Open source detection methods, devices, systems, electronic equipment and media for security inspection equipment

Abstract

The embodiment of the present invention provides an open source detection method, device, system, electronic device and medium for security inspection equipment. The method is applied to a security inspection system, which includes a control device, an image acquisition device and a security inspection device. The field of view of the image acquisition device includes a first conveyor belt area located in front of the security inspection channel according to the running direction of the conveyor belt, wherein the control device obtains a conveyor belt image of the security inspection device acquired by the image acquisition device, determines whether there is an object to be detected based on the difference between the image feature corresponding to the preset trigger position in the conveyor belt image and the image feature corresponding to the preset trigger position in the pre-acquired first background image, and controls the opening of the radiation source of the security inspection device based on the determination result of the object to be detected. Since the image feature corresponding to the preset trigger position in the conveyor belt image will not be affected by factors such as the height and shape of the object to be detected, the accuracy of the open source detection of the security inspection device is high.

Description

Technical Field

[0001] The present invention relates to the field of security inspection technology, and in particular to an open source detection method, device, system, electronic equipment and medium for security inspection equipment. Background Art

[0002] Security inspection equipment is an electronic device that uses a conveyor belt to transport the inspected items into the X-ray inspection channel to complete the inspection. At present, in order to extend the service life of the radiation source, reduce power consumption, and reduce ionizing radiation, the radiation source can be turned on only when the inspected items are detected on the conveyor belt, and can be kept off when there are no inspected items.

[0003] In the open source detection method of the security inspection equipment, an infrared light barrier is installed at the entrance of the conveyor belt. When the inspected item is placed on the conveyor belt and moves to the position of the infrared light barrier along with the conveyor belt, the infrared rays will be blocked, so that the infrared light barrier receiving end will not be able to receive the infrared rays. This indicates that there are inspected items on the conveyor belt. The main controller of the security inspection equipment immediately triggers an alarm signal and controls the radiation source to turn on.

[0004] However, since the infrared light barrier can only detect whether a line between the transmitting end and the receiving end is blocked, and the infrared light barrier has a certain height, that is, the infrared light it emits is a certain distance from the surface of the conveyor belt, so when encountering ultra-thin objects to be detected, the height of the objects to be detected may be lower than the detection height of the infrared light barrier, and the infrared light will not be blocked, resulting in missed detection. When encountering special-shaped objects to be detected, the infrared light is blocked multiple times at the edge of the objects to be detected, which will cause false triggering. It can be seen that the current open source detection method of security inspection equipment has the problem of low detection accuracy. Summary of the invention

[0005] The purpose of the embodiments of the present invention is to provide a method, device, system, electronic device and medium for detecting open source of security inspection equipment, so as to improve the accuracy of open source detection of security inspection equipment. The specific technical solution is as follows:

[0006] In a first aspect, an embodiment of the present invention provides an open source detection method for security inspection equipment, which is applied to a control device in a security inspection system, wherein the security inspection system further includes an image acquisition device and a security inspection equipment, and the method includes:

[0007] Acquire the conveyor belt image of the security inspection device captured by the image acquisition device, wherein the field of view of the image acquisition device includes a first conveyor belt area located in front of the security inspection channel according to the running direction of the conveyor belt;

[0008] Determine whether there is a detected object based on a difference between an image feature corresponding to a preset trigger position in the conveyor belt image and an image feature corresponding to the preset trigger position in a pre-captured first background image, wherein the first background image is an image of the first conveyor belt area captured by the image capture device when no detected object is present;

[0009] Based on the determination result of the detected object, the radiation source of the security inspection device is controlled to turn on.

[0010] Optionally, the step of determining whether there is a detected object based on a difference between an image feature corresponding to a preset trigger position in the conveyor belt image and an image feature corresponding to the preset trigger position in a pre-collected first background image includes:

[0011] Calculate the average pixel value of pixels at a preset trigger position in the conveyor belt image; if the difference between the average pixel value and the target pixel value reaches a preset difference, determine that there is a detected object, wherein the target pixel value is the average pixel value of pixels at the preset trigger position in one or more first background images collected in advance; or,

[0012] A feature vector at a preset trigger position in the conveyor belt image is extracted as a vector to be processed; if the similarity between the vector to be processed and the target feature vector does not reach a preset similarity, it is determined that there is a detected object, wherein the target feature vector is a feature vector at the preset trigger position in a first background image collected in advance, or is an average value of the feature vectors at the preset trigger position in multiple first background images.

[0013] Optionally, the conveyor belt of the security inspection equipment has a specific pattern;

[0014] The step of determining whether there is a detected object based on a difference between an image feature corresponding to a preset trigger position in the conveyor belt image and an image feature corresponding to the preset trigger position in a pre-collected first background image comprises:

[0015] Determining encoding information corresponding to the conveyor belt image based on pattern features at a preset trigger position in the conveyor belt image and a preset encoding rule;

[0016] If the difference between the coding information corresponding to the conveyor belt image and the target coding information reaches a preset threshold, it is determined that there is an object to be detected, wherein the target coding information is the information encoded according to the preset coding rule for the pattern features at the preset trigger position in the pre-captured first background image.

[0017] Optionally, the specific pattern is a stripe pattern along the running direction of the conveyor belt, and the width of the stripes in the stripe pattern is determined according to the minimum volume of the detected object.

[0018] Optionally, the method for determining the preset trigger position includes:

[0019] Determine the target trigger position according to the conveyor belt running speed of the security inspection equipment and the opening delay of the radiation source, wherein the time required for the inspected object to run from the target trigger position to the position corresponding to the radiation source according to the conveyor belt running speed is not less than the opening delay;

[0020] According to the internal parameters and external parameters of the image acquisition device, the position of the target trigger position in the image acquired by the image acquisition device is calculated as the preset trigger position.

[0021] Optionally, the field of view of the image acquisition device also includes a second conveyor belt area located behind the security inspection channel according to the running direction of the conveyor belt;

[0022] The method further comprises:

[0023] Determine whether there is a detected object based on a difference between an image feature corresponding to a preset end position in the conveyor belt image and an image feature corresponding to the preset end position in a pre-collected second background image, wherein the second background image is an image of the second conveyor belt area collected by the image acquisition device when no detected object is present;

[0024] If there is, and no detected object is detected at the preset trigger position within the target time length, the radiation source of the security inspection device is controlled to be turned off.

[0025] Optionally, the security inspection system further includes a detection unit, and the detection unit is used to detect whether there is an object to be inspected on the conveyor belt; the method further includes:

[0026] Acquiring a detection result of the detection unit;

[0027] The step of controlling the radiation source of the security inspection device to turn on based on the determination result of the detected object includes:

[0028] When at least one of the detection result and the determination result of the detected object indicates the presence of the detected object, controlling the radiation source of the security inspection device to turn on; or,

[0029] A weighted result of the detection result and the determination result of the detected object is calculated based on a preset weight, and when the weighted result indicates that the detected object exists, the radiation source of the security inspection device is controlled to turn on.

[0030] Optionally, the security inspection system further includes a display device; and the method further includes:

[0031] The conveyor belt image is sent to the display device, so that the display device displays the conveyor belt image and displays a mark corresponding to the preset trigger position in the conveyor belt image.

[0032] Optionally, the image acquisition device is a monocular camera, a binocular camera or a depth camera.

[0033] In a second aspect, an embodiment of the present invention provides an open source detection device for security inspection equipment, which is applied to a control device in a security inspection system, wherein the security inspection system further includes an image acquisition device and a security inspection device, and the device includes:

[0034] A conveyor belt image acquisition module, used to acquire the conveyor belt image of the security inspection device acquired by the image acquisition device, wherein the field of view of the image acquisition device includes a first conveyor belt area located in front of the security inspection channel according to the running direction of the conveyor belt;

[0035] A first determination module, configured to determine whether there is a detected object based on a difference between an image feature corresponding to a preset trigger position in the conveyor belt image and an image feature corresponding to the preset trigger position in a pre-captured first background image, wherein the first background image is an image of the first conveyor belt area captured by the image capture device when no detected object is present;

[0036] The radiation source activation module is used to control the activation of the radiation source of the security inspection device based on the determination result of the detected object.

[0037] Optionally, the first determining module includes:

[0038] A first determination submodule is configured to calculate an average pixel value of pixels at a preset trigger position in the conveyor belt image; if the difference between the average pixel value and a target pixel value reaches a preset difference, it is determined that there is a detected object, wherein the target pixel value is an average pixel value of pixels at the preset trigger position in one or more first background images collected in advance; or,

[0039] A feature vector at a preset trigger position in the conveyor belt image is extracted as a vector to be processed; if the similarity between the vector to be processed and the target feature vector does not reach a preset similarity, it is determined that there is a detected object, wherein the target feature vector is a feature vector at the preset trigger position in a first background image collected in advance, or is an average value of the feature vectors at the preset trigger position in multiple first background images.

[0040] Optionally, the conveyor belt of the security inspection equipment has a specific pattern;

[0041] The first determining module includes:

[0042] A coding information determination submodule, used to determine the coding information corresponding to the conveyor belt image based on the pattern features at the preset trigger position in the conveyor belt image and the preset coding rules;

[0043] The second determination submodule is used to determine the presence of the detected object if the difference between the coding information corresponding to the conveyor belt image and the target coding information reaches a preset threshold, wherein the target coding information is the pattern feature at the preset trigger position in the pre-captured first background image, encoded according to the preset coding rule.

[0044] Optionally, the specific pattern is a stripe pattern along the running direction of the conveyor belt, and the width of the stripes in the stripe pattern is determined according to the minimum volume of the detected object.

[0045] Optionally, the device further includes a preset trigger position determining module, and the preset trigger position determining module is used to determine the preset trigger position, including:

[0046] A target trigger position determination submodule, used to determine the target trigger position according to the conveyor belt running speed of the security inspection device and the turn-on delay of the radiation source, wherein the time required for the inspected object to run from the target trigger position to the position corresponding to the radiation source according to the conveyor belt running speed is not less than the turn-on delay;

[0047] The preset trigger position determination submodule is used to calculate the position of the target trigger position in the image captured by the image capture device according to the internal parameters and external parameters of the image capture device as the preset trigger position.

[0048] Optionally, the field of view of the image acquisition device also includes a second conveyor belt area located behind the security inspection channel according to the running direction of the conveyor belt;

[0049] The device also includes:

[0050] A second determination module is used to determine whether there is a detected object based on a difference between an image feature corresponding to a preset end position in the conveyor belt image and an image feature corresponding to the preset end position in a pre-collected second background image, wherein the second background image is an image of the second conveyor belt area collected by the image acquisition device when there is no detected object;

[0051] The radiation source shut-down module is used to control the radiation source of the security inspection device to shut down if there is an object to be detected at the preset trigger position and no object is detected within a target time period.

[0052] Optionally, the security inspection system further includes a detection unit, which is used to detect whether there is an object to be inspected on the conveyor belt; the device also includes:

[0053] A detection result acquisition module, used to obtain the detection result of the detection unit;

[0054] The ray source activation module comprises:

[0055] a radiation source activation submodule, configured to control the radiation source of the security inspection device to be activated when at least one of the detection result and the detection result indicates the presence of the detected object; or

[0056] The method is used to calculate a weighted result of the detection result and the determination result of the detected object based on a preset weight, and when the weighted result indicates that there is a detected object, control the radiation source of the security inspection device to turn on.

[0057] Optionally, the security inspection system further includes a display device; and the device further includes:

[0058] The image display module is used to send the conveyor belt image to the display device so that the display device displays the conveyor belt image and displays the mark corresponding to the preset trigger position in the conveyor belt image.

[0059] Optionally, the image acquisition device is a monocular camera, a binocular camera or a depth camera.

[0060] In a third aspect, an embodiment of the present invention provides a security inspection system, the system comprising a control device, an image acquisition device and a security inspection device, wherein:

[0061] The security inspection device is used to inspect the inspected items; the image acquisition device is used to acquire the conveyor belt image of the security inspection device, wherein the field of view of the image acquisition device includes the first conveyor belt area located in front of the security inspection channel according to the running direction of the conveyor belt;

[0062] The control device is used to obtain the conveyor belt image; determine whether there is an object to be detected based on the difference between the image features corresponding to the preset trigger position in the conveyor belt image and the image features corresponding to the preset trigger position in the pre-captured first background image; and control the radiation source of the security inspection device to turn on based on the determination result of the object to be detected, wherein the first background image is an image of the first conveyor belt area captured by the image acquisition device when there is no object to be detected.

[0063] Optionally, the control device can be specifically used to calculate the average pixel value of pixels at a preset trigger position in the conveyor belt image; if the difference between the average pixel value and the target pixel value reaches a preset difference, it is determined that there is a detected object, wherein the target pixel value is the average pixel value of pixels at the preset trigger position in one or more first background images collected in advance; or,

[0064] Specifically, it can be used to extract the feature vector at the preset trigger position in the conveyor belt image as the vector to be processed; if the similarity between the vector to be processed and the target feature vector does not reach the preset similarity, it is determined that there is a detected object, wherein the target feature vector is the feature vector at the preset trigger position in a first background image collected in advance, or is the average value of the feature vectors at the preset trigger position in multiple first background images.

[0065] Optionally, the conveyor belt of the security inspection equipment has a specific pattern;

[0066] The control device can be specifically used to determine the coding information corresponding to the conveyor belt image based on the pattern features at the preset trigger position in the conveyor belt image and the preset coding rules; if the difference between the coding information corresponding to the conveyor belt image and the target coding information reaches a preset threshold, it is determined that there is a detected object, wherein the target coding information is the information encoded according to the preset coding rule for the pattern features at the preset trigger position in the pre-collected first background image.

[0067] Optionally, the specific pattern is a stripe pattern along the running direction of the conveyor belt, and the width of the stripes in the stripe pattern is determined according to the minimum volume of the detected object.

[0068] Optionally, the control device can also be used to determine the target trigger position based on the conveyor belt running speed of the security inspection device and the turn-on delay of the radiation source, wherein the time required for the inspected object to run from the target trigger position to the position corresponding to the radiation source at the conveyor belt running speed is not less than the turn-on delay; based on the internal parameters and external parameters of the image acquisition device, the position of the target trigger position in the image captured by the image acquisition device is calculated as a preset trigger position.

[0069] Optionally, the field of view of the image acquisition device also includes a second conveyor belt area located behind the security inspection channel according to the running direction of the conveyor belt;

[0070] The control device can also be used to determine whether there is an object to be detected based on the difference between the image features corresponding to the preset end position in the conveyor belt image and the image features corresponding to the preset end position in the pre-captured second background image, wherein the second background image is an image of the second conveyor belt area captured by the image acquisition device when there is no object to be detected; if there is, and the object to be detected is not detected at the preset trigger position within the target time length, the radiation source of the security inspection device is controlled to be turned off.

[0071] Optionally, the security inspection system further includes a detection unit;

[0072] The control device can also be used to obtain the detection result of the detection unit; when at least one of the detection result and the determination result of the detected object indicates the presence of the detected object, control the radiation source of the security inspection device to turn on; or, calculate the weighted result of the detection result and the determination result of the detected object based on a preset weight, and when the weighted result indicates the presence of the detected object, control the radiation source of the security inspection device to turn on.

[0073] Optionally, the security inspection system further includes a display device;

[0074] The control device may also be used to send the conveyor belt image to the display device, so that the display device displays the conveyor belt image and displays a mark corresponding to the preset trigger position in the conveyor belt image.

[0075] Optionally, the image acquisition device is a monocular camera, a binocular camera or a depth camera.

[0076] In a fourth aspect, an embodiment of the present invention provides an electronic device, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0077] Memory, used to store computer programs;

[0078] The processor is used to implement any method step described in the first aspect when executing the program stored in the memory.

[0079] In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method steps described in any one of the first aspects are implemented.

[0080] Beneficial effects of the embodiments of the present invention:

[0081] In the solution provided by the embodiment of the present invention, there is a control device in the security inspection system, and the security inspection system also includes an image acquisition device and a security inspection device. The control device obtains a conveyor belt image of the security inspection device acquired by the image acquisition device, wherein the field of view of the image acquisition device includes a first conveyor belt area located in front of the security inspection channel according to the running direction of the conveyor belt, and determines whether there is a detected object based on the difference between the image feature corresponding to the preset trigger position in the conveyor belt image and the image feature corresponding to the preset trigger position in the pre-acquired first background image, wherein the first background image is an image of the first conveyor belt area acquired by the image acquisition device when there is no detected object, and based on the determination result of the detected object, the radiation source of the security inspection device is controlled to be turned on. Since the first background image is an image of the first conveyor belt area acquired by the image acquisition device when there is no detected object, based on the difference between the image feature corresponding to the preset trigger position in the conveyor belt image and the image feature corresponding to the preset trigger position in the first background image, it can be determined whether there is a detected object, and then the radiation source of the security inspection device can be controlled to be turned on. The image feature corresponding to the preset trigger position in the conveyor belt image will not be affected by factors such as the height and shape of the detected object, so the accuracy of the open source detection of the security inspection device is high, and the problem of missed or erroneous activation of the radiation source can be effectively solved. Of course, it is not necessary to achieve all of the advantages described above at the same time to implement any product or method of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other embodiments can also be obtained based on these drawings.

[0083] Figure 1 A flow chart of an open source detection method for security inspection equipment provided by an embodiment of the present invention;

[0084] Figure 2 Based on Figure 1 A structural schematic diagram of the security inspection system of the illustrated embodiment;

[0085] Figure 3 Based on Figure 1 Another structural schematic diagram of the security inspection system of the illustrated embodiment;

[0086] Figure 4 for Figure 1 A specific flow chart of step S102 in the illustrated embodiment;

[0087] Figure 5 Based on Figure 4 A schematic diagram of the first conveyor belt area of ​​the illustrated embodiment;

[0088] Figure 6 Based on Figure 1 A flow chart of a method for determining a preset trigger position in the illustrated embodiment;

[0089] Figure 7 Based on Figure 1 A flow chart of a closed source detection method for security inspection equipment in the illustrated embodiment;

[0090] Figure 8 Based on Figure 1 Another structural schematic diagram of the security inspection system of the illustrated embodiment;

[0091] Fig. 9 A schematic diagram of the structure of an open source detection device for security inspection equipment provided by an embodiment of the present invention;

[0092] Fig.10 A schematic diagram of the structure of a security inspection system provided by an embodiment of the present invention;

[0093] Fig.11 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0094] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field based on this application belong to the scope of protection of the present invention.

[0095] In order to improve the accuracy of open source detection of security inspection equipment, embodiments of the present invention provide an open source detection method, device, system, electronic device, computer readable storage medium and computer program product for security inspection equipment. First, an open source detection method for security inspection equipment provided by an embodiment of the present invention is introduced.

[0096] The open source detection method for security inspection equipment provided by the embodiment of the present invention can be applied to a control device that needs to control the opening of a radiation source in a security inspection system. The security inspection system also includes an image acquisition device and a security inspection device.

[0097] like Figure 1 As shown, an open source detection method for security inspection equipment is applied to a control device in a security inspection system, and the method includes:

[0098] S101, acquiring a conveyor belt image of the security inspection device acquired by the image acquisition device;

[0099] Among them, the field of view of the image acquisition device includes the first conveyor belt area located in front of the security inspection channel according to the running direction of the conveyor belt.

[0100] S102, determining whether there is a detected object based on a difference between an image feature corresponding to a preset trigger position in the conveyor belt image and an image feature corresponding to the preset trigger position in a pre-collected first background image;

[0101] The first background image is an image of the first conveyor belt area captured by the image acquisition device when there is no detected object.

[0102] S103, based on the determination result of the detected object, controlling the radiation source of the security inspection device to turn on.

[0103] It can be seen that in the solution provided in the embodiment of the present invention, there is a control device in the security inspection system, and the security inspection system also includes an image acquisition device and a security inspection device. The control device obtains a conveyor belt image of the security inspection device acquired by the image acquisition device, wherein the field of view of the image acquisition device includes a first conveyor belt area located in front of the security inspection channel according to the running direction of the conveyor belt, and determines whether there is an object to be detected based on the difference between the image features corresponding to the preset trigger position in the conveyor belt image and the image features corresponding to the preset trigger position in the pre-acquired first background image, wherein the first background image is an image of the first conveyor belt area acquired by the image acquisition device when there is no object to be detected, and based on the determination result of the object to be detected, the radiation source of the security inspection device is controlled to be turned on. Since the first background image is an image of the first conveyor belt area captured by the image acquisition device when there is no detected object, based on the difference between the image features corresponding to the preset trigger position in the conveyor belt image and the image features corresponding to the preset trigger position in the first background image, it can be determined whether there is a detected object, and then the radiation source of the security inspection device is controlled to be turned on. The image features corresponding to the preset trigger position in the conveyor belt image will not be affected by factors such as the height and shape of the detected object. Therefore, the open source detection of the security inspection equipment has high accuracy, which can effectively solve the problem of missed or mistaken activation of the radiation source.

[0104] Security inspection equipment can provide safety protection for people in public places such as stations, subway stations, conference centers, and large event venues. In the security inspection equipment, infrared light barriers are usually used to detect whether there are detected objects on the conveyor belt. However, when detecting ultra-thin objects and special-shaped objects, it is easy to have problems of missed detection and false detection. Therefore, in the solution provided by the embodiment of the present invention, the control device of the security inspection system can judge whether there are detected objects on the conveyor belt according to the conveyor belt image captured by the image acquisition device, and then control the radiation source to turn on.

[0105] Specifically, the image acquisition device of the security inspection system can acquire the conveyor belt image of the security inspection device. The image acquisition device of the security inspection system can be set up above the conveyor belt. The field of view center of the image acquisition device can be aligned with the conveyor belt. The field of view range of the image acquisition device includes the first conveyor belt area located in front of the security inspection channel according to the running direction of the conveyor belt. In other words, the image acquisition device can acquire images in the conveyor belt area located in front of the security inspection channel according to the running direction of the conveyor belt. In this way, it can be ensured that when an object to be inspected is placed on the conveyor belt, the image acquisition device can acquire the conveyor belt image including the object to be inspected.

[0106] In one embodiment, the array of image acquisition devices is parallel or perpendicular to the running direction of the conveyor belt, that is, the conveyor belt remains parallel or perpendicular in the conveyor belt image captured by the image acquisition device to reduce errors caused by image distortion, thereby reducing the workload of subsequent image correction.

[0107] After the image acquisition device acquires the conveyor belt image of the security inspection device, in step S101, the control device of the security inspection system can obtain the conveyor belt image acquired by the image acquisition device. The conveyor belt image can be a grayscale image or a color image, which is not specifically limited here.

[0108] like Figure 2 As shown, the security inspection system includes an image acquisition device 201, a conveyor belt 203, a radiation source 205, an X-ray detector 206, and a control device 207. The image acquisition device 201 is set above the conveyor belt so that the center of the field of view of the image acquisition device 201 is aligned with the conveyor belt 203, and the first conveyor belt area is the position of the dotted line frame 202. At this time, there is an object 204 to be inspected in 202, and the image acquisition device 201 can acquire the conveyor belt image including the object 204 to be inspected, so the control device 207 can obtain the conveyor belt image acquired by the image acquisition device 201.

[0109] After the control device obtains the conveyor belt image captured by the image acquisition device, it can determine whether there is an object to be detected based on the difference between the image features corresponding to the preset trigger position in the conveyor belt image and the image features corresponding to the preset trigger position in the pre-captured first background image.

[0110] The first background image is an image of the first conveyor belt area captured by the image acquisition device when there is no detected object. If there is a detected object in the first conveyor belt area, there is a difference between the image features corresponding to the preset trigger position in the conveyor belt image and the image features corresponding to the preset trigger position in the pre-captured first background image, then the control device can determine that there is a detected object on the conveyor belt. The preset trigger position can be displayed in the display device of the security inspection system.

[0111] In one implementation, the preset trigger position may be an area, and the area may be composed of a row of pixels, or a plurality of rows of pixels, which is not specifically limited herein.

[0112] like Figure 2 As shown, the security inspection system includes an image acquisition device 201, a conveyor belt 203, a radiation source 205, an X-ray detector 206, a control device 207 and a display device 208, wherein the first conveyor belt area is at the position of the dotted frame 202, and there is an object to be detected 204 in 202. The image acquisition device 201 can acquire the conveyor belt image including the object to be detected 204, then, the control device 207 can obtain the conveyor belt image acquired by the image acquisition device 201, and the conveyor belt image can be displayed in the display device 208, wherein a preset trigger line 209 is displayed in the display device 208, that is, the preset trigger position, and the control device 207 can determine that there is an object to be detected 204 on the conveyor belt 203 based on the difference between the image feature corresponding to the preset trigger line 209 in the conveyor belt image and the image feature corresponding to the preset trigger line 209 in the pre-acquired first background image.

[0113] Based on the difference between the image features corresponding to the preset trigger position in the conveyor belt image and the image features corresponding to the preset trigger position in the pre-collected first background image, the control device can determine whether there are detected objects on the conveyor belt, and further, based on the determination result of the detected objects, the control device can control the radiation source of the security inspection device to turn on.

[0114] For example, Figure 2 As shown, the control device 207 can determine that there is a detected object 204 on the conveyor belt 203 based on the difference between the image features corresponding to the preset trigger line 209 in the conveyor belt image and the image features corresponding to the preset trigger line 209 in the pre-collected first background image. Then, the control device 207 can control the radiation source 205 to turn on.

[0115] In the scheme of the present embodiment, since the first background image is an image of the first conveyor belt area captured by the image acquisition device when there is no detected object, based on the difference between the image features corresponding to the preset trigger position in the conveyor belt image and the image features corresponding to the preset trigger position in the first background image, it can be determined whether there is a detected object, and then the radiation source of the security inspection device is controlled to be turned on. The image features corresponding to the preset trigger position in the conveyor belt image will not be affected by factors such as the height and shape of the detected object. Therefore, the open source detection of the security inspection device has high accuracy, which can effectively solve the problem of missed or mistaken activation of the radiation source.

[0116] As an implementation manner of an embodiment of the present invention, the step of determining whether there is a detected object based on the difference between the image feature corresponding to the preset trigger position in the conveyor belt image and the image feature corresponding to the preset trigger position in the pre-collected first background image may include:

[0117] Calculate the average pixel value of pixels at a preset trigger position in the conveyor belt image; if the difference between the average pixel value and the target pixel value reaches a preset difference, determine that there is a detected object, wherein the target pixel value is the average pixel value of pixels at the preset trigger position in one or more first background images collected in advance; or,

[0118] A feature vector at a preset trigger position in the conveyor belt image is extracted as a vector to be processed; if the similarity between the vector to be processed and the target feature vector does not reach a preset similarity, it is determined that there is a detected object, wherein the target feature vector is a feature vector at the preset trigger position in a first background image collected in advance, or is an average value of the feature vectors at the preset trigger position in multiple first background images.

[0119] Since image features may include multiple features such as image color features, texture features, shape features, and spatial relationship features, when comparing the image features corresponding to the preset trigger position in the conveyor belt image with the image features corresponding to the preset trigger position in the pre-collected first background image, different image features can be compared, and then it can be determined whether there is an object to be detected based on the comparison results of the image features.

[0120] In one embodiment, the control device can calculate the average pixel value of pixels at a preset trigger position in the conveyor belt image. If the difference between the average pixel value and the target pixel value reaches a preset difference, then it can be determined that there is a detected object, wherein the target pixel value can be the average pixel value of pixels at a preset trigger position in a first background image collected in advance, or it can be the average pixel value of pixels at a preset trigger position in multiple first background images.

[0121] For example, when there is no detected object on the conveyor belt, the image acquisition device can acquire images of N first conveyor belt areas, wherein the average pixel values ​​at the corresponding preset trigger positions in the images of the first conveyor belt areas are S and 1 , S 2 ……S N , then the average pixel value S at the corresponding preset trigger position in the image of the N first conveyor belt areas can be obtained. 目标 =(S 1 +S 2 +……+S N) / N, which is the target pixel value. At a certain moment when the conveyor belt is running, when the control device calculates the average pixel value S of the pixels at the preset trigger position in the conveyor belt image 平均 and the target pixel value S 目标 The difference between them reaches the preset difference S 预 When the detected object is detected, it can be determined that there is an object on the conveyor belt.

[0122] In another embodiment, the control device can extract a feature vector at a preset trigger position in the conveyor belt image, and use the feature vector as a vector to be processed. If the similarity between the vector to be processed and the target feature vector does not reach a preset similarity, then it can be determined that there is an object to be detected. The feature vector can be a two-dimensional image feature acquired by a monocular camera, or a three-dimensional image feature acquired by a binocular camera or a depth camera. The target feature vector can be a feature vector at a preset trigger position in a pre-collected first background image, or it can be the average value of feature vectors at preset trigger positions in multiple first background images.

[0123] For example, when there is no detected object on the conveyor belt, the image acquisition device can acquire images of N first conveyor belt areas, wherein the feature vectors at the corresponding preset trigger positions in the images of the first conveyor belt areas are M and 1 、M 2 ……M N , then, the average value M of the feature vector at the corresponding preset trigger position in the image of the N first conveyor belt areas can be obtained. 目标 , which is the target feature vector. At a certain moment when the conveyor belt is running, when the control device extracts the feature vector M at the preset trigger position in the conveyor belt image 待处理 With the target feature vector M 目标 The similarity between them does not reach the preset similarity M 预 When the detected object is detected, it can be determined that there is an object on the conveyor belt.

[0124] It can be seen that in this embodiment, the average pixel value of the pixels at the preset trigger position in the conveyor belt image is calculated; if the difference between the average pixel value and the target pixel value reaches the preset difference, it is determined that there is a detected object, wherein the target pixel value is the average pixel value of the pixels at the preset trigger position in one or more first background images collected in advance; or, the feature vector at the preset trigger position in the conveyor belt image is extracted as the vector to be processed; if the similarity between the vector to be processed and the target feature vector does not reach the preset similarity, it is determined that there is a detected object, wherein the target feature vector is the feature vector at the preset trigger position in a first background image collected in advance, or is the average value of the feature vectors at the preset trigger position in multiple first background images. Since the image features corresponding to the preset trigger position in the conveyor belt image can be compared with the image features corresponding to the preset trigger position in the first background image collected in advance based on different image features, the determination result of the detected object is more accurate, so as to improve the accuracy of the open source detection of the security inspection equipment, and thus effectively solve the problem of the radiation source being opened or opened by mistake.

[0125] As an implementation method of the present invention, since the image acquisition device is sensitive to the color of the detected object in the conveyor belt image, when the color of the detected object on the conveyor belt is close to the conveyor belt, the accuracy of the conveyor belt image acquired by the image acquisition device may be reduced. In order to improve the accuracy of the conveyor belt image acquired by the image acquisition device, a specific pattern can be coated on the conveyor belt, that is, the conveyor belt of the above security inspection device can have a specific pattern. The specific pattern can be a stripe pattern, a floral pattern, etc., which is not specifically limited here.

[0126] In one embodiment, a stripe pattern may be coated on the surface of the conveyor belt along the running direction of the conveyor belt.

[0127] like Figure 3 As shown, the security inspection system includes an image acquisition device 301, a conveyor belt 302, a radiation source 303, an X-ray detector 304, and a control device 305, wherein a mutually parallel black and white alternate stripe pattern 306 is coated along the running direction of the conveyor belt 302 from left to right as a specific pattern of the conveyor belt 302.

[0128] Since the surface of the inspected object has black and white spaced stripes patterns that are parallel to each other, and the probability that the black and white spaced stripes pattern on the surface completely fits the black and white spaced stripes pattern on the conveyor belt is very low, coating the black and white spaced stripes pattern can effectively solve the problem of false detection or missed detection of the inspected object due to the color of the inspected object being close to the color of the conveyor belt.

[0129] like Figure 4As shown, the step of determining whether there is a detected object based on the difference between the image feature corresponding to the preset trigger position in the conveyor belt image and the image feature corresponding to the preset trigger position in the pre-collected first background image may include:

[0130] S401, determining coding information corresponding to the conveyor belt image based on pattern features at a preset trigger position in the conveyor belt image and a preset coding rule;

[0131] The conveyor belt of the security inspection equipment may have a specific pattern, so a coding rule may be preset based on the pattern features of the specific pattern. The control device determines the coding information corresponding to the conveyor belt image based on the pattern features at the preset trigger position in the conveyor belt image and the preset coding rules. Among them, the preset coding rules may represent the correspondence between the pattern features of the specific pattern and the character information. The characters may be numbers, letters, etc., which are not specifically limited here. Encoding the pattern features using the preset coding rules helps to simplify the calculation and improve the efficiency of judging whether the detected object exists.

[0132] As an implementation, the conveyor belt of the security inspection device has a specific pattern of a stripe pattern. Based on the pattern characteristics of the stripe pattern, the preset coding rule can be to correspond each stripe to a character one by one. The control device can determine the coding information corresponding to the conveyor belt image based on the pattern characteristics of the stripe pattern at a preset trigger position in the conveyor belt image and the preset coding rule.

[0133] For example, the specific pattern of the conveyor belt is a pattern of parallel black and white stripes, wherein the distribution of black stripes and white stripes is black stripes, white stripes, black stripes, white stripes, black stripes, and white stripes. Then, based on the pattern features, the preset encoding rule may be to correspond the white stripes to 1 in the binary code and the black stripes to 0 in the binary code. Thus, it can be determined that the encoding information corresponding to the conveyor belt image is 010101.

[0134] For another example, the specific pattern of the conveyor belt is a pattern of parallel black and white stripes, wherein the distribution of black stripes and white stripes is black stripes, white stripes, black stripes, white stripes, black stripes, and white stripes. Then, based on the pattern characteristics, the preset coding rule may be to correspond the white stripes to the letter A and the black stripes to the letter B. Then, it can be determined that the coding information corresponding to the conveyor belt image is BABA.

[0135] S402, if the difference between the coding information corresponding to the conveyor belt image and the target coding information reaches a preset threshold, it is determined that there is a detected object;

[0136] The target coding information is information obtained by encoding the pattern features at the preset trigger position in the pre-collected first background image according to the preset coding rule.

[0137] After the control device determines the coding information corresponding to the conveyor belt image, it will compare it with the target coding information. If the difference between the coding information corresponding to the conveyor belt image and the target coding information reaches a preset threshold, then it can be determined that there is a detected object on the conveyor belt.

[0138] In one embodiment, the specific pattern of the conveyor belt of the security inspection device is a stripe pattern. Based on the pattern characteristics of the stripe pattern, each stripe can be matched with a binary code. Then, the control device can perform XOR processing on the coding information corresponding to the conveyor belt image and the target coding information. If the number of bits with a difference in the XOR result reaches a preset threshold, it can be determined that there is a detected object on the conveyor belt. The target coding information is the information obtained by encoding the pattern characteristics of the stripe pattern at the preset trigger position in the pre-collected first background image according to the preset coding rules.

[0139] like Figure 5 As shown, along the running direction of the conveyor belt, a black and white spaced stripe pattern is coated with each other in parallel. The first conveyor belt area of ​​the conveyor belt is at the position of the dotted box 501. There is a detected object 502 in 501, and the preset trigger position of the conveyor belt image is 503. Based on the pattern characteristics of the black and white spaced stripe pattern, the preset coding rule can be to correspond the white stripes to 1 in the binary code and the black stripes to 0 in the binary code. Then, the target coding information can be obtained as 10101010. At each time from time1 to time8, the control device determines the coding information corresponding to the conveyor belt image as shown in the following table:

[0140] time Encoded information time1 10101010 time2 10101010 time3 10101010 time4 10101010 time5 10101010 time6 10001010 time7 10101010 time8 10101010

[0141] Since the surface pattern of the detected object 502 on the conveyor belt is inconsistent with the black and white stripe pattern on the conveyor belt, the second white stripe in the black and white stripe pattern of the conveyor belt will be blocked. Therefore, at time 6, the control device determines that the coding information corresponding to the conveyor belt image is 10001010 based on the pattern features at 503 in the conveyor belt image and the preset coding rules, and performs XOR processing on the coding information 10001010 and the target coding information 10101010. The number of bits that differ is 1, which has reached the preset threshold. Therefore, it can be determined that there is a detected object on the conveyor belt.

[0142] In addition, if the control device determines that the difference between the coding information corresponding to the conveyor belt image and the target coding information is only 1 bit, it can be considered that the volume of the detected object is relatively small. If the control device determines that the difference between the coding information corresponding to the conveyor belt image and the target coding information is multiple bits, it can be considered that the volume of the detected object is relatively large. The size of the preset threshold can be used to adjust the size of the detected object to be identified, and is not specifically limited here.

[0143] It can be seen that in this embodiment, based on the pattern features at the preset trigger position in the conveyor belt image and the preset coding rules, the coding information corresponding to the conveyor belt image is determined. If the difference between the coding information corresponding to the conveyor belt image and the target coding information reaches a preset threshold, it is determined that there is a detected object, wherein the target coding information is information obtained by encoding the pattern features at the preset trigger position in the pre-collected first background image according to the preset coding rules. Since the existence of the detected object can be determined when the difference between the coding information corresponding to the conveyor belt image and the target coding information reaches the preset threshold, the accuracy of determining the detected object is further improved, and the accuracy of the open source detection of the security inspection equipment can be improved, and the problem of the radiation source being opened or opened by mistake can be effectively solved.

[0144] As an implementation manner of an embodiment of the present invention, the above-mentioned specific pattern is a stripe pattern along the running direction of the conveyor belt, and the width of the stripes in the stripe pattern is determined according to the minimum volume of the detected object.

[0145] In one case, the specific pattern of the conveyor belt is a stripe pattern along the running direction of the conveyor belt. If the volume of the detected object is too small, when the detected object is placed on the conveyor belt, the position occupied by the detected object may be within the stripes in the stripe pattern, resulting in the control device being unable to accurately determine the coding information corresponding to the conveyor belt image when the detected object is on the conveyor belt, and thus being unable to determine the existence of the detected object. Therefore, the width of the stripes in the stripe pattern can be determined based on the minimum volume of the detected object, so that the position occupied by the detected object with the minimum volume can be no less than the width of the stripes in the stripe pattern. Exemplarily, when the detected object is placed on the conveyor belt, the position occupied by the minimum volume of the detected object on the conveyor belt is greater than or equal to the width of the specific stripes on the conveyor belt, thereby ensuring that the detected object can be detected.

[0146] like Figure 5 As shown, the specific pattern of the conveyor belt is a black and white stripe pattern parallel to each other along the running direction of the conveyor belt, and the position occupied by the detected object 502 on the conveyor belt is not less than the width of the white stripe and the width of the black stripe, so that the control device can determine the coded information corresponding to the conveyor belt image when the detected object 502 is located on the conveyor belt.

[0147] It can be seen that in this embodiment, the specific pattern is a stripe pattern along the running direction of the conveyor belt, and the width of the stripes in the stripe pattern is determined according to the minimum volume of the detected object. Therefore, the detection capability of smaller detected objects can be adjusted by adjusting the width of the stripe pattern, thereby solving the problem of missed detection and false detection of detected objects.

[0148] As an implementation manner of an embodiment of the present invention, the above-mentioned method for determining the preset trigger position is as follows: Figure 6 As shown, this may include:

[0149] S601, determining a target trigger position according to a conveyor belt running speed of the security inspection device and a start delay of the radiation source;

[0150] The time required for the detected object to run from the target trigger position to the position corresponding to the radiation source according to the running speed of the conveyor belt is not less than the start delay.

[0151] The preset trigger position is a position displayed on the display device, and the preset trigger position is determined based on the target trigger position. The target trigger position is the actual position on the conveyor belt corresponding to the preset trigger position. In one embodiment, the target trigger position can be determined based on the conveyor belt running speed of the security inspection device and the turn-on delay of the radiation source, wherein the time required for the inspected object to run from the target trigger position to the position corresponding to the radiation source according to the conveyor belt running speed is not less than the turn-on delay of the radiation source.

[0152] For example, Figure 2 As shown, the security inspection system includes an image acquisition device 201, a conveyor belt 203, a ray source 205, an X-ray detector 206, a control device 207 and a display device 208, wherein the first conveyor belt area is the position of the dotted box 202. According to the running speed of the conveyor belt 203 and the opening delay of the ray source 205, the target trigger position can be determined in 202. When the detected object 204 is placed on the conveyor belt, the time required for the detected object 204 to run from the target trigger position to the position corresponding to the ray source 205 according to the running speed of the conveyor belt is not less than the opening delay of the ray source 205.

[0153] S602: Calculate the position of the target trigger position in the image captured by the image capture device according to the internal parameters and external parameters of the image capture device as a preset trigger position.

[0154] After determining the target trigger position according to the conveyor belt running speed of the security inspection equipment and the opening delay of the radiation source, the control device can calculate the position of the target trigger position in the image captured by the image capture device according to the internal and external parameters of the image capture device as the preset trigger position. Specifically, the external parameter of the image capture device is the transformation matrix between the coordinate system of the image capture device and the world coordinate system, which is used to determine the relative position relationship between the coordinate system of the image capture device and the world coordinate system. The internal parameter of the image capture device is used to determine the projection relationship of the image capture device from the three-dimensional space to the two-dimensional image. After determining the target trigger position, the actual coordinates of the target trigger position can be obtained. Then, the control device can calculate the coordinates in the image captured by the image capture device corresponding to the actual coordinates of the target trigger position according to the internal and external parameters of the image capture device, that is, convert the actual coordinates of the target trigger position into image coordinates, and then obtain the position of the target trigger position in the image captured by the image capture device, and use this position as the preset trigger position.

[0155] It can be seen that in this embodiment, the target trigger position is determined according to the conveyor belt running speed of the security inspection equipment and the opening delay of the radiation source, wherein the time required for the detected object to run from the target trigger position to the position corresponding to the radiation source according to the conveyor belt running speed is not less than the opening delay, and the position of the target trigger position in the image captured by the image acquisition device is calculated according to the internal and external parameters of the image acquisition device as the preset trigger position. Since the preset trigger position is determined based on the target trigger position, it is possible to accurately determine whether there is a detected object on the conveyor belt, improve the accuracy of the open source detection of the security inspection equipment, and effectively solve the problem of missed opening and mistaken opening of the radiation source of the security inspection equipment.

[0156] As an implementation of an embodiment of the present invention, the field of view of the above-mentioned image acquisition device also includes a second conveyor belt area located behind the security inspection channel according to the running direction of the conveyor belt;

[0157] Since the control device can control the radiation source to turn on when it determines that there is an object to be inspected on the conveyor belt, and can control the radiation source to turn off after the object to be inspected passes through the radiation source, the field of view of the image acquisition device can also include a second conveyor belt area located behind the security inspection channel in the direction of the conveyor belt.

[0158] like Figure 7 As shown, the above method may also include:

[0159] S701, determining whether there is a detected object based on a difference between an image feature corresponding to a preset end position in the conveyor belt image and an image feature corresponding to the preset end position in a pre-collected second background image;

[0160] The second background image is an image of the second conveyor belt area captured by the image acquisition device when there is no detected object.

[0161] After the control device of the security inspection system obtains the conveyor belt image captured by the image acquisition device, it can determine whether there is an object to be inspected based on the difference between the image features corresponding to the preset end position in the conveyor belt image and the image features corresponding to the preset end position in the pre-captured second background image.

[0162] The second background image is an image of the second conveyor belt area captured by the image acquisition device when there is no detected object. If there is a detected object in the second conveyor belt area, there is a difference between the image features corresponding to the preset end position in the conveyor belt image and the image features corresponding to the preset end position in the pre-captured second background image, then the control device can determine that there is a detected object on the conveyor belt. The preset end position can be displayed on the display device of the security inspection system.

[0163] S702: If there is, and no detected object is detected at the preset trigger position within the target time, control the radiation source of the security inspection device to be turned off.

[0164] If the control device determines that there is an object to be detected on the conveyor belt, and no object to be detected is detected at the preset trigger position within the target time, the radiation source of the security inspection device can be controlled to be turned off. The target time is the time from when the control device controls the radiation source to turn on to when the object to be detected passes the preset end position.

[0165] It can be seen that in this embodiment, based on the difference between the image features corresponding to the preset end position in the conveyor belt image and the image features corresponding to the preset end position in the pre-collected second background image, it is determined whether there is a detected object, wherein the second background image is an image of the second conveyor belt area collected by the image acquisition device when there is no detected object, and if there is, and the detected object is not detected at the preset trigger position within the target time length, the radiation source of the security inspection device is controlled to be turned off. Since the control device can use the image collected by the same image acquisition device, based on the difference between the image features corresponding to the preset end position in the conveyor belt image and the image features corresponding to the preset end position in the pre-collected second background image, it is determined whether there is a detected object, and when the detected object is not detected at the preset trigger position within the target time length, the radiation source is controlled to be turned off, and the multi-position detection function is realized, which can reduce the difficulty of installation and debugging of the security inspection system and reduce the cost of the security inspection system.

[0166] As an implementation of an embodiment of the present invention, the security inspection system further includes a detection unit; the detection unit is used to detect whether there is an object to be inspected on the conveyor belt (for example, the detection unit is used to detect whether an object to be inspected has entered the security inspection channel). The detection unit can be any sensor that can be used to detect whether there is an object to be inspected on the conveyor belt, including but not limited to various types of light barriers.

[0167] The above method may further include:

[0168] Obtaining the detection result of the detection unit; for example, obtaining the detection result of whether the detected object enters the security inspection channel;

[0169] A detection unit is installed on the conveyor belt, and the control device can obtain the detection result of the detection unit. For example, taking the detection unit as an infrared light barrier, when there is a detected object on the conveyor belt, the infrared light emitted by the transmitting end of the infrared light barrier will be blocked, and the receiving end of the infrared light barrier cannot receive the infrared light, and it is determined that there is a detected object on the conveyor belt. Among them, the infrared light barrier can be installed at the entrance of the conveyor belt, and can also be installed in the first conveyor belt area, which is not specifically limited here.

[0170] like Figure 8 As shown in the figure, taking the detection unit as an infrared light barrier as an example, the security inspection system includes an image acquisition device 801, an infrared light barrier 802, a conveyor belt 803, a ray source 804, an X-ray detector 805, and a control device 806. The infrared light barrier 802 is installed at the left entrance of the conveyor belt 803. If the conveyor belt 803 is placed with the detected object, the infrared rays emitted by the transmitting end of the infrared light barrier 802 will be blocked, and the receiving end of the infrared light barrier 802 cannot receive the infrared rays, that is, the connection state of the infrared light barrier is cut off, then the control device can obtain the detection result of the infrared light barrier.

[0171] The above step of controlling the radiation source of the security inspection device to turn on based on the determination result of the detected object may include:

[0172] When at least one of the detection result and the determination result of the detected object indicates the presence of the detected object, controlling the radiation source of the security inspection device to turn on; or,

[0173] A weighted result of the detection result and the determination result of the detected object is calculated based on a preset weight, and when the weighted result indicates that the detected object exists, the radiation source of the security inspection device is controlled to turn on.

[0174] In one embodiment, a detection unit is installed at the entrance of the conveyor belt, and a control device can obtain the detection result of the detection unit at the entrance of the conveyor belt, as well as a conveyor belt image of the first conveyor belt area acquired by an image acquisition device. Then, the control device can control the radiation source of the security inspection device to turn on when at least one of the detection result and the determination result of the detected object indicates the presence of the detected object.

[0175] For example, Figure 8 As shown, taking the detection unit as an infrared light barrier as an example, the infrared light barrier 802 is set at the left entrance of the conveyor belt 803. If the receiving end of the infrared light barrier 802 cannot receive infrared rays, that is, when the detected object is detected, the control device 806 can obtain the detection result of the infrared light barrier 802, identify the existence of the detected object, and then control the ray source 804 to turn on. If the detected object is an ultra-thin object and its height is lower than the detection height of the infrared light barrier 802, then the infrared light barrier 802 cannot detect the ultra-thin object, and the control device 806 cannot identify the existence of the detected object. Until the image acquisition device acquires the image of the conveyor belt, the control device can identify the existence of the detected object based on the determination result of the detected object, and then control the ray source 804 to turn on.

[0176] In another embodiment, the weights of the detection results and the determination results of the detected objects can be set in advance, and the control device can calculate the weighted results of the detection results and the determination results of the detected objects based on the preset weights. When the weighted results indicate the presence of the detected objects, the radiation source of the security inspection device is controlled to turn on.

[0177] For example, Figure 8 As shown, the infrared light barrier 802 is set at the left entrance of the conveyor belt 803. If the detected object blocks the infrared light, the control device 806 can obtain the detection result of the infrared light barrier 802, and its preset weight is W 红 When the detected object passes through the first conveyor belt area, the control device 806 can determine the result of the detected object, and its preset weight is W 确定 , the control device can be based on W 红 and W 确定 , calculate the weighted result of the detection result and the determination result of the detected object. When the weighted result is greater than 0.5, it can be identified that the detected object exists, and then the ray source 804 can be controlled to turn on.

[0178] It can be seen that in this embodiment, when at least one of the detection result and the determination result of the detected object indicates the presence of the detected object, the ray source of the security inspection device is controlled to be turned on; or, the weighted result of the detection result and the determination result of the detected object is calculated based on the preset weight, and when the weighted result indicates the presence of the detected object, the ray source of the security inspection device is controlled to be turned on. Since the control device can control the turning on of the ray source based on the detection result of the detection unit and the determination result of the detected object, the problem of the difficulty of infrared light tent in determining ultra-thin objects and special-shaped objects is solved, the accuracy of determining the detected object is further improved, and the accuracy of the open source detection of the security inspection device is improved, thereby effectively solving the problem of missed turning on and mistaken turning on of the ray source.

[0179] As an implementation manner of an embodiment of the present invention, the security inspection system further includes a display device; the method may further include:

[0180] The conveyor belt image is sent to the display device, so that the display device displays the conveyor belt image and displays a mark corresponding to the preset trigger position in the conveyor belt image.

[0181] After the control device acquires the conveyor belt image captured by the image acquisition device, it can send the conveyor belt image to the display device so that the display device displays the conveyor belt image and can display a mark corresponding to the preset trigger position in the conveyor belt image.

[0182] For example, Figure 8 As shown, the security inspection system includes an image acquisition device 801, an infrared light barrier 802, a conveyor belt 803, a ray source 804, an X-ray detector 805, a control device 806, and a display device 807. The control device 806 can obtain the conveyor belt image 808 acquired by the image acquisition device 801, and send the conveyor belt image 808 to the display device 807. The display device 807 can display the conveyor belt image 808 and display a mark 809 corresponding to a preset trigger position in the conveyor belt image 808.

[0183] It can be seen that in this embodiment, the control device can send the conveyor belt image to the display device so that the display device displays the conveyor belt image, and can display a mark corresponding to the preset trigger position in the conveyor belt image. Through the mark, it can be observed whether the detected object on the conveyor belt reaches the preset trigger position, so as to accurately determine whether there is a detected object on the conveyor belt, improve the accuracy of the open source detection of the security inspection equipment, and effectively solve the problem of leaking and mistakenly opening the radiation source.

[0184] As an implementation manner of an embodiment of the present invention, the above-mentioned image acquisition device is a monocular camera, a binocular camera or a depth camera.

[0185] There are many types of image acquisition devices, which can be monocular cameras, binocular cameras or depth cameras. Among them, binocular cameras or depth cameras can capture images with depth information. Depth information refers to the distance of the captured object from the camera represented by different colors or brightness in the video.

[0186] When the image acquisition device is a monocular camera, the specific implementation method of the control device controlling the ray source to turn on is the same as step S101 to step S103, which will not be repeated here. When the image acquisition device is set to a binocular camera or a depth camera, the steps of controlling the ray source to turn on the control device are as follows:

[0187] The first step is to set up a binocular camera or a depth camera above the conveyor belt and align the center of the camera's field of view with the conveyor belt.

[0188] In the second step, the control device can obtain the conveyor belt image of the security inspection device captured by the binocular camera or the depth camera;

[0189] In the third step, the control device can determine whether there is a detected object based on the difference between the image feature corresponding to the preset trigger position in the conveyor belt image and the image feature corresponding to the preset trigger position in the pre-collected first background image. When there is a detected object on the conveyor belt, the distance between the detected object and the camera lens will change, resulting in a change in the brightness or color of the conveyor belt image. Therefore, the brightness or color of the image can be used as an image feature.

[0190] For example, when there is an object A to be detected on the conveyor belt and A is at the target trigger position in the first conveyor belt area, the binocular camera or the depth camera can obtain the conveyor belt image a1. Since A has a certain height compared to when there is no object to be detected on the conveyor belt, there is a difference between the brightness corresponding to the preset trigger position in a1 and the brightness corresponding to the preset trigger position in the pre-captured first background image, and the control device can determine that there is an object A to be detected.

[0191] In the fourth step, the control device can control the radiation source of the security inspection device to turn on based on the determination result of the detected object.

[0192] It can be seen that in this embodiment, the image acquisition device is a monocular camera, a binocular camera or a depth camera. Among them, a binocular stereo vision camera or a depth vision camera is used to obtain the depth information between the surface of the conveyor belt and the camera lens, and then use the change in depth information to determine whether there are any inspected objects on the conveyor belt, thereby improving the accuracy of open source detection of security inspection equipment, and effectively solving the problem of leakage and mistaken opening of the radiation source.

[0193] Corresponding to the above-mentioned open source detection method for security inspection equipment, an embodiment of the present invention further provides an open source detection device for security inspection equipment. The open source detection device for security inspection equipment provided by an embodiment of the present invention is introduced below.

[0194] like Fig. 9 As shown, an open source detection device for security inspection equipment is applied to a control device in a security inspection system. The security inspection system also includes an image acquisition device and a security inspection device. The device includes:

[0195] The conveyor belt image acquisition module 910 is used to acquire the conveyor belt image of the security inspection device acquired by the image acquisition device, wherein the field of view of the image acquisition device includes the first conveyor belt area located in front of the security inspection channel according to the running direction of the conveyor belt;

[0196] A first determination module 920, configured to determine whether there is a detected object based on a difference between an image feature corresponding to a preset trigger position in the conveyor belt image and an image feature corresponding to the preset trigger position in a pre-collected first background image, wherein the first background image is an image of the first conveyor belt area collected by the image acquisition device when no detected object is present;

[0197] The radiation source activation module 930 is used to control the radiation source of the security inspection device to be activated based on the determination result of the detected object.

[0198] It can be seen that in the solution provided in the embodiment of the present invention, there is a control device in the security inspection system, and the security inspection system also includes an image acquisition device and a security inspection device. The control device obtains a conveyor belt image of the security inspection device acquired by the image acquisition device, wherein the field of view of the image acquisition device includes a first conveyor belt area located in front of the security inspection channel according to the running direction of the conveyor belt, and determines whether there is an object to be detected based on the difference between the image features corresponding to the preset trigger position in the conveyor belt image and the image features corresponding to the preset trigger position in the pre-acquired first background image, wherein the first background image is an image of the first conveyor belt area acquired by the image acquisition device when there is no object to be detected, and based on the determination result of the object to be detected, the radiation source of the security inspection device is controlled to be turned on. Since the first background image is an image of the first conveyor belt area captured by the image acquisition device when there is no detected object, based on the difference between the image features corresponding to the preset trigger position in the conveyor belt image and the image features corresponding to the preset trigger position in the first background image, it can be determined whether there is a detected object, and then the radiation source of the security inspection device is controlled to be turned on. The image features corresponding to the preset trigger position in the conveyor belt image will not be affected by factors such as the height and shape of the detected object. Therefore, the open source detection of the security inspection equipment has high accuracy, which can effectively solve the problem of missed or mistaken activation of the radiation source.

[0199] As an implementation manner of the embodiment of the present invention, the first determining module 920 may include:

[0200] A first determination submodule is configured to calculate an average pixel value of pixels at a preset trigger position in the conveyor belt image; if the difference between the average pixel value and a target pixel value reaches a preset difference, it is determined that there is a detected object, wherein the target pixel value is an average pixel value of pixels at the preset trigger position in one or more first background images collected in advance; or,

[0201] A feature vector at a preset trigger position in the conveyor belt image is extracted as a vector to be processed; if the similarity between the vector to be processed and the target feature vector does not reach a preset similarity, it is determined that there is a detected object, wherein the target feature vector is a feature vector at the preset trigger position in a first background image collected in advance, or is an average value of the feature vectors at the preset trigger position in multiple first background images.

[0202] As an implementation method of the embodiment of the present invention, the conveyor belt of the security inspection equipment has a specific pattern;

[0203] The first determining module 920 may include:

[0204] A coding information determination submodule, used to determine the coding information corresponding to the conveyor belt image based on the pattern features at the preset trigger position in the conveyor belt image and the preset coding rules;

[0205] The second determination submodule is used to determine the presence of the detected object if the difference between the coding information corresponding to the conveyor belt image and the target coding information reaches a preset threshold, wherein the target coding information is the pattern feature at the preset trigger position in the pre-captured first background image, encoded according to the preset coding rule.

[0206] As an implementation manner of the embodiment of the present invention, the specific pattern is a stripe pattern along the running direction of the conveyor belt, and the width of the stripes in the stripe pattern is determined according to the minimum volume of the detected object.

[0207] As an implementation manner of an embodiment of the present invention, the above-mentioned device may further include a preset trigger position determination module, and the preset trigger position determination module is used to determine the preset trigger position, which may include:

[0208] A target trigger position determination module, used to determine the target trigger position according to the conveyor belt running speed of the security inspection equipment and the turn-on delay of the radiation source, wherein the time required for the inspected object to run from the target trigger position to the position corresponding to the radiation source according to the conveyor belt running speed is not less than the turn-on delay;

[0209] The preset trigger position determination module is used to calculate the position of the target trigger position in the image captured by the image capture device according to the internal parameters and external parameters of the image capture device as the preset trigger position.

[0210] As an implementation of an embodiment of the present invention, the field of view of the image acquisition device also includes a second conveyor belt area located behind the security inspection channel according to the running direction of the conveyor belt;

[0211] The device may also include:

[0212] A second determination module is used to determine whether there is a detected object based on a difference between an image feature corresponding to a preset end position in the conveyor belt image and an image feature corresponding to the preset end position in a pre-collected second background image, wherein the second background image is an image of the second conveyor belt area collected by the image acquisition device when there is no detected object;

[0213] The radiation source shut-down module is used to control the radiation source of the security inspection device to shut down if there is an object to be detected at the preset trigger position and no object is detected within a target time period.

[0214] As an implementation method of an embodiment of the present invention, the security inspection system further includes a detection unit, which is used to detect whether there is an object to be detected on the conveyor belt; the device may also include:

[0215] A detection result acquisition module, used to obtain the detection result of the detection unit;

[0216] The radiation source activation module 930 may include:

[0217] a radiation source activation submodule, configured to control the radiation source of the security inspection device to be activated when at least one of the detection result and the detection result indicates the presence of the detected object; or

[0218] The method is used to calculate a weighted result of the detection result and the determination result of the detected object based on a preset weight, and when the weighted result indicates that there is a detected object, control the radiation source of the security inspection device to turn on.

[0219] As an implementation method of the embodiment of the present invention, the security inspection system further includes a display device; the device may also include:

[0220] The image display module is used to send the conveyor belt image to the display device so that the display device displays the conveyor belt image and displays the mark corresponding to the preset trigger position in the conveyor belt image.

[0221] As an implementation manner of the embodiment of the present invention, the image acquisition device is a monocular camera, a binocular camera or a depth camera.

[0222] The embodiment of the present invention also provides a security inspection system, such as Fig.10 As shown, the system includes a control device 1020, an image acquisition device 1010 and a security inspection device 1030, wherein:

[0223] The security inspection device 1030 is used to inspect the inspected object;

[0224] The image acquisition device 1010 is used to acquire the conveyor belt image of the security inspection device, wherein the field of view of the image acquisition device includes the first conveyor belt area located in front of the security inspection channel according to the running direction of the conveyor belt;

[0225] The control device 1020 is used to obtain the conveyor belt image; determine whether there is an object to be detected based on the difference between the image features corresponding to the preset trigger position in the conveyor belt image and the image features corresponding to the preset trigger position in the pre-captured first background image; and control the radiation source of the security inspection device to turn on based on the determination result of the object to be detected, wherein the first background image is an image of the first conveyor belt area captured by the image acquisition device when there is no object to be detected.

[0226] It can be seen that in the solution provided in the embodiment of the present invention, there is a control device in the security inspection system, and the security inspection system also includes an image acquisition device and a security inspection device. The control device obtains a conveyor belt image of the security inspection device acquired by the image acquisition device, wherein the field of view of the image acquisition device includes a first conveyor belt area located in front of the security inspection channel according to the running direction of the conveyor belt, and determines whether there is an object to be detected based on the difference between the image features corresponding to the preset trigger position in the conveyor belt image and the image features corresponding to the preset trigger position in the pre-acquired first background image, wherein the first background image is an image of the first conveyor belt area acquired by the image acquisition device when there is no object to be detected, and based on the determination result of the object to be detected, the radiation source of the security inspection device is controlled to be turned on. Since the first background image is an image of the first conveyor belt area captured by the image acquisition device when there is no detected object, based on the difference between the image features corresponding to the preset trigger position in the conveyor belt image and the image features corresponding to the preset trigger position in the first background image, it can be determined whether there is a detected object, and then the radiation source of the security inspection device is controlled to be turned on. The image features corresponding to the preset trigger position in the conveyor belt image will not be affected by factors such as the height and shape of the detected object. Therefore, the open source detection of the security inspection equipment has high accuracy, which can effectively solve the problem of missed or mistaken activation of the radiation source.

[0227] As an implementation of an embodiment of the present invention, the control device 1020 can be specifically used to calculate the average pixel value of pixels at a preset trigger position in the conveyor belt image; if the difference between the average pixel value and the target pixel value reaches a preset difference, it is determined that there is a detected object, wherein the target pixel value is the average pixel value of pixels at the preset trigger position in one or more first background images collected in advance; or,

[0228] Specifically, it can be used to extract the feature vector at the preset trigger position in the conveyor belt image as the vector to be processed; if the similarity between the vector to be processed and the target feature vector does not reach the preset similarity, it is determined that there is a detected object, wherein the target feature vector is the feature vector at the preset trigger position in a first background image collected in advance, or is the average value of the feature vectors at the preset trigger position in multiple first background images.

[0229] As an implementation method of the embodiment of the present invention, the conveyor belt of the security inspection equipment has a specific pattern;

[0230] The control device 1020 can be specifically used to determine the coding information corresponding to the conveyor belt image based on the pattern features at the preset trigger position in the conveyor belt image and the preset coding rules; if the difference between the coding information corresponding to the conveyor belt image and the target coding information reaches a preset threshold, it is determined that there is a detected object, wherein the target coding information is the information encoded according to the preset coding rules for the pattern features at the preset trigger position in the pre-captured first background image.

[0231] As an implementation manner of the embodiment of the present invention, the specific pattern is a stripe pattern along the running direction of the conveyor belt, and the width of the stripes in the stripe pattern is determined according to the minimum volume of the detected object.

[0232] As an implementation mode of an embodiment of the present invention, the control device 1020 can also be used to determine the target trigger position based on the conveyor belt running speed of the security inspection equipment and the turn-on delay of the radiation source, wherein the time required for the inspected object to run from the target trigger position to the position corresponding to the radiation source at the conveyor belt running speed is not less than the turn-on delay; based on the internal parameters and external parameters of the image acquisition device, the position of the target trigger position in the image captured by the image acquisition device is calculated as a preset trigger position.

[0233] As an implementation of an embodiment of the present invention, the field of view of the image acquisition device also includes a second conveyor belt area located behind the security inspection channel according to the running direction of the conveyor belt;

[0234] The control device 1020 can also be used to determine whether there is an object to be detected based on the difference between the image features corresponding to the preset end position in the conveyor belt image and the image features corresponding to the preset end position in the pre-captured second background image, wherein the second background image is an image of the second conveyor belt area captured by the image acquisition device when there is no object to be detected; if there is, and the object to be detected is not detected at the preset trigger position within the target time length, the radiation source of the security inspection device is controlled to be turned off.

[0235] As an implementation method of the embodiment of the present invention, the security inspection system further includes a detection unit, which is used to detect whether there is an object to be inspected on the conveyor belt;

[0236] The control device 1020 can also be used to obtain the detection result of the detection unit; when at least one of the detection result and the determination result of the detected object indicates the presence of the detected object, control the radiation source of the security inspection device to turn on; or, calculate the weighted result of the detection result and the determination result of the detected object based on a preset weight, and when the weighted result indicates the presence of the detected object, control the radiation source of the security inspection device to turn on.

[0237] As an implementation method of the embodiment of the present invention, the security inspection system further includes a display device;

[0238] The control device 1020 may also be used to send the conveyor belt image to the display device, so that the display device displays the conveyor belt image and displays a mark corresponding to the preset trigger position in the conveyor belt image.

[0239] As an implementation manner of the embodiment of the present invention, the image acquisition device is a monocular camera, a binocular camera or a depth camera.

[0240] The embodiment of the present invention further provides an electronic device, such as Fig.11 As shown, it includes a processor 1101, a communication interface 1102, a memory 1103 and a communication bus 1104, wherein the processor 1101, the communication interface 1102, and the memory 1103 communicate with each other through the communication bus 1104.

[0241] Memory 1103, used for storing computer programs;

[0242] The processor 1101 is used to implement the open source detection method steps of the security inspection equipment described in any of the above embodiments when executing the program stored in the memory 1103.

[0243] It can be seen that in the solution provided in the embodiment of the present invention, there is a control device in the security inspection system, and the security inspection system also includes an image acquisition device and a security inspection device. The control device obtains a conveyor belt image of the security inspection device acquired by the image acquisition device, wherein the field of view of the image acquisition device includes a first conveyor belt area located in front of the security inspection channel according to the running direction of the conveyor belt, and determines whether there is an object to be detected based on the difference between the image features corresponding to the preset trigger position in the conveyor belt image and the image features corresponding to the preset trigger position in the pre-acquired first background image, wherein the first background image is an image of the first conveyor belt area acquired by the image acquisition device when there is no object to be detected, and based on the determination result of the object to be detected, the radiation source of the security inspection device is controlled to be turned on. Since the first background image is an image of the first conveyor belt area captured by the image acquisition device when there is no detected object, based on the difference between the image features corresponding to the preset trigger position in the conveyor belt image and the image features corresponding to the preset trigger position in the first background image, it can be determined whether there is a detected object, and then the radiation source of the security inspection device is controlled to be turned on. The image features corresponding to the preset trigger position in the conveyor belt image will not be affected by factors such as the height and shape of the detected object. Therefore, the open source detection of the security inspection equipment has high accuracy, which can effectively solve the problem of missed or mistaken activation of the radiation source.

[0244] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0245] The communication interface is used for communication between the above electronic device and other devices.

[0246] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0247] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0248] In another embodiment provided by the present invention, a computer-readable storage medium is also provided, in which a computer program is stored. When the computer program is executed by a processor, the steps of the open source detection method for security inspection equipment described in any of the above embodiments are implemented.

[0249] In another embodiment provided by the present invention, a computer program product including instructions is also provided, which, when executed on a computer, enables the computer to execute the open source detection method for security inspection equipment described in any of the above embodiments.

[0250] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk Solid State Disk (SSD)), etc.

[0251] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0252] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for devices, systems, electronic devices, computer-readable storage media, and computer program products, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0253] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

1. An open source detection method for security inspection equipment, It is characterized in that A control device applied to a security inspection system, wherein the security inspection system further comprises an image acquisition device and a security inspection device, and the method comprises: Acquire the conveyor belt image of the security inspection device captured by the image acquisition device, wherein the field of view of the image acquisition device includes a first conveyor belt area located in front of the security inspection channel according to the running direction of the conveyor belt; Determine whether there is a detected object based on a difference between an image feature corresponding to a preset trigger position in the conveyor belt image and an image feature corresponding to the preset trigger position in a pre-captured first background image, wherein the first background image is an image of the first conveyor belt area captured by the image capture device when no detected object is present; Based on the determination result of the detected object, controlling the radiation source of the security inspection device to turn on; Wherein, the conveyor belt of the security inspection equipment has a specific pattern, and the specific pattern is a stripe pattern along the running direction of the conveyor belt, and the width of the stripes in the stripe pattern is determined according to the minimum volume of the detected object.

2. The method according to claim 1, It is characterized in that The step of determining whether there is a detected object based on a difference between an image feature corresponding to a preset trigger position in the conveyor belt image and an image feature corresponding to the preset trigger position in a pre-collected first background image comprises: Determining encoding information corresponding to the conveyor belt image based on pattern features at a preset trigger position in the conveyor belt image and a preset encoding rule; If the difference between the coding information corresponding to the conveyor belt image and the target coding information reaches a preset threshold, it is determined that there is an object to be detected, wherein the target coding information is the information encoded according to the preset coding rule for the pattern features at the preset trigger position in the pre-captured first background image.

3. The method according to claim 1, It is characterized in that The method for determining the preset trigger position includes: Determine the target trigger position according to the conveyor belt running speed of the security inspection equipment and the opening delay of the radiation source, wherein the time required for the inspected object to run from the target trigger position to the position corresponding to the radiation source according to the conveyor belt running speed is not less than the opening delay; According to the internal parameters and external parameters of the image acquisition device, the position of the target trigger position in the image acquired by the image acquisition device is calculated as the preset trigger position.

4. The method according to claim 1, It is characterized in that The field of view of the image acquisition device also includes a second conveyor belt area located after the security inspection channel according to the running direction of the conveyor belt; The method further comprises: Determine whether there is a detected object based on a difference between an image feature corresponding to a preset end position in the conveyor belt image and an image feature corresponding to the preset end position in a pre-collected second background image, wherein the second background image is an image of the second conveyor belt area collected by the image acquisition device when no detected object is present; If there is, and no detected object is detected at the preset trigger position within the target time length, the radiation source of the security inspection device is controlled to be turned off.

5. The method according to claim 1, It is characterized in that The security inspection system further includes a detection unit, which is used to detect whether there is an object to be inspected on the conveyor belt; the method further includes: Acquiring a detection result of the detection unit; The step of controlling the radiation source of the security inspection device to turn on based on the determination result of the detected object includes: When at least one of the detection result and the determination result of the detected object indicates the presence of the detected object, controlling the radiation source of the security inspection device to turn on; or, A weighted result of the detection result and the determination result of the detected object is calculated based on a preset weight, and when the weighted result indicates that the detected object exists, the radiation source of the security inspection device is controlled to turn on.

6. The method according to any one of claims 1 to 5, It is characterized in that The security inspection system further includes a display device; and the method further includes: The conveyor belt image is sent to the display device, so that the display device displays the conveyor belt image and displays a mark corresponding to the preset trigger position in the conveyor belt image.

7. The method according to any one of claims 1 to 5, It is characterized in that The image acquisition device is a monocular camera, a binocular camera or a depth camera.

8. An open source detection device for security inspection equipment, It is characterized in that A control device applied to a security inspection system, wherein the security inspection system further comprises an image acquisition device and a security inspection device, wherein the device comprises: A conveyor belt image acquisition module, used to acquire the conveyor belt image of the security inspection device acquired by the image acquisition device, wherein the field of view of the image acquisition device includes a first conveyor belt area located in front of the security inspection channel according to the running direction of the conveyor belt; A first determination module, configured to determine whether there is a detected object based on a difference between an image feature corresponding to a preset trigger position in the conveyor belt image and an image feature corresponding to the preset trigger position in a pre-captured first background image, wherein the first background image is an image of the first conveyor belt area captured by the image capture device when no detected object is present; A radiation source activation module is used to control the activation of the radiation source of the security inspection device based on the determination result of the detected object; wherein, the conveyor belt of the security inspection device has a specific pattern, the specific pattern is a stripe pattern along the running direction of the conveyor belt, and the width of the stripes in the stripe pattern is determined according to the minimum volume of the detected object.

9. A security inspection system, It is characterized in that The system includes a control device, an image acquisition device and a security inspection device, wherein: The security inspection equipment is used to inspect the inspected items; The image acquisition device is used to acquire the conveyor belt image of the security inspection device, wherein the field of view of the image acquisition device includes a first conveyor belt area located in front of the security inspection channel according to the running direction of the conveyor belt; The control device is used to obtain the conveyor belt image; determine whether there is an object to be detected based on the difference between the image features corresponding to the preset trigger position in the conveyor belt image and the image features corresponding to the preset trigger position in the pre-collected first background image; and control the radiation source of the security inspection device to turn on based on the determination result of the object to be detected, wherein the first background image is an image of the first conveyor belt area collected by the image acquisition device when there is no object to be detected, and the conveyor belt of the security inspection device has a specific pattern, which is a stripe pattern along the running direction of the conveyor belt, and the width of the stripes in the stripe pattern is determined according to the minimum volume of the object to be detected.

10. An electronic device, It is characterized in that It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, for implementing the method steps described in any one of claims 1 to 7 when executing a program stored in a memory.

11. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method steps described in any one of claims 1 to 7 are implemented.

Images