A method and system for filtering congested areas

Abstract

The embodiment of the present application discloses a method and system for filtering a congested area. The congested area filtering method comprises: obtaining an input road condition image; obtaining a congested detection area through a congestion detection model based on the road condition image; obtaining suspected illegally parked vehicle information; determining whether a vehicle is illegally parked based on information related to the suspected illegally parked vehicle information and in combination with the congested detection area; and outputting the result of the determination.

Description

Technical Field

[0001] The present application relates to the field of image processing, and in particular to a method and system for filtering congested areas. Background Art

[0002] With the rapid development of social economy and the continuous improvement of people's living standards, vehicles have become a necessity in family life, which has also led to an increasing number of various vehicles in cities. For the existing public transportation system, with the continuous increase in the number of various vehicles, traffic congestion has become more and more common. In some cases, for example, when congestion occurs on an illegal parking lane, since the detection area of ​​the illegal parking event is larger than the detection area where congestion detection is performed only in the congested area, it is necessary to shield the illegal parking events that occur in the congested lane. Therefore, a congested area filtering method is needed to filter the illegal parking events of vehicles that occur in the congested lane, thereby reducing the false alarm rate of illegal parking events. Summary of the invention

[0003] One aspect of the present application provides a congestion area filtering method. The method includes: obtaining an input road condition image; obtaining a congestion detection area through a congestion detection model based on the road condition image; obtaining suspected illegally parked vehicle information; based on information related to the suspected illegally parked vehicle information, combined with the congestion detection area, determining whether the vehicle is illegally parked; and outputting the determination result.

[0004] In some embodiments, the method for determining whether a vehicle is illegally parked based on information related to the suspected illegally parked vehicle information and in combination with the congestion detection area includes: determining a shielding area based on the congestion detection area; and determining whether the suspected illegally parked vehicle is located in the shielding area.

[0005] In some embodiments, the method of determining a shielding area based on the congestion detection area includes: determining a related polygon based on the congestion detection area; and expanding the related polygon as a shielding area.

[0006] In some embodiments, the associated polygon may be a minimum circumscribed polygon.

[0007] In some embodiments, the method of expanding the relevant polygon as a shielding area includes: determining the long side and the short side of the relevant polygon; and determining the shielding area based on the extension lines of the long side and the short side and the boundary of the road condition image.

[0008] In some embodiments, the method for determining a shielded area based on the extension lines of the long side and the short side and the road condition image boundary includes: extending the long side and the short side to the road condition image boundary; determining the intersection of the extension line and the road condition image boundary; and determining that the area enclosed by the road condition image boundary and the extension line is a shielded area.

[0009] In some embodiments, the method of determining a shielded area based on the congestion detection area further includes: determining a shielded area based on lane lines of the congestion detection area.

[0010] Another aspect of the present application provides a congestion area filtering system. The system includes: an acquisition module for acquiring an input road condition image and obtaining suspected illegally parked vehicle information; a congestion detection module for acquiring a congestion detection area through a congestion detection model based on the road condition image; a determination module for determining whether a vehicle is illegally parked based on information related to the suspected illegally parked vehicle information and in combination with the congestion detection area; and an output module for outputting the result of the determination.

[0011] In some embodiments, the system for determining the cleanliness level of a vehicle further includes: a shielding area determination module, configured to determine a shielding area based on the congestion detection area; and a determination module, configured to determine whether the suspected illegally parked vehicle is located in the shielding area.

[0012] Another aspect of the present application provides a device for filtering a congested area, comprising at least one storage medium and at least one processor, wherein the at least one storage medium is used to store computer instructions; and the at least one processor is used to execute the computer instructions to implement the method for filtering a congested area as described above.

[0013] Another aspect of the present application provides a computer-readable storage medium, wherein the storage medium stores computer instructions. When the computer instructions are executed by a processor, the method for filtering a congested area as described above is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The present application will be further described in the form of exemplary embodiments, which will be described in detail by way of the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0015] Figure 1 is a schematic diagram of an application scenario of a congested area filtering system according to some embodiments of the present application;

[0016] Figure 2 is a module diagram of a congested area filtering system according to some embodiments of the present application;

[0017] Figure 3 is an exemplary flow chart of a congested area filtering method according to some embodiments of the present application;

[0018] Figure 4 is an exemplary flow chart of a method for determining a shielding area according to some embodiments of the present application;

[0019] Figure 5 is an exemplary flow chart of another method for determining a shielding area according to some embodiments of the present application.

[0020] Figures 6A-6H It is a schematic diagram of determining the intersection of an extension line and a road condition image boundary according to some embodiments of the present application. DETAILED DESCRIPTION

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0022] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0023] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprises" and "includes" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0024] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, the various steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0025] Figure 1 It is a schematic diagram of an application scenario of the congested area filtering system 100 according to some embodiments of the present application.

[0026] The congested area filtering system 100 can be an online monitoring platform for road management. For example, the congested area filtering system 100 can filter events that occur in congested areas to reduce false alarms of illegal parking events or other events due to congestion. In some embodiments, the congested area filtering system 100 can be applied to urban traffic roads, tunnels, highways, airport roads, railway station roads and other roads. In some embodiments, the congested area filtering system 100 can be applied to roads with heavy traffic or complex road conditions that are prone to congestion. In some embodiments, the congested area filtering system 100 can also be applied to the entrances or exits of highways, tunnels, expressways and other roads. Figure 1 As shown, the congested area filtering system 100 may include a server 110 , a network 120 , a terminal 130 , a storage device 140 , and an image acquisition device 150 .

[0027] In some embodiments, the server 110 can process data and / or information from at least one component of the system or an external data source (e.g., a cloud data center). In some embodiments, the server 110 can be a single server, or a computing platform composed of multiple servers, and the multiple server groups can be centralized or distributed, and can be dedicated or provided by other devices or systems at the same time. In some embodiments, the server 110 can be local or remote. For example, the server 110 can access information and / or data stored in the terminal 130 and the storage device 140 through the network 120. In some embodiments, the server 110 can be directly connected to the terminal 130, the storage device 140, and the image acquisition device 150 to access the information and / or data stored therein. In some embodiments, the server 110 can be implemented on a cloud platform. For example, the cloud platform may include one or any combination of a private cloud, a public cloud, a hybrid cloud, a community cloud, a decentralized cloud, an internal cloud, etc. In other embodiments, the server 110 can be one of the terminals 130 at the same time.

[0028] The server 110, the terminal 130, and other components may include a processing device. In some embodiments, the processing device may include one or more processing engines (e.g., a single-core processing engine or a multi-core processing engine). The processing device may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), an application-specific instruction set processor (ASIP), and other processing devices well known to those skilled in the art. The processing device may process the data and / or information obtained from the image acquisition device 150, the terminal 130, and / or the storage device 140, and process these data and / or information or control other devices in the system based on these data, information, and / or processing results to perform one or more functions described in this application. For example, the processing device may receive an image captured by the image acquisition device 150, and process the image to determine whether it is in a congestion detection area, determine whether the vehicle is illegally parked in combination with other relevant information, and finally output the determination result to the terminal 130.

[0029] The network 120 connects the components of the system so that the components can communicate with each other. The network between the components in the system can be any one or more of a wired network or a wireless network. For example, the network 120 may include a cable network, a wired network, an optical fiber network, a telecommunications network, an internal network, the Internet, a local area network (LAN), a wide area network (WAN), a wireless local area network (WLAN), a metropolitan area network (MAN), a public switched telephone network (PSTN), a Bluetooth network, a ZigBee network (ZigBee), a near field communication (NFC), a bus within a device, a line within a device, a cable connection, etc. or any combination thereof. The network connection between each two components can be in one of the above-mentioned ways, or in multiple ways.

[0030] The terminal 130 is one or more terminal devices or software used by the user. In some embodiments, the terminal 130 may be used by one or more users, including users who directly use the service, and other related users. In some embodiments, the user described above refers to the relevant staff or service requester who uses the congestion filtering system 100. In some embodiments, the terminal 130 may include various types of devices with information receiving and / or sending functions. For example, it may be a mobile device 130-1, a tablet computer 130-2, a laptop computer 130-3, a transportation system terminal device 130-4, etc., or any combination thereof. The above examples are only used to illustrate the wide range of the equipment and not to limit its scope.

[0031] The storage device 140 may store data and / or instructions. The storage device may include one or more storage components, each of which may be an independent device or part of another device. In some embodiments, the storage device 140 may include a mass storage device, a removable memory, a volatile read-write memory, a read-only memory (ROM), etc. or any combination thereof. In some embodiments, the storage device 140 may be implemented on a cloud platform.

[0032] In some embodiments, the storage device 140 may be connected to the network 120 to communicate with one or more components (e.g., the server 110, the terminal 130, the image acquisition device 150) in the congested area filtering system 100. One or more components in the congested area filtering system 100 may access data or instructions stored in the storage device 140 through the network 120. In some embodiments, the storage device 140 may be directly connected or communicate with one or more components (e.g., the server 110, the terminal 130, the image acquisition device 150) in the congested area filtering system 100. In some embodiments, the storage device 140 may be a part of the server 110.

[0033] The image acquisition device 150 can capture images of the monitored area. In some embodiments, the image acquisition device 150 can send the collected image data of the monitored area to the storage device 140 for storage. In some embodiments, the image acquisition device 150 can send the collected image data to the server 110. In some embodiments, the image acquisition device 150 may include any combination of one or more of a spherical camera, a hemispherical camera, a surveillance camera, a smart camera, a pinhole camera, etc. In some embodiments, the image acquisition device 150 may also include any combination of one or more of a driving recorder, smart glasses, a smart helmet, a mobile phone, a tablet, etc. In some embodiments, the image acquisition device 150 may include any combination of one or more of a digital camera, a SLR camera, a micro single camera, etc. In some embodiments, the image acquisition device may include any device with a camera. In some embodiments, the camera may include any device with an image capture function.

[0034] The server 110 can communicate with the terminal 130, the storage device 140, and the image acquisition device 150 through the network 120 to provide the function of filtering the congested area. In some embodiments, the server 110 can obtain the collected road condition image from the storage device 140 or the image acquisition device 150, detect its congested detection area and obtain the suspected illegally parked vehicle information. In some embodiments, the server 110 can determine whether the vehicle is illegally parked based on the shielded area determined by the congested detection area and the suspected illegally parked vehicle information, and send the determination result to the terminal 130. The storage device 140 and the network 120 serve the above process.

[0035] Figure 2 2 is a block diagram of a congested area filtering system 200 according to some embodiments of the present application. Figure 2 As shown, the congestion area filtering system 200 may include an acquisition module 210 , a congestion detection module 220 , a shielding area determination module 230 , a determination module 240 , and an output module 250 .

[0036] The acquisition module 210 can be used to acquire road condition images and suspected illegally parked vehicles.

[0037] In some embodiments, the acquisition module 210 can acquire road condition images and suspected illegally parked vehicle images acquired by the image acquisition device 150. In some embodiments, the image acquisition device 150 can also acquire information related to the road condition image and suspected illegally parked vehicle information. In some embodiments, the road condition image and its related information, the suspected illegally parked vehicle image and its related information can be acquired by the same or different image acquisition devices 150. In some embodiments, the acquisition method of the image acquisition device 150 can include any combination of one or more of timed acquisition, real-time acquisition, panoramic acquisition, and slice acquisition. The specific implementation process of the module can refer to steps 310 and 330.

[0038] The congestion detection module 220 may be used to determine a congestion detection area.

[0039] In some embodiments, the congestion detection module 220 can obtain the congestion detection area in the road condition image through the congestion detection model. In some embodiments, the congestion detection module 220 can also be used to train the congestion detection model and verify the trained congestion detection model. The specific implementation process of the module can be referred to step 320.

[0040] The shielding area determination module 230 may be configured to determine the shielding area in combination with the congestion detection area.

[0041] In some embodiments, the shielding area determination module 230 can determine the shielding area by determining the relevant polygon of the congestion detection area or expanding the relevant polygon. For example, the relevant polygon can be the minimum circumscribed moment, and for another example, the long side and the short side of the relevant polygon can be extended respectively to expand. In some embodiments, the shielding area determination module 230 can also determine the shielding area by the lane line of the congestion detection area. The specific implementation process of the module can be referred to step 340, process 400 and process 500.

[0042] The determination module 240 may be used to determine whether a suspected illegally parked vehicle is illegally parked.

[0043] In some embodiments, the determination module 240 can determine whether the suspected illegally parked vehicle is illegally parked based on the information related to the suspected illegally parked vehicle and the congestion detection area. In some embodiments, the suspected illegally parked vehicle can be determined to be illegally parked by determining whether the suspected illegally parked vehicle is located in a shielding area determined based on the congestion detection area, thereby filtering illegal parking events in the congested area. The specific implementation process of the module can be referred to step 350.

[0044] The output module 250 may be used for the result of the determination.

[0045] In some embodiments, the output module 250 may output the determination result of the illegal parking event to the terminal 130. In some embodiments, the output module 250 may report the vehicle-related information determined as the illegally parked vehicle and delete the relevant information of the vehicle determined as not illegally parked or perform other subsequent processing. The specific implementation process of the module can be referred to step 360.

[0046] It should be understood that Figure 2 The system and its modules shown can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented by hardware, software or a combination of software and hardware. Among them, the hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or a dedicated design hardware. Those skilled in the art will understand that the above-mentioned method and system can be implemented using computer executable instructions and / or included in a processor control code, such as a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. Such code is provided on the carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of the present application can not only be implemented by hardware circuits such as ultra-large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but can also be implemented by software such as executed by various types of processors, and can also be implemented by a combination of the above-mentioned hardware circuits and software (for example, firmware).

[0047] It should be noted that the above description of the congested area filtering system 200 and its modules is only for convenience of description and does not limit the present application to the scope of the embodiments. It is understandable that, after understanding the principle of the system, those skilled in the art may arbitrarily combine the modules or form a subsystem to connect with other modules without deviating from the principle. For example, in some embodiments, Figure 2The data acquisition module 210, congestion detection module 220, shielding area determination module 230, determination module 240, and output module 250 disclosed in the system can be different modules in one system, or one module can realize the functions of two or more modules mentioned above. Each module in the congestion area filtering system 200 can share a storage module, or each module can have its own storage module. Such variations are all within the protection scope of this application.

[0048] Figure 3 FIG. 1 is an exemplary flow chart of a congested area filtering method according to some embodiments of the present application. Figure 3 As shown, a congestion area filtering method, the method specifically comprises the following steps:

[0049] Step 310 , obtaining an input road condition image. In some embodiments, step 310 may be implemented by the obtaining module 210 .

[0050] In some embodiments, the road condition image is an image reflecting traffic road condition information, such as vehicle driving conditions, lane congestion, traffic flow conditions, etc. In some embodiments, the road condition image can be obtained by continuous shooting through a fixed image acquisition device pre-set in the road. In some embodiments, the fixed image acquisition device may include one or any combination of a road condition monitoring device, a public security monitoring device, a road violation monitoring device, a speed monitoring device, a vehicle flow monitoring device, etc. In some embodiments, the monitoring / monitoring device may be any device with a camera function. In some embodiments, the road condition image can be obtained by continuous shooting through a mobile image acquisition device. In some embodiments, the mobile image acquisition device may include one or any combination of a driving recorder, a camera, a mobile phone, a tablet, a computer, smart glasses, etc.

[0051] In some embodiments, the acquired road condition image may be various types of image information such as video, recording, and photo. In some embodiments, the acquired road condition image may be real-time video information, which is used to reflect the road condition information in real time. In some embodiments, the acquired road condition image may be a recorded video on the road, which is used to reflect the road condition information of a certain time period in the past. In some embodiments, the acquired road condition image may be one or more photos, which are used to reflect the road condition information at a certain point in time.

[0052] In some embodiments, the road condition information can be acquired in real time throughout the day, can be acquired at certain time intervals, or can be acquired within a pre-set specific time period. In some embodiments, the acquisition module 210 can acquire a road condition image at regular intervals according to a set time threshold. In some embodiments, the time threshold can be set based on the processing capacity of the system, and can also be determined based on the road traffic volume. For example, if the traffic volume is large, the value of the time interval is small. In some embodiments, the acquisition module 210 can be set to acquire within a certain time period, such as a time period prone to congestion. In some embodiments, the acquisition can be set during the peak congestion period of commuting, and not acquired during times when the traffic volume is small, such as in the early morning. In some embodiments, the specific time period can be flexibly set according to the traffic commuting conditions or other relevant information in different cities or regions.

[0053] In some embodiments, the acquired road condition image also includes image-related feature information such as image shooting time, image shooting location, image type, and image acquisition method. In some embodiments, the acquired road condition image can directly proceed to step 320, or can be filtered first to pre-exclude some images where there is obviously no congestion. In some embodiments, the images where there is obviously no congestion can be pre-excluded by filtering information such as the number of vehicles passing through within a period of time, the image shooting location (for example, the location is very remote), and the image shooting time (for example, around two or three in the morning).

[0054] Step 320 , based on the road condition image, obtain a congestion detection area through a congestion detection model. In some embodiments, step 320 may be implemented by the congestion detection module 220 .

[0055] In some embodiments, the congestion detection area is a congestion area that can be detected and identified in the road condition image. In the congestion area, the road is in a congested state, and vehicles are moving slowly or even unable to move forward. In some embodiments, the congestion detection area often appears in places in the city where there are fewer lanes but a large amount of traffic, or where the surrounding roads are under construction, etc. In some embodiments, the congestion area also has certain time characteristics, and congestion is more likely to form in certain time periods, such as rush hour on weekdays.

[0056] In some embodiments, the congestion detection area in the road condition image can be directly obtained through the congestion detection model. In some embodiments, the input of the congestion detection model is the road condition image, and the output is whether the road condition image includes the congestion detection area. If the result is that the congestion detection area is included, the detected congestion detection area also needs to be output at the same time.

[0057] In some embodiments, the congestion detection model is a machine learning model, which may be a supervised learning model for classification, such as a linear classifier (such as LR), Naive Bayes (NB), K-nearest neighbor (KNN), decision tree (DT), integrated model (RF / GDBT, etc.), etc. It may also be a supervised learning model for regression, such as linear regression, support vector machine (SVM), K-nearest neighbor (KNN), regression tree (DT), integrated model (ExtraTrees / RF / GDBT), etc.

[0058] In some embodiments, the machine learning model can be trained by sample images of information to be annotated. In some embodiments, the training process includes: obtaining sample road condition images; annotating whether the sample images contain congestion detection areas and the specific location of the congestion detection areas in the images; inputting the annotated sample images into the machine learning model for training to obtain a trained congestion detection model. In some embodiments, the sample images can be divided into a training set and a validation set, the images in the training set are used to train the congestion detection model, and the sample images in the validation set are used to validate the trained congestion detection model.

[0059] Step 330 , obtaining information of suspected illegally parked vehicles. In some embodiments, step 330 may be implemented by the obtaining module 210 .

[0060] In some embodiments, the suspected illegally parked vehicle is a vehicle that has stopped driving in the illegally parked area for various reasons, and may be a vehicle that has stopped temporarily for a short period of time or a vehicle that has been parked for a long time. In some embodiments, the illegally parked vehicle may be captured by different types of image acquisition devices, which may be fixed or mobile.

[0061] In some embodiments, the illegal parking area may be some specific areas, for example, emergency lanes, highway entrances and exits, fire lanes, sidewalks, emergency refuge passages, emergency lanes, convenience store entrances, entrances and exits for people and vehicles, gas stations or toll station queuing waiting areas, etc., or a combination of one or more of the above. In some embodiments, the illegal parking area is a fixed area, and the congestion area has uncertainty in time and location. Therefore, vehicles suspected of illegal parking in the illegal parking area may stop in the illegal parking area due to congestion in the lane where they are located. In such a case, it is necessary to filter the suspected illegally parked vehicles obtained to exclude those that are determined to be illegally parked due to congestion.

[0062] In some embodiments, when a vehicle enters an illegal parking area, the image acquisition device will automatically capture a photo of the vehicle. If the vehicle exits the illegal parking area within a certain period of time (e.g., within 5 minutes), the captured photo of the vehicle will be automatically deleted; if the vehicle does not exit the illegal parking area within a certain period of time (e.g., within 5 minutes), the image acquisition device will automatically capture a second photo of the vehicle and upload the photo of the vehicle at the same time. In some embodiments, a suspected illegally parked vehicle is a vehicle that has not exited the illegal parking area within a certain period of time, has had a second photo of the vehicle captured, but has not yet been reported.

[0063] In some embodiments, the suspected illegally parked vehicle information may include the license plate number, vehicle model, vehicle color, owner information, suspected illegal parking time, suspected illegal parking location, etc. In some embodiments, the suspected illegally parked vehicle information can be obtained by identifying the vehicle license plate number through an image acquisition device, and obtaining other vehicle information (such as vehicle model, owner information, etc.) through the license plate number. In some embodiments, the suspected illegal parking time / location of the vehicle can be directly obtained by the time when the image acquisition device identifies the suspected illegally parked vehicle and the location where the image acquisition device is set.

[0064] Step 340 , determining a shielded area based on the congestion detection area. In some embodiments, step 340 may be implemented by the shielded area determination module 230 .

[0065] In some embodiments, the shielded area is an area in which the situation in the area can be filtered in some cases. In some embodiments, the shielded area is an area in which suspected illegally parked vehicles located in the area can be filtered, and the suspected illegally parked vehicles stop driving in the area for some reason. In some embodiments, the suspected illegally parked vehicles may stop driving in the illegally parked area due to lane congestion, or due to a car accident or other reasons. In some embodiments described in the present application, the shielded area is mainly an area for filtering suspected illegally parked vehicles that stop driving in the area due to congestion. In this area, suspected illegally parked vehicles will not be determined as illegally parked.

[0066] In some embodiments, the shielded area can be determined by different methods based on the congestion detection area. For example, the congestion detection area output in step 320 can be directly filtered as a shielded area. In some embodiments, the detected congestion detection area may not include all congested vehicles, or may not cover the entire congested lane, so that a vehicle outside the congestion detection area stops driving due to lane congestion and cannot be filtered and reported as illegally parked. Therefore, the congestion detection area can also be expanded in different forms, and the expanded area is determined as a shielded area, and then filtered. In some embodiments, the expansion of the congestion detection area may include methods such as determining related polygons or extending the boundary lines of the area. For specific steps, see. Figure 4 and Figure 5 The content is not described in detail here.

[0067] Step 350 , determining whether the suspected illegally parked vehicle is located in the shielded area. In some embodiments, step 350 may be implemented by the determination module 240 .

[0068] In some embodiments, when a vehicle is identified as a suspected illegally parked vehicle, it is necessary to determine whether the vehicle is illegally parked based on the relevant information of the suspected illegally parked vehicle and the determined shielded area. In some embodiments, the relevant information of the suspected illegally parked vehicle may include the license plate number, vehicle model, vehicle color, owner information, suspected illegal parking time of the vehicle, suspected illegal parking location of the vehicle, etc. In some embodiments, the suspected illegally parked vehicles can be flexibly filtered according to the relevant information of the suspected illegally parked vehicles. For example, if the suspected illegal parking time of the vehicle is not within the illegal parking time of the illegal parking area, the suspected illegally parked vehicle can be directly filtered.

[0069] In some embodiments, it is also necessary to determine whether the suspected illegally parked vehicle is located in the shielded area determined in step 340. The shielded area can be directly the congestion detection area or the area after the congestion detection area is expanded. In some embodiments, if the suspected illegally parked vehicle is located in the determined shielded area, the suspected illegally parked vehicle can be filtered and not determined as an illegally parked vehicle; if the suspected illegally parked vehicle is not located in the determined shielded area, the suspected illegally parked vehicle can be determined as an illegally parked vehicle and the illegally parked vehicle can be reported. In some embodiments, different methods can be used to determine whether the suspected illegally parked vehicle is located in the shielded area, such as area determination method, angle determination method, ray method, etc., or other algorithms that can achieve the same effect.

[0070] Step 360 , outputting the determination result. In some embodiments, step 360 may be implemented by the output module 250 .

[0071] In some embodiments, the output is performed according to the above determination results. In some embodiments, if the suspected illegally parked vehicle is located in the shielded area and is not determined to be an illegally parked vehicle, the vehicle information is not reported, and the suspected illegally parked vehicle and related information can be processed later, or the related information can be directly deleted. In some embodiments, if the suspected illegally parked vehicle is determined to be an illegally parked vehicle, the vehicle information can be reported, and the illegally parked vehicle can be penalized with points deducted or fined according to the specific circumstances of the illegally parked vehicle.

[0072] In some embodiments, for suspected illegally parked vehicles that are not determined to be illegally parked vehicles, if the vehicles in front and behind them are both stopped in the illegally parked area, then with a certain probability, the vehicles in front and behind them will also be located in the shielded area. For the vehicles in front and behind, if they are determined to be illegally parked vehicles, it may be that the shielded area does not cover the area where the vehicles in front and behind are located, and the determination can be made after a new shielded area is determined again to a certain extent.

[0073] In some embodiments, the congested area filtering system 200 can also be used for filtering other events, not only illegal parking events, for example, planning of vehicle driving routes, selection of vehicle parking locations, etc.

[0074] It should be noted that the above description of process 300 is only for example and explanation, and does not limit the scope of application of the present application. For those skilled in the art, various modifications and changes can be made to process 300 under the guidance of the present application. However, these modifications and changes are still within the scope of the present application. For example, step 330 can be performed simultaneously with steps 310, 320, and 340, or before step 310.

[0075] Figure 4 FIG. 4 is an exemplary flow chart of a shielding area determination method 400 according to some embodiments of the present application. In some embodiments, the shielding area determination method 400 may be executed by the congestion area filtering system 200 .

[0076] Step 410 , determining a relevant polygon based on the congestion detection area. In some embodiments, step 410 may be implemented by the shielding area determination module 230 .

[0077] In some embodiments, the congestion detection area can be directly used as a shielding area, but it is often impossible to cover all congested areas, so the congestion detection area needs to be expanded to make its coverage wider. In some embodiments, a related polygon can be determined based on the congestion detection area, and the related polygon is circumscribed to the boundary of the congestion detection area and has a range larger than the congestion detection area. In some embodiments, the related polygon can expand the coverage of the congestion detection area to a certain extent, that is, expand the shielding area of ​​illegal parking events, thereby reducing the false alarm rate of illegal parking events.

[0078] In some embodiments, the relevant polygon may be a minimum bounding rectangle (MBR), also known as a minimum bounding rectangle, etc. In some embodiments, the relevant polygon may also be a circumscribed rhombus, a circumscribed circle, etc. of the congestion detection area. In some embodiments, the minimum circumscribed moment is the maximum range of a number of two-dimensional shapes (e.g., a point, a straight line, a polygon) represented by two-dimensional coordinates, that is, a rectangle whose lower boundary is defined by the minimum horizontal coordinate, the maximum horizontal coordinate, the minimum vertical coordinate, and the maximum vertical coordinate of each vertex of a given two-dimensional shape. In some embodiments, the minimum circumscribed moment is a rectangular frame with the minimum area or the minimum perimeter circumscribed to the two-dimensional polygon under the two-dimensional coordinate representation. The minimum circumscribed moment may be in any direction, not limited to being parallel to the coordinate axis. In some embodiments, the minimum circumscribed moment of the congestion detection area may be calculated by a rotation basis algorithm, a convex hull algorithm, etc.

[0079] Step 420 , determining the long side and the short side of the relevant polygon. In some embodiments, step 420 may be implemented by the shielding area determination module 230 .

[0080] In some embodiments, the calculated minimum circumscribed moment can also be expanded or extended to expand the shielding area. In some embodiments, it is necessary to first determine the long side and short side of the minimum circumscribed moment, and then extend the boundary accordingly according to the long side and short side. In some embodiments, the long side is the two relatively longer sides of the four boundaries of the minimum circumscribed moment, and the short side is the two relatively shorter sides of the four boundaries of the minimum circumscribed moment.

[0081] In some embodiments, the long side and the short side can be determined by the following method: Assume that the four vertices of the minimum circumscribed moment are p1, p2, p3, and p4 in order; calculate the distance L between p1 and p2, and between p2 and p3 p12 With L p23 ; Compare L p12 With L p23 The size of p12 Greater than L p23 , then the long side is the side composed of p1 and p2 and the side composed of p3 and p4, and the short side is the side composed of p2 and p2 and the side composed of p1 and p4; if L p23 Greater than L p12 , then the long side is the side formed by p2 and p3 and the side formed by p1 and p4, and the short side is the side formed by p1 and p2 and the side formed by p3 and p4. In some embodiments, the long side and the short side can also be determined by determining the difference in the vertex coordinates of the minimum circumscribed moment, or other methods that can achieve the same effect.

[0082] In some embodiments, the long side and the short side of the minimum circumscribed moment can be determined by extending the long side and the short side respectively, thereby expanding the boundary of the minimum circumscribed moment and expanding the shielding area.

[0083] Step 430 , extending the long side and the short side to the boundary of the road condition image. In some embodiments, step 430 may be implemented by the shielding area determination module 230 .

[0084] In some embodiments, since the congestion detection area often cannot completely cover the entire congestion area, even if it has been expanded to the minimum circumscribed moment of the congestion detection area, there may still be vehicles affected by the congestion outside the area of ​​the minimum circumscribed moment, and these vehicles cannot be filtered. Therefore, it is necessary to extend the boundary of the minimum circumscribed moment and continue to expand the shielding area, so as to filter as many vehicles as possible in the congestion area.

[0085] In some embodiments, the long side determined in step 420 is extended to the boundary of the road condition image, and the short side determined in step 420 is extended to the boundary of the road condition image. In some embodiments, the above steps can also be performed alternately, and the order of execution is not limited. In some embodiments, only the long side can be extended to the boundary of the road condition image without extending the short side, or only the short side can be extended to the boundary of the road condition image without extending the long side.

[0086] Step 440 , determining the intersection of the extension line and the road condition image boundary. In some embodiments, step 440 may be implemented by the shielding area determination module 230 .

[0087] In some embodiments, the method for determining the intersection of the extension lines of the long side and the short side and the boundary of the road condition image can be set in a two-dimensional coordinate axis, and the coordinates of the intersection can be solved by calculation. In some embodiments, the boundary of the road condition image can be set as a coordinate axis, and one corner is the origin of the coordinate, which can be any one of the upper left corner, lower left corner, upper right corner, and lower right corner of the image. In some embodiments, if the upper left corner of the image is used as the origin of the coordinate, the horizontal right is the positive direction of the X axis, and the vertical downward is the positive direction of the Y axis.

[0088] In some embodiments, if the slope of the equation of the line where the extension line is located is greater than 0, the intersection of the extension line and the upper left boundary of the image is divided into two cases, and the intersection solution steps are as follows: Assume that x is 0, substitute the y value solved in the equation of the line; if the y value is greater than 0, the intersection point is located at the left boundary of the image (such as Fig. 6A As shown), the intersection coordinates are (0, y); if the y value is less than 0, the intersection point is located at the upper boundary of the image (such as Figure 6B As shown), we need to assume that y is 0 and then substitute it into the equation of the line to solve for the value of x. The coordinates of the intersection point are (x, 0).

[0089] In some embodiments, if the slope of the equation of the line where the extension line is located is greater than 0, the intersection of the extension line and the lower right border of the image is divided into two cases, and the steps for solving the intersection are as follows: set the image width value (the length of the upper and lower borders) to width, and the height value (the length of the left and right borders) to height; assume that x is width, substitute it into the equation of the line to solve the y value; if the y value is less than height, the intersection point is located at the right border of the image (such as Figure 6C ), the intersection coordinates are (width, y); if the y value is greater than the height, the intersection point is located at the lower boundary of the image (such as Fig.6D As shown), we need to assume that y is height and then substitute it into the equation of the line to solve for the value of x. The coordinates of the intersection point are (x, height).

[0090] In some embodiments, if the slope of the equation of the line where the extension line is located is less than 0, the intersection of the extension line and the upper right boundary of the image is divided into two cases, and the intersection solving steps are as follows: set the image width value to width and the height value to height; assume that x is width, substitute it into the equation of the line to solve the y value; if the y value is greater than 0, the intersection point is located at the right boundary of the image (such as Fig. 6E ), the intersection coordinates are (width, y); if the y value is less than 0, the intersection point is located at the upper boundary of the image (such as Fig. 6F As shown), we need to assume that y is 0 and then substitute it into the equation of the line to solve for the value of x. The coordinates of the intersection point are (x, 0).

[0091] In some embodiments, if the slope of the equation of the line where the extension line is located is less than 0, the intersection of the extension line and the lower left boundary of the image is divided into two cases, and the intersection solution steps are as follows: set the image width value to width and the height value to height; assume that x is 0, substitute it into the equation of the line to solve the y value; if the y value is less than height, the intersection point is located at the left boundary of the image (such as Figure 6G As shown), the intersection coordinates are (0, y); if the y value is greater than height, the intersection point is located at the lower boundary of the image (such as Figure 6H As shown), we need to assume that y is height and then substitute it into the equation of the line to solve for the value of x. The coordinates of the intersection point are (x, height).

[0092] In some embodiments, the intersection of the extended line of the long side and the road condition image boundary and the intersection of the extended line of the short side and the road condition image boundary can be solved separately without affecting each other, and the corresponding intersections are solved. In some embodiments, if only the long side or only the short side needs to be extended, only the intersection of the extended line to be extended and the road condition image boundary needs to be solved.

[0093] Step 450 , determining the area enclosed by the road condition image boundary and the extension line as a shielded area. In some embodiments, step 450 may be implemented by the shielded area determination module 230 .

[0094] In some embodiments, four intersection points of the two extended lines of the long side / short side and the road condition image boundary can be solved according to step 440. In some embodiments, if only one of the long side and the short side needs to be extended, the four solved intersection points are connected, and the enclosed area is the area enclosed by the road condition image boundary and the extended lines, which can be determined as the shielded area.

[0095] In some embodiments, if both the long side and the short side need to be extended, there are four long side intersection points and short side intersection points between the long side and the short side and the road condition image boundary, respectively. In some embodiments, the four long side intersection points and the four short side intersection points are respectively enclosed into a region, and the union of the two regions is obtained to obtain the final shielding region.

[0096] In some embodiments, based on the determined shielded area, it can be determined in step 350 whether the vehicle belongs to the shielded area, thereby achieving the purpose of filtering the congested area.

[0097] It should be noted that the above description of process 400 is only for example and explanation, and does not limit the scope of application of the present application. For those skilled in the art, various modifications and changes can be made to process 400 under the guidance of the present application. However, these modifications and changes are still within the scope of the present application. For example, the relevant polygons determined in step 410 can be directly used as shielding areas, etc.

[0098] Figure 5 FIG. 5 is an exemplary flow chart of another method for determining a shielded area according to some embodiments of the present application. In some embodiments, the shielded area determination method 500 may be executed by the congested area filtering system 200 .

[0099] Step 510 , determining lane lines of the congestion detection area. In some embodiments, step 510 may be implemented by the shielding area determination module 230 .

[0100] In some embodiments, lane lines are traffic markings used to separate traffic flows for vehicles, and are generally white dashed or solid lines or yellow dashed or solid lines. In some embodiments, lane lines in the congestion detection area may be identified, thereby using another method to determine the shielding area.

[0101] In some embodiments, the lane lines in the congestion detection area can be identified by color selection, ROI (Region of Interest) selection, or a combination of color selection and ROI selection. In some embodiments, the lane lines in the congestion detection area can also be identified by edge detection, Hough transform, or other methods that can achieve the desired effect. In some embodiments, the lane lines identified in the congestion detection area can assist in determining the shielding area that needs to be filtered.

[0102] Step 520 , extending the lane line of the congestion detection area. In some embodiments, step 520 may be implemented by the shielding area determination module 230 .

[0103] In some embodiments, in the same road condition image, for vehicles in the same lane, if a vehicle is located in the congestion detection area, the vehicles in front and behind it should also be affected by the congestion and be in the congestion area. In some embodiments, the vehicles in front and behind the congestion detection area also need to be shielded, so the lane line identified in the congestion detection area can be directly extended to the boundary of the road condition image.

[0104] In some embodiments, the lane lines of the congestion detection area determined in step 510 may be extended to the boundary of the road condition image, or may be extended only to a predetermined distance (for example, a distance of 5 meters, 10 meters, 20 meters, 30 meters, etc.) or other limited places.

[0105] Step 530 : determining a shielded area based on the extension line of the lane line. In some embodiments, step 530 may be implemented by the shielded area determination module 230 .

[0106] In some embodiments, based on the extension of the lane line in the congestion detection area and the road condition image boundary, the intersection of the extension line and the image boundary can be solved. The specific solution method is similar to the method in step 440, or other methods that can achieve the same effect, which will not be described in detail here. In some embodiments, the four intersections of the extension line and the image boundary are connected, and the enclosed area is the area enclosed by the road condition image boundary and the extension line, which can be determined as the shielded area.

[0107] In some embodiments, based on the determined shielded area, it can be determined in step 350 whether the vehicle belongs to the shielded area, thereby achieving the purpose of filtering the congested area.

[0108] It should be noted that the above description of process 500 is only for example and illustration, and does not limit the scope of application of the present application. For those skilled in the art, various modifications and changes can be made to process 500 under the guidance of the present application. However, these modifications and changes are still within the scope of the present application.

[0109] The beneficial effects that may be brought about by the embodiments of the present application include but are not limited to: (1) filtering illegal parking events of vehicles occurring in congested areas, thereby shielding illegal parking events in congested areas; (2) expanding the shielded area by determining the minimum circumscribed moment of the congested detection area, and reducing the false alarm rate of illegal parking events; (3) extending the long side and short side of the minimum circumscribed moment, expanding the shielded area, and reducing the false alarm rate of illegal parking events. It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects that may be produced may be any one or a combination of the above, or any other possible beneficial effects.

[0110] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of the present application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements and amendments to the present application. Such modifications, improvements and amendments are suggested in the present application, so such modifications, improvements and amendments still belong to the spirit and scope of the exemplary embodiments of the present application.

[0111] At the same time, the present application uses specific words to describe the embodiments of the present application. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of the present application. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, some features, structures or characteristics in one or more embodiments of the present application can be appropriately combined.

[0112] In addition, it will be appreciated by those skilled in the art that various aspects of the present application may be illustrated and described by a number of patentable categories or situations, including any new and useful process, machine, product or combination of substances, or any new and useful improvements thereto. Accordingly, various aspects of the present application may be performed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software may all be referred to as "data blocks", "modules", "engines", "units", "components" or "systems". In addition, various aspects of the present application may be represented as a computer product located in one or more computer-readable media, which includes computer-readable program code.

[0113] A computer storage medium may include a propagated data signal containing computer program code, for example, in baseband or as part of a carrier wave. The propagated signal may be in a variety of forms, including electromagnetic, optical, etc., or a suitable combination. A computer storage medium may be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, device or apparatus to communicate, propagate or transmit the program for use. The program code on the computer storage medium may be transmitted via any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of the above media.

[0114] The computer program coding required for the operation of each part of the application can be written in any one or more programming languages, including object-oriented programming languages ​​such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc., conventional procedural programming languages ​​such as C language, VisualBasic, Fortran2003, Perl, COBOL2002, PHP, ABAP, dynamic programming languages ​​such as Python, Ruby and Groovy, or other programming languages, etc. The program coding can be run completely on the user's computer, or run on the user's computer as an independent software package, or run partly on the user's computer and partly on the remote computer, or run completely on the remote computer or processing device. In the latter case, the remote computer can be connected to the user's computer through any network form, such as a local area network (LAN) or a wide area network (WAN), or connected to an external computer (e.g., via the Internet), or in a cloud computing environment, or used as a service such as software as a service (SaaS).

[0115] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this application, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this application. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this application. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing processing device or mobile device.

[0116] Similarly, it should be noted that in order to simplify the description of the disclosure of this application and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this application, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the object of this application are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0117] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of the present application are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0118] Each patent, patent application, patent application disclosure, and other materials, such as articles, books, instructions, publications, documents, etc., cited in this application are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the content of this application, documents that limit the broadest scope of the claims of this application (currently or later attached to this application) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the attached materials of this application are inconsistent or conflicting with the content described in this application, the descriptions, definitions, and / or use of terms in this application shall prevail.

[0119] Finally, it should be understood that the embodiments described in this application are only used to illustrate the principles of the embodiments of the present application. Other variations may also fall within the scope of the present application. Therefore, as an example and not a limitation, the alternative configurations of the embodiments of the present application may be considered to be consistent with the teachings of the present application. Accordingly, the embodiments of the present application are not limited to the embodiments explicitly introduced and described in the present application.

Claims

1. A congested area filtering method, characterized in that: The method comprises: Obtaining an input road condition image; Based on the road condition image, obtaining a congestion detection area through a congestion detection model; Obtain information about suspected illegally parked vehicles; Based on the information related to the suspected illegally parked vehicle information and in combination with the congestion detection area, determining whether the vehicle is illegally parked; The method for determining whether a vehicle is illegally parked based on the information related to the suspected illegally parked vehicle information and in combination with the congestion detection area includes: Determine a shielded area based on the congestion detection area; and determine whether the suspected illegally parked vehicle is located in the shielded area; The method for determining a shielding area based on the congestion detection area comprises: Determine a relevant polygon based on the congestion detection area; expand the relevant polygon as a shielding area; The result of the determination is output.

2. The congested area filtering method according to claim 1, characterized in that: The associated polygon may be a minimum circumscribed polygon.

3. The congested area filtering method according to claim 1, characterized in that: The method of expanding the relevant polygon as a shielding area comprises: Determine the long side and the short side of the relevant polygon; A shielding area is determined based on the extension lines of the long side and the short side and the boundary of the road condition image.

4. The congested area filtering method according to claim 3, characterized in that: The method for determining the shielding area based on the extension line of the long side and the short side and the boundary of the road condition image includes: Extending the long side and the short side to the boundary of the road condition image; Determining the intersection of the extension line and the boundary of the road condition image; Determine that an area enclosed by the road condition image boundary and the extension line is a shielding area.

5. The congested area filtering method according to claim 1, characterized in that: The method for determining a shielding area based on the congestion detection area further includes: A shielded area is determined based on lane lines in the congestion detection area.

6. A congested area filtering system, characterized in that: include: An acquisition module is used to acquire input road condition images and obtain information about suspected illegally parked vehicles; A congestion detection module, configured to obtain a congestion detection area through a congestion detection model based on the road condition image; A determination module, configured to determine whether a vehicle is illegally parked based on information related to the suspected illegally parked vehicle information and in combination with the congestion detection area; A shielding area determination module, used to determine a shielding area based on the congestion detection area; The determination module is further used to determine whether the suspected illegally parked vehicle is located in the shielding area; The shielding area determination module is used to determine the relevant polygon based on the congestion detection area; expanding the relevant polygon as a shielding area; The output module is used to output the result of the determination.

7. The congested area filtering system according to claim 6, characterized in that: The associated polygon may be a minimum circumscribed polygon.

8. The congested area filtering system according to claim 6, characterized in that: The shielding area determination module is used for: Determine the long side and the short side of the relevant polygon; A shielding area is determined based on the extension lines of the long side and the short side and the boundary of the road condition image.

9. The congested area filtering system according to claim 8, characterized in that: The shielding area determination module is used for: Extending the long side and the short side to the boundary of the road condition image; Determining the intersection of the extension line and the boundary of the road condition image; Determine that an area enclosed by the road condition image boundary and the extension line is a shielding area.

10. The congested area filtering system according to claim 6, characterized in that: The shielding area determination module is also used for: A shielded area is determined based on lane lines in the congestion detection area.

11. A device for filtering a congested area, comprising a processor, characterized in that: The processor is used to execute the congested area filtering method according to any one of claims 1 to 5.

12. A computer-readable storage medium storing computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the method for filtering a congested area according to any one of claims 1 to 5.

Images