License plate information determination method and device, electronic equipment and storage medium

Abstract

The invention provides a license plate information determination method and device, electronic equipment and a storage medium, and relates to the technical field of monitoring, and the method comprises the steps: determining a target closed region through which an illegal parking vehicle passes based on the target feature information in an illegal parking snapshot image; determining a target gate monitoring device through which the illegal parking vehicle passes according to the target closed area and the road relation map; determining first license plate information jointly collected by the target checkpoint monitoring devices, and determining target license plate information of the illegal parking vehicle in the first license plate information; wherein the road relation map comprises a closed area node, a bayonet monitoring equipment node and an access relation between the closed area node and the bayonet monitoring equipment node, and the access of the closed area node is provided with bayonet monitoring equipment. According to the technical scheme provided by the invention, the license plate information of the illegal parking vehicle can be determined under the condition that the license plate of the illegal parking vehicle cannot be captured on the roadside of the no-parking area, and the purpose of illegal parking confirmation is achieved.

Description

Technical Field

[0001] The present invention relates to the field of monitoring technology, and in particular to a method, device, electronic equipment and storage medium for determining license plate information. Background Art

[0002] Illegally parked vehicle detection plays an important role in road traffic management. In related technologies, illegally parked vehicles can be detected by roadside illegal parking capture equipment. If the same vehicle is captured twice at the same location in the illegal parking area, and the capture time interval is greater than the set threshold, the vehicle is confirmed as an illegally parked vehicle. This method requires capturing the license plate of the illegally parked vehicle during the illegal parking period to confirm the illegal parking, but due to obstructions between vehicles, obstructions by trees beside the road, blind spots in the shooting angle, etc., there may be situations where the license plate cannot be captured. In this way, if the license plate is not captured, the identity of the illegally parked vehicle cannot be obtained to confirm the illegal parking. Summary of the invention

[0003] The present invention provides a method, device, electronic device and storage medium for determining license plate information, so as to solve the problem in the prior art that illegal parking cannot be confirmed when the license plate of the illegally parked vehicle cannot be captured on the roadside, thereby determining the license plate information of the illegally parked vehicle and achieving the purpose of illegal parking confirmation.

[0004] The present invention provides a method for determining license plate information, comprising:

[0005] Based on the target feature information in the illegally parked image, determine the target closed area where the illegally parked vehicle passes;

[0006] Determine the target checkpoint monitoring device that the illegally parked vehicle passes through according to the target closed area and road relationship map; wherein the road relationship map includes closed area nodes, checkpoint monitoring device nodes, and entry and exit relationships between the closed area nodes and the checkpoint monitoring device nodes, and checkpoint monitoring devices are set at the entrances and exits of the closed area nodes;

[0007] The first license plate information collected by each of the target checkpoint monitoring devices is determined, and the target license plate information of the illegally parked vehicle is determined in the first license plate information.

[0008] According to a method for determining license plate information provided by the present invention, the determining of the first license plate information collected by each target checkpoint monitoring device comprises:

[0009] For each of the target checkpoint monitoring devices, based on the first time when the roadside monitoring device in the target closed area connected to the target checkpoint monitoring device collects the target roadside monitoring image, determine the target time for the target checkpoint monitoring device to collect the image of the illegally parked vehicle; wherein the target roadside monitoring image is an image containing the target feature information;

[0010] Acquire a first target vehicle image captured by the target checkpoint monitoring device at the corresponding target time;

[0011] Determine the intersection of the first target vehicle images between the target checkpoint monitoring devices to obtain the first license plate information.

[0012] According to a method for determining license plate information provided by the present invention, determining the target license plate information of the illegally parked vehicle in the first license plate information includes:

[0013] In the case where the first license plate information is at least two, determining a new target checkpoint monitoring device through which the illegally parked vehicle passes;

[0014] Acquire a second target vehicle image captured by the new target checkpoint monitoring device;

[0015] The license plate information included in both the second target vehicle image and the first license plate information is determined, and the target license plate information of the illegally parked vehicle is determined in the license plate information.

[0016] According to a method for determining license plate information provided by the present invention, the target time for the target checkpoint monitoring device to collect images of the illegally parked vehicle is determined based on the first time when the roadside monitoring device in the target closed area connected to the target checkpoint monitoring device collects the target roadside monitoring image, including:

[0017] For each target closed area in the target closed area connected to the target checkpoint monitoring device, obtaining the position information of the first target roadside monitoring device in the target closed area; the first target roadside monitoring device is the roadside monitoring device that has collected the target roadside monitoring image;

[0018] The target time for the target checkpoint monitoring device to capture the image of the illegally parked vehicle is determined based on the first time and the position information when the first target roadside monitoring device in each of the target closed areas captures the target roadside monitoring image.

[0019] According to a method for determining license plate information provided by the present invention, the method of determining a target closed area passed by an illegally parked vehicle based on target feature information in an illegally parked captured image includes:

[0020] Based on the target feature information in the illegal parking capture image, determining a second target roadside monitoring device corresponding to the roadside monitoring image containing the target feature information;

[0021] Determine the target closed area through which the illegally parked vehicle passes according to the position information of the second target roadside monitoring device;

[0022] Wherein, the target feature information includes vehicle feature information of the illegally parked vehicle and / or human feature information of the driver of the illegally parked vehicle.

[0023] According to a method for determining license plate information provided by the present invention, the road relationship graph is constructed based on the following steps:

[0024] Determine a basic road section from the acquired map road network data, wherein the exit of the basic road section is provided with a checkpoint monitoring device;

[0025] If no checkpoint monitoring device is installed at the entrance of the basic road section, determine a target related road section related to the entrance of the basic road section, and if no checkpoint monitoring device is installed at the entrance of the target related road section, determine the target related road section as a new basic road section, and repeat the above steps until a target related road section with a checkpoint monitoring device installed at the entrance is found;

[0026] The basic road section and all the target-related road sections form a closed area, determine the closed area node based on the closed area, and determine the checkpoint monitoring device set at the exit of the basic road section and the checkpoint monitoring device set at the entrance of the target-related road section where the checkpoint monitoring device is set as the checkpoint monitoring device node respectively;

[0027] The road relationship map is constructed based on the closed area node, the checkpoint monitoring device node, and the entry and exit relationship between the closed area node and the checkpoint monitoring device node.

[0028] According to a method for determining license plate information provided by the present invention, determining the closed area node based on the closed area includes:

[0029] Acquire first vehicle data of all imported vehicles in the closed area and second vehicle data of all exported vehicles in the closed area within a preset historical time period;

[0030] determining a proportion of the same vehicle data between the first vehicle data and the second vehicle data to the first vehicle data;

[0031] When the ratio is greater than a preset ratio threshold, the second closed area is determined as the closed area node.

[0032] The present invention also provides a vehicle license plate information determination device, comprising:

[0033] An area determination module is used to determine the target closed area through which the illegally parked vehicle passes based on the target feature information in the illegally parked image;

[0034] A checkpoint determination module, used to determine the target checkpoint monitoring device through which the illegally parked vehicle passes according to the target closed area and road relationship map; wherein the road relationship map includes closed area nodes, checkpoint monitoring device nodes, and entry and exit relationships between the closed area nodes and the checkpoint monitoring device nodes, and checkpoint monitoring devices are provided at the entry and exit of the closed area nodes;

[0035] The license plate determination module is used to determine the first license plate information collected by each of the target checkpoint monitoring devices, and determine the target license plate information of the illegally parked vehicle in the first license plate information.

[0036] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, any of the above-mentioned methods for determining license plate information is implemented.

[0037] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method for determining license plate information as described above is implemented.

[0038] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method for determining license plate information as described above is implemented.

[0039] The method, device, electronic device and storage medium for determining license plate information provided by the present invention first determine the target closed area through which the illegally parked vehicle passes based on the target feature information in the illegally parked captured image, and then determine the target checkpoint monitoring device through which the illegally parked vehicle passes based on the target closed area and the road relationship map. When the illegally parked vehicle passes through these target checkpoint monitoring devices, the license plate will be captured. The road relationship map includes closed area nodes, checkpoint monitoring device nodes and the entry and exit relationships between the closed area nodes and the checkpoint monitoring device nodes. The entrance and exit of each closed area node are all provided with a checkpoint monitoring device. In this way, the road relationship map can be used to identify the license plate information of the illegally parked vehicle. The network is characterized by closed areas, checkpoint monitoring equipment, and the in-and-out relationship between the two, which is convenient for locating illegally parked vehicles; then the first license plate information collected by each target checkpoint monitoring equipment is determined, and the target license plate information of the illegally parked vehicle is determined in the first license plate information. For the same illegally parked vehicle, each target checkpoint monitoring equipment it passes through can collect the license plate information of the illegally parked vehicle. In this way, the first license plate information collected by each target checkpoint monitoring equipment is most likely the license plate information of the illegally parked vehicle, and the target license plate information of the illegally parked vehicle can be determined in the first license plate information, thereby realizing the determination of the license plate information of the illegally parked vehicle. Even if the license plate of the illegally parked vehicle cannot be captured on the roadside of the no-parking zone, the license plate information of the illegally parked vehicle can be determined using the license plate information collected by the target checkpoint monitoring equipment that the illegally parked vehicle passes through, thereby achieving the purpose of illegal parking confirmation. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 is a flow chart of a method for determining license plate information provided by an embodiment of the present invention;

[0042] Figure 2 It is a schematic diagram of a process of constructing a road relationship map provided by an embodiment of the present invention;

[0043] Figure 3 This is one of the schematic diagrams of the principle of determining a closed area in an embodiment of the present invention;

[0044] Figure 4 This is the second schematic diagram of the principle of determining a closed area in an embodiment of the present invention;

[0045] Figure 5 is a schematic diagram of the structure of a road relationship graph in an embodiment of the present invention;

[0046] Figure 6 is a schematic diagram of the structure of a device for determining license plate information provided by an embodiment of the present invention;

[0047] Figure 7 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] It should be noted that the serial numbers assigned to the objects described in the present invention, such as "first", "second", etc., are only used to distinguish the objects described and do not have any order or technical meaning.

[0050] Illegal parking of vehicles can be detected by using a parking ball or a detection system designed for illegal parking. These methods require capturing the vehicle's license plate during the period of illegal parking in order to confirm the illegally parked vehicle. However, no-parking zones may not have devices designed to detect illegal parking. Or, devices designed to detect illegal parking may be installed but the license plate may not be captured by the devices due to obstruction between vehicles or trees along the road. In this case, personnel are required to handle the situation on site, wasting human resources.

[0051] As for urban roads, there are many roadside monitoring devices installed on both sides of the road, which can monitor the monitored road sections for security, and vehicles can be captured through these roadside monitoring devices. At the same time, when a vehicle passes through an intersection, if there is a checkpoint monitoring device at the intersection, the license plate of the vehicle can be photographed by the checkpoint monitoring device.

[0052] Based on this, an embodiment of the present invention provides a method for determining license plate information, which can construct a road relationship map based on the setting position of the checkpoint monitoring equipment in the map road network data, and the road relationship map includes closed area nodes, checkpoint monitoring equipment nodes and the entry and exit relationship between the closed area nodes and the checkpoint monitoring equipment nodes. The entrance and exit of each closed area node are equipped with checkpoint monitoring equipment. Through the road relationship map, the import and exit relationship between the road area and the checkpoint monitoring equipment in the map road network can be reflected; on this basis, the target closed area passed by the illegally parked vehicle can be determined based on the target feature information of the illegally parked vehicle captured by the roadside illegal parking capture device, and the target checkpoint monitoring equipment passed by the illegally parked vehicle is determined according to the target closed area and the road relationship map, and the first license plate information collected by these target checkpoint monitoring equipment is searched. These first license plate information are most likely the license plate information of the illegally parked vehicle, and the target license plate information of the illegally parked vehicle can be determined therefrom. For example, when there is only one first license plate information, it can be directly determined as the target license plate information of the illegally parked vehicle; or, when there are multiple first license plate information, it can be output to the illegal parking supervisor for further confirmation, or the search range of the checkpoint monitoring equipment can be further expanded for further retrieval and confirmation until the only license plate information is determined. In this way, if the license plate of the illegally parked vehicle cannot be captured on the roadside of the prohibited parking area, the license plate information of the illegally parked vehicle can be determined by using the license plate information collected by the target checkpoint monitoring equipment that the illegally parked vehicle passes through, thereby achieving the purpose of illegal parking confirmation.

[0053] Combine the following Figure 1-Figure 5 The license plate information determination method of the present invention is described. The license plate information determination method can be applied to electronic devices such as terminal devices or servers. The terminal devices may include mobile phones, computers, vehicle-mounted devices, tablet computers, wearable devices, etc.; the servers may include independent servers, cluster servers or cloud servers, etc. The license plate information determination method can also be applied to a license plate information determination device set in an electronic device such as a terminal device or a server, and the license plate information determination device can be implemented by software, hardware or a combination of both.

[0054] Figure 1 The flowchart of the method for determining the license plate information provided by the embodiment of the present invention is exemplarily shown. Figure 1 As shown, the license plate information determination method may include the following steps 110 to 130.

[0055] Step 110: Based on the target feature information in the illegally parked vehicle captured image, determine the target closed area that the illegally parked vehicle passed through.

[0056] The target feature information may include vehicle feature information of the illegally parked vehicle and / or body feature information of the driver of the illegally parked vehicle.

[0057] Exemplarily, the vehicle characteristic information of the illegally parked vehicle may include at least one of the vehicle body identification feature, vehicle body painting feature, vehicle model feature, and vehicle body color feature, but is not limited thereto. The driver's body characteristic information may be the body characteristic information when the driver opens the door to get off the vehicle or the body characteristic information when the driver opens the door to get on the vehicle, or the body characteristic information of the driver sitting in the vehicle seat collected through the window glass or windshield, etc.

[0058] When the roadside illegal parking capture device or ordinary roadside monitoring equipment captures the same vehicle twice at the same location in the no-parking zone, and the capture time interval is greater than the set threshold, the vehicle is determined to be an illegally parked vehicle. At this time, the vehicle feature information of the illegally parked vehicle and / or the human feature information of the driver of the illegally parked vehicle can be extracted from the illegally parked captured image of the illegally parked vehicle.

[0059] For example, after capturing an illegally parked vehicle's captured image, it can be determined whether the illegally parked vehicle's license plate information is included in the illegally parked vehicle's captured image. If so, the license plate information of the illegally parked vehicle can be directly obtained; if not, the target feature information in the illegally parked vehicle's captured image can be obtained.

[0060] For a road section in a road network, a road checkpoint can be set at the entrance and / or exit, and the checkpoint monitoring equipment of the road checkpoint can be used to monitor vehicles passing through the road section and collect vehicle images including license plates. According to the location where the checkpoint monitoring equipment is set and the road network information of the road section where it is located, the import and export attributes of the checkpoint monitoring equipment can be determined, or the import and export attributes of the checkpoint monitoring equipment can be directly saved in the road network data. Based on this, according to the setting location of the checkpoint monitoring equipment in the map road network data and its import and export attributes, and combined with the connectivity relationship of each road section in the map road network data, the road area where the import and export are both set with checkpoint monitoring equipment can be determined. It can be understood that a road area can include at least one road section, these road sections form a connected road network area, and the import and export of the road area are both set with checkpoint monitoring equipment. Based on this, the road area can be regarded as a closed area where both the regional import and regional exit are monitored, and the road network can be divided into multiple closed areas accordingly.

[0061] The target feature information can be used to identify illegally parked vehicles. When the illegally parked vehicles leave the no-parking zone, the closed area where the roadside monitoring equipment that can collect roadside monitoring images matching the target feature information is located can be determined as the target closed area based on the target feature information.

[0062] Step 120: Determine the target checkpoint monitoring device through which the illegally parked vehicle passes according to the target closed area and the road relationship map.

[0063] The road relationship map is constructed based on the location of the checkpoint monitoring equipment in the map road network data, and includes closed area nodes, checkpoint monitoring equipment nodes, and the entry and exit relationships between the closed area nodes and the checkpoint monitoring equipment nodes. The entrances and exits of the closed area nodes are all equipped with checkpoint monitoring equipment. The checkpoint monitoring equipment may include at least one of image acquisition devices such as cameras and cameras.

[0064] The road relationship map can reflect the import and export relationship between the closed areas and the checkpoint monitoring equipment in the map road network. For a closed area, the checkpoint monitoring equipment at its import and export can be known according to the road relationship map; and two adjacent closed areas can be connected through a checkpoint monitoring equipment, which is both the entrance checkpoint monitoring equipment of one of the two adjacent closed areas and the exit checkpoint monitoring equipment of the other closed area. After determining the target closed areas through which the illegally parked vehicle passes according to step 110, the checkpoint monitoring equipment that the illegally parked vehicle passes through when passing through these target closed areas in sequence can be determined according to the road relationship map, that is, the target checkpoint monitoring equipment is obtained.

[0065] Exemplarily, the road network data within the closed area can be saved in the road relationship map as an attribute of the closed area.

[0066] Step 130: Determine the first license plate information collected by each target checkpoint monitoring device, and determine the target license plate information of the illegally parked vehicle in the first license plate information.

[0067] After the target checkpoint monitoring device is determined, for each target checkpoint monitoring device, the target time for the target checkpoint monitoring device to collect images of illegally parked vehicles can be determined based on the first time when the roadside monitoring device in the target closed area connected to it collects the target roadside monitoring image. After the target time of each target checkpoint monitoring device is determined, the first target vehicle image collected by each target checkpoint monitoring device within its corresponding target time is obtained, and the license plate intersection of the first target vehicle images between the target checkpoint monitoring devices is taken to obtain the first license plate information. Among them, the target roadside monitoring image is a roadside monitoring image that contains target feature information.

[0068] Exemplarily, after determining the target time of each target checkpoint monitoring device, for each target checkpoint monitoring device, the first vehicle image captured by the target checkpoint monitoring device during its corresponding target time can be obtained first, and then the second vehicle image containing the target feature information can be searched from the first vehicle image, and the second vehicle image can be determined as the first target vehicle image. In this way, the target feature information can be used to filter out vehicle images that do not match illegally parked vehicles, reduce the number of non-illegally parked vehicle images when determining the first license plate information, improve the efficiency and accuracy of determining the first license plate information, and further improve the efficiency and accuracy of determining the target license plate information.

[0069] Since the illegally parked vehicle passes through each target checkpoint monitoring device, each target checkpoint monitoring device can collect the license plate information of the illegally parked vehicle. In this way, the first license plate information collected by each target checkpoint monitoring device is most likely the license plate information of the illegally parked vehicle, and the target license plate information of the illegally parked vehicle can be further determined from the first license plate information. For example, when there is only one first license plate information, the first license plate information can be determined as the target license plate information of the illegally parked vehicle; or, when there are at least two first license plate information, the first license plate information can be output to the illegal parking supervisor for further confirmation, or the search range of the checkpoint monitoring device can be further expanded, and the first target vehicle image collected by the expanded new target checkpoint monitoring device can be used to further screen the first license plate information until a unique license plate information is determined, and the license plate information is used as the target license plate information.

[0070] It is understandable that the electronic device can determine all target checkpoint monitoring devices that the illegally parked vehicle has passed through based on the target feature information and the road relationship map, take the intersection of the license plate information of the first target vehicle image between each target checkpoint monitoring device, obtain the first license plate information, and then determine the target license plate information in the first license plate information. Alternatively, the electronic device can first determine two target checkpoint monitoring devices based on the target feature information and the road relationship map, take the first license plate information collected by the two target checkpoint monitoring devices, and then determine the common license plate information once each time a target checkpoint monitoring device is determined, that is, take the license plate information intersection of the first target vehicle image of the target checkpoint monitoring device determined each time and the first license plate information determined previously, and screen out the common license plate. As long as there are multiple common license plates, continue to expand to the next target checkpoint monitoring device until the screened common license plate is one, and the license plate information of the license plate is determined as the target license plate information.

[0071] Exemplarily, for each target checkpoint monitoring device, any one target closed area can be selected from the two adjacent target closed areas connected to it, and the target time for the target checkpoint monitoring device to collect images of illegally parked vehicles can be determined based on the first time when the roadside monitoring device in the target closed area collects the roadside monitoring image containing the target feature information. For example, the time when the illegally parked vehicle travels to the target checkpoint monitoring device can be estimated based on the first time in combination with the road network speed, and the time or the time of the preset time period before and after the time can be determined as the target time. For another example, the selected target closed area and the target checkpoint monitoring device have an exit in and out relationship, and the second time when the illegally parked vehicle arrives at the target checkpoint monitoring device can be determined based on the first time and position information when the first roadside monitoring device in the target closed area collects the target roadside monitoring image, and the second time can be determined as the target time, or the time range of the preset time period before and after the second time can be determined as the target time. Among them, the first target roadside monitoring device is the roadside monitoring device that collects the target roadside monitoring image.

[0072] For example, an illegally parked vehicle needs to pass through the target checkpoint monitoring device A when traveling from the target closed area 1 to the target closed area 2. The time when the illegally parked vehicle is collected in the target closed area 1 is t1. According to the road network data in the target closed area 1, the road network speed in the target closed area 1, the location information of the roadside monitoring device that collects the illegally parked vehicle, and the location information of the target checkpoint monitoring device A at the exit of the target closed area 1 can be obtained. According to the road network speed, the location information of the roadside monitoring device, and the location information of the target checkpoint monitoring device A, the time t required for the illegally parked vehicle to travel from the location where the target closed area 1 is collected to the target checkpoint monitoring device A can be determined. Based on the time t and t1, the second time t2=t1+t at which the illegally parked vehicle arrives at the target checkpoint monitoring device A can be determined, and the time period from t2 or (t2-Δt) to (t2+Δt) can be determined as the target time. Wherein, Δt is a preset time period.

[0073] Exemplarily, for each target checkpoint monitoring device, the first time when the respective roadside monitoring devices in the two adjacent target closed areas connected to it respectively capture images of illegally parked vehicles can be obtained, and the time period formed by the two first times can be determined as the target time for the target checkpoint monitoring device to capture images of the illegally parked vehicles; or, the second time when the illegally parked vehicle arrives at the target checkpoint monitoring device can be determined based on the two first times and the position information of the roadside monitoring devices that respectively capture images of the illegally parked vehicles, and the second time can be determined as the target time, or the time range of a preset time period before and after the second time can be determined as the target time.

[0074] It can be understood that according to the target time corresponding to each target checkpoint monitoring device, the vehicle images collected by the illegally parked vehicles passing through each target checkpoint monitoring device in sequence can be obtained in chronological order, and the target vehicle image can be acquired within the time period when the illegally parked vehicles pass through the target checkpoint monitoring device, thereby ensuring that the vehicle image of the illegally parked vehicles is acquired.

[0075] The license plate information determination method provided by the embodiment of the present invention first determines the target closed area through which the illegally parked vehicle passes based on the target feature information in the illegally parked captured image, and then determines the target checkpoint monitoring device through which the illegally parked vehicle passes according to the target closed area and the road relationship map. When the illegally parked vehicle passes through these target checkpoint monitoring devices, the license plate will be captured. The road relationship map includes closed area nodes, checkpoint monitoring device nodes, and the entry and exit relationships between the closed area nodes and the checkpoint monitoring device nodes. The entrance and exit of each closed area node are all provided with a checkpoint monitoring device. In this way, the road network can be mapped into a closed area through the road relationship map. The domain, the checkpoint monitoring equipment and the in-and-out relationship between the two are characterized to facilitate the positioning of illegally parked vehicles; then the first license plate information collected by each target checkpoint monitoring equipment is determined, and the target license plate information of the illegally parked vehicle is determined in the first license plate information. For the same illegally parked vehicle, each target checkpoint monitoring equipment it passes through can collect the license plate information of the illegally parked vehicle. In this way, the first license plate information collected by each target checkpoint monitoring equipment is very likely to be the license plate information of the illegally parked vehicle, and the target license plate information of the illegally parked vehicle can be determined in the first license plate information, thereby realizing the determination of the license plate information of the illegally parked vehicle. Even if the license plate of the illegally parked vehicle cannot be captured on the roadside, the license plate information of the illegally parked vehicle can be determined using the license plate information collected by the target checkpoint monitoring equipment that the illegally parked vehicle passes through, thereby achieving the purpose of illegal parking confirmation.

[0076] based on Figure 1 The method for determining the license plate information of the corresponding embodiment, Figure 2 A schematic diagram showing a flow chart of a method for constructing a road relationship graph in an embodiment of the present invention is shown as an example. Figure 2 As shown, the road relationship map can be constructed based on the following steps 210 to 250.

[0077] Step 210: Determine a basic road section from the acquired map road network data, wherein a checkpoint monitoring device is provided at the exit of the basic road section.

[0078] In the map road network data, some sections of the road will be set up with road checkpoints, and the vehicles passing through will be monitored by the checkpoint monitoring equipment at the road checkpoints. For example, checkpoint monitoring equipment can be set up for import checkpoints, export checkpoint monitoring equipment, or checkpoint monitoring equipment can be set up for import and export. A section of the road with a checkpoint monitoring equipment set up at the export can be selected from the map road network data as the basic section, that is, a section of the road with a checkpoint monitoring equipment set up in the departure direction can be selected.

[0079] Step 220: In the case where no checkpoint monitoring equipment is provided at the entrance of the basic road section, a target related road section related to the entrance of the basic road section is determined.

[0080] After selecting the basic road section, determine whether the entrance of the basic road section is also equipped with checkpoint monitoring equipment. If so, the basic road section is a monitored closed section. The basic road section can be directly determined as a closed area to obtain a closed area node.

[0081] If the entrance of the basic section is not equipped with checkpoint monitoring equipment, the import-related sections are extended according to the map road network data, and the target import-related sections are determined from the sections connected to the entrance and through which vehicles can enter the entrance. Specifically, multiple road sections can be connected at intersections such as T-junctions and crossroads, and the entrance of each road section can converge from the three driving directions of left turn, right turn and straight ahead. When there is no checkpoint monitoring equipment at the entrance of the basic road section, first determine an extended road section from the relevant road sections that can enter the entrance. If there is no checkpoint monitoring equipment at the exit of the extended road section in the driving direction of entering the entrance of the basic road section, then determine whether a checkpoint monitoring equipment is set at the exit direction of the extended road section entering other relevant road sections. If so, there is no need to continue to extend to other relevant road sections, and the extended road section is determined as the target relevant road section; if there is no checkpoint monitoring equipment at the exit direction of the extended road section entering any of the other relevant road sections, then continue to extend to one of the relevant road sections, make the same judgment and extension for all other relevant road sections, and determine all extended relevant road sections as target relevant road sections.

[0082] Step 230: If the entrance of the target relevant road section is not equipped with a checkpoint monitoring device, the target relevant road section is determined as a new basic road section, and the above steps are repeated until a target relevant road section with an checkpoint monitoring device installed at the entrance is found.

[0083] After determining the target relevant road section, determine whether the entrance of the target relevant road section is equipped with a checkpoint monitoring device. If so, the entrance and exit of the road area composed of the target relevant road section and the basic road section have checkpoint monitoring devices, forming a closed road monitoring area. The basic road section and the target relevant road section can be combined into a closed area to obtain a closed area node. If the entrance of the target relevant road section is not equipped with a checkpoint monitoring device, the target relevant road section is determined as a new basic road section, and steps 220 to 230 are repeated. The search is continued until the target relevant road section with a checkpoint monitoring device installed at the entrance is found.

[0084] Step 240: The basic road section and all target-related road sections are grouped into a closed area, the closed area nodes are determined based on the closed area, and the checkpoint monitoring equipment set at the exit of the basic road section and the checkpoint monitoring equipment set at the import of the target-related road section with the checkpoint monitoring equipment set at the import are respectively determined as checkpoint monitoring equipment nodes.

[0085] For example, Figure 3 One of the schematic diagrams of the principle of determining a closed area in an embodiment of the present invention is exemplified, taking the case where a checkpoint monitoring device does not distinguish lanes as an example, referring to Figure 3 As shown, the north exit and the south exit of section 1 are respectively provided with checkpoint monitoring equipment 311 and checkpoint monitoring equipment 312. With section 1 as the basic section, the checkpoint monitoring equipment 331 is provided at the southward entrance left turn direction, but no checkpoint monitoring equipment is provided at the southward right turn direction. At this time, section 1 is extended to section 2 to check the situation of section 2. Since the exit of section 2 itself lacks a checkpoint monitoring equipment, it is necessary to extend its exit direction, that is, to section 3, and continue to check the entrance situation of sections 2 and 3. If the entrances of sections 2 and 3 are both provided with checkpoint monitoring equipment, sections 1, 2 and 3 can be regarded as a whole to form a closed area. If the entrance of section 2 is not provided with a checkpoint monitoring equipment, section 2 is continued to be extended according to the map road network data in the same way as section 1, until the entrances of all extended sections are provided with checkpoint monitoring equipment, and section 1 and all extended sections can be regarded as a whole to form a closed area.

[0086] Checkpoint monitoring equipment can also be set up by lane, with different checkpoint monitoring equipment monitoring different driving directions, that is, distinguishing by lane, and judging the situations of the three driving directions of left turn, right turn and straight ahead respectively. Figure 4 The second schematic diagram of the principle of determining the closed area in the embodiment of the present invention is exemplified. Taking the checkpoint monitoring device to distinguish the lane as an example, the information of the checkpoint monitoring device can be bound to the road section where it is located to obtain the corresponding relationship between the checkpoint monitoring device and the road section. Through this corresponding relationship, the setting of the checkpoint monitoring device on the road section and the lane monitored by each checkpoint monitoring device can be known. Figure 4As shown, with section 1 as the basic section, the north exit of section 1 is equipped with a checkpoint monitoring device 41 for detecting the right turn direction and a checkpoint monitoring device 42 for detecting the straight and left turn directions, and the south entrance is equipped with a checkpoint monitoring device 43 for detecting the left turn direction; while the south entrance to the right turn of section 1 is not equipped with a checkpoint monitoring device, that is, the right turn direction of section 2 is not equipped with a checkpoint monitoring device, so section 1 is extended to section 2; section 2 can be driven to the straight direction of section 3 and a checkpoint monitoring device 44 is installed, so there is no need to extend section 3, so it is only necessary to detect the conditions of section 1 and section 2. If the entrance of section 2 is equipped with checkpoint monitoring devices for three driving directions, section 1 and section 2 can be used as a whole to form a closed area. If there is no checkpoint monitoring equipment at the entrance of Section 2 in one driving direction, Section 2 can be extended in the same way as Section 1 based on the map road network data until checkpoint monitoring equipment is installed in the three entrance directions of the extended section. Section 1 and all the extended sections can be treated as a whole to form a closed area.

[0087] according to Figure 3 and Figure 4 The closed area determination principle shown in the figure is that it can be understood that the closed area determination process is the process of finding suitable road sections to form the road area based on the map road network data. These road sections must first meet the requirements that the exit of the road section itself is equipped with a checkpoint monitoring device, that is, there is a checkpoint monitoring device in the direction of departure, and the sections related to the entrance are all equipped with checkpoint monitoring devices. For intersections such as crossroads and T-junctions, the entrance of a section of road can be converged by the three driving directions of left turn, right turn and straight. If there is no checkpoint monitoring device in a driving direction, it is necessary to continue to extend the search based on that driving direction.

[0088] It is understandable that, for a closed area, a vehicle will definitely leave through one or several checkpoints after entering the closed area. In this way, the accuracy of the detection of illegally parked vehicles can be ensured through the division of the closed area.

[0089] For example, after the basic road section and all target-related road sections form a closed area, the closed area can be directly determined as a closed area node, or the historical vehicle data of the closed area's entrance and exit can be used to further confirm whether the closed area is indeed a closed area with both entrances and exits monitored, such as determining whether the vehicle data entering and exiting the closed area within a period of time is consistent. If consistent, it means that no vehicles have passed through other entrances and exits, and the closed area is indeed a closed area with both entrances and exits monitored. In this way, after the closed area is obtained according to the map road network data, the closed area can be further confirmed using the historical vehicle data entering and exiting the closed area, which can improve the accuracy of the closed area node.

[0090] Specifically, determining a closed area node based on a closed area may include: obtaining first vehicle data of all imported vehicles in the closed area and second vehicle data of all exported vehicles in the closed area within a preset historical time period; determining the proportion of identical vehicle data between the first vehicle data and the second vehicle data in the first vehicle data; and when the proportion is greater than a preset proportion threshold, determining the closed area as a closed area node.

[0091] For example, the first vehicle data may be the number of vehicles passing through all entrances of the closed area, and the second vehicle data may be the number of vehicles passing through all exits of the closed area.

[0092] For example, historical vehicle traffic data of a closed area within one month can be obtained. As long as the ratio between the number of imported vehicles and the number of exported vehicles reaches a certain threshold, for example, at least m% of the vehicles that pass through the import checkpoint monitoring device also pass through the export checkpoint monitoring device, that is, the ratio of the difference between the number of imported vehicles and the number of exported vehicles to the number of imported vehicles is less than (100-m)%, then the road section within the closed area is considered to be a closed road section, that is, it is verified that the closed area is indeed a closed area with both imports and exports monitored.

[0093] Step 250: Construct a road relationship map based on the closed area nodes, the checkpoint monitoring device nodes, and the entry and exit relationships between the closed area nodes and the checkpoint monitoring device nodes.

[0094] The road relationship map includes closed area nodes and checkpoint monitoring equipment nodes. There is an entry-exit relationship between the closed area nodes and the checkpoint monitoring equipment nodes. Each closed area node can include the road network data and roadside monitoring equipment information in its corresponding closed area.

[0095] For example, Figure 5 The schematic diagram of the structure of the road relationship map in the embodiment of the present invention is exemplarily shown. Figure 5 As shown, taking the road relationship map including 5 closed area nodes from area 1 to area 5 and 10 checkpoint monitoring equipment nodes from checkpoint 1 to checkpoint 10 as an example, each closed area node corresponds to a closed area, these closed areas can be connected through checkpoint monitoring equipment, and there are clear entry and exit directions between closed areas and checkpoint monitoring equipment. At the same time, each closed area maintains a whole, which can include the road network data and roadside monitoring equipment information in the closed area.

[0096] based on Figure 1The license plate information determination method of the corresponding embodiment, in an example embodiment, determining the target closed area passed by the illegally parked vehicle based on the target feature information in the illegally parked snapshot image may include: determining the second target roadside monitoring device corresponding to the roadside monitoring image containing the target feature information based on the target feature information in the illegally parked snapshot image; determining the target closed area passed by the illegally parked vehicle according to the position information of the second target roadside monitoring device; wherein the target feature information includes vehicle feature information of the illegally parked vehicle and / or human feature information of the driver of the illegally parked vehicle.

[0097] For each closed area, a roadside monitoring image collected by the roadside monitoring equipment in the closed area can be obtained to detect whether the roadside monitoring image contains feature information that matches the target feature information. If the roadside monitoring image contains feature information that matches the target feature information, the closed area is determined to be a target closed area.

[0098] Exemplarily, the target feature information of all closed areas can be compared at the same time; or the road relationship map can be used to continuously search for adjacent closed areas, and the target feature information of the retrieved closed areas can be compared until a preset number of closed areas are retrieved. Specifically, the road relationship map can be combined, and the closed area where the illegally parked vehicle is located when the illegally parked vehicle is captured as the starting area. Based on the road relationship map, the starting area, the adjacent area of ​​the starting area, and the closed area further adjacent to the adjacent area are searched in turn, and so on, until a preset number of closed areas are found. For each closed area found, the roadside monitoring image collected by the roadside monitoring equipment in the closed area is compared with the target feature information.

[0099] For example, Figure 5 Taking the road relationship map shown as an example, it is assumed that in the closed area 1 represented by the area 1 node, the illegal parking capture device captures an illegally parked vehicle M. After the illegally parked vehicle M leaves the illegally parked position, the adjacent areas can be searched along the exit direction of area 1 according to the road relationship map, such as finding area 2 and area 4, and the areas adjacent to area 2 and area 4 respectively can be searched along the exit directions of area 2 and area 4, such as finding area 5 and area 3. In this way, a preset number of closed areas can be found, and the roadside monitoring images collected by the roadside monitoring equipment in these closed areas are respectively matched with the target feature information of the illegally parked vehicle M. If the match is successful, it means that the illegally parked vehicle M has passed through the successfully matched closed area, and the successfully matched closed area can be determined as the target closed area.

[0100] Exemplarily, for each closed area for feature comparison, it can be determined whether there is a roadside monitoring device to be compared in the closed area whose monitoring angle is the same as the capture angle of the illegal parking capture device when capturing the illegally parked vehicle. If so, the roadside monitoring image collected by the roadside monitoring device to be compared is compared for target feature information to determine whether the roadside monitoring image collected by the roadside monitoring device to be compared contains feature information that matches the target feature information. If it does, the closed area is the target closed area where the illegally parked vehicle passed. In this way, by performing feature comparison with the monitoring image of the roadside monitoring device with the same capture angle, the speed and accuracy of feature matching can be improved.

[0101] based on Figure 1 In a method for determining the license plate information of a corresponding embodiment, in an exemplary embodiment, determining the first license plate information collected by each target checkpoint monitoring device may include: for each target checkpoint monitoring device, based on the first time when the roadside monitoring device in the target closed area connected to the target checkpoint monitoring device collects the target roadside monitoring image, determining the target time for the target checkpoint monitoring device to collect images of illegally parked vehicles; obtaining the first target vehicle image collected by the target checkpoint monitoring device within the corresponding target time; determining the intersection of the first target vehicle images between each target checkpoint monitoring device, and obtaining the first license plate information. Among them, the target roadside monitoring image is an image containing target feature information, and collecting the target roadside monitoring image can determine that the illegally parked vehicle has been collected.

[0102] Specifically, for each target checkpoint monitoring device, the target time for the target checkpoint monitoring device to collect images of illegally parked vehicles can be determined by using the first time when the roadside monitoring devices in the two adjacent target closed areas connected to it collect the target roadside monitoring image; or, any one target closed area can be selected from the two adjacent target closed areas connected to it, and the target time for the target checkpoint monitoring device to collect images of illegally parked vehicles can be determined based on the first time when the roadside monitoring device in the target closed area collects the roadside monitoring image containing target feature information.

[0103] Exemplarily, any one of the target closed areas can be selected from two adjacent target closed areas connected to the target checkpoint monitoring device. Based on the first time of the target closed area and the road network speed of the target closed area, the time when the illegally parked vehicle travels to the target checkpoint monitoring device can be estimated, and the time or the time of a preset time period before and after the time is determined as the target time. Alternatively, the time when the illegally parked vehicle travels to the target checkpoint monitoring device can be determined based on the first time and position information when the first target roadside monitoring device in the target closed area collects the target roadside monitoring image, and the time or the time of a preset time period before and after the time is determined as the target time. Among them, the first target roadside monitoring device is a roadside monitoring device that collects the target roadside monitoring image.

[0104] For example, the time period formed by the first time when the roadside monitoring equipment of the first target closed area collects the target roadside monitoring image and the first time when the roadside monitoring equipment of the second target closed area collects the target roadside monitoring image can be determined as the target time for the target checkpoint monitoring equipment to collect images of illegally parked vehicles. The first target closed area and the second target closed area are two adjacent target closed areas connected by the target checkpoint monitoring equipment.

[0105] Exemplarily, based on the first time when the roadside monitoring device in the target closed area connected to the target checkpoint monitoring device collects the target roadside monitoring image, determining the target time for the target checkpoint monitoring device to collect images of the illegally parked vehicle may include: for each of the two adjacent target closed areas connected to the target checkpoint monitoring device, obtaining the location information of the first target roadside monitoring device in the target closed area; determining the target time for the target checkpoint monitoring device to collect images of the illegally parked vehicle according to the first time and location information when the first target roadside monitoring device of each of the two adjacent target closed areas collects the target roadside monitoring image. For example, the second time when the illegally parked vehicle arrives at the target checkpoint monitoring device may be determined according to the first time and location information when the first target roadside monitoring device of each of the two adjacent target closed areas collects the target roadside monitoring image, and the target time for the target checkpoint monitoring device to collect images of the illegally parked vehicle is determined based on the second time. Among them, the first target roadside monitoring device is a roadside monitoring device that collects the target roadside monitoring image.

[0106] For example, assuming that the two adjacent target closed areas connected to the target checkpoint monitoring device A are the target closed area 1 and the target closed area 2, that is, the illegally parked vehicle needs to pass through the target checkpoint monitoring device A when traveling from the target closed area 1 to the target closed area 2, the time when the illegally parked vehicle is collected in the target closed area 1 is t1, and the time when the illegally parked vehicle is collected in the target closed area 2 is t3, then the time period from t1 to t3 can be determined as the target time for the target checkpoint monitoring device A to acquire the target vehicle image. Alternatively, the speed of the illegally parked vehicle can be determined based on the position information of the roadside monitoring device that collects the illegally parked vehicle in the target closed area 1, the position information of the roadside monitoring device that collects the illegally parked vehicle in the target closed area 2, and the time t1 and t3, and the second time t2 when the illegally parked vehicle arrives at the target checkpoint monitoring device can be determined based on the speed, and the time period from t2 or (t2-Δt) to (t2+Δt) can be determined as the target time. Wherein, Δt is a preset time period.

[0107] After obtaining the target time corresponding to the target checkpoint monitoring device A, the first target vehicle image collected by the target checkpoint monitoring device A within the target time can be obtained. For each determined target checkpoint monitoring device, the first target vehicle image corresponding to each can be obtained according to the processing method of the target checkpoint monitoring device A. Assuming that the determined target checkpoint monitoring devices include the target checkpoint monitoring device A, the target checkpoint monitoring device B and the target checkpoint monitoring device C, after determining the first target vehicle image of each target checkpoint monitoring device, the intersection of the license plate information of the first target vehicle image of the target checkpoint monitoring device A, the first target vehicle image of the target checkpoint monitoring device B and the first target vehicle image of the target checkpoint monitoring device C can be taken to obtain the first license plate information collected by each target checkpoint monitoring device, and then the target license plate information is determined in the first license plate information.

[0108] In an exemplary embodiment, if the number of first license plate information collected by each target checkpoint monitoring device is at least two, for example, the target checkpoint monitoring devices determined are target checkpoint monitoring device A, target checkpoint monitoring device B and target checkpoint monitoring device C, the first target vehicle image collected by target checkpoint monitoring device A contains license plate information a and b, the first target vehicle image collected by target checkpoint monitoring device B contains license plate information a, b and c, and the first target vehicle image collected by target checkpoint monitoring device C contains license plate information a, b and d, then the first license plate information collected by each target checkpoint monitoring device is a and b, and the license plate information of the illegally parked vehicle cannot be uniquely confirmed. At this time, the retrieval range can be expanded, and more target closed areas can be matched using the target feature information and combined with the road relationship map. The new target checkpoint monitoring device can be determined using the matched new target closed area, and the vehicle image collected by the new target checkpoint monitoring device is further intersected with the first license plate information for license plate search, so as to finally determine the unique license plate information of the illegally parked vehicle and improve the accuracy of illegal parking confirmation.

[0109] Specifically, determining the target license plate information of the illegally parked vehicle in the first license plate information may include: when there are at least two pieces of first license plate information, determining a new target checkpoint monitoring device through which the illegally parked vehicle passes; acquiring a second target vehicle image captured by the new target checkpoint monitoring device; determining the license plate information contained in both the second target vehicle image and the first license plate information, and determining the target license plate information of the illegally parked vehicle in the license plate information.

[0110] For example, the first license plate information determined is a and b, and a new target checkpoint monitoring device D is further determined based on the target feature information and the road relationship map. The first target vehicle image collected by the target checkpoint monitoring device D contains license plate information b and d. Taking the intersection of the first license plate information and the first license plate information can obtain the intersection license plate information b, and then it can be determined that the target license plate information of the illegally parked vehicle is license plate information b.

[0111] In this way, as long as there are enough target closed areas obtained by feature comparison, the same license plate information will inevitably be found in the vehicle images collected by the checkpoint monitoring devices passing through these target closed areas, that is, the target license plate information of the illegally parked vehicle will be obtained. In other words, the more target closed areas obtained by comparing the target feature information, the more target checkpoint monitoring devices will be determined, so that the more vehicle images with license plate information intersections will be taken, and the more accurate the target license plate information of the illegally parked vehicle will be determined.

[0112] Below Figure 5 The road relationship graph shown further illustrates the license plate information determination method provided in the embodiment of the present invention.

[0113] Reference Figure 5, assuming that vehicle M has entered the closed area represented by the node of area 1, and when illegally parked on section 1 of the closed area, it was captured by the roadside monitoring device Cam1 of section 1, and the time interval between two consecutive captures of vehicle M at the illegally parked position is greater than the set threshold, then vehicle M is determined to be an illegally parked vehicle, and the vehicle characteristic information and driver's body characteristic information of vehicle M are recorded. After vehicle M leaves the no-parking zone of section 1, it is assumed that it successively enters the closed areas represented by areas 2, 5, and 4, and finally stays in the closed area represented by area 4. Based on the vehicle characteristic information and driver's body characteristic information of vehicle M, characteristic information matching the vehicle characteristic information and driver's body characteristic information can be compared in the roadside monitoring images collected by the roadside monitoring devices in these three closed areas. According to Figure 5 It can be seen from the road relationship map that, in chronological order, those who enter these three closed areas must pass through checkpoint monitoring device 1, checkpoint monitoring device 7 and checkpoint monitoring device 5 in turn.

[0114] For any of the three closed areas, the location information of the roadside monitoring device in the closed area that captured the vehicle M and the time when the vehicle M was captured can be determined based on the road network data in the closed area. For each of the checkpoint monitoring devices 1, 7 and 5, the time when the vehicle M arrived at the checkpoint monitoring device can be determined based on the time when the roadside monitoring devices in the two adjacent closed areas connected to the checkpoint monitoring device captured the vehicle M and the location information of the roadside monitoring device that captured the vehicle M, and the time or the time range of the preset time period before and after the time can be determined as the target time for the checkpoint monitoring device to capture the vehicle M. According to the target time of each checkpoint monitoring device, the vehicle images captured by each checkpoint monitoring device when the vehicle M passes through the checkpoint monitoring device 1, the checkpoint monitoring device 7 and the checkpoint monitoring device 5 can be obtained, and then the license plate information captured by each checkpoint monitoring device together can be determined. For example, the intersection of the license plate information of the vehicle images between the checkpoint monitoring device 1, the checkpoint monitoring device 7 and the checkpoint monitoring device 5 can be taken to obtain the license plate information captured by each checkpoint monitoring device. Alternatively, the license plate information captured by the checkpoint monitoring device 1 and the checkpoint monitoring device 7 can be first determined in chronological order to obtain the first intersection license plate information, and then the license plate information contained in the vehicle image captured by the checkpoint monitoring device 5 and the first intersection license plate information can be determined to obtain the license plate information captured by the three checkpoint monitoring devices.

[0115] If the license plate information captured by the checkpoint monitoring device 1, the checkpoint monitoring device 7 and the checkpoint monitoring device 5 together is more than one, the search range can be further expanded. Figure 5The road relationship map shown uses the vehicle feature information of vehicle M and the driver's body feature information to match more closed areas. The more closed areas that vehicle M passes through are matched, the more accurately the license plate information of vehicle M can be determined.

[0116] The license plate information determination method provided by the embodiment of the present invention can use the map road network data to divide the closed area of ​​road monitoring, and establish the road relationship map between the closed area and the checkpoint monitoring equipment set at the entrance and exit; the roadside monitoring equipment can be used to capture illegal parking, and the vehicle feature information and driver's body feature information of the illegally parked vehicle in the illegal parking capture image can be extracted. Based on the vehicle feature information and the driver's body feature information, the target closed area through which the illegally parked vehicle passes can be determined by feature comparison, and the checkpoint monitoring equipment that the illegally parked vehicle must pass can be determined according to the road relationship map using the roadside capture data of these target closed areas. According to the time sequence and road network data, the license plate information collected together is retrieved from the vehicle images collected by these checkpoint monitoring equipment, so as to confirm the license plate information of the illegally parked vehicle. In the case that no device for illegal parking is installed in the prohibited parking area or the license plate of the illegally parked vehicle cannot be captured by the roadside, the license plate information of the illegally parked vehicle can also be determined by using the vehicle image collected by the target checkpoint monitoring equipment through which the illegally parked vehicle passes, so as to achieve the purpose of illegal parking confirmation.

[0117] The license plate information determination device provided by the present invention is described below. The license plate information determination device described below and the license plate information determination method described above can be referred to each other.

[0118] Figure 6 The schematic diagram of the structure of the vehicle license plate information determination device provided by the embodiment of the present invention is exemplarily shown. Figure 6 As shown, the license plate information determination device may include: an area determination module 610, which is used to determine the target closed area passed by the illegally parked vehicle based on the target feature information in the illegally parked snapshot image; a checkpoint determination module 620, which is used to determine the target checkpoint monitoring device passed by the illegally parked vehicle according to the target closed area and the road relationship map; wherein the road relationship map includes closed area nodes, checkpoint monitoring device nodes and entry and exit relationships between closed area nodes and checkpoint monitoring device nodes, and checkpoint monitoring devices are provided at the entry and exit of the closed area nodes; a license plate determination module 630, which is used to determine the first license plate information collected by each target checkpoint monitoring device, and determine the target license plate information of the illegally parked vehicle in the first license plate information.

[0119] In an example embodiment, the license plate determination module 630 includes: a first determination unit, used to determine, for each target checkpoint monitoring device, the target time for the target checkpoint monitoring device to collect images of illegally parked vehicles based on the first time when the roadside monitoring device in the target closed area connected to the target checkpoint monitoring device collects the target roadside monitoring image; wherein the target roadside monitoring image is an image containing target feature information; an acquisition unit, used to obtain the first target vehicle image collected by the target checkpoint monitoring device within the corresponding target time; and a second determination unit, used to determine the intersection of the first target vehicle images between the target checkpoint monitoring devices to obtain the first license plate information.

[0120] In an exemplary embodiment, the second determination unit may include: a first determination subunit, used to determine a new target checkpoint monitoring device through which the illegally parked vehicle passes when the first license plate information is at least two; a first acquisition subunit, used to acquire a second target vehicle image captured by the new target checkpoint monitoring device; a second determination subunit, used to determine the license plate information contained in both the second target vehicle image and the first license plate information, and determine the target license plate information of the illegally parked vehicle in the license plate information.

[0121] In an exemplary embodiment, the first determination unit may include: a second acquisition subunit, for acquiring, for each target closed area in which the target checkpoint monitoring device is connected, the location information of the first target roadside monitoring device in the target closed area, wherein the first target roadside monitoring device is a roadside monitoring device that collects target roadside monitoring images; and a third determination subunit, for determining the target time for the target checkpoint monitoring device to collect images of illegally parked vehicles based on the first time and location information when the respective first target roadside monitoring devices in each target closed area collect the target roadside monitoring images.

[0122] In an exemplary embodiment, the area determination module 610 may include: a third determination unit, used to determine a second target roadside monitoring device corresponding to a roadside monitoring image containing target feature information based on target feature information in the illegally parked captured image; a fourth determination unit, used to determine a target closed area passed by an illegally parked vehicle based on location information of the second target roadside monitoring device; wherein the target feature information includes vehicle feature information of the illegally parked vehicle and / or human feature information of the driver of the illegally parked vehicle.

[0123] In an exemplary embodiment, the license plate information determination device may also include a graph construction module, which is used to: determine a basic road section from the acquired map road network data, and the exit of the basic road section is provided with a checkpoint monitoring device; if the checkpoint monitoring device is not provided at the entrance of the basic road section, determine a target-related road section related to the entrance of the basic road section, and if the checkpoint monitoring device is not provided at the entrance of the target-related road section, determine the target-related road section as a new basic road section, and repeat the above steps until the target-related road section with the checkpoint monitoring device provided at the entrance is found; form the basic road section and all the target-related road sections into a closed area, determine the closed area nodes based on the closed area, and determine the checkpoint monitoring device provided at the exit of the basic road section and the checkpoint monitoring device provided at the entrance of the target-related road section with the checkpoint monitoring device provided at the entrance as checkpoint monitoring device nodes respectively; and construct a road relationship graph based on the closed area nodes, the checkpoint monitoring device nodes, and the entry and exit relationships between the closed area nodes and the checkpoint monitoring device nodes.

[0124] In an exemplary embodiment, the graph construction module can be specifically used to: obtain first vehicle data of all imported vehicles in a closed area and second vehicle data of all exported vehicles in the closed area within a preset historical time period; determine the proportion of the same vehicle data between the first vehicle data and the second vehicle data in the first vehicle data; and when the proportion is greater than a preset proportion threshold, determine the closed area as a closed area node.

[0125] Figure 7 An example of a structural diagram of an electronic device is shown in FIG. Figure 7 As shown, the electronic device may include: a processor 710, a communication interface 720, a memory 730 and a communication bus 740, wherein the processor 710, the communication interface 720 and the memory 730 communicate with each other through the communication bus 740. The processor 710 may call the logic instructions in the memory 730 to execute the license plate information determination method provided by any of the above method embodiments.

[0126] In addition, the logic instructions in the above-mentioned memory 730 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0127] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the license plate information determination method provided by any of the above method embodiments.

[0128] On the other hand, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the license plate information determination method provided by any of the above method embodiments.

[0129] Exemplarily, the computer-readable storage medium includes a non-transitory computer-readable storage medium.

[0130] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0131] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0132] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for determining license plate information, characterized in that: include: Based on the target feature information in the illegally parked image, determine the target closed area where the illegally parked vehicle passes; Determine the target checkpoint monitoring device that the illegally parked vehicle passes through according to the target closed area and road relationship map; wherein the road relationship map includes closed area nodes, checkpoint monitoring device nodes, and entry and exit relationships between the closed area nodes and the checkpoint monitoring device nodes, and checkpoint monitoring devices are set at the entrances and exits of the closed area nodes; The first license plate information collected by each of the target checkpoint monitoring devices is determined, and the target license plate information of the illegally parked vehicle is determined in the first license plate information.

2. The method for determining license plate information according to claim 1, characterized in that: The road relationship graph is constructed based on the following steps: Determine a basic road section from the acquired map road network data, wherein the exit of the basic road section is provided with a checkpoint monitoring device; If no checkpoint monitoring device is installed at the entrance of the basic road section, determine a target related road section related to the entrance of the basic road section, and if no checkpoint monitoring device is installed at the entrance of the target related road section, determine the target related road section as a new basic road section, and repeat the above steps until a target related road section with a checkpoint monitoring device installed at the entrance is found; The basic road section and all the target-related road sections form a closed area, determine the closed area node based on the closed area, and determine the checkpoint monitoring device set at the exit of the basic road section and the checkpoint monitoring device set at the entrance of the target-related road section where the checkpoint monitoring device is set as the checkpoint monitoring device node respectively; The road relationship map is constructed based on the closed area node, the checkpoint monitoring device node, and the entry and exit relationship between the closed area node and the checkpoint monitoring device node.

3. The method for determining license plate information according to claim 2, characterized in that: The determining the closed area node based on the closed area includes: Acquire first vehicle data of all imported vehicles in the closed area and second vehicle data of all exported vehicles in the closed area within a preset historical time period; determining a proportion of the same vehicle data between the first vehicle data and the second vehicle data to the first vehicle data; When the ratio is greater than a preset ratio threshold, the second closed area is determined as the closed area node.

4. The method for determining license plate information according to any one of claims 1 to 3, characterized in that: The determining of the first license plate information collected by each of the target checkpoint monitoring devices comprises: For each of the target checkpoint monitoring devices, based on the first time when the roadside monitoring device in the target closed area connected to the target checkpoint monitoring device collects the target roadside monitoring image, determine the target time for the target checkpoint monitoring device to collect the image of the illegally parked vehicle; wherein the target roadside monitoring image is an image containing the target feature information; Acquire a first target vehicle image captured by the target checkpoint monitoring device within the corresponding target time; Determine the intersection of the first target vehicle images between the target checkpoint monitoring devices to obtain the first license plate information.

5. The method for determining license plate information according to claim 4, characterized in that: The step of determining the target license plate information of the illegally parked vehicle in the first license plate information includes: In the case where the first license plate information is at least two, determining a new target checkpoint monitoring device through which the illegally parked vehicle passes; Acquire a second target vehicle image captured by the new target checkpoint monitoring device; The license plate information included in both the second target vehicle image and the first license plate information is determined, and the target license plate information of the illegally parked vehicle is determined in the license plate information.

6. The method for determining license plate information according to claim 4, characterized in that: The determining of the target time for the target checkpoint monitoring device to collect images of the illegally parked vehicle based on the first time when the roadside monitoring device in the target closed area connected to the target checkpoint monitoring device collects the target roadside monitoring image comprises: For each target closed area in the target closed area connected to the target checkpoint monitoring device, obtaining the position information of the first target roadside monitoring device in the target closed area; the first target roadside monitoring device is the roadside monitoring device that has collected the target roadside monitoring image; The target time for the target checkpoint monitoring device to capture the image of the illegally parked vehicle is determined based on the first time and the position information when the first target roadside monitoring device of each target closed area captures the target roadside monitoring image.

7. The method for determining license plate information according to any one of claims 1 to 3, characterized in that: The step of determining the target closed area through which the illegally parked vehicle passes based on the target feature information in the illegally parked image includes: Based on the target feature information in the illegal parking capture image, determining a second target roadside monitoring device corresponding to the roadside monitoring image containing the target feature information; Determine the target closed area through which the illegally parked vehicle passes according to the position information of the second target roadside monitoring device; Wherein, the target feature information includes vehicle feature information of the illegally parked vehicle and / or human feature information of the driver of the illegally parked vehicle.

8. A device for determining license plate information, characterized in that: include: An area determination module is used to determine the target closed area through which the illegally parked vehicle passes based on the target feature information in the illegally parked image; A checkpoint determination module, used to determine the target checkpoint monitoring device through which the illegally parked vehicle passes according to the target closed area and road relationship map; wherein the road relationship map includes closed area nodes, checkpoint monitoring device nodes, and entry and exit relationships between the closed area nodes and the checkpoint monitoring device nodes, and checkpoint monitoring devices are provided at the entry and exit of the closed area nodes; The license plate determination module is used to determine the first license plate information collected by each of the target checkpoint monitoring devices, and determine the target license plate information of the illegally parked vehicle in the first license plate information.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the license plate information determination method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the license plate information determination method according to any one of claims 1 to 7 is implemented.

Images