A target snapshot region adjustment method and device, electronic equipment and medium

Abstract

Embodiments of the present application disclose a target snapshot area adjustment method and device, electronic equipment and medium. The method comprises: identifying a target appearing in a target snapshot area set in a collection area; analyzing the identification result of the target to determine a target analysis result; and adjusting the target snapshot area according to the target analysis result. The above scheme can automatically adjust the target snapshot area based on target analysis results of different dimensions, automatically optimize the setting position of the target snapshot area in the collection area, and does not require manual adjustment, which can adapt to diversified actual scene requirements. At the same time, the above scheme can also improve the efficiency and success of target identification in the target snapshot area, and to a certain extent, reduce the cost required for system maintenance.

Description

Technical Field

[0001] This application relates to the field of machine vision technology, and in particular to a method, apparatus, electronic device and medium for adjusting the target capture area. Background Technology

[0002] In existing capture cameras, the capture area often needs to be manually drawn and delineated. For example, the capture area of ​​a license plate capture camera needs to be manually drawn and delineated based on the real-time image from the camera. Once the license plate recognition area is determined, it remains fixed and cannot be automatically adjusted or optimized according to environmental conditions. Furthermore, each adjustment of the capture area requires manual operation, which cannot guarantee accuracy on every occasion, making the process tedious, complex, and inefficient. Summary of the Invention

[0003] This application provides a method, device, electronic device, and medium for adjusting a target capture area, which solves the technical problems of low efficiency and inaccuracy caused by relying solely on manual adjustment of the target capture area. It enables flexible and automatic adjustment of the target capture area setting position based on target analysis results from different dimensions, adapting to diverse actual scenario needs and greatly improving adjustment efficiency and flexibility.

[0004] According to a first aspect of this application, a method for adjusting a target capture area is provided, the method comprising:

[0005] For a target capture area set in the acquisition area, identify the target appearing in the target capture area; wherein, the acquisition area is the image captured by the image acquisition device from the channel entering the set area;

[0006] The target identification results are analyzed to determine the target analysis results; wherein, the target identification results include at least one of the following: the number of targets, whether the targets have entered the set area, and the target identification accuracy.

[0007] The target capture area is adjusted based on the target analysis results.

[0008] According to a second aspect of this application, a target capture area adjustment device is provided, the device comprising:

[0009] The target recognition module is used to identify targets appearing in the target capture area set in the acquisition area; wherein, the acquisition area is the image captured by the image acquisition device from the channel entering the set area;

[0010] The target analysis result determination module is used to analyze the target identification results and determine the target analysis results; wherein, the target identification results include at least one of the following: the number of targets, whether the targets have entered the set area, and the target identification accuracy;

[0011] The target capture area adjustment module is used to adjust the target capture area based on the target analysis results.

[0012] According to a third aspect of this application, an electronic device is provided, the electronic device comprising:

[0013] At least one processor; and

[0014] A memory that is adjusted and connected to at least one processor target capture area; wherein...

[0015] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to perform the target capture area adjustment method of any embodiment of this application.

[0016] According to a fourth aspect of this application, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute and implement the target capture area adjustment method of any embodiment of this application.

[0017] The technical solution of this application embodiment identifies targets appearing in a target capture area set within a collection area. The collection area is the image captured by the image acquisition device from a channel entering the designated area. The target identification results are analyzed to determine the target analysis results. The target capture area is then adjusted based on the target analysis results. This solution can flexibly and automatically adjust the target capture area based on target analysis results from different dimensions, automatically optimizing the setting position of the target capture area within the collection area without manual adjustment, thus adapting to diverse real-world scenario requirements. Furthermore, this solution improves the efficiency and success rate of target identification within the target capture area, reducing system maintenance costs to some extent.

[0018] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 A flowchart illustrating a method for adjusting a target capture area provided in an embodiment of this application;

[0021] Figure 2 This is a schematic diagram of a target capture area set in a data acquisition area, provided in an embodiment of this application.

[0022] Figure 3 A flowchart illustrating another method for adjusting the target capture area provided in this application embodiment;

[0023] Figure 4a A schematic diagram of a preset boundary when a target enters a designated area, provided as an embodiment of this application;

[0024] Figure 4b A schematic diagram of a preset boundary when a target enters a designated area, provided as an embodiment of this application;

[0025] Figure 5 A schematic diagram illustrating the distribution of a first motion region and a second motion region within a target capture area, provided in an embodiment of this application;

[0026] Figure 6 A flowchart illustrating another method for adjusting the target capture area provided in this application embodiment;

[0027] Figure 7a This is a schematic diagram of a ray effect formed within a target capture area, provided in an embodiment of this application.

[0028] Figure 7b This is a schematic diagram of another ray effect formed within the target capture area provided in an embodiment of this application;

[0029] Figure 7c A schematic diagram illustrating a scenario where two other endpoints are taken from each of the two rays, as provided in this application embodiment;

[0030] Figure 8 A flowchart illustrating another method for adjusting the target capture area provided in this application embodiment;

[0031] Figure 9 This is a schematic diagram of the structure of a target capture area adjustment device provided in an embodiment of this application;

[0032] Figure 10This is a schematic diagram of the structure of an electronic device for implementing a target capture area adjustment method, provided in an embodiment of this application. Detailed Implementation

[0033] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0034] It should be noted that the terms "first," "second," "third," "fourth," "actual," "preset," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0035] Figure 1 This flowchart illustrates a method for adjusting a target capture area according to an embodiment of this application. This embodiment is applicable to situations where a capture area set within a data acquisition area needs adjustment. The method can be executed by a target capture area adjustment device, which can be implemented in hardware and / or software. This device can be configured in an electronic device and is generally integrated into any electronic device with network communication capabilities, such as a mobile terminal, PC, or server. Figure 1 As shown, the method in this embodiment of the application specifically includes the following steps:

[0036] S110. For the target capture area set in the acquisition area, identify the target appearing in the target capture area; wherein, the acquisition area is the image captured by the image acquisition device from the channel entering the set area.

[0037] The acquisition area can be the acquisition area within the image acquisition interface of the image acquisition device, or it can be understood as the field of view within the image acquisition interface of the image acquisition device. The target capture area is the capture area set within the acquisition area. The target capture area is generally a portion of the acquisition area, not the entire area. Only the content entering the target capture area is captured and analyzed to avoid unnecessary image acquisition processes. If necessary, it can also be set to the entire acquisition area. The target capture area can be pre-set within any range of the acquisition area; the resulting value is the initially set target capture area. Figure 2 This is a schematic diagram of a target capture area set in a data acquisition area, as provided in an embodiment of this application. Figure 2 As shown, the area set within the acquisition area is the target capture area.

[0038] The acquisition area is what the image acquisition device displays when it captures images of a channel entering the designated area. The designated area refers to a pre-defined region within the actual scene; for example, it could be a parking lot or a residential area. The channel within the designated area is the passageway used to enter or leave that area. For example, if the image acquisition device is a camera, the designated area is a parking lot, and the channel is the parking lot entrance, then the acquisition area would be the area captured by the camera at the parking lot entrance. The image acquisition device can be positioned directly facing the direction the target is approaching from the channel within the designated area, or it can be positioned to the left or right of the channel, directly facing the direction the target is perpendicular to the designated area.

[0039] Specifically, for the target capture area set within the acquisition area, targets appearing within the target capture area can be identified. Here, "target" refers to the object to be analyzed. Targets can refer to the same type of object, and multiple targets may be identified within the target capture area. For example, a target can be a vehicle or a pedestrian. Alternatively, a target can be various identified vehicles; each vehicle is considered a target. If multiple vehicles appear within the target capture area, multiple targets can be identified.

[0040] S120. Analyze the target identification results to determine the target analysis results. The target identification results include at least one of the following: the number of targets, whether the targets have entered the designated area, and the target identification accuracy.

[0041] In real-world scenarios, while the target capture area can be pre-set in the data acquisition area, this setup may not be suitable for the actual scenario due to a lack of testing. Adjustments may be necessary. Alternatively, changes in the actual scenario may necessitate adjustments to the pre-set target capture area. In these cases, analyzing the data obtained from the pre-set target capture area is crucial to determining whether and how to adjust it.

[0042] The target analysis results can reflect the capture effect corresponding to the target capture area set at this time, and can be used to adjust the target capture area.

[0043] Specifically, in the process of identifying targets from the target capture area, the number of targets can be identified and analyzed. For example, it can be analyzed how many targets can be identified in the target capture area, whether the number of identified targets is reasonable, etc., so as to determine the target analysis results based on the number of identified targets.

[0044] During the process of identifying targets from the target capture area, it is also possible to identify and analyze whether the target has entered the set area. For example, it can be analyzed whether the target has entered the set area or not, thereby determining whether the target capture area set at this time can capture the relevant target that has entered the set area.

[0045] During the process of identifying targets from the target capture area, the identification results can also be analyzed. For example, after the target is identified, it can be determined whether the identification result is accurate.

[0046] It's important to note that the number of targets, whether a target enters the designated area, and the target identification result are essentially analyzed from three different dimensions. When identifying and analyzing targets appearing in the target capture area, at least one of these three dimensions can be analyzed. For example, one dimension can be analyzed; or two dimensions can be analyzed; or all three dimensions can be analyzed. In other words, the target identification result is analyzed to determine the target analysis result.

[0047] S130. Adjust the target capture area based on the target analysis results.

[0048] Once the target analysis results are determined, the capture effect of the target capture area can be determined. The target capture area can then be adjusted based on the target analysis results. Specifically, the coordinate information of the target capture area to be adjusted can be sent to the image acquisition device, and the position of the target capture area can be adjusted so that the adjusted target capture area can meet the needs of the actual scene.

[0049] It should be noted that the adjustment of the target capture area in this embodiment can be a periodic adjustment or an adjustment triggered only when the triggering condition is met.

[0050] The technical solution of this application embodiment identifies targets appearing in a target capture area set within a collection area. The collection area is the image captured by the image acquisition device from a channel entering the designated area. The target identification results are analyzed to determine the target analysis results. The target capture area is then adjusted based on the target analysis results. This solution can flexibly and automatically adjust the target capture area based on target analysis results from different dimensions, automatically optimizing the setting position of the target capture area within the collection area without manual adjustment, thus adapting to diverse real-world scenario requirements. Furthermore, this solution improves the efficiency and success rate of target identification within the target capture area, reducing system maintenance costs to some extent.

[0051] Figure 3 This is a flowchart of another target capture area adjustment method provided in this application embodiment. Based on the technical solutions of the above embodiments, this embodiment further optimizes the process of determining the target analysis result by analyzing whether the target enters a set area, and adjusting the target capture area according to the target analysis result. This embodiment can be combined with various optional solutions in one or more of the above embodiments. Solutions not described in detail in this application embodiment are found in the above embodiments. Figure 3 As shown, the method in this embodiment of the application specifically includes the following steps:

[0052] S310. For the target capture area set in the acquisition area, identify the target appearing in the target capture area; wherein, the acquisition area is the image captured by the image acquisition device from the channel entering the set area.

[0053] S320, Identify the targets that have entered the designated area and the targets that have not entered the designated area.

[0054] Among them, "entering targets" refers to targets that have entered the designated area, and "non-entering targets" refers to targets that have not entered the designated area.

[0055] Specifically, the determination of whether a target has entered or not can be based on relevant detection devices in the actual scene to determine whether the target has entered the set area, or it can be based on the movement of the target captured in the target capture area to determine whether the target has entered the set area.

[0056] As an optional but non-limiting implementation, determining the targets that have entered the designated area and the targets that have not entered the designated area may include the following steps A1-A3:

[0057] Step A1: Track the appearing target using a detection device to determine the target's detection trajectory; wherein, the detection device is used to detect the entrance of the designated area.

[0058] The detection device can be used to detect the entrance of a designated area, including detecting whether a target is present at the entrance and detecting the target's movement trajectory. The detection device can be a radar detector, an infrared detector, or an inductive loop detector, etc. The detection trajectory reflects the target's movement in the real-world scene.

[0059] Specifically, if the detection device detects a target at the entrance of the designated area, it will continue to track the target and determine its detection trajectory. If the target's detection trajectory is determined, it means that the target has entered the designated area in the actual scene; if the target's detection trajectory is not determined, it means that the target has not entered the designated area in the actual scene. The target's detection trajectory can be determined by at least one detection device installed within the designated area.

[0060] It should be noted that although the detection device can determine the detection trajectory of a target, it cannot determine which specific target object the trajectory corresponds to; the detection trajectory has not yet established a correlation with its associated target. For example, it cannot determine whether the currently obtained detection trajectory is the trajectory of target 1 or target 2.

[0061] Step A2: For each target, the target's identification trajectory and detection trajectory in the target capture area are compared to determine the same target.

[0062] The recognition trajectory consists of at least one recognition point for the same target identified within the target capture area. Essentially, the recognition trajectory reflects the movement of the same target within the target capture area. Specifically, based on the first captured area, the first recognition point when the target is detected in the first captured area can be determined; based on the second captured area, the second recognition point when the target is detected in the second captured area can be determined. Each recognition point has its own corresponding coordinate information, and so on. Based on at least one continuously captured area by the image acquisition device, at least one recognition point for the same target can be determined, and the target's recognition trajectory can be determined based on this at least one recognition point.

[0063] It should be noted that there may be multiple target identification trajectories determined based on at least one continuously acquired image of the acquisition area; that is, multiple target-specific identification trajectories may be identified. Similarly, the detection trajectory determined by the detection device may also be the detection trajectory of multiple targets. However, no corresponding relationship is established between the targets in these two types of trajectories, although the identification trajectories can identify the target object. Therefore, the target's identification trajectory can be compared with the detection trajectory to identify the same target. In other words, the identification trajectory and detection trajectory belonging to the same target are associated.

[0064] Specifically, during the collision between the target's identification trajectory and the detection trajectory, if the degree of overlap between the identification trajectory and the detection trajectory exceeds a set threshold, then the identification trajectory and the detection trajectory are considered to correspond to the same target.

[0065] Step A3: Determine the approaching and non-approaching targets based on the relative position of the target's detection trajectory and the set area.

[0066] The relative positional relationship includes: the detection trajectory is located within the set area, or the detection trajectory is located outside the set area, or part of the detection trajectory is located within the set area and part of the detection trajectory is located outside the set area. If part of the detection trajectory is located within the set area and part of the detection trajectory is located outside the set area, it indicates that the target has entered the set area.

[0067] By using the above method, the detection trajectory obtained by the detection device is compared with the target's identification trajectory to determine the target to which the detection trajectory belongs. Then, based on the detection trajectory, the approaching target and the non-approaching target can be determined, ensuring the authenticity and accuracy of the results.

[0068] As an alternative but non-limiting implementation, determining the targets entering the designated area and the targets not entering the designated area may further include the following steps B1-B3:

[0069] Step B1: Based on the target's identification trajectory in the target capture area, determine the boundary that the target passes through when leaving the target capture area.

[0070] The boundary of the target capture area is defined as the boundary through which the target leaves the target capture area. This boundary is the closest to the point where the target last appeared within the target capture area. For example, consider the following: Figure 4a As shown, if the latest point where the target appears in the target capture area is point A, then the target is determined to have passed through the left boundary when it leaves. If the latest point where the target appears in the target capture area is point B, then the target is determined to have passed through the lower boundary when it leaves.

[0071] Specifically, based on the target's identification trajectory and related time information, the target's entry and exit directions within the target capture area can be determined. Furthermore, based on the target's identification trajectory and exit direction within the target capture area, the boundary that the target traverses when leaving the target capture area can be determined.

[0072] Step B2: If the boundary belongs to the preset boundary, then the target is determined to be an inbound target; wherein, the preset boundary is the boundary that the target passes through when it leaves the target capture area after entering the set area.

[0073] The preset boundary is used to reflect the boundary traversed by the trajectory of a target entering the designated area in a real-world scenario as it leaves the target capture area. For example, Figure 4a This application provides a schematic diagram of a preset boundary when a target enters a designated area, as shown in the embodiment of the present application. Figure 4a As shown in the diagram, the arrows indicate the direction of entry into the designated area in the actual scene. The image capture device is positioned directly opposite this entry direction, so the preset boundary can be set at the lower boundary of the target capture area. Figure 4a In the process of the target entering the set area, if the path in the target capture area is to exit from the lower boundary, then the lower boundary is the preset boundary.

[0074] For example, Figure 4b Another schematic diagram of the preset boundary of a target entering a designated area, provided in an embodiment of this application, is shown below. Figure 4b As shown in the diagram, the arrows point in the direction of entry into the designated area in the actual scene. The image capture device is positioned directly opposite the direction of entry, perpendicular to the direction of entry. Therefore, the preset boundary can be set to the left of the target capture area. Figure 4b In the process of the target entering the set area, if the path in the target capture area is to exit from the left boundary, then the left boundary is the preset boundary.

[0075] It should be noted that the setting of the preset boundary needs to be determined based on the direction of entry into the set area and the position of the image acquisition device.

[0076] Specifically, if it is determined that the boundary crossed by the target leaving the target capture area belongs to a preset boundary, then the target is determined to be an incoming target.

[0077] Step B3: Otherwise, determine the target as an unentered target.

[0078] If it is determined that the boundary crossed by the target as it leaves the target capture area does not belong to the preset boundary, then the target is determined to be a target that has not entered the field. For example, with Figure 4a For example, if the boundary crossed by the target as it leaves the target capture area is determined to be the left boundary of the target capture area, it does not belong to... Figure 4a The preset boundary at the bottom center indicates that the target is a non-entry target and has not entered the set area.

[0079] Using the above method, it is only necessary to determine whether a target has entered the field or not based on the target's identification trajectory and the preset boundary. If it is an entering target, the boundary that the target passes through when leaving the target capture area must belong to the preset boundary; otherwise, it is a non-entering target. The above method can more conveniently and quickly determine whether a target has entered the field, and is more efficient.

[0080] S330. Adjust the target capture area based on the first movement area of ​​the incoming target within the target capture area and the second movement area of ​​the non-incoming target within the target capture area.

[0081] The first motion area reflects the area covered by the entire movement of an approaching target within the target capture area. The second motion area reflects the area covered by the entire movement of a non-approaching target within the target capture area.

[0082] Specifically, regarding the initially set target capture area, in real-world scenarios, when capturing images based on this target capture area, the captured footage may not only capture the movement of entering targets but also the movement of targets that have not yet entered the area. For example, a camera at a parking lot entrance may capture the movement of vehicles in the entrance lane, as well as the surrounding green belts or flower beds on both sides of the entrance. If vehicles are also moving in the vicinity of these green belts or flower beds, their movement will also be captured in the footage. It is evident that in such real-world scenarios, the capture field of view is excessively large; that is, the initially set target capture area is too large, encompassing not only the desired targets but also those that are not. Clearly, such a target capture range is unreasonable, as capturing and analyzing unnecessary targets leads to a waste of capture and computing resources.

[0083] To address this, the target capture area can be adjusted based on the first motion area of ​​the approaching target within the target capture area and the second motion area of ​​the non-approaching target within the target capture area. The aim is to remove the second motion area within the target capture area, thereby reducing the size of the target capture area and minimizing unnecessary captures of non-approaching targets.

[0084] As an optional but non-limiting implementation, adjusting the target capture area based on the first motion area of ​​the approaching target within the target capture area and the second motion area of ​​the non-approaching target within the target capture area may include the following steps C1-C3:

[0085] Step C1: Cluster the points of the incoming target in the target capture area to obtain the first motion area.

[0086] The location of a point is the position of the target when it is detected in the target capture area. The location of a point can be coordinate information.

[0087] Specifically, when a target is identified, its location can be determined using a pre-defined fixed point. This pre-defined fixed point can be the target's center point, or its left or right vertices, etc. For example, using a license plate as the target, the center point of the license plate at each location can be used as the target's position, or the left vertices of the license plate at each location can be used as the target's position. It should be noted that for the same target, the same rules should be followed when determining the target's position at different locations.

[0088] When identifying an approaching target within the target capture area, at least one point will be identified over time. These points, when aggregated, reflect the movement range of the approaching target within the target capture area. Specifically, a pre-defined clustering algorithm can be used to cluster the points of the approaching target within the target capture area. This algorithm could be DBSCAN, OPTICS, or similar algorithms. After clustering the points of the approaching target, the first movement area can be obtained.

[0089] It should be noted that the clustering of points related to the approaching targets involves clustering the points corresponding to at least two approaching targets. In other words, clustering can be performed on the points corresponding to at least two approaching targets, aiming to ensure that the resulting first movement area can cover as many points related to the approaching targets as possible.

[0090] Step C2: Cluster the points of the non-entering target in the target capture area to obtain the second motion area.

[0091] Using the same clustering principle, a preset clustering algorithm can be used to cluster the points of at least two non-entering targets within the target capture area to obtain the second motion area. For specific principles and details, please refer to the relevant descriptions above; they will not be elaborated upon here.

[0092] It should be noted that in the process of clustering the points related to the non-entry targets, the points corresponding to at least two non-entry targets are also clustered. The aim is to ensure that the second movement area obtained after clustering can cover as many points related to the non-entry targets as possible.

[0093] Step C3: Determine the complement region of the first motion region in the second motion region, remove the complement region in the target capture region, or the complement region and the region extending from the complement region to the boundary of the target capture region away from the set region.

[0094] Among them, the complement region of the first motion region in the second motion region essentially reflects the motion region that the target that has not yet entered the field actually corresponds to. Because there may be overlapping areas between the first motion region and the second motion region, useful information related to the target that has entered the field can still be captured in the overlapping areas. Therefore, the second motion region cannot be removed directly. Instead, the overlapping areas should be considered before removing the relevant areas.

[0095] Specifically, we can first determine the overlapping region between the first and second motion regions, and then remove the overlapping region from the second motion region to obtain the complement region of the first motion region within the second motion region. For example, Figure 5This application provides a schematic diagram illustrating the distribution of a first motion region and a second motion region within a target capture area, as shown in the embodiments of this application. Figure 5 As shown, within the target capture area, the region formed by S1 and S2 is the first motion region. The region formed by S2 and S3 is the second motion region. Calculations show that the overlapping area between the first and second motion regions is S2. Subtracting the overlapping area S2 from the second motion region yields the complement region of the first motion region within the second motion region, which is region S3 in the diagram. It is evident that the overlapping area S2 still captures useful information related to the approaching target, while only region S3 truly corresponds to the motion region of the non-approaching target.

[0096] After determining the complement region of the first motion region in the second motion region, the complement region can be removed from the target capture region to remove the areas in the target capture region that do not need to be captured, thereby reducing the size of the target capture region.

[0097] Alternatively, the complement region and the region extending from the complement region towards the boundary of the target capture area can be removed from the target capture area. The "side away from the set area" can be set based on actual needs; it can be set to the left, right, upper, or lower side of the set area. It should be noted that the setting of the side away from the set area is related to the orientation of the image acquisition device in the actual scene, aiming to remove unnecessary capture areas at the edges of the target capture area.

[0098] Specifically, the area extending from the supplementary capture area towards the boundary of the target capture area essentially reflects the more peripheral areas within the target capture area that are related to the supplementary capture area. If useful information related to the approaching target can no longer be captured within the supplementary capture area, then the more peripheral areas related to the supplementary capture area are even less likely to capture useful information related to the approaching target. This removal scheme not only removes the supplementary capture area but also removes, to a certain extent, unnecessary capture areas at the more peripheral edges of the target capture area.

[0099] For example, continue as follows Figure 5 As shown, when removing areas within the target capture area, one approach is to remove the complement region S3. Another approach is to not only remove the complement region S3, but also remove the area formed by extending from S3 upwards away from the set area to the boundary of the target capture area, thus achieving a reduction in the target capture area.

[0100] The technical solution of this application embodiment identifies targets appearing in a target capture area set within a collection area; determines entering targets that have entered the set area and non-entering targets that have not entered the set area; and adjusts the target capture area based on the first motion area of ​​the entering target within the target capture area and the second motion area of ​​the non-entering target within the target capture area. The above solution analyzes whether a target has entered the set area, particularly determining the second motion area corresponding to non-entering targets, and adjusting the target identification capture area based on the second motion area. This achieves a reduction in the target capture area, thereby reducing unnecessary captures of non-entering targets. To a certain extent, this avoids the waste of capture resources and computing power, making the automatic adjustment of the target capture area more flexible and better suited to the needs of actual scenarios.

[0101] Figure 6 This is a flowchart illustrating another target capture area adjustment method provided in this application embodiment. Based on the technical solutions of the above embodiments, this embodiment further optimizes the process of analyzing the target identification results to determine the target analysis results and adjusting the target capture area according to the target analysis results. This embodiment can be combined with various optional solutions in one or more of the above embodiments. Solutions not described in detail in this application embodiment are found in the above embodiments. Figure 6 As shown, the method in this embodiment of the application specifically includes the following steps:

[0102] S610. For the target capture area set in the acquisition area, identify the target appearing in the target capture area; wherein, the acquisition area is the image captured by the image acquisition device from the channel entering the set area.

[0103] S620. If the feature recognition result of the target is inaccurate, then based on the target's recognition trajectory in the target capture area, predict the additional movement area of ​​the target outside the target capture area in the acquisition area.

[0104] During the feature recognition process of a target within a capture area, inaccurate recognition results may occur. For example, taking a vehicle as an example, if the initial target capture area is set too small, the captured image of the vehicle within that area will be incomplete, resulting in very few vehicle features that can be identified. Consequently, relevant vehicle features (such as vehicle color, height, and width) may not be recognized, leading to inaccurate recognition results. Such situations are clearly caused by setting the target capture area too small, resulting in insufficient target feature information to be captured, leading to inaccurate feature recognition results. Therefore, if the feature recognition results are inaccurate, it is necessary to consider adjusting the target capture area. It should be noted that the feature recognition results can be manually reviewed and judged to determine their accuracy.

[0105] Specifically, if the feature recognition result of the target is inaccurate, an additional movement area of ​​the target outside the target capture area can be predicted based on the target's recognition trajectory within the target capture area. This additional movement area is still within the capture area and still contains the target's motion information. Specifically, the additional movement area can be determined based on the target's movement trajectory in other areas outside the target capture area within the capture area.

[0106] As an optional but non-limiting implementation, predicting additional motion areas of the target outside the target capture area within the acquisition area based on the target's recognition trajectory in the target capture area may include the following steps D1-D4:

[0107] Step D1: For each target, determine the critical coordinates of the target in the target capture area, as well as the intermediate coordinates of the features that can identify the target; wherein, the critical coordinates include the coordinates of the first time the target is detected in the target capture area or the coordinates of the last time the target is detected in the target capture area.

[0108] The critical coordinates reflect the two most specific coordinates during target detection within the target capture area: the coordinates at the first and last time a target is detected. At adjacent coordinates, only the presence of a target within the capture area is noted, but its features may not yet be identified. The intermediate coordinates represent the coordinates at which target features are identified during the target capture area identification process. It should be noted that as long as target features are identified within the capture area, these specific coordinates can serve as intermediate coordinates; that is, there can be at least one intermediate coordinate.

[0109] It should be noted that critical coordinates and intermediate coordinates essentially reflect the coordinates at key time points during the target identification process within the target capture area. For each target within the target capture area, its corresponding critical coordinates and intermediate coordinates can be determined.

[0110] Step D2: Connect the critical coordinates with the intermediate coordinates as the endpoints to form a ray.

[0111] Specifically, for the same target, a ray can be formed by connecting the target's intermediate coordinates to its critical coordinates. By performing the same operation on each target, multiple rays can be created.

[0112] For example, Figure 7a This is a schematic diagram of a ray effect formed within a target capture area provided in an embodiment of this application, as shown below. Figure 7a As shown, Figure 7a The diagram shows the critical coordinates of each target, which are the coordinates at the moment the target is first detected in the target capture area. Specifically, points q1, q2, and q3 are the critical coordinates at the moment each target is first detected in the target capture area, and points p1, p2, and p3 are the intermediate coordinates corresponding to each target. It can be seen that ray L1 can be formed based on points p1 and q1, ray L2 can be formed based on points p2 and q2, and ray L3 can be formed based on points p3 and q3, with each ray corresponding to a different target.

[0113] For example, Figure 7b This is a schematic diagram of another ray effect formed within the target capture area provided in an embodiment of this application, such as... Figure 7b As shown, Figure 7b The diagram shows the critical coordinates of each target, which are the coordinates of the last time the target was detected in the target capture area. Specifically, points q4, q5, and q6 are the critical coordinates of the last time each target was detected in the target capture area, while points p4, p5, and p6 are the corresponding intermediate coordinates of each target. It can be seen that ray L4 can be formed based on points p4 and q4, ray L5 can be formed based on points p5 and q5, and ray L6 can be formed based on points p6 and q6, with each ray corresponding to a different target.

[0114] Step D3: For the two rays with the largest included angle between the lines corresponding to each target, take the other endpoint on the ray so that the other endpoint is outside the target capture area and the distance from the intersection of the ray and the boundary of the target capture area is a preset distance.

[0115] Specifically, for each ray, the two rays whose included angle is the largest are identified by the straight lines containing each ray. Another endpoint is taken from each of these two rays, ensuring that both endpoints are outside the target capture area. Simultaneously, the distances between these two endpoints and the intersection points of their respective rays with the boundary of the target capture area are preset distances. These preset distances can be set based on actual needs, and are less than or equal to the distance between the boundary of the target capture area and the boundary of the acquisition area along the ray's extension direction.

[0116] For example, with Figure 7a The following explanation uses the formation of various rays as an example. Figure 7c This application provides a schematic diagram illustrating a scenario where two endpoints are taken from each of the two rays, according to an embodiment of the present application. Figure 7c Corresponding to Figure 7a The situation of each ray in the middle. For example... Figure 7c As shown, for each ray's line, the angle between rays L1 and L3 is the largest. Therefore, we take two endpoints, m1 and m3, on rays L1 and L3 respectively. The intersection of ray L1 and the boundary of the target capture area is n1, and the intersection of ray L3 and the boundary of the target capture area is n3. When choosing the two endpoints m1 and m3, it is necessary to ensure that the distance between m1 and n1 is a preset distance, and the distance between m3 and n3 is also a preset distance. Essentially, this means ensuring that neither of the selected endpoints exceeds the range of the capture area and that they are located outside the target capture area to expand the target capture area.

[0117] Step D4: The line connecting the two other endpoints, the boundary between the two rays in the target capture area, and the area formed by the two rays are taken as the additional motion area.

[0118] Specifically, continue as follows Figure 7c As shown, the line connecting the two endpoints m1 and m3 in the diagram, the boundary between the two rays in the target capture area, and the area formed by the two rays are considered as the additional motion area. Figure 7c The region formed between midpoint m1, point m3, point n1, and point n3 is the extra motion region.

[0119] S630 adds an extra motion area to the target capture area.

[0120] Once the additional motion area is identified, it can be added to the target capture area to expand and adjust the target capture area.

[0121] It should be noted that, for Figure 7b The principle of determining the additional motion region based on the formation of various rays is the same as the principle described above, and will not be elaborated on here.

[0122] The technical solution of this application embodiment identifies targets appearing in the target capture area within the acquisition area. If the identification result of the target feature recognition is inaccurate, it predicts additional movement areas of the target outside the target capture area in the acquisition area based on the target's identification trajectory within the target capture area, and then adds these additional movement areas to the target capture area. This solution analyzes the target identification result to determine additional movement areas located outside the target capture area but still within the acquisition area. Since useful information related to the approaching target can also be captured in these additional movement areas, adding them to the target capture area expands and adjusts the target capture area, thereby achieving a wider range of target capture. This makes the automatic adjustment of the target capture area more flexible and better suited to the needs of actual scenarios.

[0123] Figure 8 This is a flowchart illustrating another target capture area adjustment method provided in this application embodiment. Based on the technical solutions of the above embodiments, this embodiment further optimizes the process of analyzing the number of targets to determine the target analysis results and adjusting the target capture area according to the target analysis results. This embodiment can be combined with various optional solutions in one or more of the above embodiments. Solutions not described in detail in this application embodiment are found in the above embodiments. Figure 8 As shown, the method in this embodiment of the application specifically includes the following steps:

[0124] S810: Identify the target appearing in the target capture area set in the acquisition area; wherein, the acquisition area is the image captured by the image acquisition device from the channel entering the set area.

[0125] S820. If the number of targets is less than the preset number, the target capture area is used as the traversal unit, the preset traversal step size is set, and the position traversal is performed with the vertex of the capture area as the starting point.

[0126] During the target identification process within the target capture area, the number of targets within that area can be counted. If the number of targets is less than the preset number, it indicates that the currently set target capture area can record too few targets, possibly due to an unreasonable setting of the target capture area's position. For example, if the target capture area is set in the bottom right corner of the entire acquisition area, it will not be directly facing all the channels of the set area, but will only capture a small portion of the channels. In such cases, the initial setting of the target capture area is clearly unreasonable and needs to be adjusted to a more suitable position.

[0127] Specifically, the target capture area can be used as the traversal unit, a preset traversal step size can be set, and the position can be traversed according to a preset traversal order, starting from the vertex of the capture area. The preset traversal step size is a pre-defined unit length that the traversal unit moves each time during the traversal. The preset traversal order includes a preset horizontal traversal order and a preset vertical traversal order. For example, it could start from the left vertex of the capture area and move the traversal unit from left to right and from top to bottom.

[0128] S830. If the number of targets detected in the target capture area is greater than or equal to the preset number when the target capture area is currently being traversed, then the current traversed position is set as the target capture area position.

[0129] During the traversal process, as the traversal unit moves, if the number of targets detected in the target capture area at the current traversal position is greater than or equal to the preset number, it means that a sufficient number of targets can be identified in the target capture area at the current position. Therefore, it is reasonable to set the target capture area at this position. Thus, the current traversal position can be used as the setting position of the target capture area to adjust the target capture area so that the adjusted target capture area is located at the setting position.

[0130] The technical solution of this application embodiment identifies targets appearing in a target capture area set in the acquisition area. If the number of targets is less than a preset number, the target capture area is used as a traversal unit, a preset traversal step size is set, and position traversal is performed starting from the vertex of the acquisition area. If the number of targets detected in the target capture area at the current traversal position is greater than or equal to the preset number, the current traversal position is used as the setting position of the target capture area to adjust the target capture area. The above solution analyzes from the dimension of the number of identified targets. When it is determined that the number of targets that can be identified in the target capture area is too small, the target capture area is used as a traversal unit to determine the setting position corresponding to the number of targets that can be identified. Based on the setting position, the target capture area is adjusted, realizing the automatic adjustment of the position of the target capture area in the acquisition area, so that the target capture area is in a more reasonable position and better meets the needs of the actual scene.

[0131] Figure 9 This is a schematic diagram of a target capture area adjustment device provided in an embodiment of this application. This device can execute the target capture area adjustment method provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects for executing the method. Figure 9As shown, the target capture area adjustment device includes a target recognition module 910, a target analysis result determination module 920, and a target capture area adjustment module 930, wherein:

[0132] The target recognition module 910 is used to identify targets appearing in the target capture area set in the acquisition area; wherein, the acquisition area is the image captured by the image acquisition device from the channel entering the set area;

[0133] The target analysis result determination module 920 is used to analyze the target identification results and determine the target analysis results; wherein, the target identification results include at least one of the following: the number of targets, whether the targets have entered the set area, and the target identification accuracy;

[0134] The target capture area adjustment module 930 is used to adjust the target capture area based on the target analysis results.

[0135] As an optional but non-limiting implementation, if the target analysis result is determined by analyzing whether the target has entered the set area, then the target capture area adjustment module 930 includes:

[0136] The target entry determination submodule is used to determine the targets that have entered the set area and the targets that have not entered the set area.

[0137] The first target capture area adjustment submodule is used to adjust the target capture area based on the first movement area of ​​the approaching target in the target capture area and the second movement area of ​​the non-approaching target in the target capture area.

[0138] As an optional but non-limiting implementation, the target entry / exit determination submodule is specifically used for: tracking emerging targets using a detection device to determine the target's detection trajectory; wherein the detection device is used to detect the entrance of the designated area; for each target, colliding the target's identification trajectory in the target capture area with the detection trajectory to determine the same target; determining the entering target and the non-entering target based on the relative positional relationship between the target's detection trajectory and the designated area; or, determining the boundary that the target passes through when leaving the target capture area based on the target's identification trajectory in the target capture area; if the boundary belongs to a preset boundary, then the target is determined to be the entering target; wherein the preset boundary is a pre-determined boundary that the target passing through when leaving the target capture area after entering the designated area; otherwise, the target is determined to be the non-entering target.

[0139] As an optional but non-limiting implementation, the first target capture area adjustment submodule is specifically used for: clustering the points of the approaching target in the target capture area to obtain the first motion area; clustering the points of the non-approaching target in the target capture area to obtain the second motion area; determining the complement region of the first motion area in the second motion area; removing the complement region from the target capture area, or the complement region and the area extending from the complement region away from the set area to the boundary of the target capture area.

[0140] As an optional but non-limiting implementation, if the target identification result is analyzed to determine the target analysis result, then the target capture area adjustment module 930 includes:

[0141] The additional motion area determination submodule is used to predict the additional motion area of ​​the target outside the target capture area in the acquisition area based on the recognition trajectory of the target in the target capture area if the recognition result of feature recognition of the target is inaccurate.

[0142] The second target capture area adjustment submodule is used to supplement the additional motion area into the target capture area.

[0143] As an optional but non-limiting implementation, the additional motion region determination submodule is specifically used for: determining, for each target, the critical coordinates of the target in the target capture area, and the intermediate coordinates that enable the identification of the target's features; wherein, the critical coordinates include the coordinates of the first detection of the target in the target capture area or the coordinates of the last detection of the target in the target capture area; connecting the critical coordinates with the intermediate coordinates as endpoints to form a ray; for the two rays corresponding to each target whose straight lines have the largest included angle, taking another endpoint on the ray, such that the other endpoint is located outside the target capture area, and the distance from the intersection of the ray and the boundary of the target capture area is a preset distance; and using the line connecting the two other endpoints, the boundary between the two rays in the target capture area, and the area formed by the two rays as the additional motion region.

[0144] As an optional but non-limiting implementation, if the number of targets is analyzed to determine the target analysis result, then the target capture area adjustment module 930 includes:

[0145] The traversal submodule is used to perform position traversal by using the target capture area as the traversal unit, setting a preset traversal step size, and using the vertex of the acquisition area as the starting point if the number of targets is less than a preset number.

[0146] The setting position determination submodule is used to set the target capture area position if the number of targets detected in the target capture area at the current traversal position is greater than or equal to a preset number.

[0147] The technical solution of this application embodiment identifies targets appearing in a target capture area set within a collection area. The collection area is the image captured by the image acquisition device from a channel entering the designated area. The target identification results are analyzed to determine the target analysis results. The target capture area is then adjusted based on the target analysis results. This solution can flexibly and automatically adjust the target capture area based on target analysis results from different dimensions, automatically optimizing the setting position of the target capture area within the collection area without manual adjustment, thus adapting to diverse real-world scenario requirements. Furthermore, this solution improves the efficiency and success rate of target identification within the target capture area, reducing system maintenance costs to some extent.

[0148] The target capture area adjustment device provided in this application embodiment can execute the target capture area adjustment method provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects of the method execution.

[0149] Figure 10 This is a schematic diagram of an electronic device for implementing a target capture area adjustment method, provided as an embodiment of this application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present application described and / or claimed herein.

[0150] like Figure 10As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded into the RAM 13 from storage unit 18. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0151] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of monitors, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless target capture area adjustment transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0152] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the target capture area adjustment method.

[0153] In some embodiments, the target capture area adjustment method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the target capture area adjustment method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the target capture area adjustment method by any other suitable means (e.g., by means of firmware).

[0154] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0155] Computer programs used to implement the methods of this application may be written in any combination of one or more programming languages. These computer programs may be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable target capture area adjustment device, such that when executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0156] In the context of this application, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0157] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0158] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via communication of any form or medium (e.g., a target capture area adjustment network). Examples of target capture area adjustment networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0159] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0160] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired information of the technical solution of this application can be achieved, and this is not limited herein.

[0161] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for adjusting the target capture area, characterized in that, The method includes: For a target capture area set in the acquisition area, identify the target appearing in the target capture area; wherein, the acquisition area is the image captured by the image acquisition device from the channel entering the set area; The target identification results are analyzed to determine the target analysis results; wherein, the target identification results include at least one of the following: the number of targets, whether the targets have entered the set area, and the target identification accuracy. The target capture area is adjusted based on the target analysis results.

2. The method according to claim 1, characterized in that, If the target is analyzed to determine whether it has entered the designated area, the target capture area is adjusted based on the target analysis result, including: Identify the targets that have entered the designated area and the targets that have not entered the designated area. The target capture area is adjusted based on the first movement area of ​​the approaching target in the target capture area and the second movement area of ​​the non-approaching target in the target capture area.

3. The method according to claim 2, characterized in that, Identifying the targets that have entered the designated area and the targets that have not entered the designated area includes: The detection device tracks the appearing target and determines the target's detection trajectory; wherein, the detection device is used to detect the entrance of the designated area; For each of the aforementioned targets, the target identification trajectory in the target capture area is compared with the detection trajectory to identify the same target; The approaching target and the non-approaching target are determined based on the relative positional relationship between the target's detection trajectory and the designated area; or, Based on the target's identification trajectory within the target capture area, determine the boundary through which the target leaves the target capture area; If the boundary belongs to a preset boundary, then the target is determined to be the approaching target; wherein, the preset boundary is a pre-determined boundary that the target passing through when leaving the target capture area after entering the set area; Otherwise, the target is determined to be the non-entry target.

4. The method according to claim 2, characterized in that, Based on the first movement area of ​​the approaching target within the target capture area and the second movement area of ​​the non-approaching target within the target capture area, the target capture area is adjusted, including: Cluster the points of the approaching target in the target capture area to obtain the first motion area; Cluster the points of the non-entering targets in the target capture area to obtain the second motion area; Determine the supplementary area of ​​the first motion area in the second motion area, remove the supplementary area in the target capture area, or the supplementary area and the area extending from the supplementary area to the boundary of the target capture area away from the set area.

5. The method according to claim 1, characterized in that, If the target identification result is analyzed to determine the target analysis result, then the target capture area is adjusted according to the target analysis result, including: If the feature recognition result of the target is inaccurate, then based on the recognition trajectory of the target in the target capture area, predict the additional movement area of ​​the target outside the target capture area in the acquisition area; The additional motion area is added to the target capture area.

6. The method according to claim 5, characterized in that, Based on the target's identification trajectory within the target capture area, predict additional movement areas of the target outside the target capture area within the acquisition area, including: For each target, determine the critical coordinates of the target in the target capture area, and the intermediate coordinates of the features that can identify the target; wherein, the critical coordinates include the coordinates of the first time the target is detected in the target capture area or the coordinates of the last time the target is detected in the target capture area; A ray is formed by connecting the critical coordinates with the intermediate coordinates as endpoints; For the two rays corresponding to each target with the largest included angle between their lines, take another endpoint on the ray so that the other endpoint is located outside the target capture area and is at a preset distance from the intersection of the ray and the boundary of the target capture area; The line connecting the two other endpoints, the boundary between the two rays in the target capture area, and the area formed by the two rays are considered as an additional motion area.

7. The method according to claim 1, characterized in that, If the number of targets is analyzed to determine the target analysis results, then the target capture area is adjusted according to the target analysis results, including: If the number of targets is less than the preset number, the target capture area is used as the traversal unit, a preset traversal step size is set, and the position traversal is performed with the vertex of the acquisition area as the starting point. If the number of targets detected in the target capture area at the current traversal position is greater than or equal to a preset number, then the current traversal position is set as the target capture area setting position.

8. A target capture area adjustment device, characterized in that, The device includes: The target recognition module is used to identify targets appearing in the target capture area set in the acquisition area; wherein, the acquisition area is the image captured by the image acquisition device from the channel entering the set area; The target analysis result determination module is used to analyze the target identification results and determine the target analysis results; wherein, the target identification results include at least one of the following: the number of targets, whether the targets have entered the set area, and the target identification accuracy; The target capture area adjustment module is used to adjust the target capture area based on the target analysis results.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the target capture area adjustment method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the target capture area adjustment method according to any one of claims 1-7.

Images