Security check channel bag detection method, device, equipment, medium and program product

Abstract

The application discloses a security check channel bag detection method, device, equipment, medium and program product. The method comprises the following steps: acquiring at least one first image of a target object located in a security check area; and analyzing the at least one first image to obtain a first detection result; wherein the detection is used to represent whether the target object carries a backpack. Thus, by using the method of the application, the effect of accurately detecting whether a passenger carries a bag at a low cost can be achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing, in particular to a security check channel bag detection method, device, equipment, medium and program product. BACKGROUND

[0002] Currently, in order to consider the passing rate, the subway entrance usually adopts a differentiated security check method to guide passengers to enter the station, that is, passengers without bags are directly released for quick passing, and passengers with bags are checked for security before entering the station.

[0003] Currently, in differentiated security check, the security guard mainly manually distinguishes whether the passenger carries a bag, and the distinguishing process needs the security guard to supervise the passengers in the no-bag channel at all times, intercepts the passengers with bags who do not comply with the direct passing, and guides them to the bag channel for security check.

[0004] The above security check method wastes manpower and may have the risk of missing detection. SUMMARY

[0005] The purpose of the embodiments of the present application is to provide a security check channel bag detection method, device, equipment, medium and program product, so as to realize the effect of low-cost and accurate detection of whether the passenger carries a bag.

[0006] The technical scheme of the present application is as follows:

[0007] In a first aspect, a security check channel bag detection method is provided, which comprises:

[0008] obtaining at least one frame of first image of a target object located in a security check area;

[0009] analyzing the at least one frame of first image to obtain a first detection result; wherein the first detection result is used to represent whether the target object carries a backpack.

[0010] In a second aspect, a security check channel bag detection device is provided, which comprises:

[0011] a first obtaining module configured to obtain at least one frame of first image of a target object located in a security check area;

[0012] a first determining module configured to analyze the at least one frame of first image to obtain a first detection result; wherein the first detection result is used to represent whether the target object carries a backpack.

[0013] In a third aspect, an electronic device is provided, which includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, and the program or instructions, when executed by the processor, implement the steps of the security channel bag detection method according to any of the embodiments of the present application.

[0014] In a fourth aspect, a readable storage medium is provided, which stores a program or instructions, and the program or instructions, when executed by a processor, implement the steps of the security channel bag detection method according to any of the embodiments of the present application.

[0015] In a fifth aspect, a computer program product is provided, and the instructions in the computer program product, when executed by a processor of an electronic device, enable the electronic device to perform the steps of the security channel bag detection method according to any of the embodiments of the present application.

[0016] The technical solutions provided by the embodiments of the present application at least bring the following beneficial effects:

[0017] In the embodiments of the present application, by analyzing the acquired at least one first image of the target object located in the security area, it can be quickly determined whether the target object carries a backpack, so that manual confirmation is not required, the confirmation efficiency of whether the target object carries a backpack is improved, the labor cost is saved, and missed detection is avoided, and the detection accuracy is improved.

[0018] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF DRAWINGS

[0019] The accompanying drawings incorporated in the specification and forming a part of it illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application, and do not limit the present application.

[0020] Figure 1 is one of the structural schematic diagrams of a security channel bag detection system according to an embodiment of the present application;

[0021] Figure 2 is another structural schematic diagram of a security channel bag detection system according to an embodiment of the present application;

[0022] Figure 3 is a third structural schematic diagram of a security channel bag detection system according to an embodiment of the present application;

[0023] Figure 4 is a working schematic diagram of image acquisition by a camera in a security channel bag detection system according to an embodiment of the present application;

[0024] Figure 5 is a flowchart of a bag detection method in a security channel provided by an embodiment of the first aspect of the present application;

[0025] Figure 6 is a schematic diagram of a security area according to an embodiment of the first aspect of the present application;

[0026] Figure 7 is a structural schematic diagram of a bag detection device in a security channel provided by an embodiment of the second aspect of the present application;

[0027] Figure 8 is a structural schematic diagram of an electronic device provided by an embodiment of the third aspect of the present application. DETAILED DESCRIPTION

[0028] In order for those skilled in the art to better understand the technical solutions of the present application, the technical solutions in the embodiments of the present application will be described in detail below with reference to the drawings. It should be understood that the specific embodiments described herein are intended to explain the present application only, not to limit the present application. The present application can be implemented without some of these specific details for those skilled in the art. The following description of the embodiments is merely to provide a better understanding of the present application by showing examples of the present application.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. The implementation described in the following exemplary embodiments does not represent all implementations consistent with the present application. Rather, they are merely examples consistent with some aspects of the present application as detailed in the appended claims.

[0030] As described in the background section, in the prior art, when detecting whether a passenger carries a backpack, there is a problem of wasting manpower and possible missed detection. To solve the above problems, the present application provides a security channel bag detection method, device, equipment, medium and program product, which can quickly determine whether the target object carries a backpack by analyzing at least one first image of the target object located in the security area. Thus, it is not necessary to manually confirm, which improves the confirmation efficiency of whether the target object carries a backpack, saves manpower cost, avoids missed detection, and improves the accuracy of detection.

[0031] The security channel bag detection method provided by the embodiments of the present application will be described in detail below with reference to the drawings and specific embodiments and their application scenarios.

[0032] Before introducing the security channel bag detection method provided by the embodiments of the present application, first introduce the security channel bag detection system for realizing the security channel bag detection method provided by the embodiments of the present application.

[0033] Figure 1 is a structural schematic diagram of a security channel bag detection system provided by the embodiments of the present application, as Figure 1 indicated, the security channel bag detection system provided by the embodiments of the present application can include an image acquisition device 110, the image acquisition device 110 is provided with a processor 120 and a camera 130. That is, the image acquisition device 110 is a device integrated with processor function and image acquisition function.

[0034] Among them, the camera 130 is used for acquiring the image of the target object located in the security area, and sending the image to the processor;

[0035] The processor 120 is used for analyzing the image and determining whether the target object in the image carries a backpack.

[0036] Among them, the image acquisition device can be a device for image acquisition and image analysis, for example, it can be a camera integrated with a camera and a processor.

[0037] The processor can be a device for processing information or data, for example, it can be a central processing unit (CPU), a micro control unit (MCU), etc.

[0038] The security area can be an area for security check of whether the user carries a backpack.

[0039] The target object can be an object for detecting whether it carries a backpack, for example, it can be a passenger.

[0040] In the embodiments of the present application, the image of the target object located in the security area is acquired by the image acquisition device, and the image is analyzed, so that whether the target object carries a backpack can be quickly determined. Thus, it is not necessary to confirm artificially, the confirmation efficiency of whether the target object carries a backpack is improved, the labor cost is saved, at the same time, the missed detection is avoided, the accuracy of detection is improved, and the camera with image acquisition function and the processor are integrated on one image acquisition device, so that the device cost is saved.

[0041] In some embodiments of the present application, in order to save computing resources, the image acquisition device 110 can include:

[0042] The first image collection device 111 is located directly above the center of the security check area.

[0043] The at least one second image collection device 112 is located at the boundary of the security check area.

[0044] It should be noted that the first image collection device 111 and the second image collection device 112 are each provided with a camera for collecting images and a processor for processing and analyzing the images.

[0045] The first image collection device 111 is further configured to analyze a second image collected by the camera in the first image collection device to determine whether the target object is located in the security check area, and analyze a first image collected by the camera in the second image collection device to determine whether the target object carries a backpack in the case where it is determined that the target object is located in the security check area.

[0046] The first image collection device can be an image collection device located directly above the center of the security check area.

[0047] The second image collection device can be a device located at the boundary of the security check area, and can be multiple devices.

[0048] The second image can be an image collected by the camera in the first image collection device.

[0049] The first image can be an image collected by the camera in the second image collection device.

[0050] In one example, referring to Figure 2 and Figure 3 , the area A is a security check area, the first image collection device 111 is located directly above the center of the security check area A, which can be a top-view camera, and the second image collection device 112 is located at four boundary points of the security check area, which can be a low-view camera.

[0051] It should be noted that the height of the first image collection device and the second image collection device in the above Figure 2 and Figure 3 from the ground can be adjusted according to user needs, and is not limited here.

[0052] In some embodiments of the present application, four low-view cameras are deployed based on the consideration of the habit of passengers carrying bags. Through statistics, it can be found that there are many ways to carry bags, such as front, back, left side and right side. The four-view cameras can capture the bags at all positions of the passengers, avoiding omission in the image collection process.

[0053] In some embodiments of the present application, in a case where it is determined that the target object is not located in the security check area, the second image acquisition device can not be triggered to acquire the first image, so as to save computing resources.

[0054] In some embodiments of the present application, how to determine whether the target object is in the security check area and how to determine whether the target object carries a backpack are described in subsequent embodiments in detail.

[0055] In the embodiments of the present application, the second image is acquired by the first image acquisition device, and whether the target object is in the security check area can be determined according to the second image. In a case where it is determined that the target object is in the security check area, the first image can be acquired by the second image acquisition device, and the first image is analyzed to determine whether the target object carries a backpack. In this way, in a case where the target object is in the security check area, the second image acquisition device is triggered to acquire the first image again, so as to save computing resources.

[0056] In some embodiments of the present application, in a case where it is determined that the target object is in the security check area, each second image acquisition device can start to acquire the first image at the same time, or the second image acquisition device of the front view angle (used to acquire the front view angle of the target object) can start to acquire first, and then the second image acquisition device of the rear view angle (used to acquire the rear view angle of the target object) can start to acquire.

[0057] In one example, referring to Figure 4 , the top view camera is the first image acquisition device, and the cameras 1-4 are the second image acquisition devices. The cameras 1 and 2 are front view cameras, the cameras 3 and 4 are rear view cameras, the block B is the field of view range of the top view camera, the straight lines a1 and a2 are two boundary lines of the security check area, and the straight line a3 is located in the security check area. When the target object starts to walk to the straight line a1, the cameras 1 and 2 are triggered to start to acquire, and the cameras 3 and 4 are in a non-working state. When the target object walks to the straight line a3, the cameras 3 and 4 are triggered to work. When the target object walks to the straight line a2, the target object walks out of the security check area, and then the cameras 1-4 all stop working.

[0058] In the embodiments of the present application, the delayed backpack image acquisition mode is to ensure that the backpack of the passenger is completely in the rear view camera, so as to ensure the integrity and detection accuracy of the backpack.

[0059] In some embodiments of the present application, in order to improve the user experience, the processor 120 can also be used to: in a case where it is determined that the target object carries a backpack, analyze the first image to determine the size type of the backpack.

[0060] The size type of the backpack includes a large backpack and a small backpack.

[0061] The large bag can be a backpack with an area greater than a first preset size threshold.

[0062] The small bag can be a backpack with an area less than the first preset size threshold.

[0063] The first preset size threshold can be a preset size threshold of the backpack, which can be set by the user as needed, and is not limited here.

[0064] In the embodiments of the present application, the processor can also be used to analyze the first image to determine the size type of the backpack if the target object carries the backpack, so that the size type of the backpack can be accurately determined to facilitate classification and passage according to the size type of the backpack.

[0065] In some embodiments of the present application, after the size type of the backpack is determined, the passenger can be divided into channels for passage according to the size type of the backpack to improve the passage efficiency.

[0066] In some embodiments of the present application, how to determine the size type of the backpack is specifically described in subsequent embodiments.

[0067] In some embodiments of the present application, in order to improve the user experience, the security channel bag detection system described above can also include:

[0068] The guiding and shunting module is used to guide the target object to the target passage channel corresponding to the size type of the backpack and the detection result based on the size type of the backpack and the detection result.

[0069] The target communication channel can be a channel that the target object can pass according to the size type of the backpack and the detection result.

[0070] In the embodiments of the present application, the guiding and shunting module guides the target object to the target passage channel corresponding to the size type of the backpack and the detection result based on the size type of the backpack and the detection result, so that the target object can be guided to the corresponding target passage channel according to the size type of the backpack and the detection result, which improves the passage efficiency and improves the user experience.

[0071] In some embodiments of the present application, the guiding and shunting module can be specifically used for:

[0072] If the detection result is that the target object does not carry a backpack or the size type of the backpack carried by the target object is a small bag, the target object can be directly passed;

[0073] If the detection result is that the target object carries a backpack and the size type of the backpack is a large bag, the target object is guided to the first target passage channel.

[0074] The first target passageway can be a passageway for passengers carrying large bags.

[0075] In one example, refer to Figure 3 The first target passage can be Figure 3 The large package channel in the middle.

[0076] In the embodiments of this application, by determining the size and type of the backpack and the detection results, the target object can be assigned to different passageways, thereby improving the passage efficiency of the target object and enhancing the user experience.

[0077] In some embodiments of this application, reference is made to Figure 2 The aforementioned security checkpoint bag detection system may also include:

[0078] Gate 160, located between the security check area and the target passage, is used to allow the target object to pass through the target passage when it is open.

[0079] In some embodiments of this application, the gate 160 is always open when no one is passing through. This ensures faster passage for passengers.

[0080] In some embodiments of this application, reference is made to Figure 2 The aforementioned security checkpoint bag detection system may also include:

[0081] The automatic interception module 140 is used to generate a gate closing command and send the closing command to the gate 150 when the detection result determines that the target object is carrying a backpack and the backpack carried by the target object is a large bag.

[0082] The gate 150 is used to control the gate 160 to close based on a closing command, so as to intercept a target object carrying a large package.

[0083] In one example, refer to Figure 2 and Figure 3 The automatic interception module 140 can be located in the gate 150, which is located in the small package / no-package channel, and is used to control the opening and closing of the gate 160.

[0084] In some embodiments of this application, reference is made to Figure 3 Automatic interception module ( Figure 3 (Not shown) can be located in the control terminal 170 placed on the gate 150.

[0085] In the embodiments of the present application, when it is determined that the detection result is that the target object carries a backpack, and the size type of the backpack carried by the target object is a large backpack, the automatic interception module generates a gate closing instruction, and sends the closing instruction to the gate machine. The gate machine controls the gate to close based on the closing instruction. When the gate is closed, the target object can pass through the large backpack channel for passing, so that the opening and closing of the gate can be automatically controlled according to the detection result.

[0086] In some embodiments of the present application, with reference to Figure 2 The security channel backpack detection system described above can further include:

[0087] The acousto-optic module 180 is configured to display the detection result and the size type of the backpack, and perform voice broadcast.

[0088] In some embodiments of the present application, the acousto-optic module can display the detection result and the size type of the backpack, and perform voice broadcast.

[0089] Specifically, in the case where the target object carries a small backpack, the following content can be broadcast: “Passenger with a backpack, please go to the ordinary security channel”. The passenger is guided to the security channel to complete the backpack security check. In the case where the target object does not carry a backpack, the following content can be broadcast: “Please pass”. In the case where there are multiple objects in the security area, an alarm can be sounded, and the following content can be broadcast: “Abnormal”.

[0090] In some embodiments of the present application, the acousto-optic module 180 can be integrated in the control terminal 170.

[0091] In the embodiments of the present application, the detection result and the size type of the backpack can be displayed by the acousto-optic module, and voice broadcast can be performed, so that the target object can intuitively view the detection result and the size type of the backpack, and pass according to the guidance of the voice broadcast, thereby improving the user experience.

[0092] In some embodiments of the present application, with reference to Figure 2 The security channel backpack detection system described above can further include a passing indication light 190, and passing can be performed based on the passing indication light.

[0093] In some embodiments of the present application, with reference to Figure 2 The security channel backpack detection system described above can further include a baffle 200, which can intercept the target object from passing and taking the vehicle.

[0094] In some embodiments of the present application, after the gate is opened, the target object can pass through the baffle 200 to take the vehicle.

[0095] In some embodiments of the present application, when the size type of the backpack and the detection result are displayed, different forms can be used for display according to different information, for example, different colors can be used for display. For example, in the case where it is determined that the target object carries a backpack and the size type of the backpack is a large backpack, the size type of the backpack and the detection result can be displayed in yellow. In the case where it is determined that the target object carries a backpack and the size type of the backpack is a small backpack, the size type of the backpack and the detection result can be displayed in green. In the case where there are multiple target objects in the security check area, red can be used to alarm that someone is tailing, and in this case, the backpack detection and the size type detection can not be performed. In this way, the security personnel and the target object can intuitively view the information of different situations, and the user experience is improved.

[0096] The security check channel backpack detection method provided by the embodiments of the present application will be described in detail below.

[0097] It should be noted that the same terms in the embodiments of the present application as in the above embodiments, and their corresponding explanations, will not be repeated here.

[0098] Figure 5 is a flowchart of a security check channel backpack detection method provided by the embodiments of the present application. The execution subject of the security check channel backpack detection method can be the security check channel backpack detection system described above. Figure 1

[0099] As shown in Figure 5 , the security check channel backpack detection method provided by the embodiments of the present application can include steps 510-520.

[0100] Step 510: Obtain at least one frame of first image of a target object located in a security check area.

[0101] Step 520: Analyze the at least one frame of first image to obtain a first detection result.

[0102] The first detection result can be a detection result obtained after analyzing the at least one frame of first image, and the first detection result can be specifically used to represent whether the target object carries a backpack.

[0103] In some embodiments of the present application, in order to further improve the accuracy of the backpack detection, before step 510, the security check channel backpack detection method described above can further include:

[0104] Obtain at least one frame of second image of the target object;

[0105] Analyze the at least one frame of second image to determine a second detection result;

[0106] Step 510 can specifically include: ​

[0107] In a case where the second detection result is determined to be that the target object is located in the security check area, at least one frame of the first image of the target object is acquired.

[0108] The second detection result can be a detection result obtained by analyzing the at least one frame of the second image, and can be used to represent whether the target object is located in the security check area.

[0109] In the embodiments of the present application, whether the target object is located in the security check area can be determined according to the second image, and in a case where the target object is determined to be located in the security check area, the first image is acquired, so that the first image is acquired again in a case where the target object is located in the security check area, thereby saving computing resources.

[0110] In some embodiments of the present application, in order to accurately determine that the target object is located in the security check area, the analysis of the at least one frame of the second image to determine the second detection result comprises:

[0111] In a case where the target object is determined to be located in the region identifier of the security check area in the at least one frame of the second image, the second detection result is determined to be that the target object is located in the security check area.

[0112] The region identifier can be an identifier used to represent the security check area, for example, can be a frame line, etc.

[0113] In one example, referring to Figure 6 , the top-view camera is the first image acquisition device, the cameras 1-4 are the second image acquisition devices, the box B is the field of view range of the top-view camera, the box A is the security check area, and the boundary line of the box A is the region identifier of the security check area. In a case where the target object is determined to be located in the box A, it is determined that the target object is located in the security check area.

[0114] In some embodiments of the present application, when it is detected that the target object starts to enter the security check area, the second image acquisition device is triggered to start to acquire the first image, and when it is detected that the target object starts to walk out of the security check area, the second image acquisition device is triggered to stop to acquire the first image.

[0115] In the embodiments of the present application, in a case where the target object is determined to be located in the region identifier of the security check area in the at least one frame of the second image, the second detection result is determined to be that the target object is located in the security check area, so that whether the target object is located in the security check area can be accurately determined.

[0116] In some embodiments of the present application, there can be a problem of tailing and escaping detection of the target object. In order to solve the problem, the acquisition of the at least one frame of the first image of the target object in a case where the second detection result is determined to be that the target object is located in the security check area can comprise:

[0117] In a case where the second detection result is that the target object is located in the security check area and the number of the target objects is 1, at least one frame of the first image of the target object is acquired.

[0118] In a case where the second detection result is that the target object is located in the security check area and the number of the target objects is greater than 1, a head-to-head distance between each two adjacent target objects is acquired, and in a case where the head-to-head distance between each two adjacent target objects is greater than a preset distance threshold, at least one frame of the first image of each target object is acquired.

[0119] The preset distance threshold can be a threshold of the head-to-head distance between each two adjacent target objects in the security check area, which can be set according to user demand and is not limited herein.

[0120] In some embodiments of the present application, in a case where the number of the target objects located in the security check area is 1, at least one frame of the first image of the target object is directly acquired by triggering the second image acquisition device. In a case where the number of the target objects located in the security check area is greater than 1, the head-to-head distance between each two adjacent target objects is determined, and in a case where the head-to-head distance between each two adjacent target objects is greater than the preset distance threshold, it is determined that no tailing behavior occurs, and then at least one frame of the first image of the target object is acquired by triggering the second image acquisition device. If the head-to-head distance between each two adjacent target objects is less than or equal to the preset distance threshold, the two target objects have tailing behavior, and at least one frame of the first image of the target object is not acquired by triggering the second image acquisition device.

[0121] In some embodiments of the present application, in a case where tailing behavior occurs, an alarm is triggered at the same time, so that the security check officer can intuitively view the tailing behavior.

[0122] In embodiments of the present application, in a case where the second detection result is that the target object is located in the security check area, whether at least one frame of the first image of the target object is acquired can be determined according to the number of the target objects, so that tailing behavior is avoided.

[0123] In some embodiments of the present application, in order to accurately determine the first detection result, the step 520 can specifically include:

[0124] analyzing the at least one frame of the first image to acquire at least one frame of the third image in which the target object is detected to carry a backpack;

[0125] obtaining the first detection result based on the first number of the third image and the second number of the first image.

[0126] The third image can be an image in which the target object is detected to carry a backpack in the first image.

[0127] In the embodiments of the present application, by analyzing the at least one first image, at least one third image in which the target object is detected to carry a backpack is obtained, and then based on the first quantity of the third image and the second quantity of the first image, the first detection result can be further accurately obtained.

[0128] In some embodiments of the present application, in order to further accurately determine the first detection result, the first detection result can be obtained based on the first quantity of the third image and the second quantity of the first image, specifically, the method can include:

[0129] In the case where the ratio of the second quantity to the first quantity is greater than a preset ratio threshold, the first detection result is determined to be that the target object carries a backpack.

[0130] The preset ratio threshold can be a preset ratio threshold of the second quantity to the first quantity, which can be set by the user as needed, and is not limited here.

[0131] In an example, the obtained first image is 15 frames, of which the first image in which the target object is detected to carry a backpack is 10 frames (i.e., the third image is 10 frames), and if the preset ratio threshold is 0.5, the ratio of the first quantity of the third image to the second quantity of the first image can be calculated, 10 / 15=0.667, and since 0.667>0.5, the first detection result is determined to be that the target object carries a backpack.

[0132] In the embodiments of the present application, in the case where the ratio of the second quantity to the first quantity is greater than the preset ratio threshold, the first detection result is determined to be that the target object carries a backpack, so that the ratio of the second quantity to the first quantity can be used to objectively and accurately determine whether the target object carries a backpack.

[0133] In some embodiments of the present application, in order to further improve the user experience, after step 520, the above-mentioned security channel bag detection method can further include:

[0134] In the case where the first detection result is determined to be that the target object carries a backpack, the at least one first image is analyzed to determine the size type of the backpack carried by the target object.

[0135] Based on the size type of the backpack, the target passage of the target object is determined.

[0136] The size type of the backpack can include a large bag and a small bag.

[0137] In the embodiments of this application, when it is determined that the first detection result is that the target object is carrying a backpack, at least one frame of the first image can be analyzed to determine the size and type of the backpack carried by the target object. Then, based on the size and type of the backpack, the target passage of the target object can be determined. In this way, the target object can pass through the target passage according to the size and type of the backpack, thereby improving the user's passage efficiency and enhancing the user experience.

[0138] In some embodiments of this application, actual research and statistics have revealed that there are currently many types of backpacks on the market, and the characteristics of backpacks viewed from the front and back differ significantly. The types of bags and backpack postures visible from the front view include: shopping bags, backpacks, lunch bags, and shoulder bags carried in various postures such as being slung across the chest, carried by the hand, on the arm, on one shoulder, or under the armpit. Backpacks viewed from the front exhibit diverse postures and are easily obscured by arms, hands, clothing, and other body parts, making backpack detection difficult and resulting in incomplete extraction of the backpack outline, thus affecting backpack size judgment. In contrast, the types of bags visible from the back view include: backpacks carried entirely on the back, shoulder bags placed on the back, etc. Back backpack postures are more uniform, and the pedestrian's back environment is simpler and less prone to obstruction, resulting in a clear backpack outline and lower difficulty in backpack detection.

[0139] Based on the backpack characteristics from different perspectives, in order to ensure both detection accuracy and timeliness, this application divides the backpack size detection mechanism into front-view backpack size detection and back-view backpack size detection (i.e., determining the backpack size type based on its position). The front-view detection can employ a more complex mechanism to ensure accuracy, while the back-view detection can use a simpler mechanism to reduce the overall detection time.

[0140] The current challenges in classifying and detecting backpack sizes and types are as follows:

[0141] 1) The images of the security check area for passengers with the same name are arranged from far to near, causing the backpack size to appear to change continuously;

[0142] 2) According to the statistical analysis of backpack sizes, there is overlap in the size ranges between large and small backpacks;

[0143] 3) Combining 1) and 2) makes it difficult to determine a uniform threshold for distinguishing between large and small packages;

[0144] 4) During the backpack inspection process, the backpack outline is not fully detected due to obstruction, resulting in size assessment errors.

[0145] To address the four challenges mentioned above, this application proposes a method to solve challenge 3) by calculating the face-to-face ratio based on face size, and to solve challenges 1) and 4) by collecting the average size of the passenger from far to near in frames. The specific solution is divided into two parts: front view and back view.

[0146] Before introducing the size type of the backpack through the front view angle and the back view angle respectively, first introduce several main concepts:

[0147] Bag face ratio: there is a size difference between bags, but in real life, the height of the face between people is in a small floating range, even between tall and short people, the detected face height will not have a large numerical difference. Based on this premise, the application conceives the idea of distinguishing large and small bags through the bag face ratio. That is, taking the face height as a reference, by comparing the large bag size with the face size, and then comparing the small bag size with the face size, the small bag and the small bag can be distinguished by comparing the two ratios, which is the concept of bag face ratio in the application.

[0148] Explanation of bag face ratio principle: by statistics of the face height of passengers with large and small bags at different distances from the camera, it can be known that the face height will change from small to large with the distance from the camera, but the overall trend of the face height of passengers with large and small bags is basically the same, and the change floating range is small. It proves the reliability of the premise that there is no large difference in face height between passengers, so the face height can be used as a reliable reference index for large and small bags, which proves the effectiveness of the method design of the application.

[0149] The size type of the backpack through the front view angle and the back view angle is introduced in detail as follows:

[0150] (1) Front view angle

[0151] In some embodiments of the application, the first image can include a first sub-image, which can be an image of the front of the target object collected, that is, the image collected by camera 1 and camera 2 in Figure 4

[0152] In order to further improve the user experience, the analysis of the at least one frame of first image to determine the size type of the backpack carried by the target object can specifically include:

[0153] determining the first height of the face region of the target object, the second height of the backpack and the first area of the backpack in each first sub-image;

[0154] For each first sub-image, the ratio of the first height and the second height is calculated to obtain a first ratio;

[0155] For each first sub-image, based on the first ratio and the first area, the size type of the backpack carried by the target object is determined.

[0156] ​The first height can be a height of a face region of the target object in the first sub-image.

[0157] The second height can be a height of a backpack of the target object in the first sub-image.

[0158] The first area can be an area of the backpack of the target object in the first sub-image.

[0159] It should be noted that when determining the first height, the second height and the first area, the same frame of the first sub-image is determined, that is, the first height, the second height and the first area are determined for each frame of the first sub-image. The face and the backpack in the same frame are used because the distance between the face and the camera and the distance between the backpack and the camera are the same in the same frame, and the influence degree of the distance on the enlargement and reduction is the same in the backpack and the face, thereby better avoiding the distance change error.

[0160] The first ratio can be a ratio of the first height and the second height.

[0161] In the embodiments of the present application, in the case where the position is that the backpack is located on the front and / or side of the target object, the first height of the face region of the target object in each frame of the first image, the second height of the backpack and the first area of the backpack can be determined first, then for each frame of the first image, the ratio of the first height and the second height is calculated to obtain the first ratio, and based on the first ratio and the first area, the size type of the backpack carried by the target object can be accurately determined.

[0162] In some embodiments of the present application, in order to further accurately determine the size type of the backpack carried by the target object, the determination of the size type of the backpack carried by the target object based on the first ratio and the first area for each frame of the first sub-image can specifically include:

[0163] The mean value of the first ratio corresponding to each frame of the first sub-image is calculated to obtain a first face-to-backpack ratio mean value;

[0164] The mean value of the first area corresponding to each frame of the first sub-image is calculated to obtain a first area mean value;

[0165] The size type of the backpack carried by the target object is determined based on the first face-to-backpack ratio mean value and the first area mean value.

[0166] The first face-to-backpack ratio mean value can be the mean value of the first ratio corresponding to each frame of the first sub-image.

[0167] The first area mean value can be the mean value of the first area corresponding to each frame of the first sub-image.

[0168] In one example, the first sub-image has 15 frames, the first ratio corresponding to each frame of the first sub-image is determined as a1, a2, …, a15 respectively, the first area corresponding to each frame of the first sub-image is b1, b2, …, b15, the mean value of a1, a2, …, a15 is calculated to obtain the first bag-face ratio mean value, then the mean value of b1, b2, …, b15 is calculated to obtain the first area mean value, and then the size type of the backpack carried by the target object can be determined according to the first bag-face ratio mean value and the first area mean value.

[0169] In the embodiments of the present application, by calculating the mean value of the first ratio corresponding to each frame of the first sub-image to obtain the first bag-face ratio mean value, and calculating the mean value of the first area corresponding to each frame of the first sub-image to obtain the first area mean value, the size type of the backpack carried by the target object can be accurately determined based on the first bag-face ratio mean value and the first area mean value.

[0170] In some embodiments of the present application, in order to further accurately determine the size type of the backpack carried by the target object, the determination of the size type of the backpack carried by the target object based on the first bag-face ratio mean value and the first area mean value can specifically include:

[0171] In the case where the first bag-face ratio mean value is less than the first preset bag-face ratio mean threshold, the size type of the backpack carried by the target object is determined as a small bag;

[0172] In the case where the first bag-face ratio mean value is greater than or equal to the first preset bag-face ratio mean threshold, and the first bag-face ratio mean value is less than or equal to the second preset bag-face ratio mean threshold, and the first area mean value is greater than the first preset area mean threshold, the size type of the backpack carried by the target object is determined as a large bag;

[0173] In the case where the first bag-face ratio mean value is greater than or equal to the first preset bag-face ratio mean threshold, and the first bag-face ratio mean value is less than or equal to the second preset bag-face ratio mean threshold, and the first area mean value is less than or equal to the first preset area mean threshold, the size type of the backpack carried by the target object is determined as a small bag;

[0174] In the case where the first bag-face ratio mean value is greater than the second preset bag-face ratio mean threshold, the size type of the backpack carried by the target object is determined as a large bag.

[0175] The first preset bag-face ratio mean threshold and the second preset bag-face ratio threshold can be a threshold of the first bag-face ratio mean value, which can be set by the user as needed, and is not limited here.

[0176] In some embodiments of the present application, the second preset bag-face ratio mean threshold is greater than the first preset bag-face ratio mean threshold.

[0177] The first preset area threshold can be a threshold of the first preset area mean value, which can be set by the user as needed, and is not limited herein.

[0178] In some embodiments of the present application, the size type of the backpack is determined according to the first average face ratio and the first average area, which can refer to Table 1 as shown below. In Table 1, rate is the first average face ratio, area is the first average area, r1 is the first preset average face ratio threshold, r2 is the second preset average face ratio threshold, and a1 is the first preset average area threshold.

[0179] Table 1

[0180]

[0181] In the embodiments of the present application, the size type of the backpack carried by the target object is determined according to the relationship between the first average face ratio and the first preset average face ratio threshold and the second preset average face ratio threshold, and the relationship between the first average area and the first preset average area threshold. In this way, the size type of the backpack carried by the target object can be accurately determined.

[0182] (2) Backward viewing angle

[0183] The first image can further include a second sub-image, which is an image of the back of the target object collected by the camera 3 and the camera 4 in the image collection device. Figure 4

[0184] To further improve the user experience, the at least one first image is analyzed to determine the size type of the backpack carried by the target object, which includes:

[0185] Determining a third height of the backpack carried by the target object in each second sub-image;

[0186] Determining the size type of the backpack carried by the target object based on the third height.

[0187] The third height can be the height of the backpack carried by the target object in the second sub-image.

[0188] In the embodiments of the present application, the third height of the backpack carried by the target object in each second sub-image is determined for the backpack in the backward viewing angle, and the size type of the backpack carried by the target object can be accurately determined based on the third height.

[0189] In some embodiments of the present application, to further accurately determine the size type of the backpack carried by the target object, the size type of the backpack carried by the target object can be determined based on the third height, which specifically includes:

[0190] ​In a case where the third height is greater than the preset height threshold, it is determined that the size type of the backpack carried by the target object is a large backpack.

[0191] In a case where the third height is less than or equal to the preset height threshold, it is determined that the size type of the backpack carried by the target object is a small backpack.

[0192] The preset height threshold can be a threshold of the third height, which can be set according to user demand and is not limited herein.

[0193] In the embodiments of the present application, the size type of the backpack carried by the target object can be accurately determined according to the relationship between the third height and the preset height threshold.

[0194] In some embodiments of the present application, after the size type of the backpack is determined in the above manner, in order to further improve user experience, the target passage of the target object is determined based on the size type of the backpack, and can specifically include:

[0195] In a case where the size type of the backpack is a large backpack, the target object is intercepted, the target passage of the target object is determined to be a first target passage, and the target object is guided to pass through the first target passage.

[0196] The first target passage can be a target passage that can be passed through by the target object carrying a large backpack, for example, the first target passage can be a large backpack passage in the security channel. Figure 2

[0197] In the embodiments of the present application, in a case where the backpack carried by the target object is a large backpack, the target object can be intercepted, the target passage of the target object is determined to be a first target passage, and the target object is guided to pass through the first target passage, thereby improving the efficiency of the target object in taking the vehicle and improving user experience.

[0198] In some embodiments of the present application, in order to further improve user experience, the above-mentioned security channel bag detection method can further include:

[0199] In a case where the target object does not carry a backpack or the size type of the backpack carried by the target object is a small backpack, the target object directly passes through.

[0200] In the embodiments of the present application, in a case where the target object does not carry a backpack or the size type of the backpack carried by the target object is a small backpack, the target object can directly pass through, thereby ensuring that the passenger can quickly pass through, improving the efficiency of passing through and improving user experience.

[0201] ​It should be noted that the security channel bag detection method provided by the embodiments of the present application can be executed by a security channel bag detection device, or a control module in the security channel bag detection device for executing the security channel bag detection method.

[0202] Based on the same inventive concept as the security channel bag detection method described above, the present application also provides a security channel bag detection device. The following will be described in detail in combination with Figure 7 The security channel bag detection device provided by the embodiments of the present application will be described in detail.

[0203] Figure 7 FIG. 7 is a structural schematic diagram of a security channel bag detection device according to an exemplary embodiment.

[0204] As Figure 7 shown, the security channel bag detection device 700 can include:

[0205] A first acquisition module 710 is configured to acquire at least one frame of first image of a target object located in a security area.

[0206] A first determination module 720 is configured to analyze the at least one frame of first image to obtain a first detection result, wherein the first detection result is used to represent whether the target object carries a backpack.

[0207] In the embodiments of the present application, by analyzing the acquired at least one frame of first image of the target object located in the security area, it can be quickly determined whether the target object carries a backpack, so that it is not necessary to confirm manually, the confirmation efficiency of whether the target object carries a backpack is improved, the labor cost is saved, at the same time, the missed detection is avoided, and the detection accuracy is improved.

[0208] In some embodiments of the present application, in order to further improve the accuracy of the backpack detection, the security channel bag detection device described above can further include:

[0209] A second acquisition module is configured to acquire at least one frame of second image of the target object.

[0210] A second determination module is configured to analyze the at least one frame of second image to determine a second detection result, wherein the second detection result is used to represent whether the target object is located in the security area.

[0211] The first determination module 720 can be specifically configured to:

[0212] In a case where the second detection result is that the target object is located in the security area, at least one frame of first image of the target object is acquired.

[0213] In some embodiments of the present application, in order to accurately determine that the target object is located in the security check area, the second determination module is specifically configured to: in a case where it is determined that the target object is located in the region identified by the security check area in the at least one frame of second image, determine that the second detection result is that the target object is located in the security check area.

[0214] In some embodiments of the present application, in order to avoid missing detection caused by the trailing problem, the first determination module 720 can be specifically configured to:

[0215] In a case where it is determined that the second detection result is that the target object is located in the security check area and the number of target objects is 1, at least one frame of first image of the target object is acquired;

[0216] In a case where it is determined that the second detection result is that the target object is located in the security check area and the number of target objects is greater than 1, the head-to-head distance between each adjacent two target objects is acquired, and in a case where the head-to-head distance between each adjacent two target objects is greater than a preset distance threshold, at least one frame of first image of each target object is acquired.

[0217] In some embodiments of the present application, in order to accurately determine the first detection result, the first determination module 720 can specifically include:

[0218] A first acquisition unit, configured to analyze the at least one frame of first image, and acquire at least one frame of third image in which it is detected that the target object carries a backpack;

[0219] A first determination unit, configured to obtain the first detection result based on a first quantity of third images and a second quantity of first images.

[0220] In some embodiments of the present application, in order to further accurately determine the first detection result, the first determination unit is specifically configured to: in a case where a ratio of the second quantity to the first quantity is greater than a preset ratio threshold, determine that the first detection result is that the target object carries a backpack.

[0221] In some embodiments of the present application, in order to further improve user experience, the security check channel bag detection device described above can further include:

[0222] A third determination module, configured to, in a case where it is determined that the first detection result is that the target object carries a backpack, analyze the at least one frame of first image, and determine a size type of the backpack carried by the target object; wherein the size type of the backpack includes a large bag and a small bag;

[0223] A fourth determination module, configured to determine a target passage of the target object based on the size type of the backpack.

[0224] In some embodiments of the present application, the first image includes a first sub-image, which is an image of the front of the target object captured; in order to further improve the user experience, the third determining module can specifically include:

[0225] a second determining unit, configured to determine a first height of a face region of the target object, a second height of the backpack, and a first area of the backpack in each first sub-image;

[0226] a third determining unit, configured to calculate a ratio of the first height to the second height to obtain a first ratio for each first sub-image;

[0227] a fourth determining unit, configured to determine the size type of the backpack carried by the target object based on the first ratio and the first area for each first sub-image.

[0228] In some embodiments of the present application, in order to further accurately determine the size type of the backpack, the fourth determining unit can specifically include:

[0229] a first determining sub-unit, configured to calculate a mean value of the first ratio corresponding to each first sub-image to obtain a first face-to-backpack ratio mean value;

[0230] a second determining sub-unit, configured to calculate a mean value of the first area corresponding to each first sub-image to obtain a first area mean value;

[0231] a third determining sub-unit, configured to determine the size type of the backpack carried by the target object based on the first face-to-backpack ratio mean value and the first area mean value.

[0232] In some embodiments of the present application, in order to further accurately determine the size type of the backpack, the third determining sub-unit can be specifically configured to:

[0233] determine that the size type of the backpack carried by the target object is a small backpack when the first face-to-backpack ratio mean value is less than a first preset face-to-backpack ratio mean value threshold;

[0234] determine that the size type of the backpack carried by the target object is a large backpack when the first face-to-backpack ratio mean value is greater than or equal to the first preset face-to-backpack ratio mean value threshold, the first face-to-backpack ratio mean value is less than or equal to a second preset face-to-backpack ratio mean value threshold, and the first area mean value is greater than a first preset area mean value threshold; wherein the second preset face-to-backpack ratio mean value threshold is greater than the first preset face-to-backpack ratio mean value threshold;

[0235] determining that the size type of the backpack carried by the target object is a small backpack, in a case where it is determined that the first average face-to-pack ratio is greater than or equal to the first preset average face-to-pack ratio threshold and less than or equal to the second preset average face-to-pack ratio threshold and the first average area is less than or equal to the first preset average area threshold.

[0236] determining that the size type of the backpack carried by the target object is a large backpack, in a case where it is determined that the first average face-to-pack ratio is greater than the second preset average face-to-pack ratio threshold.

[0237] In some embodiments of the present application, the first image further includes a second sub-image, which is an image of the back of the target object collected; in order to further accurately determine the size type of the backpack, the third determination module can specifically include: a fifth determination unit configured to determine a third height of the backpack carried by the target object in each frame of the second sub-image.

[0238] a sixth determination unit configured to determine the size type of the backpack carried by the target object based on the third height.

[0239] In some embodiments of the present application, in order to further accurately determine the size type of the backpack, the sixth determination unit can be specifically configured to:

[0240] determining that the size type of the backpack carried by the target object is a large backpack, in a case where it is determined that the third height is greater than a preset height threshold;

[0241] determining that the size type of the backpack carried by the target object is a small backpack, in a case where it is determined that the third height is less than or equal to the preset height threshold.

[0242] In some embodiments of the present application, in order to further improve user experience, the fourth determination module can be specifically configured to:

[0243] in a case where the size type of the backpack is a large backpack, intercepting the target object, determining a target passage channel of the target object as a first target passage channel, and guiding the target object to pass through the first target passage channel.

[0244] In some embodiments of the present application, in order to further improve user experience, the security channel backpack detection device can further include:

[0245] a fifth determination module configured to, in a case where the target object does not carry a backpack or the size type of the backpack carried by the target object is a small backpack, the target object directly passes through.

[0246] The security channel bag detection device provided by the embodiments of the present application can be used to execute the security channel bag detection method provided by the above-mentioned method embodiments, and has similar implementation principles and technical effects. For brevity, the above-mentioned method embodiments will not be described again.

[0247] Based on the same inventive concept, the embodiments of the present application further provide an electronic device.

[0248] Figure 8 is a structural schematic diagram of an electronic device provided by the embodiments of the present application. As shown in Figure 8 The electronic device can include a processor 801 and a memory 802 storing computer programs or instructions.

[0249] Specifically, the processor 801 can include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or can be configured to implement one or more integrated circuits of the embodiments of the present application.

[0250] The memory 802 can include a mass storage for data or instructions. By way of example and not limitation, the memory 802 can include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. Where appropriate, the memory 802 can include removable or non-removable (or fixed) media. Where appropriate, the memory 802 can be internal or external to the integrated gateway disaster recovery device. In certain embodiments, the memory 802 is non-volatile solid-state memory. The memory can include read-only memory (ROM), random-access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical, or other physical / tangible memory storage devices. Thus, in general, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software that, when executed (e.g., by one or more processors), is operable to perform the operations described above as being provided by the security channel bag detection method.

[0251] The processor 801 reads and executes the computer program instructions stored in the memory 802 to implement any one of the security channel bag detection methods in the above-mentioned embodiments.

[0252] In one example, the electronic device can further include a communication interface 803 and a bus 810. As shown in Figure 8 the processor 801, the memory 802, and the communication interface 803 are connected through the bus 810 and complete communication therebetween.

[0253] The communication interface 803 is mainly used to realize the communication between the modules, devices, units and / or devices in the embodiments of the present application.

[0254] The bus 810 includes hardware, software or both to couple the components of the electronic device to each other. By way of example, and not limitation, the bus can include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association local (VLB) bus, or another suitable bus or combination of two or more of these. Where appropriate, the bus 810 can include one or more buses. Although the present embodiments describe and show a particular bus, the present application contemplates any suitable bus or interconnect.

[0255] The electronic device can execute the security channel bag detection method in the embodiments of the present application, thereby realizing Figure 5 the security channel bag detection method described.

[0256] In addition, in combination with the security channel bag detection method in the above embodiments, the embodiments of the present application can provide a readable storage medium to realize. The readable storage medium has program instructions stored thereon; the program instructions are executed by the processor to realize any one of the security channel bag detection methods in the above embodiments.

[0257] In addition, in combination with the security channel bag detection method in the above embodiments, the embodiments of the present application can provide a computer program product to realize. The instructions in the computer program product are executed by the processor of the electronic device, so that the electronic device executes any one of the security channel bag detection methods in the above embodiments.

[0258] It is to be understood that the application is not limited to particular configurations and processes described herein and shown in the drawings, as such can include any arrangement or process that is functionally equivalent to the embodiments described herein. For simplicity and clarity, detailed descriptions of well-known methods, procedures, components, and circuits have been omitted in order to avoid obscuring the application. In the above embodiments, a number of specific steps are described and illustrated as examples. However, the methods process of the present application are not limited to the specific steps described and illustrated, as various modifications, permutations, additions and omissions can be made to the steps described without departing from the spirit and scope of the application.

[0259] The functional blocks shown in the block diagrams of the above described structures can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application specific integrated circuits (ASICs), appropriate firmware, plug-ins, functional cards, etc. When implemented in software, the elements of the application are program or code segments that are used to perform the required tasks. The program or code segments can be stored in a machine readable medium or transmitted through a data signal carried in a carrier wave over a transmission medium or communication link. A "machine readable medium" includes any medium that can store or transfer information. Examples of machine readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. The code segments can be downloaded via computer networks such as the Internet, intranet, etc.

[0260] It is also to be understood that the example embodiments described in the present application are based on a series of steps or devices to describe some methods or systems. However, the present application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiments, or in an order different from the embodiments, or several steps can be performed simultaneously.

[0261] The computer program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other processing devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other processing devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. Such processes can be realized by a

[0262] The above merely describes a specific implementation of the present application. Those skilled in the art can clearly understand the specific working processes of the system, modules and units described above for the convenience and brevity of description, and the corresponding processes in the foregoing method embodiments can be referred to, which will not be described herein again. It should be understood that the protection scope of the present application is not limited in this way, and any person skilled in the art can easily think of various equivalent modifications or replacements within the technical range disclosed by the present application, and these modifications or replacements should be covered within the protection scope of the present application.

Claims

1. A method for detecting bags in security checkpoints, characterized in that, The method includes: Acquire at least one first image frame of the target object located in the security check area; The first image frame is analyzed to obtain a first detection result; wherein the first detection result is used to characterize whether the target object is carrying a backpack; The method further includes: If the first detection result indicates that the target object is carrying a backpack, the at least one frame of the first image is analyzed to determine the size type of the backpack carried by the target object; wherein, the size type of the backpack includes large bags and small bags; Based on the size and type of the backpack, determine the target passage for the target object; The first image includes a first sub-image, which is a frontal image of the target object. Analyzing the at least one frame of the first image to determine the size and type of the backpack carried by the target object includes: In the case where the backpack is located in front of and / or to the side of the target object, determine the first height of the face region of the target object, the second height of the backpack, and the first area of ​​the backpack in the first sub-image of each frame; For each frame's first sub-image, the ratio of the first height to the second height is calculated to obtain the first ratio; For each frame's first sub-image, the size type of the backpack carried by the target object is determined based on the first ratio and the first area.

2. The method according to claim 1, characterized in that, Before acquiring at least one first frame of an image of the target object located in the security check area, the method further includes: Obtain at least one frame of the second image of the target object; The at least one frame of the second image is analyzed to determine a second detection result; wherein the second detection result is used to characterize whether the target object is located in the security check area; The acquisition of at least one frame of a first image of a target object located in the security check area includes: If the second detection result indicates that the target object is located within the security check area, at least one frame of the first image of the target object is acquired.

3. The method according to claim 2, characterized in that, The step of analyzing the at least one frame of the second image to determine the second detection result includes: If it is determined that the target object is located within the area identifier of the security check area in at least one frame of the second image, the second detection result is determined to be that the target object is located within the security check area.

4. The method according to claim 2, characterized in that, When the second detection result indicates that the target object is located within the security check area, acquiring at least one frame of a first image of the target object includes: If the second detection result indicates that the target object is located within the security check area and the number of the target object is 1, at least one frame of the first image of the target object is acquired. If the second detection result indicates that the target object is located within the security check area and the number of target objects is greater than 1, the head-to-head distance between each pair of adjacent target objects is obtained. If the head-to-head distance between each pair of adjacent target objects is greater than a preset distance threshold, at least one frame of the first image of each target object is obtained.

5. The method according to claim 1, characterized in that, The step of analyzing the at least one frame of the first image to obtain a first detection result includes: Analyze the at least one frame of the first image to obtain at least one frame of the third image in which the target object is detected to be carrying a backpack; The first detection result is obtained based on the first number of the third image and the second number of the first image.

6. The method according to claim 5, characterized in that, The first detection result is obtained based on the first number of third images and the second number of first images, including: If the ratio of the second quantity to the first quantity is greater than a preset ratio threshold, the first detection result is determined to be that the target object is carrying a backpack.

7. The method according to claim 1, characterized in that, For each frame of the first sub-image, determining the size type of the backpack carried by the target object based on the first ratio and the first area includes: Calculate the mean of the first ratios corresponding to the first sub-images of each frame to obtain the mean of the first face-covering ratio; Calculate the mean of the first area corresponding to the first sub-image of each frame to obtain the mean of the first area; Based on the first average face-to-body ratio and the first average area, the size and type of the backpack carried by the target object are determined.

8. The method according to claim 7, characterized in that, The step of determining the size type of the backpack carried by the target object based on the first average face-to-body ratio and the first average area includes: If the average face-to-bag ratio of the first bag is less than the average face-to-bag ratio of the first preset threshold, the size type of the backpack carried by the target object is determined to be a small bag. If the average first bag-to-face ratio is greater than or equal to the first preset average bag-to-face ratio threshold, and the average first bag-to-face ratio is less than or equal to the second preset average bag-to-face ratio threshold, and the average first area is greater than the first preset average area threshold, then the size type of the backpack carried by the target object is determined to be a large bag; wherein, the second preset average bag-to-face ratio threshold is greater than the first preset average bag-to-face ratio threshold. If the average first bag-to-face ratio is greater than or equal to the first preset average bag-to-face ratio threshold, and the average first bag-to-face ratio is less than or equal to the second preset average bag-to-face ratio threshold, and the average first area is less than or equal to the first preset average area threshold, then the size type of the backpack carried by the target object is determined to be a small bag. If the average value of the first bag-to-face ratio is greater than the average value of the second preset bag-to-face ratio threshold, the backpack carried by the target object is determined to be a large bag.

9. The method according to claim 1, characterized in that, The first image also includes a second sub-image, which is an image of the back of the target object. The step of analyzing the at least one frame of the first image to determine the size and type of the backpack carried by the target object includes: Determine the third height of the backpack carried by the target object in the second sub-image of each frame; Based on the third altitude, the size and type of the backpack carried by the target object are determined.

10. The method according to claim 9, characterized in that, Determining the size and type of the backpack carried by the target object based on the third altitude includes: If the third height is determined to be greater than a preset height threshold, the backpack carried by the target object is determined to be a large bag. If the third height is determined to be less than or equal to the preset height threshold, the backpack carried by the target object is determined to be a small bag.

11. The method according to claim 8 or 10, characterized in that, Determining the target passage for the target object based on the size and type of the backpack includes: If the backpack is a large bag, the target object is intercepted, the target passage of the target object is determined to be the first target passage, and the target object is guided to pass through the first target passage.

12. The method according to claim 8 or 10, characterized in that, The method further includes: If the target object is not carrying a backpack, or if the backpack carried by the target object is a small bag, the target object may pass directly.

13. A bag detection device for security checkpoints, characterized in that, The device includes: The first acquisition module is used to acquire at least one frame of a first image of a target object located in the security check area; A first determining module is used to analyze the at least one frame of the first image to obtain a first detection result; wherein the first detection result is used to characterize whether the target object is carrying a backpack; The device further includes: The third determining module is used to analyze the at least one frame of the first image to determine the size type of the backpack carried by the target object when the first detection result indicates that the target object is carrying a backpack; wherein the size type of the backpack includes large bags and small bags; The fourth determining module is used to determine the target passageway of the target object based on the size and type of the backpack; The first image includes a first sub-image, which is a frontal image of the target object. The third determining module specifically includes: The second determining unit is used to determine the first height of the face region of the target object, the second height of the backpack, and the first area of ​​the backpack in each frame of the first sub-image; The third determining unit is used to calculate the ratio of the first height to the second height for each frame of the first sub-image, and obtain the first ratio. The fourth determining unit is used to determine the size type of the backpack carried by the target object for each frame of the first sub-image, based on the first ratio and the first area.

14. An electronic device, characterized in that, The electronic device includes: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, it implements the bag detection method for security checkpoints as described in any one of claims 1-12.

15. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions, which, when executed by a processor, implement the bag detection method for security checkpoints as described in any one of claims 1-12.

16. A computer program product, characterized in that, When the instructions in the computer program product are executed by the processor of the electronic device, the electronic device causes the electronic device to perform the bag detection method at the security checkpoint as described in any one of claims 1-12.

Images