A vehicle position intelligent video monitoring device and method
By obtaining video data of the vehicle intrusion area in the airport video surveillance system, determining the real-time positioning information and GPS coordinates of the vehicle, and marking the vehicle position in the screen, the problem of difficult locations during vehicle intrusion is solved and the safety of the airport is improved and monitoring efficiency.
Patent Information
- Application Number
- CN202410917628.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-10
- Publication Date
- 2024-11-01
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
In the flight and docking areas of the airport, due to the vast road network area and small vehicle image size during vehicle intrusion, it is difficult for supervisors to clearly view the vehicle location, which increases safety hazards.
An intelligent video monitoring device and method for vehicle location is designed, including early warning information acquisition, shooting video data acquisition, GPS positioning coordinate set determination and vehicle labeling subsystem. By obtaining video data of vehicle intrusion area, real-time positioning information of the vehicle and GPS positiones coordinates and marks the vehicle position in the screen to avoid the problem that the vehicle is difficult to identify in large areas.
Improve the safety of vehicle intrusion areas, ensure that supervisors can clearly view the vehicle location, and improve safety and monitoring efficiency.
Smart Images

Figure CN118537805B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of data identification, and in particular to a vehicle position intelligent video monitoring device and method. Background Art
[0002] At present, with the increase in passenger volume, airports are facing greater challenges in ensuring production safety. In recent years, there have been many vehicle intrusion incidents at domestic and foreign airports, many of which were caused by vehicles mistakenly entering the flight area or parking area of the aircraft.
[0003] To address this problem, the airport has adopted a vehicle management system that tracks the GPS coordinates of vehicles in real time by installing GPS positioning devices on the vehicles. Once a vehicle is identified as illegally entering the flight area or parking area of the aircraft, the vehicle management system can promptly issue an alarm to the airport management personnel. In addition to the vehicle management system, the airport is also equipped with a video surveillance system, allowing management personnel to observe the situation in the flight area and parking area in real time.
[0004] The invention patent with application number: CN201780075225.5 discloses a method and system for video-based positioning and mapping, wherein the method includes: obtaining a series of images from one or more cameras associated with the vehicle traveling through the road network, the series of images reflecting the environment of the road network on which the vehicle is traveling, wherein each of the images has an associated camera position at which the image is recorded. Then, a local map representation representing the area of the road network on which the vehicle is traveling is generated using at least some of the obtained images and the associated camera positions. The generated local map representation is compared with a section of a reference map, the reference map section covering the area of the road network on which the vehicle is traveling, and the geographic location and orientation of the vehicle within the road network are determined based on the comparison.
[0005] However, although the above-mentioned existing technology realizes the positioning of the vehicle, when the road network is large and the supervisor wants to obtain the real-time position of the vehicle, there is a problem that the area of the road network is vast and the image size of the vehicle in the picture is very small and cannot be clearly viewed, which increases safety hazards.
[0006] In view of this, there is an urgent need for a vehicle position intelligent video monitoring device and method to at least solve the above-mentioned deficiencies. Summary of the invention
[0007] One of the purposes of the present invention is to provide a vehicle position intelligent video monitoring device and method, obtain warning information when a vehicle enters an area that is not allowed to enter, and determine the vehicle's real-time positioning information and the vehicle's intrusion area based on the warning information. The captured video data of the vehicle intrusion area is obtained, and the GPS positioning coordinate set of the vehicle intrusion area screen is determined. According to the vehicle's real-time positioning information and the GPS positioning coordinate set, the vehicle's position coordinates are determined and marked accordingly in the vehicle intrusion area screen, thereby avoiding the problem that the intruding vehicle cannot be clearly viewed when the vehicle intrusion area is too large or the target is too small, thereby improving safety.
[0008] An embodiment of the present invention provides a vehicle position intelligent video monitoring device, comprising:
[0009] The early warning information acquisition subsystem is used to obtain early warning information, including: vehicle intrusion area and vehicle real-time positioning information;
[0010] A shooting video data acquisition subsystem is used to acquire shooting video data of the area where the vehicle intrudes;
[0011] A GPS positioning coordinate set determination subsystem, used to determine the GPS positioning coordinate set of the vehicle intrusion area screen according to the captured video data;
[0012] The vehicle marking subsystem is used to determine the vehicle position coordinates in the GPS positioning coordinate set based on the real-time vehicle positioning information, and mark the vehicle position coordinates accordingly in the vehicle intrusion area screen.
[0013] Preferably, the early warning information acquisition subsystem includes:
[0014] An intrusion event acquisition module, used for attempting to acquire intrusion events in a target area;
[0015] The warning information determination module is used to analyze the intrusion event and determine the warning information if the acquisition attempt is successful.
[0016] Preferably, the GPS positioning coordinate set determination subsystem includes:
[0017] A regional GPS information determination module is used to determine regional GPS information according to the area intruded by the vehicle;
[0018] A regional GPS information mapping rule determination module is used to determine the regional GPS information mapping rule based on the captured video data;
[0019] The GPS positioning coordinate set acquisition module is used to acquire the GPS positioning coordinate set according to the regional GPS information and the regional GPS information mapping rule.
[0020] Preferably, the regional GPS information mapping rule determination module includes:
[0021] A key area marking submodule is used to mark key areas in the captured video data;
[0022] The regional information acquisition submodule is used to obtain regional information of key areas;
[0023] An independent determination rule determination submodule is used to determine whether the regional information satisfies the independent determination rule according to the regional information;
[0024] A first rule determination submodule, for obtaining a first geographic feature of a key area if the area information satisfies an independent determination rule, and determining a regional GPS information mapping rule based on the first geographic feature;
[0025] The second rule determination submodule is used to obtain the first geographical feature of the key area and the second geographical feature of the non-key area if the area information does not meet the independent determination rule, and determine the regional GPS information mapping rule according to the first geographical feature and the second geographical feature;
[0026] The second rule determines the submodule, including:
[0027] A feature combination determining unit, configured to determine a feature combination according to the first geographical feature and the second geographical feature;
[0028] The regional GPS information mapping rule determination unit is used to determine the regional GPS information mapping rule according to the feature combination.
[0029] Preferably, the independent determination rule determination submodule includes:
[0030] An area type acquisition unit, used for parsing the area information and acquiring a first area identifier of a key area;
[0031] An identification type acquisition unit, used to acquire the identification type of the first area identification;
[0032] An independent determination marker control library construction unit, used to construct an independent determination marker control library;
[0033] A unit for determining items to be matched, used to determine items to be matched according to the identification type and the independent determination identification reference library;
[0034] a target identification type determination unit, configured to match the first area identification of each identification type and use the identification type being matched as the target identification type;
[0035] A matching unit, used to determine whether the first area identifier of the target identifier type and the second area identifier of the target identifier type in the to-be-matched item match each other;
[0036] The determination unit is used to determine that if all the matches are consistent, the region information satisfies the independent determination rule, otherwise it does not satisfy the rule.
[0037] Preferably, the independent determination marker control library construction unit comprises:
[0038] A monitoring query record acquisition subunit is used to acquire monitoring query records;
[0039] A key frame determination subunit, used to determine the key frame according to the monitoring query record;
[0040] A sight line information acquisition subunit, used to acquire sight line information on a key frame;
[0041] A sight feature acquisition subunit, used to characterize sight information and acquire sight features;
[0042] An association relationship establishment subunit is used to establish an association relationship between sight line features and key frames;
[0043] An independent determination mark acquisition model acquisition subunit is used to learn the association relationship using a deep learning model, and when the deep learning model is completed, the independent determination mark acquisition model is acquired;
[0044] An output association relationship acquisition subunit is used to input the captured video data into the independent determination identifier acquisition model to acquire the output association relationship;
[0045] The independent determination identification reference library construction subunit is used to construct an independent determination identification reference library according to the output association relationship.
[0046] Preferably, the intrusion event acquisition module includes:
[0047] The airport map acquisition submodule is used to obtain the airport map containing the target area;
[0048] The passage route determination submodule is used to determine the passage route of the target area according to the airport map;
[0049] The associated vehicle information acquisition submodule is used to acquire the associated vehicle information of the passing route;
[0050] The associated vehicle feature acquisition submodule is used to characterize the associated vehicle information and acquire the associated vehicle features;
[0051] The electronic fence setting submodule is used to set the electronic fences of vehicles with different operation attributes based on the electronic fence technology and the characteristics of the associated vehicles;
[0052] The report information acquisition submodule is used to obtain the report information of the electronic fence system;
[0053] The intrusion event acquisition submodule is used to acquire the intrusion event according to the report information.
[0054] Preferably, the associated vehicle information acquisition submodule includes:
[0055] A task release information acquisition unit, used to acquire task release information;
[0056] A vehicle task determination unit, used to determine the vehicle task according to the task release information;
[0057] A task location semantics determination unit, used to determine the task location semantics according to the vehicle task;
[0058] The driving trajectory planning unit is used to plan the driving trajectory on the airport map according to the semantics of the mission location;
[0059] A route overlap section determination unit, used to determine the route overlap section according to the driving trajectory and the passing route;
[0060] The associated vehicle information determining unit is used to determine the associated vehicle information based on a preset associated vehicle information acquisition template and according to the route overlap section and the vehicle identification.
[0061] An embodiment of the present invention provides a vehicle position intelligent video monitoring method, comprising:
[0062] Step 1: Obtain warning information, including: vehicle intrusion area and vehicle real-time positioning information;
[0063] Step 2: Obtain the video data of the vehicle intrusion area;
[0064] Step 3: Determine the GPS positioning coordinate set of the vehicle intrusion area according to the captured video data;
[0065] Step 4: According to the real-time positioning information of the vehicle, determine the vehicle position coordinates in the GPS positioning coordinate set, and mark the vehicle position coordinates in the vehicle intrusion area screen accordingly.
[0066] Preferably, step 1: obtaining warning information includes:
[0067] Try to obtain intrusion information in the target area;
[0068] If the acquisition attempt is successful, the intrusion event is analyzed and the warning information is determined.
[0069] The beneficial effects of the present invention are:
[0070] The present invention obtains warning information when a vehicle enters an area that is not allowed to enter, and determines the real-time positioning information of the vehicle and the vehicle intrusion area according to the warning information. The captured video data of the vehicle intrusion area is obtained, and the GPS positioning coordinate set of the vehicle intrusion area screen is determined. According to the real-time positioning information of the vehicle and the GPS positioning coordinate set, the vehicle position coordinates are determined and marked accordingly in the vehicle intrusion area screen, thereby avoiding the problem that the intruding vehicle cannot be clearly viewed when the vehicle intrusion area is too large or the target is too small, thereby improving safety.
[0071] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures specifically pointed out in the present application documents.
[0072] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS
[0073] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:
[0074] Figure 1 A schematic diagram of an intelligent video monitoring device for vehicle position according to an embodiment of the present invention;
[0075] Figure 2 Schematic diagram of a vehicle position intelligent video monitoring method in an embodiment of the present invention. DETAILED DESCRIPTION
[0076] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.
[0077] The embodiment of the present invention provides a vehicle position intelligent video monitoring device, such as Figure 1 As shown, including:
[0078] The early warning information acquisition subsystem 1 is used to acquire early warning information, which includes: vehicle intrusion area and vehicle real-time positioning information; wherein the vehicle intrusion area is: the location of the area that the vehicle enters that is not allowed to enter, such as: apron No. 3; the vehicle real-time positioning information is: GPS positioning information of the intruding vehicle;
[0079] The captured video data acquisition subsystem 2 is used to acquire captured video data of the vehicle intruding into the area; wherein the captured video data is: monitoring data of a monitoring device preset in the vehicle intruding into the area;
[0080] The GPS positioning coordinate set determination subsystem 3 is used to determine the GPS positioning coordinate set of the vehicle intrusion area picture according to the captured video data; wherein the GPS positioning coordinate set is: a set of GPS positioning coordinates of the actual position corresponding to each picture point of the vehicle intrusion area picture;
[0081] The vehicle marking subsystem 4 is used to determine the vehicle position coordinates in the GPS positioning coordinate set according to the real-time vehicle positioning information, and mark the vehicle position coordinates in the vehicle intrusion area screen accordingly. The vehicle position coordinates are: the GPS positioning coordinates in the GPS positioning coordinate set corresponding to the real-time vehicle positioning information; when marking, determine that the vehicle position coordinates correspond to the screen point of the vehicle intrusion area screen, and mark it based on the preset marking method.
[0082] The working principle and beneficial effects of the above technical solution are:
[0083] This application obtains warning information when a vehicle enters an area that is not allowed to enter, and determines the real-time positioning information of the vehicle and the area that the vehicle has entered based on the warning information. The video data of the area where the vehicle has entered is obtained, and the GPS positioning coordinate set of the area where the vehicle has entered is determined. Based on the real-time positioning information of the vehicle and the GPS positioning coordinate set, the vehicle position coordinates are determined and marked accordingly in the area where the vehicle has entered, thus avoiding the problem of intruding vehicles not being able to be clearly viewed due to the vehicle intrusion area being too large or the target being too small, and thus improving safety.
[0084] In one embodiment, the early warning information acquisition subsystem includes:
[0085] The intrusion event acquisition module is used to attempt to acquire intrusion events in a target area; wherein the target area is: an area that is manually input in advance and vehicles are not allowed to enter; the intrusion event is: an event in which a vehicle that is not allowed to enter the target area enters the target area;
[0086] The warning information determination module is used to analyze the intrusion event and determine the warning information if the acquisition attempt is successful.
[0087] The working principle and beneficial effects of the above technical solution are:
[0088] This application introduces intrusion events in the target area, and determines warning information based on the intrusion events, thereby improving the reliability of obtaining warning information.
[0089] In one embodiment, the GPS positioning coordinate set determination subsystem includes:
[0090] The regional GPS information determination module is used to determine the regional GPS information according to the vehicle intrusion area; wherein the regional GPS information is: GPS positioning information of the vehicle intrusion area;
[0091] The regional GPS information mapping rule determination module is used to determine the regional GPS information mapping rule according to the captured video data; wherein the regional GPS information mapping rule is: which part of the video screen corresponds to which GPS coordinate;
[0092] The GPS positioning coordinate set acquisition module is used to acquire the GPS positioning coordinate set according to the regional GPS information and the regional GPS information mapping rule.
[0093] The working principle and beneficial effects of the above technical solution are:
[0094] This application determines the regional GPS information of the area where the vehicle has intruded, and at the same time, determines the regional GPS information mapping rules based on the captured video data (what GPS coordinates are corresponding to where in the video screen). According to the regional GPS information and the regional GPS information mapping rules, a GPS positioning coordinate set is obtained. The accuracy and standardization of the GPS positioning coordinate set acquisition are improved.
[0095] In one embodiment, the regional GPS information mapping rule determination module includes:
[0096] The key area marking submodule is used to mark the key areas in the captured video data; wherein the key areas are: the captured images of key entities in the captured video data, such as: the runway marking images, the parking space marking images, etc.;
[0097] The area information acquisition submodule is used to acquire the area information of the key area; wherein the area information is: the area ID of the key area;
[0098] The independent determination rule determination submodule is used to determine whether the regional information satisfies the independent determination rule according to the regional information; wherein the independent determination rule is: a rule that can directly determine the GPS positioning coordinate set according to the key area;
[0099] The first rule determination submodule is used to obtain the first geographical feature of the key area if the area information satisfies the independent determination rule, and determine the regional GPS information mapping rule according to the first geographical feature; wherein the first geographical feature is a characteristic representation of the regional information of the key area, such as the GPS location of the key area and the direction in which the key area is presented in the video; when determining the regional GPS information mapping rule according to the first geographical feature, the local area GPS information that meets the first geographical feature in the regional GPS information is determined according to the first geographical feature, the local area GPS information is determined, and the regional GPS information mapping rule is determined according to the mapping relationship between the local area GPS information and the vehicle intrusion area;
[0100] The second rule determination submodule is used to obtain the first geographical feature of the key area if the area information does not meet the independent determination rule, and at the same time, obtain the second geographical feature of the non-key area, and determine the regional GPS information mapping rule according to the first geographical feature and the second geographical feature; wherein the second geographical feature is: a characteristic representation of the non-key area, such as: an image feature of the non-key area;
[0101] The second rule determines the submodule, including:
[0102] A feature combination determining unit, configured to determine a feature combination according to the first geographical feature and the second geographical feature;
[0103] The regional GPS information mapping rule determination unit is used to determine the regional GPS information mapping rule according to the feature combination. When determining the regional GPS information mapping rule according to the feature combination, the local area GPS information that meets the first geographical feature in the regional GPS information is determined according to the feature combination, and then the local area GPS information is corrected according to the second geographical feature to determine the target GPS information, and the regional GPS information mapping rule is determined according to the mapping relationship between the target GPS information and the vehicle intrusion area.
[0104] The working principle and beneficial effects of the above technical solution are:
[0105] The present application determines the key areas in the captured video data, and then characterizes the key areas to obtain the first geographic feature. The more key areas of known information, the more accurate the GPS positioning coordinate set determined according to the first geographic feature. An independent determination rule is introduced to determine whether the GPS information of the local area to be located can be directly determined based on the regional information of the key area and perform subsequent mapping. If the regional information meets the independent determination rule, the regional GPS information mapping rule is directly determined according to the first geographic feature. If the regional information does not meet the independent determination rule, the second geographic feature of the non-key area is obtained to determine the feature combination composed of the first geographic feature and the second geographic feature. According to the feature combination, the local area GPS information that meets the first geographic feature in the regional GPS information is determined, and then the local area GPS information is corrected according to the second geographic feature to determine the target GPS information. According to the mapping relationship between the target GPS information and the vehicle intrusion area, the regional GPS information mapping rule is determined, thereby improving the construction efficiency of the regional GPS information mapping rule.
[0106] In one embodiment, the independent decision rule determination submodule includes:
[0107] The area type acquisition unit is used to parse the area information and acquire the first area identifier of the key area; wherein the first area identifier is: a unique identifier ID of the key area, such as: terminal A, terminal B, etc.;
[0108] An identification type acquisition unit, used to acquire the identification type of the first area identification; wherein the identification type is: the area type of the key area, such as: terminal building, runway, etc.;
[0109] An independent determination identification comparison library construction unit is used to construct an independent determination identification comparison library; wherein the independent determination identification comparison library includes: a database composed of a combination of identification IDs that can be used as a basis for determining a key area of a GPS positioning coordinate set;
[0110] The to-be-matched item determination unit is used to determine the to-be-matched item according to the identification type and the independent determination identification comparison library; wherein the to-be-matched item is: an identification item in the independent determination identification comparison library that is consistent with the identification type;
[0111] a target identification type determination unit, configured to match the first area identification of each identification type and use the identification type being matched as the target identification type;
[0112] A matching unit, used to determine whether the first area identifier of the target identifier type and the second area identifier of the target identifier type in the to-be-matched item match each other;
[0113] The determination unit is used to determine that if all the matches are consistent, the region information satisfies the independent determination rule, otherwise it does not satisfy the rule.
[0114] The working principle and beneficial effects of the above technical solution are:
[0115] This application obtains the unique first region identifier of the key region, and determines the items to be matched with the same identifier type composition according to the identifier type of the first region identifier and the independent determination identifier comparison library. Match the first region identifier of each identifier type, and determine whether the first region identifier of the target identifier type being matched and the second region identifier of the target identifier type in the items to be matched are consistent. If they are consistent, the region information meets the independent determination rule, otherwise it does not meet the rule, and the determination process of independent determination is more reasonable.
[0116] In one embodiment, the independently determined marker control library construction unit comprises:
[0117] The monitoring query record acquisition subunit is used to acquire the monitoring query record; wherein the monitoring query record is: a query log in the airport video monitoring system in which a person manually determines which area the visual interface belongs to based on an object in the video, including information such as a timestamp, a camera ID, and a querying person;
[0118] The key frame determination subunit is used to determine the key frame according to the monitoring query record; wherein the key frame is: a video frame of the captured video data whose dwell time is greater than or equal to a preset query time threshold;
[0119] The sight line information acquisition subunit is used to acquire the sight line information on the key frame; wherein the sight line information is: the sight line information when the querying person views the key frame;
[0120] The sight feature acquisition subunit is used to characterize the sight information and obtain the sight feature; wherein the sight feature is: a characteristic representation of the sight information, such as: a marker of the sight point, the duration of stay, and the incident angle, etc.;
[0121] The association relationship establishment subunit is used to establish the association relationship between the sight line feature and the key frame; wherein the association relationship is: which kind of attention marker corresponds to which key frame, and the attention marker is determined according to the sight line feature, for example: if the cumulative sight stay time of the marker at the sight point is greater than 6 seconds, it is regarded as the attention marker;
[0122] The independent determination identification acquisition model acquisition subunit is used to learn the association relationship using the deep learning model, and when the deep learning model is completed, the independent determination identification acquisition model is acquired; wherein the independent determination identification acquisition model is: an AI model that replaces manual work to determine which marker can determine which geographical area the picture belongs to based on the markers in the video;
[0123] The output association relationship acquisition subunit is used to input the captured video data into the independent determination mark acquisition model to obtain the output association relationship; wherein the output association relationship is: which marker corresponds to which video frame corresponding to which geographic area;
[0124] The independent determination identification comparison library construction subunit is used to construct the independent determination identification comparison library according to the output association relationship. When constructing the independent determination identification comparison library according to the output association relationship, the identification IDs of the identification objects of interest corresponding to the same video frame are divided into the same group and stored in the blank database. When each group is stored, the construction is completed.
[0125] The working principle and beneficial effects of the above technical solution are:
[0126] This application obtains monitoring query records in the airport video surveillance system that manually determine which area the visual interface belongs to based on the objects in the video, and determines the video frames (key frames) of the captured video data whose dwell time is greater than or equal to the preset query time threshold. Characterize the sight line information on the key frame to obtain the sight line feature. Establish an association between the sight line feature and the key frame, and then use the deep learning model to learn which focus marker corresponds to the key frame, and obtain the learned independent determination marker acquisition model. The independent determination marker acquisition model determines the marker that can determine which geographical area the picture belongs to based on the input captured video data, and divides the identification IDs of the markers of interest corresponding to the same video frame into the same group and stores them in a blank database to obtain an independent determination marker comparison library. The model is used to automatically learn the captured video data to obtain the independent determination marker information, which is more intelligent.
[0127] In one embodiment, the intrusion event acquisition module includes:
[0128] The airport map acquisition submodule is used to acquire an airport map containing the target area; wherein the airport map is: a map depicting the internal structure and geographical layout of the airport, including runways, terminals, aprons and road areas;
[0129] The route determination submodule is used to determine the route to the target area based on the airport map; wherein the route is: a route that can reach the target area;
[0130] The associated vehicle information acquisition submodule is used to acquire the associated vehicle information of the pass route; wherein the associated vehicle information is: relevant information of vehicles allowed to run on the pass route, such as: what kind of vehicle label and which pass time;
[0131] The associated vehicle feature acquisition submodule is used to characterize the associated vehicle information and obtain the associated vehicle features; wherein the associated vehicle features are: a characteristic representation of the associated vehicle information, for example: 3:00-4:00, the patrol vehicle No. 0087 is allowed to pass;
[0132] The electronic fence setting submodule is used to set the electronic fence of vehicles with different operation attributes based on the electronic fence technology and the characteristics of the associated vehicles; among which, the operation attributes are: the type of work of the vehicle:
[0133] The report information acquisition submodule is used to acquire the report information of the electronic fence system; wherein the report information is: information generated by the electronic fence system, including: which vehicles have entered or left which electronic fence area, and the time and date;
[0134] The intrusion event acquisition submodule is used to acquire the intrusion event according to the report information.
[0135] The working principle and beneficial effects of the above technical solution are:
[0136] This application obtains an airport map containing the target area and determines the route that can enter the target area. It obtains the associated vehicle information of the vehicles that are allowed to run on the route and determines the associated vehicle characteristics. It introduces electronic fence technology and sets the electronic fence according to the associated vehicle characteristics. After the setting is completed, the report information of the electronic fence system is obtained, and the report information is parsed to obtain the intrusion event, which improves the timeliness of the acquisition of the intrusion event.
[0137] In one embodiment, the associated vehicle information acquisition submodule includes:
[0138] The task release information acquisition unit is used to acquire task release information; wherein the task release information is: information released by the airport management department or the dispatch center about the task that the vehicle needs to perform, such as: dispatching a certain vehicle from where to where to transport luggage;
[0139] The vehicle task determination unit is used to determine the vehicle task according to the task release information; wherein the vehicle task is: the task that the vehicle needs to perform;
[0140] The mission location semantics determination unit is used to determine the mission location semantics according to the vehicle mission; wherein the mission location semantics is: the semantics of the location in the airport obtained by parsing the vehicle mission;
[0141] The driving trajectory planning unit is used to plan the driving trajectory on the airport map according to the semantics of the mission location; wherein the driving trajectory is obtained based on the route planning technology. During planning, it is determined that the semantics of the mission location corresponds to the starting position and the end position on the airport map, and then the route between the starting position and the end position is planned;
[0142] A route overlap section determination unit is used to determine the route overlap section according to the driving trajectory and the passing route; wherein the route overlap section is: the part where the driving trajectory and the passing route overlap;
[0143] The associated vehicle information determination unit is used to determine the associated vehicle information based on a preset associated vehicle information acquisition template according to the route overlap segment and the vehicle identification. The associated vehicle information acquisition template is used to generate the associated vehicle information by comparing the route overlap segment and the vehicle identification.
[0144] The working principle and beneficial effects of the above technical solution are:
[0145] This application determines the vehicle task based on the obtained task release information. Perform semantic analysis on the vehicle task to obtain the task location semantics. Based on the task location semantics, determine that the task location semantics corresponds to the starting position and the end position on the airport map, and then plan the driving trajectory between the starting position and the end position. Determine the route overlap segment between the driving trajectory and the pass route. Introduce an associated vehicle information acquisition template, determine the associated vehicle information based on the route overlap segment and the vehicle identification, and improve the rationality of the associated vehicle information acquisition.
[0146] The embodiment of the present invention provides a vehicle position intelligent video monitoring method, such as Figure 2 As shown, including:
[0147] Step 1: Obtain warning information, including: vehicle intrusion area and vehicle real-time positioning information;
[0148] Step 2: Obtain the video data of the vehicle intrusion area;
[0149] Step 3: Determine the GPS positioning coordinate set of the vehicle intrusion area according to the captured video data;
[0150] Step 4: According to the real-time positioning information of the vehicle, determine the vehicle position coordinates in the GPS positioning coordinate set, and mark the vehicle position coordinates in the vehicle intrusion area screen accordingly.
[0151] In one embodiment, step 1: obtaining warning information includes:
[0152] Step 1: Obtain warning information, including:
[0153] Try to get intrusion information in the target area;
[0154] If the acquisition attempt is successful, the intrusion event is analyzed and the warning information is determined.
[0155] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.
Claims
1. A vehicle position intelligent video monitoring device, characterized in that: include: The early warning information acquisition subsystem is used to obtain early warning information, including: vehicle intrusion area and vehicle real-time positioning information; A shooting video data acquisition subsystem, used to acquire shooting video data of the area where the vehicle intrudes; A GPS positioning coordinate set determination subsystem, used to determine the GPS positioning coordinate set of the vehicle intrusion area screen according to the captured video data; The vehicle marking subsystem is used to determine the vehicle position coordinates in the GPS positioning coordinate set according to the real-time vehicle positioning information, and mark the vehicle position coordinates in the vehicle intrusion area screen accordingly; The GPS positioning coordinate set determination subsystem includes: A regional GPS information determination module is used to determine regional GPS information according to the area intruded by the vehicle; A regional GPS information mapping rule determination module is used to determine the regional GPS information mapping rule based on the captured video data; A GPS positioning coordinate set acquisition module, used to acquire a GPS positioning coordinate set according to regional GPS information and regional GPS information mapping rules; The regional GPS information mapping rule determination module includes: A key area marking submodule is used to mark key areas in the captured video data; The regional information acquisition submodule is used to obtain regional information of key areas; An independent determination rule determination submodule is used to determine whether the regional information satisfies the independent determination rule according to the regional information; A first rule determination submodule, for obtaining a first geographic feature of a key area if the area information satisfies an independent determination rule, and determining a regional GPS information mapping rule based on the first geographic feature; The second rule determination submodule is used to obtain the first geographical feature of the key area and the second geographical feature of the non-key area if the area information does not meet the independent determination rule, and determine the regional GPS information mapping rule according to the first geographical feature and the second geographical feature; The second rule determines the submodule, including: A feature combination determining unit, configured to determine a feature combination according to the first geographical feature and the second geographical feature; A regional GPS information mapping rule determination unit, used to determine the regional GPS information mapping rule according to the feature combination; Independent decision rule decision submodule, including: An area type acquisition unit, used for parsing the area information and acquiring a first area identifier of a key area; An identification type acquisition unit, used to acquire the identification type of the first area identification; An independent determination marker control library construction unit, used to construct an independent determination marker control library; A unit for determining items to be matched, used to determine items to be matched according to the identification type and the independent determination identification reference library; a target identification type determination unit, configured to match the first area identification of each identification type and use the identification type being matched as the target identification type; A matching unit, used to determine whether the first area identifier of the target identifier type and the second area identifier of the target identifier type in the to-be-matched item match each other; A determination unit, used for determining that if all the matches are consistent, the region information satisfies the independent determination rule, otherwise it does not satisfy the rule; Independent determination of the identification control library construction unit, including: A monitoring query record acquisition subunit is used to acquire monitoring query records; A key frame determination subunit, used to determine the key frame according to the monitoring query record; A sight line information acquisition subunit, used to acquire sight line information on a key frame; A sight feature acquisition subunit, used to characterize sight information and acquire sight features; An association relationship establishment subunit is used to establish an association relationship between sight line features and key frames; An independent determination mark acquisition model acquisition subunit is used to learn the association relationship using a deep learning model, and when the deep learning model is completed, the independent determination mark acquisition model is acquired; An output association relationship acquisition subunit is used to input the captured video data into the independent determination identifier acquisition model to acquire the output association relationship; The independent determination identification reference library construction subunit is used to construct an independent determination identification reference library according to the output association relationship.
2. The vehicle position intelligent video monitoring device according to claim 1, characterized in that: The early warning information acquisition subsystem includes: An intrusion event acquisition module, used for attempting to acquire intrusion events in a target area; The warning information determination module is used to analyze the intrusion event and determine the warning information if the acquisition attempt is successful.
3. A vehicle position intelligent video monitoring device as claimed in claim 2, characterized in that: The intrusion event acquisition module includes: The airport map acquisition submodule is used to obtain the airport map containing the target area; The passage route determination submodule is used to determine the passage route of the target area according to the airport map; The associated vehicle information acquisition submodule is used to acquire the associated vehicle information of the passing route; The associated vehicle feature acquisition submodule is used to characterize the associated vehicle information and acquire the associated vehicle features; The electronic fence setting submodule is used to set the electronic fences of vehicles with different operation attributes based on the electronic fence technology and the characteristics of the associated vehicles; The report information acquisition submodule is used to obtain the report information of the electronic fence system; The intrusion event acquisition submodule is used to acquire the intrusion event according to the report information.
4. The vehicle position intelligent video monitoring device according to claim 3, characterized in that: The associated vehicle information acquisition submodule includes: A task release information acquisition unit, used to acquire task release information; A vehicle task determination unit, used to determine the vehicle task according to the task release information; A task location semantics determination unit, used to determine the task location semantics according to the vehicle task; The driving trajectory planning unit is used to plan the driving trajectory on the airport map according to the semantics of the mission location; A route overlap section determination unit, used to determine the route overlap section according to the driving trajectory and the passing route; The associated vehicle information determining unit is used to determine the associated vehicle information based on a preset associated vehicle information acquisition template and according to the route overlap section and the vehicle identification.
5. A vehicle position intelligent video monitoring method, characterized in that: include: Step 1: Obtain warning information, including: vehicle intrusion area and vehicle real-time positioning information; Step 2: Obtain the video data of the vehicle intrusion area; Step 3: Determine the GPS positioning coordinate set of the vehicle intrusion area according to the captured video data; Step 4: According to the real-time positioning information of the vehicle, determine the vehicle position coordinates in the GPS positioning coordinate set, and mark the vehicle position coordinates in the vehicle intrusion area screen accordingly; Step 3: Determine the GPS coordinate set of the vehicle intrusion area based on the captured video data, including: Determine the regional GPS information based on the area intruded by the vehicle; Determine regional GPS information mapping rules based on captured video data; Obtaining a GPS positioning coordinate set according to regional GPS information and regional GPS information mapping rules; According to the captured video data, determine the regional GPS information mapping rules, including: Marking key areas in captured video data; Get regional information of key areas; According to the regional information, judging whether the regional information satisfies the independent determination rule; If the regional information satisfies the independent determination rule, the first geographical feature of the key area is obtained, and the regional GPS information mapping rule is determined according to the first geographical feature; If the regional information does not meet the independent determination rule, the first geographical feature of the key area is obtained, and at the same time, the second geographical feature of the non-key area is obtained, and the regional GPS information mapping rule is determined according to the first geographical feature and the second geographical feature; If the regional information does not meet the independent determination rule, the first geographical feature of the key area is obtained, and at the same time, the second geographical feature of the non-key area is obtained. According to the first geographical feature and the second geographical feature, the regional GPS information mapping rule is determined, including: Determining a feature combination based on the first geographic feature and the second geographic feature; Determine regional GPS information mapping rules based on feature combinations; According to the regional information, it is judged whether the regional information satisfies the independent judgment rule, including: Parse the area information and obtain the first area identifier of the key area; Obtaining the identification type of the first area identification; Construct an independent determination identification control library; Determine the items to be matched according to the identification type and the independent identification reference library; Match the first area identifier of each identifier type, and use the identifier type being matched as the target identifier type; Determine whether the first area identifier of the target identifier type and the second area identifier of the target identifier type in the to-be-matched item match each other; If all matches are consistent, the region information meets the independent judgment rule, otherwise it does not; Construct an independent identification reference library, including: Get monitoring query records; Determine the key frame according to the monitoring query record; Get the sight line information on the key frame; Characterize the sight line information and obtain sight line features; Establish the association between sight features and key frames; The deep learning model is used to learn the association relationship. When the deep learning model is completed, the independent judgment mark acquisition model is obtained; Input the captured video data into the independent determination identification acquisition model to obtain the output association relationship; Based on the output association relationship, an independent judgment identification reference library is constructed.
6. A vehicle position intelligent video monitoring method as claimed in claim 5, characterized in that: Step 1: Obtain warning information, including: Try to get intrusion information in the target area; If the acquisition attempt is successful, the intrusion event is analyzed and the warning information is determined.
Citation Information
Patent Citations
Method and system for video-based positioning and mapping
CN110062871A
Traffic flow parameter real-time detection method based on traffic monitoring video
CN110033479A
Method and system for identifying position of vehicle in monitoring video
CN111597954A
Localization system for monitoring objects in real-time
WO2014195164A2
A device, method and system for vehicle monitoring by using GPS position of vehicle for making payment collected by various authorities associtaed with the vehicle
WO2021250695A1
