Method and apparatus for determining gate state, electronic device, computer-readable medium

Abstract

The present disclosure provides a method and apparatus for determining the state of a gate, which specifically relates to technical fields such as big data, image recognition, and intelligent transportation. The specific implementation solution is as follows: Collect images of the gate to be recognized and its surroundings; Based on the image of the gate to be recognized, determine the structural type of the gate to be recognized and the opening width of the gate to be recognized; In response to the opening width not meeting the preset width value, based on the image of the surroundings of the gate to be recognized, detect whether the gate to be recognized meets the passing or blocking condition corresponding to the structural type; In response to detecting that the passing or blocking condition corresponding to the structural type is met, determine the first passing state of the gate to be recognized. This implementation method improves the accuracy of determining the state of the gate to be recognized.

Description

Technical Field

[0001] The present disclosure relates to the field of computer application technologies, specifically to technologies such as big data, image recognition, and intelligent transportation, and particularly to a method and apparatus for determining the state of a gate, an electronic device, a computer-readable medium, and a computer program product. Background Art

[0002] A gate is an element in map data, which affects the end-point guidance and route planning of map navigation; if the gate data fails to accurately depict the gate in the real world, it is likely to cause a relatively poor data search state, such as detouring or being guided to a different place in map data navigation. Summary of the Invention

[0003] A method and apparatus for determining the state of a gate, an electronic device, a computer-readable medium, and a computer program product are provided.

[0004] According to a first aspect, a method for determining the state of a gate is provided. The method includes: collecting an image of a gate to be recognized and its surroundings; determining the structural type and the opening width of the gate to be recognized based on the image of the gate to be recognized; in response to the opening width not satisfying a preset width value, detecting whether the gate to be recognized satisfies a passing or blocking condition corresponding to the structural type based on the image of the surroundings of the gate to be recognized; and in response to detecting that the passing or blocking condition corresponding to the structural type is satisfied, determining the first passing state of the gate to be recognized.

[0005] According to a second aspect, an apparatus for determining the state of a gate is provided. The apparatus includes: a collecting unit configured to collect an image of a gate to be recognized and its surroundings; a structure determining unit configured to determine the structural type and the opening width of the gate to be recognized based on the image of the gate to be recognized; a condition detecting unit configured to, in response to the opening width not satisfying a preset width value, detect whether the gate to be recognized satisfies a passing or blocking condition corresponding to the structural type based on the image of the surroundings of the gate to be recognized; and an identifying unit configured to, in response to detecting that the passing or blocking condition corresponding to the structural type is satisfied, determine the first passing state of the gate to be recognized.

[0006] According to a third aspect, an electronic device is provided. The electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method described in any implementation manner of the first aspect.

[0007] According to a fourth aspect, a non-transitory computer-readable storage medium storing computer instructions is provided, and the computer instructions are used to cause a computer to execute the method described in any implementation manner of the first aspect.

[0008] According to a fifth aspect, there is provided a computer program product including a computer program which, when executed by a processor, implements the method described in any implementation manner of the first aspect.

[0009] For the method and apparatus for determining the state of a gate provided by the embodiments of the present disclosure, first, images of the gate to be recognized and its surroundings are collected; second, based on the image of the gate to be recognized, the structural type of the gate to be recognized and the opening width of the gate to be recognized are determined; third, in response to the opening width not meeting a preset width value, based on the image of the surroundings of the gate to be recognized, it is detected whether the gate to be recognized meets the passing or blocking condition corresponding to the structural type; finally, in response to detecting that the passing or blocking condition corresponding to the structural type is met, the first passing state of the gate to be recognized is determined. Thus, after recognizing the structural type of the gate and the opening width of the gate, by detecting whether the gate meets the passing or blocking condition corresponding to the structural type, the passing state of the gate can be effectively judged, improving the accuracy of gate state detection.

[0010] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become easily understandable through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The drawings are used to better understand the solution and do not constitute a limitation to the present disclosure. Among them:

[0012] Figure 1 is a flowchart of an embodiment of the method for determining the state of a gate according to the present disclosure;

[0013] Figure 2 is a flowchart of another embodiment of the method for determining the state of a gate according to the present disclosure;

[0014] Figure 3 is a flowchart of still another embodiment of the method for determining the state of a gate according to the present disclosure;

[0015] Figure 4 is a schematic structural diagram of an embodiment of the apparatus for determining the state of a gate according to the present disclosure;

[0016] Figure 5 is a block diagram of an electronic device for implementing the method for determining the state of a gate in the embodiments of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] The following describes exemplary embodiments of the present disclosure with reference to the accompanying drawings. Various details of the embodiments of the present disclosure are included to facilitate understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, descriptions of well-known functions and structures are omitted below for clarity and conciseness.

[0018] In this embodiment, "first" and "second" are only used for descriptive purposes and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include at least one such feature.

[0019] In view of the above-mentioned deficiencies, the present disclosure provides a method for determining the state of a gate. Figure 1 Fig. 100 shows a flowchart of an embodiment of the method for determining the state of a gate according to the present disclosure. The method for determining the state of a gate includes the following steps:

[0020] Step 101, collect images of the gate to be recognized and its surroundings.

[0021] In this embodiment, the images of the gate to be recognized and its surroundings include: the image of the gate to be recognized, and the images of the surroundings of the gate to be recognized. Here, the gate to be recognized is the gate whose state is to be recognized, and the images of the surroundings of the gate to be recognized can be images of objects, people, traffic facilities, etc. around the gate to be recognized. The execution entity on which the method for determining the state of a gate runs can collect images of the gate to be recognized and its surroundings through an image acquisition device. The execution entity can also communicate with a terminal device to obtain the images of the gate to be recognized and its surroundings stored on the terminal device.

[0022] Step 102, based on the image of the gate to be recognized, determine the structural type of the gate to be recognized and the opening width of the gate to be recognized.

[0023] In this embodiment, the gate to be recognized can be a gate belonging to various different structural types. Specifically, the structural types can include: retractable gates, lifting gates, swing gates, revolving gates, etc. For gates of different structural types, the control methods for these gates are different. Through gates of different structural types, the passing conditions of the gate to be recognized can be determined. For example, for a lifting gate, an automatic sensing device needs to identify the vehicle entering the gate to be recognized and then lift the middle blocking rod of the lifting gate.

[0024] In this embodiment, the opening width of the gate to be recognized is obtained by performing image detection and segmentation on the image of the gate to be recognized. The above step 102 includes: matching the gate to be recognized with gate templates of different structural types to determine the structural type of the gate to be recognized.

[0025] After obtaining the structural type of the gate to be recognized, if it is detected that the structural type of the gate to be recognized belongs to a symmetric structure (such as a fan-shaped gate), divide the two symmetric sides of the gate to be recognized, determine the distance between the two sides, and based on the preset proportional relationship between the image and the actual gate size, convert the distance between the two sides into the actual opening width of the gate to be recognized.

[0026] After obtaining the structural type of the gate to be recognized, if the structural type of the gate to be recognized belongs to an asymmetric structure (such as a retractable gate, a lifting rod gate, etc.), determine the movable part of the gate to be recognized (the lifting rod of the lifting rod gate) and the fixed part that cooperates with the movable part (the base that supports the lifting rod of the lifting rod gate), determine the distance between the closest endpoint of the movable part to the fixed part and the fixed part, and based on the preset proportional relationship between the image and the actual gate size, convert this distance into the actual opening width of the gate to be recognized.

[0027] In this embodiment, the preset width value can be set based on the structural type of the gate to be recognized. For example, the preset width value is 2 meters.

[0028] Optionally, when it is detected that the opening width meets the preset width value, it can be determined that the gate is a suspected open gate; further, obtain the user trajectory data near the gate to be recognized, determine the traffic change amount of the gate to be recognized; detect whether the traffic change amount is greater than the set threshold. If the traffic change amount is greater than the set threshold, determine that the first traffic state of the gate to be recognized is the open state.

[0029] In this optional implementation manner, the set threshold is the result of statistics on different user trajectory data under different time windows. For example, the set threshold is the daily change amount of personnel, and the set threshold is 10 people / day.

[0030] In the technical solution of the present disclosure, the processing of collection, storage, use, processing, transmission, provision, and disclosure of the involved user trajectory data all comply with the provisions of relevant laws and regulations and do not violate public order and good customs.

[0031] Step 103, in response to the opening width not meeting the preset width value, based on the image around the gate to be recognized, detect whether the gate to be recognized meets the passing and blocking conditions corresponding to the structural type.

[0032] In this embodiment, the passing and blocking conditions include: passing condition and blocking condition. Among them, the passing condition includes: there is a guarding object corresponding to the structural type of the gate to be recognized around the gate to be recognized. The guarding object includes: sentry box, automatic induction device and guarding personnel. The automatic induction device is a device for controlling the opening or closing of the gate to be recognized, and the automatic induction device can also be a device for recognizing the license plate and date of the passing vehicle. The blocking condition includes: whether there is an object blocking in front of the gate to be recognized. The blocking object includes: steps, obstacles and blocking objects. The obstacles include: trees, cement piles, roadblocks, etc. The blocking objects include: cement bags, walls, etc.

[0033] Step 104, in response to detecting that the passing and blocking conditions corresponding to the structural type are met, determine the first passing state of the gate to be recognized.

[0034] In this embodiment, the states of the gate include: passing state, restricted state and direction state. Among them, the first passing state can be a state determined based on the passing state of the gate to be recognized, and is used to represent whether the gate to be recognized is open or not. The first passing state includes: open state and non-open state. When the opening width of the gate to be recognized does not meet the preset width value, and the gate to be recognized meets the passing conditions corresponding to the structural type of the gate to be recognized, determine that the first passing state of the gate to be recognized is the open state. Restricted state

[0035] The restricted state is determined based on the permissions of the passing personnel of the gate to be recognized, and is used to represent whether internal and external vehicles are allowed to pass, and whether internal and external personnel are allowed to pass. The restricted state includes: internal, external, internal and external.

[0036] The direction state is determined based on the direction of the personnel or vehicle to be recognized for passing, and is used to represent the direction of the flow of people or vehicles allowed by the gate to be recognized. The direction state includes: one-way state and two-way state. Among them, the one-way state includes entrance and exit; the two-way state is the entrance and exit.

[0037] In this embodiment, when the opening width of the gate to be recognized meets the preset width value, and the gate to be recognized meets the blocking conditions corresponding to the structural type of the gate to be recognized, determine that the first passing state of the gate to be recognized is the non-open state.

[0038] In this embodiment, when the structural type of the gate to be recognized is a sector gate, the passing condition in the passing and blocking conditions corresponding to the sector gate includes: there is a sentry box around the sector gate. The above step 104 may further include: in response to detecting that there is a sentry box around the sector gate, determine that the first passing state of the sector gate is the open state.

[0039] In this embodiment, when the structural type of the gate to be recognized is a sector gate, the blocking condition corresponding to the sector gate includes: there is a roadblock within the set distance range corresponding to the sector gate, and determine that the first passing state of the sector gate is the non-open state.

[0040] In this embodiment, when the structural type of the gate to be recognized is a lifting bar gate, the passing conditions for the corresponding fan-shaped gate include: there is an automatic sensing device around the lifting bar gate, which can sense vehicles and control the lifting and lowering of the lifting bar gate freely, and determine that the first passing state of the lifting bar gate is the open state.

[0041] The method for determining the gate state provided by the embodiment of the present disclosure includes: first, collecting images of the gate to be recognized and its surroundings; second, based on the image of the gate to be recognized, determining the structural type and the opening width of the gate to be recognized; third, in response to the opening width not meeting the preset width value, based on the image of the surroundings of the gate to be recognized, detecting whether the gate to be recognized meets the passing and blocking conditions corresponding to the structural type; finally, in response to detecting that the passing and blocking conditions corresponding to the structural type are met, determining the first passing state of the gate to be recognized. Thus, after recognizing the structural type and the opening width of the gate, by detecting whether the gate meets the passing and blocking conditions corresponding to the structural type, the passing state of the gate can be effectively judged, improving the accuracy of gate state detection.

[0042] The passing states of the gate include: open type. For the open type of the gate, the determination methods of the open type for gates of different structural types are different. For example, for a fan-shaped gate, its open type needs to be combined with the scene where the gate is located. Therefore, Figure 2 FIG. 200 shows a flow chart of another embodiment of the method for determining the gate state according to the present disclosure. The above method for determining the gate state includes the following steps:

[0043] Step 201, collect images of the gate to be recognized and its surroundings.

[0044] Step 202, based on the image of the gate to be recognized, determine the structural type and the opening width of the gate to be recognized.

[0045] Step 203, in response to the opening width not meeting the preset width value, based on the image of the surroundings of the gate to be recognized, detect whether the gate to be recognized meets the passing and blocking conditions corresponding to the structural type.

[0046] Step 204, in response to detecting that the passing and blocking conditions corresponding to the structural type are met, determine the first passing state of the gate to be recognized.

[0047] It should be understood that the operations and features in the above steps 201 - 204 respectively correspond to the operations and features in steps 101 - 104. Therefore, the descriptions of the operations and features in steps 101 - 104 above also apply to steps 201 - 204, and will not be repeated here.

[0048] Step 205, obtain the data of the region of interest of the gate to be recognized.

[0049] In this embodiment, the ROI refers to the area where the gate to be identified is located, such as a residential area, hospital, or school. The ROI data is AOI (Area of Interest) data, which is part of the map data and a type of data within the map data. The AOI data can be used to determine the map area where the gate to be identified is located. For example, the gate to be identified is the north gate of a residential area, or the main gate of a company.

[0050] Step 206: Determine the scene where the door to be identified is located based on the region of interest data.

[0051] In this embodiment, the area of interest data is used to characterize the area where the gate to be identified is located. The scene where the gate to be identified is located can be determined from the area where the gate to be identified is located. For example, if the gate to be identified is a fan-shaped gate of a community, then the scene where the gate to be identified is located is a non-company or factory scene; for another example, if the gate to be identified is a fan-shaped gate of a company, then the scene where the gate to be identified is located is a company scene.

[0052] Step 207: Based on the scenario, update the first traffic status to obtain an updated traffic status.

[0053] In this embodiment, the first traffic status is inaccurate in some scenarios. After determining the scenario, the first traffic status is updated to obtain an updated traffic status.

[0054] The updated traffic state may be the same as the first traffic state or the opposite of the first traffic state.

[0055] For example, the first passage state is determined to be an open state. If the scene where the gate to be identified is located is a company factory scene, and the closed fan-shaped door meets the corresponding passage conditions of the fan-shaped door, then the first passage state is updated, and the updated passage state is an open state.

[0056] For example, the first access state is determined to be an open state. If the scene where the gate to be identified is located is not a company or factory scene, and the closed fan-shaped door meets the corresponding access conditions of the fan-shaped door, then the access conditions are deemed invalid, and the updated access state is a closed state.

[0057] The gate status determination method provided in this embodiment determines the scene where the gate to be identified is located through the area of interest data of the gate to be identified, updates the first traffic status based on the scene, and obtains the updated traffic status. Therefore, by combining with the scene where the gate to be identified is located, the first traffic status of the gate to be identified is updated, which can provide an effective basis for marking the state of the gate to be identified in the map.

[0058] When predicting passability based on trajectory features, it is generally based on the absolute quantity of trajectories at a specific time, such as the number of trajectory crossings, without considering its change quantity. When the traffic volume of the gate to be recognized changes, it indicates that the gate to be recognized may change from a non-passable state to a passable state. Therefore, the traffic change quantity of the gate to be recognized can effectively determine the traffic state of the gate to be recognized. Figure 3 Fig. 300 shows a flow chart of still another embodiment of the gate state determination method according to the present disclosure. The above-mentioned gate state determination method includes the following steps:

[0059] Step 301, based on the acquired user trajectory data, determine the traffic change quantity of the gate to be recognized.

[0060] In this embodiment, the user trajectory data includes the planned route data and the actual route data of the user. When the actual route data of the user passes through the gate to be recognized, the traffic volume corresponding to the gate to be recognized is obtained. The change value of the traffic volume of the user at the gate to be recognized in the unit time window is the traffic change quantity.

[0061] Step 302, detect whether the traffic change quantity is greater than a preset threshold; if the traffic change quantity is greater than the preset threshold, execute step 303; if the traffic change quantity is less than the preset threshold, execute step 308.

[0062] In this embodiment, the trajectory features at the gate to be recognized change significantly. The trajectory features include: the traffic change quantity and the yaw change quantity. That is, when both the traffic change quantity and the yaw change quantity are greater than the preset threshold, it indicates that the state of the gate to be recognized has changed, and it is necessary to further determine the change situation of the gate state.

[0063] Step 303, collect images of the gate to be recognized and its surroundings, and then execute step 304.

[0064] Step 304, based on the image of the gate to be recognized, determine the structure type and the opening width of the gate to be recognized, and then execute step 305.

[0065] Step 305, in response to the opening width not meeting the preset width value, based on the image of the surroundings of the gate to be recognized, detect whether the gate to be recognized meets the passing or blocking condition corresponding to the structure type, and then execute step 306.

[0066] Step 306, in response to detecting that the passing or blocking condition corresponding to the structure type is met, determine the first traffic state of the gate to be recognized.

[0067] It should be understood that the operations and features in the above Step 303 - Step 306 respectively correspond to the operations and features in Step 101 - 104. Therefore, the descriptions of the operations and features in Step 101 - 104 above also apply to Step 303 - Step 306 and will not be elaborated here.

[0068] Step 307, end.

[0069] Step 308, determine that the gate to be recognized is in a non - open state, and then execute Step 307.

[0070] The method for determining the gate state provided in this embodiment determines the traffic change amount of the gate to be recognized through user trajectory data, and based on the traffic change amount, determines whether to collect the image of the gate to be recognized and its surroundings, so as to combine the image of the gate to be recognized and the traffic change amount of the gate to be recognized to determine the first traffic state of the gate to be recognized, which can provide an effective basis for the annotation of the gate state to be recognized in the map.

[0071] In some embodiments of the present disclosure, the above - mentioned method for determining the gate state includes: determining the traffic change amount of the gate to be recognized based on the acquired user trajectory data; collecting the image of the gate to be recognized and its surroundings in response to detecting that the traffic change amount is greater than a preset threshold; determining the structural type of the gate to be recognized and the opening width of the gate to be recognized based on the image of the gate to be recognized; detecting whether the gate to be recognized meets the passing - obstruction condition corresponding to the structural type based on the image around the gate to be recognized in response to the opening width not meeting the preset width value; determining the first traffic state of the gate to be recognized in response to detecting that it meets the passing - obstruction condition corresponding to the structural type; acquiring the region of interest data of the gate to be recognized; determining the scene where the gate to be recognized is located based on the region of interest data; and updating the first traffic state based on the scene to obtain the updated traffic state.

[0072] The method for determining the gate state provided in this embodiment determines the scene where the gate to be recognized is located through the region of interest data of the gate to be recognized, and updates the first traffic state based on the scene to obtain the updated traffic state. Thus, by combining with the scene where the gate to be recognized is located and the traffic change amount of the gate to be recognized, the first traffic state of the gate to be recognized is updated, which can provide an effective basis for the annotation of the gate state to be recognized in the map.

[0073] When the gate to be recognized changes from the open state to the non-open state, the yaw of the user near the gate to be recognized changes accordingly. Through the change of the yaw, the passing state of the gate can be effectively analyzed. In some other embodiments of the present disclosure, the above-mentioned gate state determination method includes: determining the yaw change amount of the gate to be recognized based on the acquired user trajectory data; in response to detecting that the yaw change amount is greater than a preset threshold, collecting images of the gate to be recognized and its surroundings; determining the structural type and the opening width of the gate to be recognized based on the image of the gate to be recognized; in response to the opening width not meeting the preset width value, detecting whether the gate to be recognized meets the passing and blocking conditions corresponding to the structural type based on the image around the gate to be recognized; in response to detecting that the passing and blocking conditions corresponding to the structural type are met, determining the first passing state of the gate to be recognized.

[0074] The gate state determination method provided in this embodiment determines the yaw change amount of the gate to be recognized based on the user trajectory data. In response to the yaw change amount being greater than the set threshold, the first passing state of the gate to be recognized is recognized through the image of the gate to be recognized and the image around the gate to be recognized, which can improve the accuracy of recognizing the passing state of the gate to be recognized.

[0075] In some embodiments of the present disclosure, the above-mentioned gate state determination method includes: determining the yaw change amount of the gate to be recognized based on the acquired user trajectory data; in response to detecting that the yaw change amount is greater than a preset threshold, collecting images of the gate to be recognized and its surroundings; determining the structural type and the opening width of the gate to be recognized based on the image of the gate to be recognized; in response to the opening width not meeting the preset width value, detecting whether the gate to be recognized meets the passing and blocking conditions corresponding to the structural type based on the image around the gate to be recognized; in response to detecting that the passing and blocking conditions corresponding to the structural type are met, determining the first passing state of the gate to be recognized; acquiring the data of the region of interest of the gate to be recognized; determining the scene where the gate to be recognized is located based on the data of the region of interest; updating the first passing state based on the scene to obtain the updated passing state.

[0076] In this embodiment, the yaw refers to the state where the planned route is to pass through the gate to be recognized, but the actual user trajectory does not pass through the gate to be recognized. The yaw change amount refers to the change of the yaw within a time window. For example, within one day, the yaw amount at the gate to be recognized is 5 routes.

[0077] The method for determining the state of the gate provided in this embodiment determines the scene where the gate to be recognized is located through the region of interest data of the gate to be recognized, updates the first passage state based on the scene, and obtains the updated passage state. Thus, by combining the yaw change amount of the gate to be recognized with the gate to be recognized and the surrounding images, the first passage of the gate to be recognized is recognized. By updating the first passage state of the gate to be recognized through the scene where the gate to be recognized is located, a reliable basis can be provided for determining the first passage state of the gate to be recognized state.

[0078] In some embodiments of the present disclosure, in view of the limitations in determining the attributes of the gate caused by the single method of image or trajectory verification currently, a method for determining the state of the gate that combines multiple sources to improve the accuracy of gate data is proposed. The specific method is as follows:

[0079] Based on the acquired user trajectory data, determine the passage change amount and yaw change amount of the gate to be recognized; based on the passage change amount and yaw change amount, determine the second passage state of the gate to be recognized; collect the image of the gate to be recognized and its surroundings; based on the image of the gate to be recognized, determine the structure type and the opening width of the gate to be recognized; in response to the opening width not meeting the preset width value, based on the image of the surroundings of the gate to be recognized, detect whether the gate to be recognized meets the through / block condition corresponding to the structure type; in response to detecting that the through / block condition corresponding to the structure type is met, determine the first passage state of the gate to be recognized. In response to detecting that the first passage state is consistent with the second passage state, store the gate to be recognized and the first passage state correspondingly in the database.

[0080] In this embodiment, the above determining the second passage state of the gate to be recognized based on the passage change amount and yaw change amount includes: in response to the passage change amount being greater than the set threshold and the yaw change amount being less than the set threshold, determine that the second passage state of the gate to be recognized is the open state; in response to the passage change amount being less than the set threshold and the yaw change amount being greater than the set threshold, determine that the second passage state of the gate to be recognized is the non-open state.

[0081] In this embodiment, the second passage state is also the state determined based on the opening type of the gate to be recognized. The second passage state may be the same as the first passage state or different from the first passage state. When the first passage state is the same as the second passage state, the first passage state is consistent with the second passage state; when the first passage state is different from the second passage state, it is determined that the first passage state is inconsistent with the second passage state.

[0082] In this embodiment, based on the user trajectory data at the gate to be recognized under different time windows (such as T+1 or T+3, and predicting based on different time windows can meet different timeliness requirements), trajectory features are determined (such as the trajectory penetration volume, the trajectory yaw volume, and the sudden drop / rise of the penetration volume and the dynamic feature of the sudden rise of the yaw volume. The comparison of the penetration volume or the yaw volume under different time windows, and a change value greater than the set threshold is considered a sudden rise or a sudden drop). Based on the trajectory features, a gate passability prediction model is constructed to calculate the probability of the change in the gate passability. When the trajectory features include the dynamic features of the penetration volume and the yaw volume, the passability change probability is the passability change amount and the yaw change amount.

[0083] The gate status determination method provided in this embodiment determines the passability change amount and the yaw change amount of the gate to be recognized through the user trajectory data; based on the passability change amount and the yaw change amount, the second passability status of the gate to be recognized is determined; based on the image of the gate to be recognized and its surroundings, the first passability status of the gate to be recognized is determined; through the consistency matching between the first passability status and the second passability status, the accuracy of the gate data is improved at low cost by integrating the image and the trajectory mining result.

[0084] In some other embodiments of the present disclosure, the above-mentioned gate status determination method includes: in response to detecting that the first passability status is inconsistent with the second passability status, generating a pass inquiry statement and performing an automatic pass inquiry using the pass inquiry statement; based on the result obtained from the automatic pass inquiry, determining the third passability status of the gate to be recognized.

[0085] In this embodiment, the automatic pass inquiry may include: AI (Artificial Intelligence) intelligent phone voice inquiry, user inquiry, and in-line yaw inquiry. Among them, the intelligent phone voice inquiry refers to converting the pass inquiry statement into voice information, connecting to the phone line of the artificial intelligence agent, and sending the pass inquiry statement to the artificial intelligence agent to implement the automatic pass inquiry, and obtaining the third passability status of the gate to be recognized returned by the artificial intelligence agent. The user inquiry refers to directly publishing the pass inquiry statement on the Internet and obtaining the inquiry result of the pass inquiry statement feedback by a third party from the Internet. The in-line yaw inquiry refers to under the guidance of the vehicle navigation engine, publishing the pass inquiry statement to the navigation engine to implement the automatic pass inquiry.

[0086] In this embodiment, the third passability status may be a status determined based on the opening type of the gate to be recognized, and the third passability status may be consistent with the first passability status or the second passability status. If the third passability status is the same as the first passability status, that is, the third passability status is consistent with the first passability status, and the third passability status is inconsistent with the second passability status; the third passability status may also be the same as the second passability status, that is, the third passability status is consistent with the second passability status, and the third passability status is inconsistent with the first passability status.

[0087] The method for determining the gate state provided in this embodiment determines the traffic change amount and yaw change amount of the gate to be recognized through user trajectory data; determines the second traffic state of the gate to be recognized based on the traffic change amount and yaw change amount; determines the first traffic state of the gate to be recognized based on the image of the gate to be recognized and its surroundings; when the first traffic state is inconsistent with the second traffic state, determines the third traffic state of the gate to be recognized through intelligent inquiry, so as to comprehensively improve the accuracy of gate data automatically and at low cost by integrating images, trajectory mining results, and intelligent voice inquiry methods.

[0088] Optionally, in another embodiment of the present disclosure, the above method for determining the gate state further includes: in response to detecting that the first traffic state is inconsistent with the second traffic state, releasing crowdsourcing for collection and verification to determine the third traffic state of the gate to be recognized.

[0089] Due to problems such as photo coverage, shooting angle, and photo quality, verifying the gate state only through static photos will bring limitations and restrictions to the judgment, resulting in inaccurate judgment results. For example, judging from a static picture that the gate to be recognized is a closed fan-shaped gate, and there is no guard booth or personnel on duty, etc., it is judged that the first traffic state of the gate to be recognized is a non-open state gate. However, actually referring to the old trajectory, looking at the gate to be recognized from inside the gate, there are people on duty, and the actual gate is open for motor vehicles to pass through.

[0090] In some alternative implementation manners of this embodiment, the image around the gate to be recognized includes: the image outside the building (such as a wall) where the gate to be recognized is located and the image inside the building where the gate to be recognized is located; based on the image around the gate to be recognized, detecting whether the gate to be recognized meets the through / obstruction condition corresponding to the structure type, including: detecting whether the image outside the building where the gate to be recognized is located meets the through / obstruction condition corresponding to the structure type; in response to detecting that the image outside the building where the gate to be recognized is located does not meet the through / obstruction condition corresponding to the structure type, detecting whether the image inside the building where the gate to be recognized is located meets the through / obstruction condition corresponding to the structure type; in response to detecting that the image inside the building where the gate to be recognized is located meets the through / obstruction condition corresponding to the structure type, determining that the gate to be recognized meets the through / obstruction condition corresponding to the structure type.

[0091] The state of the gate includes: the traffic state and the vehicle restriction state. When the traffic state of the gate to be recognized is the open state, in order to better recognize the restriction state of the open gate to be recognized, in some embodiments of the present disclosure, the above method for determining the gate state further includes: in response to the first traffic state of the gate to be recognized being the open state, detecting whether there is a sign image in the image around the gate to be recognized; in response to there being a sign image in the image around the gate to be recognized, recognizing the text information in the sign image; determining the restriction state of the gate to be recognized based on the text information.

[0092] In this embodiment, when the gate to be recognized has a vehicle restriction status, a sign is generally hung outside the gate to be recognized, and text information such as "Internal Open" and "Internal and External Open" is marked on the sign. The restriction status of the gate to be recognized can be determined through the text information.

[0093] The method for determining the gate status provided in this embodiment, after determining that the first passage status of the gate to be recognized is the open status, determines the restriction status of the gate to be recognized based on the text information in the sign image in the image around the gate to be recognized, providing a reliable basis for accurately determining the restriction status of the gate to be recognized and improving the reliability of the detection of the restriction status of the gate to be recognized.

[0094] The status of the gate includes: passage status, restriction status, and direction status. When the passage direction of the gate to be recognized changes, in order to better recognize the direction status of the open gate to be recognized, in some embodiments of the present disclosure, the above method for determining the gate status further includes: detecting whether the passage direction of the gate to be recognized changes based on user trajectory data; in response to the passage direction of the gate to be recognized changing, determining the direction status of the gate to be recognized based on the image around the gate to be recognized.

[0095] In this embodiment, the user trajectories in the user trajectory data have different directions. When passing through the gate to be recognized, if the user trajectory changes, it can be determined that the vehicle or pedestrian flow direction of the gate to be recognized has changed.

[0096] In this embodiment, the determining the direction status of the gate to be recognized based on the image around the gate to be recognized includes: 1. Based on the image around the gate to be recognized, determine the sign in front of the gate, and identify whether there is text information such as "Exit", "Entrance", "Entrance and Exit", etc. on the sign in front of the gate. If there is such text information, determine the direction status of the gate to be recognized; 2. Based on the image around the gate to be recognized, determine the ground image near the gate to be recognized, and identify whether there is a one-way underground arrow in the ground image near the gate. Determine the direction status of the gate to be recognized according to the direction of the underground arrow; 3. Based on the image around the gate to be recognized, determine the automatic induction device near the gate to be recognized, and identify the orientation of the induction device. For example, if the electronic induction device beside the gate faces the entering side, it means the gate is an entrance.

[0097] The method for determining the gate status provided in this embodiment determines whether the passage direction of the gate to be recognized changes based on user trajectory data; when the passage direction of the gate to be recognized changes, determines the passage direction of the gate to be recognized based on the image around the gate to be recognized. Thus, a reliable basis is provided for determining the direction status of the gate to be recognized.

[0098] Further refer to Figure 4, as an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a gate status determination device. This device embodiment corresponds to Figure 1 the method embodiment shown, and this device can be specifically applied to various electronic devices.

[0099] As shown in Figure 4 , the gate status determination device 400 provided in this embodiment includes: a collection unit 401, a structure determination unit 402, a condition detection unit 403, and an identification unit 404. Among them, the above collection unit 401 can be configured to collect images of the gate to be identified and its surroundings. The above structure determination unit 402 can be configured to determine the structure type of the gate to be identified and the opening width of the gate to be identified based on the image of the gate to be identified. The above condition detection unit 403 can be configured to, in response to the opening width not meeting the preset width value, detect whether the gate to be identified meets the through / obstruction condition corresponding to the structure type based on the image of the surroundings of the gate to be identified. The above identification unit 404 can be configured to, in response to detecting that the through / obstruction condition corresponding to the structure type is met, determine the first passage state of the gate to be identified.

[0100] In this embodiment, in the gate status determination device 400: the specific processing of the collection unit 401, the structure determination unit 402, the condition detection unit 403, and the identification unit 404 and the technical effects brought by them can respectively refer to Figure 1 the relevant descriptions of steps 101, 102, 103, and 104 in the corresponding embodiments, which will not be elaborated here.

[0101] In some alternative implementation manners of this embodiment, the above device further includes: an update unit (not shown in the figure). The above update unit is further configured to obtain the region of interest data of the gate to be identified; determine the scene where the gate to be identified is located based on the region of interest data; update the first passage state based on the scene to obtain the updated passage state.

[0102] In some alternative implementation manners of this embodiment, the above device 400 further includes: a passage judgment unit (not shown in the figure). Among them, the above passage judgment unit can be configured to determine the passage change amount of the gate to be identified based on the acquired user trajectory data; in response to detecting that the passage change amount is greater than the set threshold, control the collection unit to work.

[0103] In some alternative implementation manners of this embodiment, the above device 400 further includes: a yaw judgment unit (not shown in the figure). Among them, the above yaw judgment unit can be configured to determine the yaw change amount of the gate to be identified based on the acquired user trajectory data; in response to detecting that the yaw change amount is greater than the set threshold, control the collection unit to work.

[0104] In some alternative implementation manners of the present disclosure, the above-mentioned device 400 further includes: an acquisition unit (not shown in the figure), a status determination unit (not shown in the figure), and a storage unit (not shown in the figure). Among them, the above-mentioned acquisition unit can be configured to determine the traffic change amount and the yaw change amount of the gate to be recognized based on the acquired user trajectory data. The above-mentioned status determination unit can be configured to determine the second traffic status of the gate to be recognized based on the traffic change amount and the yaw change amount. The above-mentioned storage unit can be configured to store the gate to be recognized and the first traffic status in the database in response to detecting that the first traffic status is consistent with the second traffic status.

[0105] In some alternative implementation manners of the present disclosure, the above-mentioned device 400 further includes: a generation unit (not shown in the figure). The above-mentioned generation unit can be configured to generate a traffic inquiry statement and perform an automatic traffic inquiry using the traffic inquiry statement in response to detecting that the first traffic status is inconsistent with the second traffic status; determine the third traffic status of the gate to be recognized based on the result obtained from the automatic traffic inquiry.

[0106] In some alternative implementation manners of the present disclosure, the above-mentioned device 400 further includes: an image detection unit (not shown in the figure). The above-mentioned image detection unit can be configured to detect whether there is a sign image in the image around the gate to be recognized in response to the first traffic status of the gate to be recognized being the open state; recognize the text information in the sign image in response to the sign image existing in the image around the gate to be recognized; determine the restricted status of the gate to be recognized based on the text information.

[0107] In some alternative implementation manners of the present disclosure, the above-mentioned device 400 further includes: a direction detection unit (not shown in the figure). The above-mentioned direction detection unit can be configured to detect whether the traffic direction of the gate to be recognized changes based on the user trajectory data; determine the direction status of the gate to be recognized based on the image around the gate to be recognized in response to the traffic direction of the gate to be recognized changing.

[0108] The gate status determination device provided by the embodiments of the present disclosure first has a collection unit 401 collect images of the gate to be recognized and its surroundings. Secondly, a structure determination unit 402 determines the structure type of the gate to be recognized and the opening width of the gate to be recognized based on the image of the gate to be recognized. Thirdly, a condition detection unit 403, in response to the opening width not meeting a preset width value, detects whether the gate to be recognized meets the passing or blocking condition corresponding to the structure type based on the image of the surroundings of the gate to be recognized. Finally, an identification unit 404, in response to detecting that the passing or blocking condition corresponding to the structure type is met, determines the first passing status of the gate to be recognized. Thus, after recognizing the gate structure type and the opening width of the gate, by detecting whether the gate meets the passing or blocking condition corresponding to the structure type, the passing status of the gate can be effectively judged, improving the accuracy of gate status detection.

[0109] In the technical solution of the present disclosure, the processing of collection, storage, use, processing, transmission, provision, and disclosure of the user's personal information involved all comply with the provisions of relevant laws and regulations and do not violate public order and good customs.

[0110] According to the embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0111] Figure 5 FIG. shows a schematic block diagram of an exemplary electronic device 500 that can be used to implement the embodiments of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, a personal digital processor, a cellular phone, a smart phone, a wearable device, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely exemplary and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0112] As Figure 5 shown, the device 500 includes a computing unit 501, which can execute various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the device 500 can also be stored. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0113] Multiple components in device 500 are connected to I / O interface 505, including: input unit 506, such as a keyboard, mouse, etc.; output unit 507, such as various types of displays, speakers, etc.; storage unit 508, such as a disk, optical disc, etc.; and communication unit 509, such as a network card, modem, wireless communication transceiver, etc. Communication unit 509 allows device 500 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0114] Computing unit 501 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of computing unit 501 include but are not limited to a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Computing unit 501 executes the various methods and processes described above, such as the gate state determination method. For example, in some embodiments, the gate state determination method can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as storage unit 508. In some embodiments, part or all of the computer program can be loaded and / or installed onto device 500 via ROM 502 and / or communication unit 509. When the computer program is loaded into RAM 503 and executed by computing unit 501, one or more steps of the gate state determination method described above can be executed. Alternatively, in other embodiments, computing unit 501 can be configured to execute the gate state determination method by any other suitable means (e.g., by means of firmware).

[0115] 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-a-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor, and can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0116] The program code for implementing the methods of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable gate state determination devices, such that when the program codes are executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program codes can be executed entirely on the machine, partially on the machine, executed partially on the machine and partially on a remote machine as an independent software package, or executed entirely on a remote machine or server.

[0117] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0118] In order to provide interaction with a user, the systems and techniques described herein can be implemented on a computer 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 a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and the input received from the user can be in any form (including acoustic input, voice input, or tactile input).

[0119] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), and the Internet.

[0120] A computer system can include a client and a server. The client and the server are generally remote from each other and typically interact through a communication network. The relationship between the client and the server is generated by computer programs that run on the respective computers and have a client-server relationship with each other.

[0121] It should be understood that various forms of the processes shown above can be used, steps can be reordered, added, or deleted. For example, the steps recited in this disclosure can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this is not limited herein.

[0122] The above specific embodiments do not constitute a limitation on the protection scope of this disclosure. 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 disclosure shall be included within the protection scope of this disclosure.

Claims

1. A method for determining the state of a gate, the method comprising: Collecting images of the gate to be recognized and its surroundings; Based on the image of the gate to be recognized, determining the structural type of the gate to be recognized and the opening width of the gate to be recognized; In response to the opening width not meeting a preset width value, based on the image of the surroundings of the gate to be recognized, detecting whether the gate to be recognized meets the through / obstruction conditions corresponding to the structural type, where the through / obstruction conditions include: a passage condition and an obstruction condition; In response to detecting that the through / obstruction conditions corresponding to the structural type are met, determining the first passage state of the gate to be recognized; Wherein, the method further comprises: Obtaining the region of interest data of the gate to be recognized; Based on the region of interest data, determining the scene where the gate to be recognized is located; Based on the scene, updating the first passage state to obtain the updated passage state.

2. The method according to claim 1, before collecting the images of the gate to be recognized and its surroundings, the method further comprises: Based on the obtained user trajectory data, determining the passage change amount of the gate to be recognized; In response to detecting that the passage change amount is greater than a set threshold, collecting the images of the gate to be recognized and its surroundings.

3. The method according to claim 1, before collecting the images of the gate to be recognized and its surroundings, the method further comprises: Based on the obtained user trajectory data, determining the yaw change amount of the gate to be recognized; In response to detecting that the yaw change amount is greater than a set threshold, collecting the images of the gate to be recognized and its surroundings.

4. The method according to claim 1, the method further comprises: Based on the obtained user trajectory data, determining the passage change amount and the yaw change amount of the gate to be recognized; Based on the passage change amount and the yaw change amount, determining the second passage state of the gate to be recognized; In response to detecting that the first passage state is consistent with the second passage state, storing the gate to be recognized and the corresponding first passage state in a database.

5. The method according to claim 4, the method further comprises: In response to detecting that the first passage state is inconsistent with the second passage state, generating a passage inquiry statement and performing an automatic passage inquiry using the passage inquiry statement; Based on the result obtained from the automatic passage inquiry, determining the third passage state of the gate to be recognized.

6. The method according to claim 1, the method further comprises: In response to the first passage state of the gate to be recognized being an open state, detecting whether there is a sign image in the image of the surroundings of the gate to be recognized; In response to there being a sign image in the image of the surroundings of the gate to be recognized, recognizing the text information in the sign image; Based on the text information, determining the restricted state of the gate to be recognized.

7. The method according to claim 1, the method further comprises: Based on the user trajectory data, detecting whether the passage direction of the gate to be recognized changes; In response to the passage direction of the gate to be recognized changing, based on the image of the surroundings of the gate to be recognized, determining the direction state of the gate to be recognized.

8. A device for determining the state of a gate, the device comprising: An acquisition unit configured to acquire an image of the gate to be identified and its surroundings; A structure determination unit configured to determine the structure type of the gate to be identified and the opening width of the gate to be identified based on the image of the gate to be identified; A condition detection unit configured to, in response to the opening width not meeting a preset width value, detect whether the gate to be identified meets a passing or blocking condition corresponding to the structure type based on the image of the surroundings of the gate to be identified, where the passing or blocking condition includes a passing condition and a blocking condition; An identification unit configured to determine a first passing state of the gate to be identified in response to detecting that the passing or blocking condition corresponding to the structure type is met; Wherein, the device further comprises: an update unit; The update unit is further configured to acquire region of interest data of the gate to be identified; determine the scene where the gate to be identified is located based on the region of interest data; and update the first passing state based on the scene to obtain an updated passing state.

9. The device according to claim 8, the device further comprising: A passing judgment unit configured to determine a passing change amount of the gate to be identified based on acquired user trajectory data; In response to detecting that the passing change amount is greater than a set threshold, control the acquisition unit to operate.

10. The device according to claim 8, the device further comprising: A yaw judgment unit configured to determine a yaw change amount of the gate to be identified based on acquired user trajectory data; In response to detecting that the yaw change amount is greater than a set threshold, control the acquisition unit to operate.

11. The device according to claim 8, the device further comprising: An acquisition unit configured to determine a passing change amount and a yaw change amount of the gate to be identified based on acquired user trajectory data; A state determination unit configured to determine a second passing state of the gate to be identified based on the passing change amount and the yaw change amount; A storage unit configured to, in response to detecting that the first passing state is consistent with the second passing state, store the gate to be identified and the first passing state in a database correspondingly.

12. The device according to claim 11, the device further comprising: A generation unit configured to, in response to detecting that the first passing state is inconsistent with the second passing state, generate a passing inquiry statement and perform an automatic passing inquiry using the passing inquiry statement; and determine a third passing state of the gate to be identified based on the result of the automatic passing inquiry.

13. The device according to claim 8, the device further comprising: An image detection unit configured to, in response to the first passing state of the gate to be identified being an open state, detect whether there is a sign image in the image of the surroundings of the gate to be identified; in response to there being a sign image in the image of the surroundings of the gate to be identified, identify the text information in the sign image; and determine the restricted state of the gate to be identified based on the text information.

14. The device according to claim 8, the device further comprising: A direction detection unit, configured to detect whether the passing direction of the gate to be recognized changes based on user trajectory data; In response to a change in the passing direction of the gate to be recognized, determine the direction state of the gate to be recognized based on the image around the gate to be recognized.

15. An electronic device, characterized in that, Comprising: At least one processor; And A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method according to any one of claims 1-7.

16. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to execute the method according to any one of claims 1-7.

17. A computer program product, comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-7.

Images