[0055] Sequentially move the first detection image data 300 after the processed first detection image data 300 or the second detection image data 400 after the processed second detection image data 400 one position forward, so that the positions of the first detection image data 300 and the second detection image data 400 correspond one by one. In this embodiment, the first detection image data 300 after the processed first detection image data 300 or the second detection image data 400 after the processed second detection image data 400 is sequentially moved one position forward, so that the position of the first detection image data 300 after the processed first detection image data 300 or the position of the second detection image data 400 after the processed second detection image data 400 is at the preset position, so that the positions of the first detection image data 300 and the second detection image data 400 correspond one by one. At this time, there is a binding relationship between the first detection image data 300 after the processed first detection image data 300 and the second detection image data 400 at the corresponding position, or there is a binding relationship between the second detection image data 400 after the processed second detection image data 400 and the first detection image data 300 at the corresponding position, thereby further solving the problem of false detection.

[0056] For example, the processing component binds the first detection image data 300 and the second detection image data 400 in a one-to-one correspondence. For example, the third first detection image data 300 is bound to the third second detection image data 400. Please refer to Figure 3 , if the third first detection image data 300 is completely missing, the processing component will regard the original fourth first detection image data 300 as the third first detection image data 300, and the original fifth first detection image data 300 as the fourth first detection image data 300, and so on; therefore, when actually binding, the processing component will bind the original fourth first detection image data 300 to the third second detection image data 400, resulting in a false detection. Therefore, it is necessary to shift the positions of the first detection image data 300 after the processed third first detection image data 300 one place backward in sequence. Similarly, please refer to Figure 3 , if the middle section of the third first detection image data 300 is missing, the processing component will regard the rear section of the original third first detection image data 300 as the fourth first detection image data 300, and the rear section of the original fourth first detection image data 300 as the fifth first detection image data 300. Therefore, it is necessary to shift the positions of the first detection image data 300 after the processed third first detection image data 300 one place forward in sequence.

[0057] In an alternative embodiment, the foreign object detection system further includes:

[0058] A first position detection sensor 510 and a second position detection sensor 520, which are respectively used to determine whether there is an object to be detected 700; wherein, the signal emission direction of the first position detection sensor 510 is parallel to the ray emission direction of the first ray source 110, and the signal emission direction of the second position detection sensor 520 is parallel to the ray emission direction of the second ray source 210. Specifically, after adopting the layout of this embodiment, no matter where the object to be detected 700 is located at any position in the width direction of the conveying device 600, the distance between the ray of the first ray source 110 and the signal line of the first position detection sensor 510 in the conveying direction of the object to be detected 700 is equal, and the distance between the ray of the second ray source 210 and the signal line of the second position detection sensor 520 in the conveying direction of the object to be detected 700 is also equal. In this way, the first preset time duration from when the object to be detected 700 triggers the first position detection sensor 510 to when the first detector 120 outputs the first detection image data 300, and the second preset time duration from when the object to be detected 700 triggers the second position detection sensor 520 to when the second detector 220 outputs the second detection image data 400 can be obtained from the conveying speed of the object to be detected 700. It should be noted that the first preset time duration and the second preset time duration here can be stored in the system of the processing component in advance, or can be obtained in real time during the detection process.

[0059] The processing component is further configured to:

[0060] Record the first moment when the object to be inspected 700 passes through the first position detection sensor 510, and record the second moment when the object to be inspected 700 passes through the second position detection sensor 520. Utilize the temporal relationship before and after between the first moment and the first time period to determine the frame loss situation of the first detection image data 300; utilize the temporal relationship before and after between the second moment and the second time period to determine the frame loss situation of the second detection image data 400. In this embodiment, by using the first moment and the first time period, the first actual duration of the object to be inspected 700 from triggering the first position detection sensor 510 to the first detector 120 outputting the first detection image data 300, and the second actual duration of the object to be inspected 700 from triggering the second position detection sensor 520 to the second detector 220 outputting the second detection image data 400 can be obtained. If the first actual duration is equal to the first preset duration, it indicates that the first detector 120 normally outputs the first detection image data 300 and the first detection image data 300 has no frame loss; if the first actual duration is greater than the first preset duration, it indicates that the first detector 120 delays in outputting the first detection image data 300 and the first detection image data 300 has frame loss; similarly, if the second actual duration is equal to the second preset duration, the second detection image data 400 has no frame loss; if the second actual duration is greater than the second preset duration, the second detection image data 400 has frame loss.

[0061] When frame loss occurs in one of the first detection image data 300 and the second detection image data 400, it is necessary to wait for an appropriate opportunity to perform an initialization operation on the first detector 120 and the second detector 220 for data update. For example, save the previous bound data, and the sequence numbers of the subsequent first detection image data 300 and second detection image data 400 are both calculated starting from the 0th position, ensuring automatic correction after frame loss, thereby solving the frame loss problem. Therefore, in an alternative embodiment, the foreign object detection system further includes a third position detection sensor 530, and the third position detection sensor 530 is located upstream of the first position detection sensor 510 and the second position detection sensor 520. That is to say, the object to be inspected 700 first triggers the third position detection sensor 530, and then triggers the first position detection sensor 510 and the second position detection sensor 520.

[0062] The processing component is further configured to:

[0063] Determine whether the Nth upload of the first detection image data 300 and the second detection image data 400 is completed, and whether the third position detection sensor 530 does not trigger the (N + 1)th time. If so, initialize the first detector 120 and the second detector 220. If not, return to the step of determining whether the Nth upload of the first detection image data 300 and the second detection image data 400 is completed, and whether the third position detection sensor 530 does not trigger the (N + 1)th time, where N is the number of times of collecting detection image data when there is no binding relationship between the first detection image data 300 and the second detection image data 400. In this embodiment, when the Nth upload of the first detection image data 300 and the second detection image data 400 is completed, and the third position detection sensor 530 does not trigger the (N + 1)th time, it means that the foreign object detection system has not detected the (N + 1)th object to be detected. At this time, the time for the (N + 1)th object to be detected to be transmitted to the first detector 120 and the second detector 220 is relatively long, which can provide more time for the initialization of the first detector 120 and the second detector 220.

[0064] An embodiment of the present application also discloses a foreign object detection system, which includes:

[0065] A first radiation source 110, and a first detector 120 for detecting the first radiation emitted by the first radiation source 110 at a first viewing angle; a second radiation source 210, and a second detector 220 for detecting the second radiation emitted by the second radiation source 210 at a second viewing angle; wherein, the first radiation emitted by the first radiation source 110 intersects with the second radiation emitted by the second radiation source 210; during the operation of the foreign object detection system, the same object to be detected 700 first enters the irradiation range of one of the first radiation and the second radiation, and then enters the irradiation range of the other of the first radiation and the second radiation, and within the first detection period, the same object to be detected 700 is simultaneously located within the irradiation ranges of the first radiation and the second radiation.

[0066] In the embodiments of the present application, the first ray intersects with the second ray. During the operation of the foreign object detection system, the same object to be inspected 700 first enters the irradiation range of one of the first ray and the second ray, and then enters the irradiation range of the other of the first ray and the second ray. That is to say, one of the first detector 120 and the second detector 220 will first detect the object to be inspected 700, and the other of the first detector 120 and the second detector 220 will then detect the object to be inspected 700. And within the first time period, the same object to be inspected 700 is simultaneously located within the irradiation ranges of the first ray and the second ray. That is to say, when one of the first detector 120 and the second detector 220 is still in the process of detecting and imaging the object to be inspected 700, that is, before the detection and imaging is completed, the other of the first detector 120 and the second detector 220 has already started to detect and image the object to be inspected 700. Thus, when the total number of the uploaded first detection image data 300 and the uploaded second detection image data 400 is inconsistent, it is convenient to process the first detection image data 300 or the second detection image data 400, so that each processed first detection image data 300 and each processed second detection image data 400 are bound and imaged in a one-to-one correspondence, thereby solving the problem of false detection.

[0067] Among them, the purpose of processing the first detection image data 300 or the second detection image data 400 is to make the binding correspondence relationship between the first detection image data 300 and the second detection image data 400 reasonable. The processing strategy can be determined according to the length relationship between the first data length L1 of the first detection image and the second data length L2 of the second detection image, and the time sequence relationship between the start and end points of the first time period when the first detector collects the first detection image data 300 and the start and end points of the second time period when the second detector collects the second detection image data 400. Specifically, reference can be made to the description in the above embodiments.

[0068] In an alternative embodiment, the foreign object detection system further includes a conveying device 600. The conveying device 600 has a conveying surface. In the vertical direction, the intersection of the orthographic projections of the first ray and the second ray is the first intersection, and the first intersection is located at one side edge of the conveying surface. Optionally, the conveying device 600 can be a belt conveyor, a chain plate conveyor, etc.

[0069] In this embodiment, the first intersection is located at one side edge of the conveying surface. That is to say, the first intersection can cover one side edge of the conveying surface, or there is a small gap between the first intersection and one side edge of the conveying surface, so that there is a preset distance between the first intersection and one side edge of the conveying surface. With such a setting, when the object to be detected 700 is placed at any position on the conveying surface, the order of the object to be detected 700 passing through the first ray and the second ray can be kept consistent, which is more conducive to judging whether there is a binding relationship between the first detection image data 300 and the second detection image data 400, and processing the first detection image data 300 or the second detection image data 400. Of course, the first intersection can also be located in the middle of the transmission surface, and this application does not limit the position of the first intersection on the conveying surface.

[0070] In an alternative embodiment, the foreign object detection system further includes:

[0071] A first position detection sensor 510 and a second position detection sensor 520, which are respectively used to determine whether there is an object to be detected 700; wherein, the signal emission direction of the first position detection sensor 510 is parallel to the ray emission direction of the first ray source 110, and the signal emission direction of the second position detection sensor 520 is parallel to the ray emission direction of the second ray source 210.

[0072] In the vertical direction, the intersection of the positive projection of the first ray and the positive projection of the second ray is the first intersection, and the intersection of the positive projection of the signal emitted by the first position detection sensor 510 and the positive projection of the signal emitted by the second position detection sensor 520 is the second intersection. The first intersection and the second intersection are arranged in sequence in the conveying direction of the foreign object detection system. In this embodiment, the first intersection and the second intersection are arranged in sequence in the conveying direction, so as to ensure that the object to be detected 700 triggers the first position detection sensor 510, the second position detection sensor 520, the first detector 120 and the second detector 220 in sequence, or ensure that the object to be detected 700 triggers the second position detection sensor 520, the first position detection sensor 510, the second detector 220 and the first detector 120 in sequence, so that the distance traveled when the object to be detected 700 triggers the first position detection sensor 510 and the first detector 120 remains unchanged, and the distance traveled when the object to be detected 700 triggers the second position detection sensor 520 and the second detector 220 remains unchanged, so as to facilitate judging whether the first detection image data 300 is lost according to the magnitude relationship between the first actual duration and the first preset duration described above, and judging whether the second detection image data 400 is lost according to the magnitude relationship between the second actual duration and the second preset duration described above.

[0073] In an alternative embodiment, the foreign object detection system further includes:

[0074] The third position detection sensor 530 is located upstream of the first position detection sensor 510 and the second position detection sensor 520. That is to say, the object to be detected 700 triggers the third position detection sensor 530 first, and then triggers the other two. The initialization time of the first detector 120 is t1, and the initialization time of the second detector 220 is t2.

[0075] The same object to be detected 700 triggers the third position detection sensor 530, the first position detection sensor 510, and the second position detection sensor 520 in sequence. The shortest time interval between triggering the third position detection sensor 530 and the first position detection sensor 510 is t3, t3 > t1, and t3 > t2. In this embodiment, t3 > t1, and t3 > t2. In this way, when the Nth upload of the first detection image data 300 is completed, and the third position detection sensor 530 does not trigger the (N + 1)th time, and when the initialization of the first detector 120 is completed, the (N + 1)th object to be detected cannot trigger the first position detection sensor 510, so as to ensure that the (N + 1)th object to be detected cannot trigger the first detector 120, so as to avoid the (N + 1)th object to be detected reaching the first detector 120 during the initialization of the first detector 120, resulting in frame loss of the first detection image data 300.

[0076] Alternatively, the same object to be detected 700 triggers the third position detection sensor 530, the second position detection sensor 520, and the first position detection sensor 510 in sequence. The shortest time interval between triggering the third position detection sensor 530 and the second position detection sensor 520 is t4, t4 > t1, and t4 > t2. In this embodiment, t4 > t1, and t4 > t2. In this way, when the Nth upload of the first detection image data 300 is completed, and the fourth position detection sensor does not trigger the (N + 1)th time, and when the initialization of the second detector 220 is completed, the (N + 1)th object to be detected cannot trigger the second position detection sensor 520, so as to ensure that the (N + 1)th object to be detected cannot trigger the second detector 220, so as to avoid the (N + 1)th object to be detected reaching the second detector 220 during the initialization of the second detector 220, resulting in frame loss of the second detection image data 400.

[0077] As Figure 11 shown, the embodiment of the present application also provides a foreign object detection method, which is applied to the foreign object detection system described in any of the above embodiments, and includes:

[0078] S110. Record the start point and end point of the first time period when the first detector 120 collects the first detection image data 300, record the start point and end point of the second time period when the second detector 220 collects the second detection image data 400, and record the first data length L1 of the first detection image and the second data length L2 of the second detection image.

[0079] S120. Determine whether L1 = L2 is satisfied, where L1 is the first data length of the current first detection image data 300, and L2 is the second data length of the current second detection image data 400.

[0080] S130. If L1 = L2 is satisfied, then determine whether Tan < Tbn < Tan' is satisfied, where Tan is the starting point of the first time period of the current first detection image data 300, Tbn is the starting point of the second time period of the current second detection image data 400, and Tan' is the ending point of the first time period of the current first detection image data 300.

[0081] S140. If Tan < Tbn < Tan' is satisfied, then bind An and Bn, where An is the current first detection image data 300 and Bn is the current second detection image data 400.

[0082] S150. If Tan < Tbn < Tan' is not satisfied, then determine whether Tan > Tbn is satisfied.

[0083] S160. If Tan > Tbn is satisfied, then use blank image data as the processed An, and bind Bn and the processed An.

[0084] S170. If Tan > Tbn is not satisfied, then use blank image data as the processed Bn, and bind An and the processed Bn.

[0085] S180. If L1 = L2 is not satisfied, then determine whether L1 > L2 is satisfied.

[0086] S190. If L1 > L2 is satisfied, then determine whether Tan - Tbn = Tan' - Tbn+1' is satisfied, where Tbn+1' is the ending point of the second time period of the next second detection image data 400.

[0087] S200. If Tan - Tbn = Tan' - Tbn+1' is satisfied, then splice Bn and Bn+1, and use the spliced Bn as the processed Bn, and bind An and the processed Bn. Here, Bn+1 is the next second detection image data 400.

[0088] S210. If Tan - Tbn = Tan' - Tbn+1' is not satisfied, then determine that there is a frame loss in the first half or the second half of the data of Bn, and bind An and Bn.

[0089] S220. If L1 > L2 is not satisfied, then determine whether Tan - Tbn = Tan+1' - Tbn' is satisfied, where Tan+1' is the ending point of the first time period of the next first detection image data 300.

[0090] S230. If Tan - Tbn = Tan+1'- Tbn' is satisfied, then splice An and An+1, and use the spliced An as the processed An, and bind Bn to the processed An. Here, An+1 is the next first detected image data 300, Tan+1' is the end point of the first time period of the next first detected image data 300, and Tbn' is the end point of the second time period of the current second detected image data 400.

[0091] S240. If Tan - Tbn = Tan+1'- Tbn' is not satisfied, then determine that data loss occurs in the first half or the second half of An, and bind An to Bn.

[0092] In the above embodiments of the present application, the differences between the various embodiments are mainly described. As long as the different optimization features between the various embodiments are not contradictory, they can be combined to form a more optimal embodiment. For the sake of brevity of the description, they will not be elaborated here. The embodiments of the present application have been described above with reference to the accompanying drawings. However, the present application is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present application, those of ordinary skill in the art can also make many forms without departing from the purpose of the present application and the scope protected by the claims, and all of them fall within the protection scope of the present application.

Claims

1. A foreign object detection system, characterized in that, the foreign object detection system includes: a first radiation source (110), and a first detector (120) for detecting x-rays emitted by the first radiation source (110) at a first viewing angle; a second radiation source (210), and a second detector (220) for detecting x-rays emitted by the second radiation source (210) at a second viewing angle; wherein, the radiation optical paths of the first radiation source (110) and the second radiation source (210) intersect; during the process of detecting a test object (700) using x-rays, the first detector (120) is used to collect first detection image data (300) of the test object (700), and the second detector (220) is used to collect second detection image data (400) of the test object (700); a processing component, configured to: record a first time period during which the first detector (120) collects the first detection image data (300), and record a second time period during which the second detector (220) collects the second detection image data (400); use the overlapping relationship between the first time period and the second time period to determine whether there is a binding relationship between the first detection image data (300) and the second detection image data (400); wherein, the binding relationship is used to indicate that the first detection image data (300) and the second detection image data (400) belong to image data of different viewing angles of the same test object (700).

2. The foreign object detection system according to claim 1, characterized in that, the processing component is specifically configured to: record a start point and an end point of the first time period during which the first detector (120) collects the first detection image data (300); record a start point and an end point of the second time period during which the second detector (220) collects the second detection image data (400); use the time sequence relationship between the start point of the first time period, the end point of the first time period, the start point of the second time period, and the end point of the second time period to determine the overlapping relationship between the first time period and the second time period.

3. The foreign object detection system according to claim 2, characterized in that, the processing component is further configured to: record a first data length (L1) of the first detection image and a second data length (L2) of the second detection image; the processing component is specifically configured to use the length relationship between the first data length (L1) and the second data length (L2), and the time sequence relationship between the start point of the first time period, the end point of the first time period, the start point of the second time period, and the end point of the second time period to determine whether there is a binding relationship between the first detection image data (300) and the second detection image data (400).

4. The foreign object detection system according to claim 3, characterized in that, the processing component is specifically configured to: When the first data length (L1) is equal to the second data length (L2), and the start point of the second time period is between the start point and the end point of the first time period, it is determined that there is a binding relationship between the first detection image data (300) and the second detection image data (400), and the first detection image data (300) is bound to the second detection image data (400).

5. The foreign object detection system according to claim 3, wherein, the processing component is further configured to: when there is no binding relationship between the first detection image data (300) and the second detection image data (400), process the first detection image data (300) or the second detection image data (400), and then bind the first detection image data (300) to the processed second detection image data (400), or bind the second detection image data (400) to the processed first detection image data (300).

6. The foreign object detection system according to claim 5, wherein, the processing component is specifically configured to: when the first data length (L1) is equal to the second data length (L2), and the start point of the first time period is greater than the start point of the second time period, it is determined that there is no binding relationship between the first detection image data (300) and the second detection image data (400), and blank image data is used as the processed first detection image data (300).

7. The foreign object detection system according to claim 5, wherein, the processing component is specifically configured to: when the first data length (L1) is equal to the second data length (L2), and the start point of the first time period is less than the start point of the second time period, there is no binding relationship between the first detection image data (300) and the second detection image data (400), and blank image data is used as the processed second detection image data (400).

8. The foreign object detection system according to claim 5, wherein, the processing component is specifically configured to: when the first data length (L1) is greater than the second data length (L2), and the difference between the start point of the first time period of the current first detection image data (300) and the start point of the second time period of the current second detection image data (400) is equal to the difference between the end point of the first time period of the current first detection image data (300) and the end point of the second time period of the next second detection image data (400), it is determined that there is no binding relationship between the first detection image data (300) and the second detection image data (400), and the current second detection image data (400) and the next second detection image data (400) are spliced, and the spliced second detection image data (400) is used as the processed second detection image data (400).

9. The foreign object detection system according to claim 8, wherein, The processing component is specifically configured to: When the first data length (L1) is less than the second data length (L2), and the difference between the start point of the first time period of the current first detection image data (300) and the start point of the second time period of the current second detection image data (400) is equal to the difference between the end point of the first time period of the next first detection image data (300) and the end point of the second time period of the current second detection image data (400), it is determined that there is no binding relationship between the first detection image data (300) and the second detection image data (400), and the current first detection image data (300) and the next first detection image data (300) are spliced, and the spliced first detection image data (300) is used as the processed first detection image data (300).

10. The foreign object detection system according to claim 5, wherein, the processing component is further configured to: Shift the first detection image data (300) located after the processed first detection image data (300) or the second detection image data (400) located after the processed second detection image data (400) one place in sequence, so that the positions of the first detection image data (300) and the second detection image data (400) correspond one by one.

11. The foreign object detection system according to claim 1, wherein, the foreign object detection system further includes: A first position detection sensor (510) and a second position detection sensor (520), which are respectively used to determine whether the object to be detected (700) exists; wherein, the signal emission direction of the first position detection sensor (510) is parallel to the ray emission direction of the first ray source (110), and the signal emission direction of the second position detection sensor (520) is parallel to the ray emission direction of the second ray source (210); the processing component is further configured to: Record the first moment when the object to be detected (700) passes through the first position detection sensor (510), and record the second moment when the object to be detected (700) passes through the second position detection sensor (520); Use the time sequence relationship between the first moment and the first time period to determine the frame loss situation of the first detection image data (300); Use the time sequence relationship between the second moment and the second time period to determine the frame loss situation of the second detection image data (400).

12. The foreign object detection system according to claim 11, wherein, the foreign object detection system further includes a third position detection sensor (530), and the third position detection sensor (530) is located upstream of the first position detection sensor (510) and the second position detection sensor (520), the processing component is further configured to: Determine whether the Nth upload of the first detected image data (300) and the second detected image data (400) is completed, and whether the third position detection sensor (530) is not triggered for the (N + 1)th time. If so, initialize the first detector (120) and the second detector (220). If not, return to the step of determining whether the Nth upload of the first detected image data (300) and the second detected image data (400) is completed, and whether the third position detection sensor (530) is not triggered for the (N + 1)th time; Wherein, N is the number of times of detecting image data acquisition corresponding to the case where there is no binding relationship between the first detected image data (300) and the second detected image data (400).

13. A foreign object detection system, Characterized in that, The foreign object detection system includes: A first radiation source (110), and a first detector (120) for detecting the first radiation emitted by the first radiation source (110) at a first viewing angle; A second radiation source (210), and a second detector (220) for detecting the second radiation emitted by the second radiation source (210) at a second viewing angle; wherein, the first radiation emitted by the first radiation source (110) and the second radiation emitted by the second radiation source (210) intersect; During the operation of the foreign object detection system, the same object to be inspected (700) first enters the irradiation range of one of the first radiation and the second radiation, and then enters the irradiation range of the other of the first radiation and the second radiation, and within the first detection period, the same object to be inspected (700) is simultaneously located within the irradiation ranges of the first radiation and the second radiation.

14. The foreign object detection system according to claim 13, Characterized in that, The foreign object detection system further includes a conveying device (600), and the conveying device (600) has a conveying surface, In the vertical direction, the intersection of the orthographic projections of the first radiation and the second radiation is the first intersection, and the first intersection is located at one side edge of the conveying surface.

15. The foreign object detection system according to claim 13, Characterized in that, The foreign object detection system further includes: A first position detection sensor (510) and a second position detection sensor (520), respectively used to determine whether there is an object to be inspected (700); wherein, the signal emission direction of the first position detection sensor (510) is parallel to the radiation emission direction of the first radiation source (110), and the signal emission direction of the second position detection sensor (520) is parallel to the radiation emission direction of the second radiation source (210); In the vertical direction, the intersection of the positive projection of the first ray and the positive projection of the second ray is the first intersection, and the intersection of the positive projection of the signal emitted by the first position detection sensor (510) and the positive projection of the signal emitted by the second position detection sensor (520) is the second intersection. The first intersection and the second intersection are arranged in sequence in the conveying direction of the foreign object detection system.

16. The foreign object detection system according to claim 15, characterized in that the foreign object detection system further includes: a third position detection sensor (530), the third position detection sensor (530) is located upstream of the first position detection sensor (510) and the second position detection sensor (520), the initialization time of the first detector (120) is t1, and the initialization time of the second detector (220) is t2. The same object to be detected (700) sequentially triggers the third position detection sensor (530), the first position detection sensor (510) and the second position detection sensor (520), and the shortest time interval between the sequential triggering of the third position detection sensor (530) and the first position detection sensor (510) is t3, t3 > t1 and t3 > t2; or, the same object to be detected (700) sequentially triggers the third position detection sensor (530), the second position detection sensor (520) and the first position detection sensor (510), and the shortest time interval between the sequential triggering of the third position detection sensor (530) and the second position detection sensor (520) is t4, t4 > t1 and t4 > t2.

Images