Method and device for determining detection area of gang gate

Abstract

The invention discloses a method and a device for determining a detection area of a row gate, and belongs to the technical field of row gates. The method for determining the detection area of the row gate machine comprises the following steps: acquiring a first depth image acquired by a target image sensor; performing feature extraction on the first depth image based on at least one of a height threshold and an area threshold to obtain a main body region of a plurality of sub-gates included in the first depth image; based on the distance information corresponding to the pixel points in the main body areas of the plurality of sub-gates, screening the main body areas of the plurality of sub-gates to obtain a target first area and a target second area; the distance information represents the distance between an object corresponding to the pixel point and the target image sensor; and determining an area between the target first area and the target second area as a to-be-detected area in the first depth image acquired by the target image sensor. The method for determining the detection area of the row gate is suitable for a large-batch deployment scene, the calibration efficiency is improved, and the labor cost is reduced.

Description

Technical Field

[0001] The present application belongs to the technical field of coupled gates, and in particular, relates to a method and device for determining a detection area of ​​a coupled gate. Background Art

[0002] In the scene of pedestrians passing through the gate, computer vision technology is used to determine the gate that needs to be opened among multiple gates, and gate positioning is the premise of computer vision technology. In related technologies, gate positioning is mainly carried out by manual calibration. However, the above method is not suitable for large-scale deployment scenarios, and the manual workload and labor cost are high. Summary of the invention

[0003] The present application aims to solve at least one of the technical problems existing in the related art. To this end, the present application proposes a detection area determination method and device for a linkage gate, which does not require manual calibration, reduces manual workload, is suitable for large-scale deployment scenarios, improves calibration efficiency, and reduces labor costs.

[0004] In a first aspect, the present application provides a method for determining a detection area of ​​a row of gates, wherein the row of gates comprises a plurality of sub-gates arranged in sequence, and an image sensor is correspondingly arranged in an upper area between adjacent sub-gates; the method comprises:

[0005] Acquire a first depth image acquired by a target image sensor; the first depth image includes a plurality of sub-gates located in an area below the target image sensor;

[0006] Performing feature extraction on the first depth image based on at least one of a height threshold and an area threshold to obtain main body areas of the plurality of sub-gates included in the first depth image;

[0007] Based on the distance information corresponding to the pixel points in the main area of ​​the plurality of sub-gates, a first target area and a second target area are screened from the main area of ​​the plurality of sub-gates; the distance information represents the distance between the object corresponding to the pixel point and the target image sensor;

[0008] An area between the first target area and the second target area is determined as an area to be detected in a first depth image acquired by a target image sensor.

[0009] According to the detection area determination method of the coupling gate machine of the present application, a first depth image is collected by a target image sensor, and features are extracted from the first depth image through one or more of a height threshold and an area threshold to obtain the main areas of the multiple sub-gates included in the first depth image. The area to be detected in the first depth image collected by the target image sensor is automatically determined from the main areas of the multiple sub-gates. No manual calibration is required, which reduces manual workload. The method is suitable for large-scale deployment scenarios, improves calibration efficiency, and reduces labor costs.

[0010] According to the detection area determination method of the linkage gate machine of the present application, based on the distance information corresponding to the pixel points in the main area of ​​the plurality of sub-gate machines, the target first area and the target second area are screened from the main area of ​​the plurality of sub-gate machines, including:

[0011] Comparing distance information corresponding to pixel points in the main area of ​​the plurality of sub-gates;

[0012] The two main body areas with the smallest distance information among the distance information corresponding to the pixel points in the main body areas of the plurality of sub-gates are determined as the first target area and the second target area.

[0013] According to the detection area determination method of the linkage gate machine of the present application, the two main body areas with the smallest distance information in the distance information corresponding to the pixel points in the main body areas of the multiple sub-gate machines are determined as the target first area and the target second area, including:

[0014] Determine two main body areas with the smallest distance information among the distance information corresponding to the pixel points in the main body areas of the plurality of sub-gates as an initial first area and an initial second area;

[0015] Respectively clipping the regions in the initial first region and the initial second region whose connectivity density is less than a density threshold, to obtain a clipped initial first region and a clipped initial second region;

[0016] The cropped initial first area and the cropped initial second area are determined as the target first area and the target second area.

[0017] According to the detection area determination method of the linkage gate machine of the present application, the step of determining the cropped initial first area and the cropped initial second area as the target first area and the target second area includes:

[0018] Based on at least one of the relative position information and the size information corresponding to the gate body included in the cropped initial first area and the cropped initial second area, align the cropped initial first area and the cropped initial second area to obtain an aligned first area and an aligned second area;

[0019] The aligned first region and the aligned second region are determined as the target first region and the target second region.

[0020] According to the detection area determination method of the linkage gate machine of the present application, the feature extraction of the first depth image based on at least one of the height threshold and the area threshold is performed to obtain the main area of ​​the plurality of sub-gate machines included in the first depth image, including:

[0021] Intercepting a pixel area whose distance information corresponding to the pixel point is greater than the height threshold from the first depth image, to obtain a main body area of ​​the plurality of sub-gates included in the first depth image;

[0022] and / or;

[0023] Pixel areas whose connected pixel areas are larger than the area threshold are intercepted from the first depth image to obtain the main areas of the multiple sub-gates included in the first depth image; the connected pixel areas are areas including pixels with the same characteristics.

[0024] According to the detection area determination method of the ramp gate of the present application, the step of acquiring the first depth image acquired by the target image sensor includes:

[0025] Acquire an initial depth image captured by the target image sensor;

[0026] At least one of filtering and binarization is performed on the initial depth image to obtain the first depth image.

[0027] According to the detection area determination method of the linkage gate machine of the present application, after determining the area between the target first area and the target second area as the area to be detected in the first depth image acquired by the target image sensor, the method further includes:

[0028] Performing feature recognition on the area to be detected to obtain a feature recognition result;

[0029] When the feature recognition result indicates that there is a gate-passing object, the area to be detected is determined as an open area;

[0030] When the feature recognition result shows that there is no object passing through the gate, the area to be detected is determined as an area that does not need to be opened.

[0031] In a second aspect, the present application provides a detection area determination device for a row of gates, wherein the row of gates comprises a plurality of sub-gates arranged in sequence, and an image sensor is correspondingly arranged in the upper area between adjacent sub-gates; the device comprises:

[0032] A first processing module, configured to obtain a first depth image acquired by a target image sensor; the first depth image includes a plurality of sub-gates located in an area below the target image sensor;

[0033] a second processing module, configured to extract features from the first depth image based on at least one of a height threshold and an area threshold, to obtain main areas of the plurality of sub-gates included in the first depth image;

[0034] A third processing module is used to filter out a first target area and a second target area from the main areas of the plurality of sub-gates based on distance information corresponding to pixel points in the main areas of the plurality of sub-gates, wherein the distance information represents the distance between the object corresponding to the pixel point and the target image sensor;

[0035] The fourth processing module is used to determine the area between the first target area and the second target area as the area to be detected in the first depth image collected by the target image sensor.

[0036] According to the detection area determination device of the coupling gate machine of the present application, a first depth image is collected by a target image sensor, and features are extracted from the first depth image through one or more of a height threshold and an area threshold to obtain the main areas of the multiple sub-gates included in the first depth image, and the area to be detected in the first depth image collected by the target image sensor is automatically determined from the main areas of the multiple sub-gates. No manual calibration is required, which reduces manual workload. The device is suitable for large-scale deployment scenarios, improves calibration efficiency, and reduces labor costs.

[0037] In a third aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for determining the detection area of ​​the coupling gate as described in the first aspect above is implemented.

[0038] In a fourth aspect, the present application provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for determining a detection area of ​​a coupling gate as described in the first aspect above is implemented.

[0039] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the method for determining the detection area of ​​the coupling gate as described in the first aspect above.

[0040] The above one or more technical solutions in the embodiments of the present application have at least one of the following technical effects:

[0041] A first depth image is collected by a target image sensor, and features are extracted from the first depth image through one or more of a height threshold and an area threshold to obtain main areas of multiple sub-gates included in the first depth image. The area to be detected in the first depth image collected by the target image sensor is automatically determined from the main areas of the multiple sub-gates. No manual calibration is required, which reduces manual workload. The system is suitable for large-scale deployment scenarios, improves calibration efficiency, and reduces labor costs.

[0042] Furthermore, by filtering the initial depth image, the noise in the initial depth image can be removed to obtain a smoother first depth image, thereby improving the image quality of the first depth image; and by binarizing the initial depth image, the contrast of the obtained first depth image can be enhanced, making the multiple sub-gates included in the first depth image clearer, thereby improving the efficiency of subsequent determination of the area to be detected.

[0043] Furthermore, by respectively cropping the areas in the initial first area and the initial second area whose connectivity density is less than the density threshold, a pixel area with a denser connectivity can be obtained, so that the obtained target first area and target second area are more in line with the actual shape of the sub-gate, reducing the interference of the door body of the sub-gate on the gate positioning, and improving the subsequent positioning accuracy.

[0044] Furthermore, by using one or more of the relative position information and size information corresponding to the gate body included in the cropped initial first area and the cropped initial second area, the cropped initial first area and the cropped initial second area are effectively aligned to obtain the aligned first area and the aligned second area, and interferences in the cropped initial first area and the cropped initial second area are removed, thereby improving the accuracy of the acquired target first area and target second area.

[0045] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0047] Figure 1This is one of the flow charts of the method for determining the detection area of ​​the linkage gate provided in the embodiment of the present application;

[0048] Figure 2 This is one of the principle schematic diagrams of the method for determining the detection area of ​​the linkage gate provided in the embodiment of the present application;

[0049] Figure 3 This is the second flow chart of the method for determining the detection area of ​​the linkage gate provided in the embodiment of the present application;

[0050] Figure 4 This is the second principle schematic diagram of the method for determining the detection area of ​​the linkage gate provided in the embodiment of the present application;

[0051] Figure 5 This is the third principle schematic diagram of the method for determining the detection area of ​​the linkage gate provided in the embodiment of the present application;

[0052] Figure 6 This is the fourth principle schematic diagram of the method for determining the detection area of ​​the linkage gate provided in the embodiment of the present application;

[0053] Figure 7 It is a structural schematic diagram of a detection area device of a linkage gate provided in an embodiment of the present application;

[0054] Figure 8 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0056] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0057] In combination with the accompanying drawings, the detection area determination method of the coupling gate machine, the detection area determination device of the coupling gate machine, the electronic device and the readable storage medium provided in the embodiments of the present application are described in detail through specific embodiments and their application scenarios.

[0058] Among them, the detection area determination method of the linkage gate can be applied to the terminal, and can be specifically executed by hardware or software in the terminal.

[0059] The terminal includes but is not limited to portable communication devices such as mobile phones or tablet computers. It should also be understood that in some embodiments, the terminal may not be a portable communication device, but a desktop computer.

[0060] In the following various embodiments, a terminal including a display and a touch-sensitive surface is described. However, it should be understood that the terminal may include one or more other physical user interface devices such as a physical keyboard, a mouse and a joystick.

[0061] The method for determining the detection area of ​​the serial gate provided in the embodiment of the present application may be executed by an electronic device or a functional module or functional entity in the electronic device that can implement the method for determining the detection area of ​​the serial gate. The electronic devices mentioned in the embodiment of the present application include but are not limited to mobile phones, tablet computers, computers, cameras, wearable devices, etc. The method for determining the detection area of ​​the serial gate provided in the embodiment of the present application is described below using an electronic device as an example of the execution subject.

[0062] like Figure 1 As shown, the method for determining the detection area of ​​the linkage gate includes: step 110, step 120, step 130 and step 140.

[0063] The coupled gate machine includes a plurality of sub-gate machines arranged in sequence.

[0064] An image sensor is correspondingly arranged in the upper area between adjacent sub-gates.

[0065] It can be understood that, in the case where the gate array includes a plurality of sub-gates, the upper area of ​​the gate array may include a plurality of image sensors.

[0066] Adjacent sub-gate machines are used to form a gate passage.

[0067] Step 110: Acquire a first depth image captured by a target image sensor;

[0068] In this step, the target image sensor is any image sensor among the multiple image sensors.

[0069] The first depth image is an image that carries distance information between an object or an object surface corresponding to a pixel and a target image sensor.

[0070] The first depth image emphasizes the geometric information of the real scene rather than the visual texture of the real scene.

[0071] The first depth image includes a plurality of sub-gates located in an area below the target image sensor.

[0072] It should be noted that the multiple sub-gates in the area below the target image sensor may be all the sub-gates included in the bank of gates, or may be part of the sub-gates included in the bank of gates.

[0073] It is understandable that, the larger the shooting field of view of the target image sensor is, the more sub-gates may be included in the first depth image captured by the target image sensor.

[0074] like Figure 2 As shown, an image sensor can be arranged at the center of the upper area between adjacent sub-gates.

[0075] The image sensor may be a structured light image sensor, or an image sensor such as a binocular stereo vision image sensor that can measure the distance between an object and the image sensor.

[0076] The specific type of the image sensor can be determined based on actual conditions and is not limited in this application.

[0077] like Figure 3 As shown, the first depth image can be collected by a 3D structured light camera.

[0078] During the actual implementation process, the mirror of the image sensor is parallel to the ground plane corresponding to the sub-gate machine. The target image sensor can capture multiple sub-gate machines within its field of view (i.e., the area below the target image sensor), that is, the target image sensor takes a bird's-eye view to obtain a first depth image.

[0079] like Figure 4 As shown, the target image sensor can capture a first depth image including four sub-gates.

[0080] Among them, G_A, G_B, G_C and G_D are the images corresponding to the sub-gate machines.

[0081] G_A_L is the left flapping door or shear door corresponding to the sub-gate machine G_A.

[0082] G_A_R is the right flapping door or shear door corresponding to the sub-gate machine G_A.

[0083] G_B_L is the left flapping door or shear door corresponding to the sub-gate machine G_B.

[0084] G_B_R is the right flapping door or shear door corresponding to the sub-gate machine G_B.

[0085] G_C_R is the right flapping door or shear door corresponding to the sub-gate machine G_C.

[0086] G_D_L is the left flapping door or shear door corresponding to the sub-gate machine G_D.

[0087] Step 120: extract features from the first depth image based on at least one of a height threshold and an area threshold to obtain main areas of the plurality of sub-gates included in the first depth image;

[0088] In this step, the height threshold is a preset value for extracting the region of interest in the first depth image.

[0089] The specific value of the height threshold can be determined based on actual conditions, for example, based on the actual height of the sub-gate and the setting height of the target image sensor, and this application does not limit it.

[0090] For example, the actual height of the sub-gate is 1 meter, and the setting height of the target image sensor is 3 meters. In order to extract the image of the sub-gate and remove the background below the sub-gate, the height threshold can be set to 2.2 meters or 2.4 meters, etc.

[0091] The area threshold is a preset value used to filter the image corresponding to the sub-gate in the first depth image.

[0092] The specific value of the area threshold can be determined based on actual conditions, for example, based on data of the actual surface area of ​​the sub-gate machine's top view, and this application does not limit this.

[0093] Taking the surface area of ​​the sub-gate machine in the top view as 0.8 square meters as an example, in order to screen out as many sub-gate machines as possible and remove objects that are not sub-gate machines, the target threshold can be set to 0.5 square meters.

[0094] The main area of ​​the sub-gate is the sub-gate and the image area corresponding to the flapping door or shearing door of the sub-gate.

[0095] In the actual implementation process, the first depth image may be subjected to feature extraction through a height threshold to obtain the main body areas of the plurality of sub-gates included in the first depth image.

[0096] It is also possible to perform feature extraction on the first depth image through an area threshold to obtain main body areas of the multiple sub-gates included in the first depth image.

[0097] During the actual execution process, the first depth image can be firstly subjected to feature extraction through a height threshold to obtain an area in the first depth image that meets the height threshold, and then feature extraction can be performed on the pixel area that meets the height threshold through an area threshold to obtain the main area of ​​the multiple sub-gates included in the first depth image.

[0098] It is also possible to first perform feature extraction on the first depth image using an area threshold to obtain an area in the first depth image that meets the area threshold, and then perform feature extraction on the pixel area that meets the area threshold using a height threshold to obtain the main area of ​​the multiple sub-gates included in the first depth image.

[0099] like Figure 4 As shown, by performing feature extraction on the first depth image through one or more of the height threshold and the area threshold, images corresponding to multiple dotted rectangular frames, namely, main body areas of multiple sub-gates, can be obtained.

[0100] Step 130: based on the distance information corresponding to the pixel points in the main areas of the plurality of sub-gates, filter out the target first area and the target second area from the main areas of the plurality of sub-gates;

[0101] In this step, the distance information represents the distance between the object corresponding to the pixel point and the target image sensor.

[0102] The distance information may be the actual distance between the pixel and the target image sensor, or may be the relative distance between the pixel and the target image sensor.

[0103] The distance information can be represented by the grayscale value of the pixel. A brighter pixel indicates that the object captured by the pixel is closer to the target image sensor, and a darker pixel indicates that the object captured by the pixel is farther away from the target image sensor.

[0104] The first target area is the sub-gate area on one side of the gate passage.

[0105] The target second area is the sub-gate area on the other side of the gate passage except the target first area.

[0106] Taking the example that the first target area is the sub-gate area on the left side of the gate passage, the second target area is the sub-gate area on the right side of the gate passage.

[0107] Taking the example that the first target area is the sub-gate area on the right side of the gate passage, the second target area is the sub-gate area on the left side of the gate passage.

[0108] In the actual implementation process, when obtaining Figure 4 After the images corresponding to the multiple dotted rectangular boxes are shown, the target first area and the target second area that the target image sensor needs to identify can be screened from the main areas of the multiple sub-gates based on the distance information corresponding to the pixel points in the images corresponding to each dotted rectangular box, that is, the dotted rectangular boxes corresponding to G_A_L, G_A and G_A_R and the dotted rectangular boxes corresponding to G_B_L, G_B and G_B_R.

[0109] Continue to refer Figure 3 In the actual implementation process, the connected domain algorithm can be used to extract features from the first depth image, and the target first region and the target second region can be screened.

[0110] Step 140: determine the area between the first target area and the second target area as the area to be detected in the first depth image acquired by the target image sensor.

[0111] In this step, the area between the first target area and the second target area is an area for pedestrians and other objects to pass through the gate, that is, a gate passage.

[0112] The area to be detected is the area where it is necessary to detect whether there is an object passing through the gate.

[0113] During the actual execution process, after determining the target first area and the target second area detected by the target image sensor, it can be determined whether the target image sensor needs to identify whether there is an object passing through the gate in the area between the target first area and the target second area. The area between the target first area and the target second area can be determined as the area to be detected in the first depth image captured by the target image sensor, and the sub-gate machine can be positioned based on the detection results.

[0114] It should be noted that, for each image sensor arranged in the area above the linkage gate, the above method can be used to determine the area to be detected in the first depth image captured by the image sensor, so as to locate the area to be detected, that is, to determine whether the door body in the area to be detected needs to be opened.

[0115] During the research and development process, the inventors discovered that in the related art, the gate was mainly positioned by manual calibration; however, the above method is not suitable for large-scale deployment scenarios, and the manual workload and labor costs are high.

[0116] The present application sets an image sensor in the area above each adjacent sub-gate in the row of gates, collects a first depth image through the target image sensor, and effectively obtains the distance information between the multiple sub-gates included in the area below the target image sensor and the target image sensor; performs feature extraction on the first depth image through one or more of the height threshold and the area threshold, removes the image area in the first depth image that is not related to the sub-gate, and obtains the main body area of ​​the multiple sub-gates included in the first depth image, thereby reducing the interference of irrelevant background on the determination of the detection area and reducing the amount of image processing data; through the distance information corresponding to the pixel points in the main body area of ​​the multiple sub-gates, the target first area and the target second area are screened from the main body area of ​​the multiple sub-gates, and the detection area corresponding to the target image sensor is effectively determined. Without manual calibration, the target image sensor can automatically determine the area to be detected corresponding to the target image sensor, which is suitable for large-scale deployment scenarios, improves calibration efficiency, and reduces labor costs.

[0117] According to the method for determining the detection area of ​​the coupling gate provided in the embodiment of the present application, a first depth image is collected by a target image sensor, and features are extracted from the first depth image through one or more of a height threshold and an area threshold to obtain the main areas of the multiple sub-gates included in the first depth image. The area to be detected in the first depth image collected by the target image sensor is automatically determined from the main areas of the multiple sub-gates. No manual calibration is required, which reduces manual workload. The method is suitable for large-scale deployment scenarios, improves calibration efficiency, and reduces labor costs.

[0118] In some embodiments, step 110 may further include:

[0119] Acquire an initial depth image captured by a target image sensor;

[0120] At least one of filtering and binarization is performed on the initial depth image to obtain a first depth image.

[0121] In this embodiment, the initial depth image is an original image captured by the target image sensor.

[0122] The filtering process is to remove noise and outliers in the initial depth image.

[0123] The filtering process may include: median filtering, Gaussian filtering, mean filtering, dilation filtering, hole filtering, etc.

[0124] The expansion filter process considers the neighborhood of a pixel point in the initial depth image, and sets the pixel value of the pixel point to the maximum value of all pixel values ​​in the neighborhood, so as to expand the multiple sub-gates included in the initial depth image.

[0125] The dilation filter process is used to fill the holes in the initial depth image so that the areas with large pixel values ​​can be expanded and connected.

[0126] For example, in the process of acquiring the initial depth image, due to the influence of noise and uneven lighting, the acquired image of the sub-gate is divided into multiple small areas. Through expansion filtering, the multiple small areas can be connected together to form a larger area.

[0127] The hole filtering process is to analyze the context information of the initial depth image and use the features of the surrounding pixels to estimate the pixel values ​​of the missing area, thereby filling the holes in the initial depth image.

[0128] During the actual implementation process, the initial depth image can be subjected to median filtering through a filtering algorithm or a filtering processor to smooth the initial depth image, and the smoothed initial depth image can be subjected to dilation filtering and hole filtering to fill invalid pixels in the smoothed initial depth image.

[0129] Of course, in the actual implementation process, different filtering processes may be performed on the initial depth image based on the image quality of the initial depth image, which is not limited in this application.

[0130] The binarization process is to set the pixel values ​​of the pixels in the initial depth image to two specific values.

[0131] In an actual implementation process, the initial depth image may be binarized by image processing software or an image processing database to obtain a first depth image.

[0132] In some embodiments, the initial depth image may be first filtered using a filtering algorithm, and then binarized using an image processing database to obtain a first depth image.

[0133] In other embodiments, the initial depth image may be first binarized using an image processing database to obtain a binarized initial depth image, and then the binarized initial depth image may be filtered using a filtering algorithm to obtain a first depth image.

[0134] like Figure 3 As shown, in the actual implementation process, the initial depth image can be filtered and binarized by a filtering binarization algorithm.

[0135] According to the detection area determination method of the row of gates provided in the embodiment of the present application, by filtering the initial depth image, the noise in the initial depth image can be removed to obtain a smoother first depth image, thereby improving the image quality of the first depth image; by binarizing the initial depth image, the contrast of the obtained first depth image can be enhanced, so that the multiple sub-gates included in the first depth image are clearer, thereby improving the quality of the first depth image and improving the efficiency of subsequent determination of the area to be detected.

[0136] In some embodiments, step 120 may further include:

[0137] A pixel area in which distance information corresponding to the pixel points is greater than a height threshold is intercepted from the first depth image to obtain a main body area of ​​the plurality of sub-gates included in the first depth image.

[0138] In this embodiment, it should be noted that the target image sensor performs overhead shooting to obtain the first depth image.

[0139] The distance information corresponding to the pixel in the first depth image represents the distance between the object corresponding to the pixel and the target image sensor.

[0140] The pixel point with the largest distance information in the target image sensor is the pixel point representing the distance between the ground and the target image sensor.

[0141] In the actual implementation process, a pixel region with distance information corresponding to the pixel points greater than the height threshold is intercepted from the first depth image to obtain a pixel region at a certain horizontal height.

[0142] Taking the actual height of the sub-gate as 1 meter, the setting height of the target image sensor as 3 meters, and the height threshold as 2.2 meters as an example, the image corresponding to 0.8 meters above the ground will be intercepted, that is, the pixel areas of 0.2 meters from the top of multiple sub-gates and the areas above the top of multiple sub-gates will be obtained.

[0143] According to the detection area determination method of the coupled gate provided in the embodiment of the present application, by intercepting the pixel area where the distance information corresponding to the pixel point is greater than the height threshold from the first depth image, objects lower than the sub-gate in the first depth image can be effectively removed, that is, the pixel area irrelevant to the sub-gate can be removed, thereby reducing the interference of irrelevant background.

[0144] In some embodiments, step 120 may further include:

[0145] Pixel areas whose connected pixel areas are larger than the area threshold are intercepted from the first depth image to obtain the main areas of the multiple sub-gates included in the first depth image; the connected pixel areas are areas including pixels with the same characteristics.

[0146] In this embodiment, the connected pixel region is a pixel region with adjacent pixel positions and the same pixel values.

[0147] In an actual implementation process, the area of ​​each connected pixel region in the first depth image may be calculated, and the calculated area of ​​the connected pixel region may be compared with the area threshold.

[0148] The pixel areas whose area of ​​connected pixel areas is greater than the area threshold are retained, and the pixel areas whose area of ​​connected pixel areas is not greater than the area threshold are deleted, so as to delete the pixel areas in the first depth image that are not related to the sub-gates, such as plastic bags and garbage on the ground, and obtain the main areas of the multiple sub-gates included in the first depth image.

[0149] According to the method for determining the detection area of ​​the coupled gate provided in the embodiment of the present application, by intercepting pixel areas whose connected pixel areas are larger than the area threshold from the first depth image, the pixel areas with larger connected area in the first depth image are retained, and the areas with smaller connected area in the first depth image are removed. The main areas of multiple sub-gates in the first depth image can be retained, and pixel areas irrelevant to the sub-gates can be deleted, thereby reducing the amount of image data that needs to be processed.

[0150] In some embodiments, step 130 may further include:

[0151] Comparing distance information corresponding to pixel points in the main area of ​​multiple sub-gates;

[0152] The two main body areas with the smallest distance information among the distance information corresponding to the pixel points in the main body areas of the plurality of sub-gates are determined as the first target area and the second target area.

[0153] In this step, the main area of ​​multiple sub-gates may include multiple pixel points, each pixel point corresponds to distance information, and the distance information corresponding to each pixel point in the main area of ​​the multiple sub-gates can be statistically analyzed, such as calculating the sum of the distance information of the main area, or calculating the average value of the distance information of the main area of ​​the multiple sub-gates, to obtain the distance information corresponding to the pixel points in the main area of ​​the multiple sub-gates.

[0154] Of course, in the actual implementation process, the distance information corresponding to the pixel points in the main area of ​​multiple sub-gates can also be determined by any other feasible method, and this application is not limited to this.

[0155] After obtaining the distance information corresponding to the pixel points in the main areas of the multiple sub-gates, the size relationships between the distance information are compared, and the two main areas with the smallest distance information corresponding to the pixel points in the main areas of the multiple sub-gates are determined as the target first area and the target second area.

[0156] Continue to refer Figure 4 By comparing the distance information corresponding to the pixel values ​​in the dotted rectangular box, it can be determined that the two main areas with the smallest distance information are the main areas corresponding to G_A_L, G_A and G_A_R, and the main areas corresponding to G_B_L, G_B and G_B_R.

[0157] According to the detection area determination method of the row of gates provided in the embodiment of the present application, by comparing the distance information corresponding to the pixel points in the main areas of the multiple sub-gates, the distance between the multiple sub-gates and the target image sensor can be determined, and the two main areas closer to the target image sensor can be effectively selected to locate the gate that is mainly photographed by the target image sensor. The selection method is simple and the selection efficiency is high.

[0158] In some embodiments, determining two main body areas with the smallest distance information among the distance information corresponding to the pixel points in the main body areas of the plurality of sub-gates as the first target area and the second target area may also include:

[0159] Determine two main body areas with the smallest distance information among the distance information corresponding to the pixel points in the main body areas of the plurality of sub-gates as an initial first area and an initial second area;

[0160] Respectively clipping the regions in the initial first region and the initial second region whose connectivity density is less than a density threshold, to obtain a clipped initial first region and a clipped initial second region;

[0161] The cropped initial first region and the cropped initial second region are determined as the target first region and the target second region.

[0162] In this embodiment, the initial first area is a pixel area of ​​the sub-gate machine and the door body corresponding to the sub-gate machine included on one side of the gate passage.

[0163] The initial second area is the pixel area of ​​the sub-gate machine and the door body corresponding to the sub-gate machine included on the other side of the gate passage.

[0164] The density threshold is a preset value for determining whether a connected region is sparsely connected.

[0165] The specific value of the density threshold can be determined based on actual conditions and is not limited in this application.

[0166] The cropped initial first region is a region obtained by removing a sparsely connected pixel region in the initial first region.

[0167] The cropped initial second region is a region obtained by removing a sparsely connected pixel region in the initial second region.

[0168] In the actual implementation process, the initial first region and the initial second region can be divided into multiple sub-regions, for example, into multiple grids of the same size, and then the ratio of the area of ​​the connected region in each grid to the entire grid is calculated to obtain the connectivity density of the initial first region and the initial second region.

[0169] The size of the divided sub-areas may be user-defined or determined based on actual conditions, and this application does not limit this.

[0170] Of course, the connectivity density of the initial first region and the initial second region may also be calculated in any other feasible manner.

[0171] The calculated connectivity density is compared with the density threshold, and the areas in the initial first region and the initial second region whose connectivity density is less than the density threshold are cropped, that is, the sparsely connected parts in the initial first region and the initial second region are removed, and the densely connected parts are retained to obtain the cropped first region and the cropped second region.

[0172] like Figure 3 As shown, in the actual execution process, the initial first area and the initial second area can be cropped respectively by a scanning cropping algorithm to obtain a cropped first area and a cropped second area.

[0173] Continue to refer Figure 4 , taking the dotted rectangular boxes corresponding to G_A_L, G_A and G_A_R as an example, the areas in the dotted rectangular boxes with connectivity density less than the density threshold are cropped, and the following can be obtained: Figure 5 The dotted rectangular frame including G_A shown in the figure removes the door body of the sub-gate to obtain a pixel area with denser connections, so that the target first area is more consistent with the actual shape of the sub-gate.

[0174] Similarly, by cropping the dotted rectangular frame of the main area corresponding to the initial second area G_B_L, G_B and G_B_R, the following can be obtained: Figure 5 The dotted rectangular frame including G_B shown in the figure removes the door body of the sub-gate machine to obtain a pixel area with denser connections, so that the target second area is more consistent with the actual shape of the sub-gate machine.

[0175] According to the detection area determination method of the coupled gate provided in the embodiment of the present application, by respectively cropping the areas in the initial first area and the initial second area whose connectivity density is less than the density threshold, a more densely connected pixel area can be obtained, so that the obtained target first area and target second area are more in line with the actual shape of the sub-gate, reducing the interference of the door body of the sub-gate on the gate positioning, and improving the subsequent positioning accuracy.

[0176] In some embodiments, determining the cropped initial first area and the cropped initial second area as the target first area and the target second area may further include:

[0177] Based on at least one of the relative position information and the size information corresponding to the gate body included in the cropped initial first area and the cropped initial second area, align the cropped initial first area and the cropped initial second area to obtain an aligned first area and an aligned second area;

[0178] The aligned first region and the aligned second region are determined as a target first region and a target second region.

[0179] In this embodiment, the relative position information is information such as the length, width, and surface area between the gate body included in the cropped initial first area and the gate body included in the cropped initial second area.

[0180] The size information is the actual size information of the gate body.

[0181] The size information may include: the length, width and surface area of ​​the gate body.

[0182] In actual application scenarios, there may be pillars, glass doors, walls, etc. next to the gate body. In the acquired first depth image, a target first area formed with the gate is larger than a pixel area formed by the gate body itself.

[0183] In the actual implementation process, it can be determined whether the obtained cropped initial first region and the obtained cropped initial second region are aligned by comparing the sizes of the cropped initial first region and the cropped initial second region.

[0184] When the sizes of the cropped initial first area and the cropped initial second area are the same, the cropped initial first area and the cropped initial second area are determined to be aligned to obtain an aligned first area and an aligned second area, and the aligned first area and the aligned second area are determined as a target first area and a target second area.

[0185] In the case that the sizes of the cropped initial first region and the cropped initial second region are not the same, it may be determined that the cropped initial first region and the cropped initial second region are not aligned.

[0186] In the case that the size of the cropped initial second region is relatively large, the cropped initial second region may be aligned based on the cropped initial first region.

[0187] In the case that the size of the cropped initial first region is relatively large, the cropped initial first region may be aligned based on the cropped initial second region.

[0188] like Figure 6 As shown, O_A in the cropped initial first area interferes with the positioning of G_A, that is, O_A expands the pixel area corresponding to G_A, so that G_A is abnormally stretched. At this time, the cropped initial first area can be aligned with the cropped initial second area that has not been abnormally stretched, that is, the upper and lower areas of the abnormally stretched initial first area after cropping are aligned with the upper alignment line and the lower alignment line, and the width of the G_B gate in the cropped initial second area is aligned with the width of the G_A gate.

[0189] In some embodiments, when the cropped initial first area and the cropped initial second area are both abnormally stretched, the cropped initial first area and the cropped initial second area can be aligned respectively using the actual size information of the sub-gate obtained in advance to obtain the aligned first area and the aligned second area.

[0190] In this embodiment, based on the actual size information of the sub-gate that has been obtained and the proportional relationship between the first depth image captured by the target image sensor and the actual scene, the width corresponding to the sub-gate in the cropped initial first area is given, and when the right x coordinate of the G_A gate is identified, the left x coordinate of the G_A gate is converted through the 3D coordinate to achieve width alignment of the G_A gate.

[0191] By performing a secondary scan on the main body area and the first depth image of the plurality of sub-gates, the length of the gate is obtained to achieve alignment of the gate length.

[0192] Similarly, the G_B gates in the initial second area after cropping can also be aligned in the above manner. To avoid repetition, this application will not go into details.

[0193] like Figure 3 As shown, in the actual execution process, the cropped initial first region and the cropped initial second region may be aligned by an alignment algorithm to obtain an aligned first region and an aligned second region.

[0194] According to the detection area determination method of the coupled gate provided in the embodiment of the present application, the cropped initial first area and the cropped initial second area are effectively aligned through one or more of the relative position information and size information corresponding to the gate body included in the cropped initial first area and the cropped initial second area to obtain the aligned first area and the aligned second area, remove interferences in the cropped initial first area and the cropped initial second area, and improve the accuracy of the acquired target first area and target second area.

[0195] In some embodiments, after step 140, the method may further include:

[0196] Perform feature recognition on the area to be detected to obtain a feature recognition result;

[0197] When the feature recognition result indicates that there is a gate-passing object, the area to be detected is determined as an open area;

[0198] When the feature recognition result shows that there is no object passing through the gate, the area to be detected is determined as an area that does not need to be opened.

[0199] In this embodiment, feature recognition is to identify whether there is an object passing through the gate in the area to be detected.

[0200] The feature recognition result is the result obtained by performing image recognition on the area to be detected.

[0201] The feature recognition result may include: the existence of the object passing through the gate and the absence of the object passing through the gate.

[0202] Objects that can pass through the gate include: people, animals, boxes and other objects.

[0203] In the actual execution process, the feature recognition of the area to be detected can be performed through neural network models, deep convolution models, machine learning models, etc. to obtain feature recognition results.

[0204] When the feature recognition result indicates that there is an object passing through the gate, it indicates that there are objects such as animals or people in the area to be detected that need to pass through the gate passage corresponding to the area to be detected. The area to be detected can be determined as an open area, and the sub-gate corresponding to the area to be detected can be determined as the sub-gate that needs to be opened, so as to locate the sub-gate.

[0205] When the feature recognition result is that there is no object passing through the gate, it indicates that there are no objects such as people or animals in the area to be detected that need to pass through the gate passage corresponding to the area to be detected. The area to be detected can be determined as an area that does not need to be opened, so that the sub-gate corresponding to the area to be detected remains closed.

[0206] According to the detection area determination method of the row of gates provided in the embodiment of the present application, features are extracted for the area to be detected to obtain feature recognition results, and it is effectively determined whether the area to be detected needs to be opened based on the feature recognition results, so as to locate the sub-gate that needs to be opened, thereby timely and automatically opening the sub-gate corresponding to the area to be detected, thereby improving the user experience.

[0207] The detection area determination method for the row gate provided in the embodiment of the present application can be executed by the detection area determination device for the row gate. In the embodiment of the present application, the detection area determination method for the row gate is executed by the detection area determination device for the row gate as an example to illustrate the detection area determination device for the row gate provided in the embodiment of the present application.

[0208] The embodiment of the present application also provides a detection area determination device for a linkage gate.

[0209] The coupled gate machine includes a plurality of sub-gate machines arranged in sequence.

[0210] An image sensor is correspondingly arranged in the upper area between adjacent sub-gates.

[0211] like Figure 7 As shown, the detection area determination device of the linkage gate includes: a first processing module 710, a second processing module 720, a third processing module 730 and a fourth processing module 740.

[0212] The first processing module 710 is used to obtain a first depth image acquired by the target image sensor; the first depth image includes a plurality of sub-gates located in the area below the target image sensor;

[0213] The second processing module 720 is used to extract features from the first depth image based on at least one of a height threshold and an area threshold to obtain main areas of the plurality of sub-gates included in the first depth image;

[0214] The third processing module 730 is used to filter out the target first area and the target second area from the main areas of the plurality of sub-gates based on the distance information corresponding to the pixel points in the main areas of the plurality of sub-gates; the distance information represents the distance between the object corresponding to the pixel point and the target image sensor;

[0215] The fourth processing module 740 is used to determine the area between the first target area and the second target area as the area to be detected in the first depth image acquired by the target image sensor.

[0216] According to the detection area determination device for the row of gates provided in the embodiment of the present application, a first depth image is collected by a target image sensor, and features are extracted from the first depth image through one or more of a height threshold and an area threshold to obtain the main areas of the multiple sub-gates included in the first depth image, and the area to be detected in the first depth image collected by the target image sensor is automatically determined from the main areas of the multiple sub-gates. No manual calibration is required, which reduces manual workload. The device is suitable for large-scale deployment scenarios, improves calibration efficiency, and reduces labor costs.

[0217] In some embodiments, the third processing module 730 may also be used to:

[0218] Comparing distance information corresponding to pixel points in the main area of ​​multiple sub-gates;

[0219] The two main body areas with the smallest distance information among the distance information corresponding to the pixel points in the main body areas of the plurality of sub-gates are determined as the first target area and the second target area.

[0220] In some embodiments, the third processing module 730 may also be used to:

[0221] Determine two main body areas with the smallest distance information among the distance information corresponding to the pixel points in the main body areas of the plurality of sub-gates as an initial first area and an initial second area;

[0222] Respectively clipping the regions in the initial first region and the initial second region whose connectivity density is less than a density threshold, to obtain a clipped initial first region and a clipped initial second region;

[0223] The cropped initial first region and the cropped initial second region are determined as the target first region and the target second region.

[0224] In some embodiments, the third processing module 730 may also be used to:

[0225] Based on at least one of the relative position information and the size information corresponding to the gate body included in the cropped initial first area and the cropped initial second area, align the cropped initial first area and the cropped initial second area to obtain an aligned first area and an aligned second area;

[0226] The aligned first region and the aligned second region are determined as a target first region and a target second region.

[0227] In some embodiments, the second processing module 720 may also be used to:

[0228] Intercepting pixel areas where distance information corresponding to pixel points is greater than a height threshold from the first depth image, and obtaining main body areas of the plurality of sub-gates included in the first depth image;

[0229] and / or;

[0230] Pixel areas whose connected pixel areas are larger than the area threshold are intercepted from the first depth image to obtain the main areas of the multiple sub-gates included in the first depth image; the connected pixel areas are areas including pixels with the same characteristics.

[0231] In some embodiments, the first processing module 710 may also be used to:

[0232] Acquire an initial depth image captured by a target image sensor;

[0233] At least one of filtering and binarization is performed on the initial depth image to obtain a first depth image.

[0234] In some embodiments, the apparatus may further include a fifth processing module, configured to:

[0235] Perform feature recognition on the area to be detected to obtain a feature recognition result;

[0236] When the feature recognition result indicates that there is a gate-passing object, the area to be detected is determined as an open area;

[0237] When the feature recognition result shows that there is no object passing through the gate, the area to be detected is determined as an area that does not need to be opened.

[0238] The detection area determination device of the gate machine in the embodiment of the present application can be an electronic device, or a component in the electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal, or other devices other than a terminal. Exemplarily, the electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, a vehicle-mounted electronic device, a mobile Internet device (Mobile Internet Device, MID), an augmented reality (augmented reality, AR) / virtual reality (virtual reality, VR) device, a robot, a wearable device, an ultra-mobile personal computer (ultra-mobile personal computer, UMPC), a netbook or a personal digital assistant (personal digital assistant, PDA), etc. It can also be a server, a network attached storage (Network Attached Storage, NAS), a personal computer (personal computer, PC), a television (television, TV), a teller machine or a self-service machine, etc., and the embodiment of the present application is not specifically limited.

[0239] The detection area determination device of the linkage gate in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an IOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0240] The detection area determination device of the linkage gate provided in the embodiment of the present application can achieve Figures 1 to 6 To avoid repetition, the various processes implemented by the method embodiment are not described here.

[0241] In some embodiments, Figure 8 As shown, an embodiment of the present application also provides an electronic device 800, including a processor 801, a memory 802, and a computer program stored in the memory 802 and executable on the processor 801. When the program is executed by the processor 801, each process of the above-mentioned detection area determination method embodiment of the coupling gate machine is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0242] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0243] An embodiment of the present application also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the above-mentioned detection area determination method embodiment of the coupling gate machine are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0244] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0245] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the above-mentioned method for determining the detection area of ​​the coupling gate.

[0246] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0247] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned detection area determination method embodiment of the coupling gate machine, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0248] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0249] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes 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 one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0250] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the relevant technology, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0251] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

[0252] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0253] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present application, and that the scope of the present application is defined by the claims and their equivalents.

Claims

1. A method for determining a detection area of ​​a gate, characterized in that: The row of gates includes a plurality of sub-gates arranged in sequence, and an image sensor is correspondingly arranged in the upper area between the adjacent sub-gates; the method includes: Acquire a first depth image acquired by a target image sensor; the first depth image includes a plurality of sub-gates located in an area below the target image sensor; Performing feature extraction on the first depth image based on at least one of a height threshold and an area threshold to obtain main body areas of the plurality of sub-gates included in the first depth image; Based on the distance information corresponding to the pixel points in the main area of ​​the plurality of sub-gates, a first target area and a second target area are screened from the main area of ​​the plurality of sub-gates; the distance information represents the distance between the object corresponding to the pixel point and the target image sensor; An area between the first target area and the second target area is determined as an area to be detected in a first depth image acquired by a target image sensor.

2. The method for determining the detection area of ​​a linkage gate according to claim 1, characterized in that: The method of screening the target first area and the target second area from the main areas of the plurality of sub-gates based on the distance information corresponding to the pixel points in the main areas of the plurality of sub-gates comprises: Comparing distance information corresponding to pixel points in the main area of ​​the plurality of sub-gates; The two main body areas with the smallest distance information among the distance information corresponding to the pixel points in the main body areas of the plurality of sub-gates are determined as the first target area and the second target area.

3. The method for determining the detection area of ​​a linkage gate according to claim 2, characterized in that: The step of determining two main body areas with the smallest distance information among the distance information corresponding to the pixel points in the main body areas of the plurality of sub-gates as the first target area and the second target area comprises: Determine two main body areas with the smallest distance information among the distance information corresponding to the pixel points in the main body areas of the plurality of sub-gates as an initial first area and an initial second area; Respectively clipping the regions in the initial first region and the initial second region whose connectivity density is less than a density threshold, to obtain a clipped initial first region and a clipped initial second region; The cropped initial first area and the cropped initial second area are determined as the target first area and the target second area.

4. The method for determining the detection area of ​​a linkage gate according to claim 3, characterized in that: The step of determining the cropped initial first area and the cropped initial second area as the target first area and the target second area includes: Based on at least one of the relative position information and the size information corresponding to the gate body included in the cropped initial first area and the cropped initial second area, align the cropped initial first area and the cropped initial second area to obtain an aligned first area and an aligned second area; The aligned first region and the aligned second region are determined as the target first region and the target second region.

5. The method for determining the detection area of ​​a linkage gate according to any one of claims 1 to 4, characterized in that: The extracting features of the first depth image based on at least one of a height threshold and an area threshold to obtain the main areas of the plurality of sub-gates included in the first depth image includes: Intercepting a pixel area whose distance information corresponding to the pixel point is greater than the height threshold from the first depth image, to obtain a main body area of ​​the plurality of sub-gates included in the first depth image; and / or; Pixel areas whose connected pixel areas are larger than the area threshold are intercepted from the first depth image to obtain the main areas of the multiple sub-gates included in the first depth image; the connected pixel areas are areas including pixels with the same characteristics.

6. The method for determining the detection area of ​​a linkage gate according to any one of claims 1 to 4, characterized in that: The step of acquiring a first depth image acquired by a target image sensor includes: Acquire an initial depth image captured by the target image sensor; At least one of filtering and binarization is performed on the initial depth image to obtain the first depth image.

7. The method for determining the detection area of ​​a linkage gate according to any one of claims 1 to 4, characterized in that: After determining the area between the first target area and the second target area as the area to be detected in the first depth image acquired by the target image sensor, the method further includes: Performing feature recognition on the area to be detected to obtain a feature recognition result; When the feature recognition result indicates that there is a gate-passing object, the area to be detected is determined as an open area; When the feature recognition result shows that there is no object passing through the gate, the area to be detected is determined as an area that does not need to be opened.

8. A detection area determination device for a coupled gate, characterized in that: The row of gates includes a plurality of sub-gates arranged in sequence, and an image sensor is correspondingly arranged in the upper area between the adjacent sub-gates; the device includes: A first processing module, configured to obtain a first depth image acquired by a target image sensor; the first depth image includes a plurality of sub-gates located in an area below the target image sensor; a second processing module, configured to extract features from the first depth image based on at least one of a height threshold and an area threshold, to obtain main areas of the plurality of sub-gates included in the first depth image; A third processing module is used to filter out a first target area and a second target area from the main areas of the plurality of sub-gates based on distance information corresponding to pixel points in the main areas of the plurality of sub-gates, wherein the distance information represents the distance between the object corresponding to the pixel point and the target image sensor; The fourth processing module is used to determine the area between the first target area and the second target area as the area to be detected in the first depth image collected by the target image sensor.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the detection area determination method of the linkage gate machine as described in any one of claims 1-7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for determining the detection area of ​​the linkage gate as described in any one of claims 1 to 7 is implemented.

Images