Method, device and equipment for extracting ground feature elements based on crowd-sourced data
By processing crowdsourced data through computer programs and using Bayes' theorem to calculate the posterior probability of geographic features, the problem of insufficient timeliness and accuracy in map updates is solved, thus achieving timely and accurate map updates.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- WUHAN NAVINFO TECH CO LTD
- Filing Date
- 2023-03-09
- Publication Date
- 2026-07-03
Smart Images
Figure CN116311124B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of map data technology, and in particular to a method, apparatus and equipment for extracting geographic features based on crowdsourced data. Background Technology
[0002] When creating or updating maps, data collection equipment (such as a data collection vehicle equipped with sensors, which may include cameras, radar, etc.) needs to patrol the environment and collect information. The collected environmental information is then compared with the map. When inconsistencies are found between the environment and the map, such as when there are no features at a certain location on the map, but features are identified at that location from the information collected by the data collection equipment, the features can be extracted and added to the map at that location, thus completing the creation or update of the map.
[0003] Because environmental data collection is a massive undertaking, relying solely on a small number of specialized data collection vehicles is insufficient to meet real-time requirements. To ensure real-time data collection, sensors can be mounted on non-specialized vehicles, allowing them to collect data as they pass by. This environmental data collected by both specialized and non-specialized vehicles can be termed crowdsourced data. However, due to limitations in sensor quality and accuracy, the accuracy of the collected data is relatively low. Extracting ground features directly based on a single data collection result, while enabling rapid map updates, compromises accuracy. Current technology employs multiple data collection sessions. Once a sufficient amount of data has accumulated, these sessions are comprehensively analyzed to determine whether to extract ground features, i.e., whether to update the map. While this method improves map update accuracy to some extent, its timeliness remains low.
[0004] Therefore, those skilled in the art urgently need a method for extracting geographic features based on crowdsourced data, which can extract geographic features in a timely and accurate manner so as to update maps in a timely and accurate manner. Summary of the Invention
[0005] To address the aforementioned technical problems, embodiments of this specification propose a method, apparatus, and device for extracting geographic features based on crowdsourced data. This method enables timely and accurate extraction of geographic features, facilitating timely and accurate map updates.
[0006] This specification provides an embodiment of a method for extracting geographic features based on crowdsourced data, including:
[0007] Obtain a first identification result; the first identification result is the result obtained by identifying the information collected by the first acquisition device at the target location at a first moment;
[0008] When the first identification result indicates that ground features exist at the target location based on the information collected by the first acquisition device, the first preset conditional probability parameter and the first prior probability of the first acquisition device are obtained; the first prior probability is obtained based on the information collected by the second acquisition device at the target location at a second time; the second time is earlier than the first time.
[0009] The first posterior probability is calculated based on the first preset conditional probability parameter and the first prior probability.
[0010] When the first posterior probability is not less than the first threshold, the ground features are extracted.
[0011] This specification provides an embodiment of an apparatus for extracting ground features based on crowdsourced data, comprising:
[0012] The first acquisition module is used to acquire a first identification result; the first identification result is the result obtained by identifying the information collected by the first acquisition device at the target location at a first moment;
[0013] The second acquisition module is used to acquire a first preset conditional probability parameter and a first prior probability of the first acquisition device when the first identification result indicates that ground features exist at the target location based on the acquisition information of the first acquisition device; the first prior probability is obtained based on the information acquired by the second acquisition device at the target location at a second time; the second time is earlier than the first time.
[0014] The first calculation module is used to calculate the first posterior probability based on the first preset conditional probability parameter and the first prior probability.
[0015] The first extraction module is used to extract the ground features when the first posterior probability is not less than the first threshold.
[0016] This specification provides an embodiment of a computer device / apparatus / system, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method described above.
[0017] This specification provides an embodiment of a computer-readable storage medium storing a computer program / instructions thereon, which, when executed by a processor, implements the steps of the method described above.
[0018] This specification provides an embodiment of a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of the method described above.
[0019] The at least one technical solution adopted in the embodiments of this specification can achieve the following beneficial effects: After information is collected from the target location, the probability of the presence of ground features at the target location can be calculated and updated in a timely manner. When the probability of the presence of ground features at the target location is updated to not less than a first threshold, the ground features can be extracted to update the map. Compared with the prior art, which requires multiple information collections before deciding whether to update the map, this is more timely. When calculating the probability of the presence of ground features at the target location, the accuracy and recognition capability of the current collection device, as well as the probability of the presence of ground features at the target location in the previous calculation, are comprehensively considered, making the probability of the presence of ground features at the target location more accurate each time, and allowing for a more accurate determination of whether to extract the ground features. Attached Figure Description
[0020] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0021] Figure 1 A flowchart illustrating a method for extracting geographic features based on crowdsourced data, provided as an embodiment of this specification;
[0022] Figure 2 This is a schematic diagram of the structure of a computer device provided in an embodiment of this specification;
[0023] Figure 3 This is a schematic diagram of the structure of a computer device / equipment / system provided in the embodiments of this specification. Detailed Implementation
[0024] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.
[0025] The embodiments described below are merely preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Various modifications and improvements made by those skilled in the art to the technical solutions of the present invention without departing from the spirit of the present invention should fall within the protection scope defined by the claims of the present invention.
[0026] To address the shortcomings of existing technologies, this solution provides the following embodiments:
[0027] Figure 1 This is a flowchart illustrating a method for extracting geographic features based on crowdsourced data, provided as an embodiment of this specification.
[0028] From a hardware perspective, the entity executing this process can be a device; from a program perspective, it can be an application running on that device. For example... Figure 1 As shown, the process may include the following steps:
[0029] Step 101: Obtain the first identification result; the first identification result is the result obtained by identifying the information collected by the first acquisition device at the target location at the first moment.
[0030] After collecting information at the target location, the first data acquisition device identifies the collected information to form a first identification result, which is then obtained. It should be noted that the first identification result can be obtained by the first data acquisition device itself recognizing the information it has collected, or it can be obtained by the first data acquisition device sending the collected information to a dedicated identification device for recognition. The target location can be determined based on the data acquisition trajectory of the first data acquisition device. For example, if the first data acquisition device identifies ground features at a certain location, that location can be recorded as a target location.
[0031] Step 103: When the first identification result indicates that ground features exist at the target location based on the information collected by the first acquisition device, the first preset conditional probability parameter and the first prior probability of the first acquisition device are obtained; the first prior probability is obtained based on the information collected by the second acquisition device at the target location at the second time; the second time is earlier than the first time.
[0032] The first preset conditional probability parameter is determined based on the accuracy and recognition capability of the first data acquisition device and is used to represent the confidence level of identifying the presence of ground features. The first and second times are not specifically defined, but are used to indicate the order of two adjacent data acquisitions. For example, if the time of the Nth data acquisition is the first time, then the time of the (N-1)th data acquisition is the second time.
[0033] Step 105: Calculate the first posterior probability based on the first preset conditional probability parameter and the first prior probability.
[0034] The first posterior probability represents the probability that ground features exist at the target location after the current calculation, and the first prior probability represents the probability that ground features exist at the target location after the previous calculation. That is, after each data collection and identification of the target location, the probability that ground features exist at the target location can be calculated once. In the current calculation, a first preset conditional probability parameter is determined based on the accuracy and identification capability of the current data collection device. The probability that ground features exist at the target location in the current calculation is then calculated based on the first preset conditional probability parameter and the probability of ground features existing at the target location obtained from the previous calculation.
[0035] It should be noted that if, after collecting information about a target location, it can be determined that the collected information contained obvious errors, or if there are other reasons why the collected information can be discarded, then no calculation will be performed for that instance.
[0036] Step 107: When the first posterior probability is not less than the first threshold, the ground features are extracted.
[0037] The first threshold can be specifically defined according to the circumstances. A value greater than or equal to 0.997 can be selected as the first threshold.
[0038] When the first posterior probability is not less than the first threshold, it means that after calculation, the probability that there are ground features at the target location is not less than the first threshold. It can be considered that there are indeed ground features at the target location, and the ground features can be extracted so that the map can be updated in a timely manner.
[0039] Figure 1 The proposed method, after collecting information about the target location, calculates the probability of the presence of ground features at that location and updates this probability in a timely manner. When the probability of ground features at the target location reaches a level not less than a first threshold, the ground features can be extracted for map updates. This method is more timely than existing technologies that require multiple data collections before deciding whether to update the map. The calculation of the probability of ground features at the target location comprehensively considers the accuracy and recognition capability of the current data collection equipment, as well as the previous probability, making each calculated probability more accurate and allowing for a more precise determination of whether to extract the ground features.
[0040] Optionally, the first preset conditional probability parameter includes a first conditional probability and a second conditional probability; the first conditional probability is the conditional probability of identifying the existence of a ground feature when the ground feature exists, and the second conditional probability is the conditional probability of identifying the existence of a ground feature when the ground feature does not exist.
[0041] The step of calculating the first posterior probability based on the first preset conditional probability parameter and the first prior probability specifically includes:
[0042] The first posterior probability is calculated using Bayes' theorem based on the first conditional probability, the second conditional probability, and the first prior probability.
[0043] A preferred computational method is the Bayesian algorithm. Specifically:
[0044] Based on the current identification result and the accuracy and identification capability of the acquisition equipment, a first preset conditional probability parameter is determined. When the identification result indicates that ground features exist at the target location based on the acquisition information from the acquisition equipment, the first preset conditional probability parameter includes a first conditional probability and a second conditional probability. The conditional probability of identifying the existence of ground features when they exist is taken as the first conditional probability; the conditional probability of identifying the existence of ground features when they do not exist is taken as the second conditional probability. The probability of ground features existing at the previously determined target location is taken as the first prior probability. The probability of ground features existing when they are identified is taken as the first posterior probability. Formulas (1) and (2) are used for calculation.
[0045] P(Report)=P(Report|Exist)*P(Exist)+P(Report|!Exist)*P(!Exist)(1)
[0046]
[0047] Where P(Report|Exist) represents the conditional probability of identifying a feature when it exists; P(Report|!Exist) represents the conditional probability of identifying a feature when it does not exist; P(Exist) represents the probability that a feature exists at the target location; P(Exist|Report) represents the probability that a feature exists when it is identified; P(!Exist) represents the probability that a feature does not exist at the target location, and P(!Exist) = 1 - P(Exist).
[0048] It should be noted that the probability of a feature's existence when it is identified in the current calculation can be used as the prior probability for the next calculation, and the calculation can be performed iteratively. In the first calculation, the prior probability is a preset value.
[0049] By employing Bayesian algorithms, the first and second conditional probabilities can be determined based on the accuracy and recognition capability of the data acquisition devices. These probabilities can be pre-determined through parameter calibration or experimentation with the acquisition devices. This allows for a more accurate determination of the reliability of the recognition results, making probability calculations more precise. Furthermore, acquisition devices with different accuracies and recognition capabilities will correspond to different conditional probabilities. This avoids the errors that arise from applying the same reliability level (based on the average value calculated from multiple acquisition devices) to different acquisition devices. It also allows for better utilization of crowdsourced data with varying levels of accuracy.
[0050] Optionally, when the first identification result indicates that no ground features were identified at the target location based on the information collected by the first acquisition device, the method further includes:
[0051] The second preset conditional probability parameter and the second prior probability of the first acquisition device are obtained; the second prior probability is obtained based on the information acquired by the third acquisition device at the target location at a third time; the third time is earlier than the first time.
[0052] The second posterior probability is calculated based on the second preset conditional probability parameter and the second prior probability.
[0053] The second preset conditional probability parameter of the first data acquisition device is used to represent the confidence level of not identifying ground features. The first and third time points are not specifically defined, but are used to indicate the order of two adjacent data acquisitions. If the time of the Kth data acquisition is the first time, then the time of the (K-1)th data acquisition is the third time.
[0054] Optionally, the second preset conditional probability parameter includes a third conditional probability and a fourth conditional probability; the third conditional probability is the conditional probability that no feature is identified when the feature exists, and the fourth conditional probability is the conditional probability that no feature is identified when the feature does not exist.
[0055] The step of calculating the second posterior probability based on the second preset conditional probability parameter and the second prior probability specifically includes:
[0056] The second posterior probability is calculated using Bayes' theorem based on the third conditional probability, the fourth conditional probability, and the second prior probability.
[0057] When using the Bayesian algorithm, if the identification result indicates that no ground features were identified at the target location based on the information collected by the acquisition device, a second preset conditional probability parameter is determined. The second preset conditional probability parameter includes a third conditional probability and a fourth conditional probability. The conditional probability of not identifying ground features when they are present is taken as the third conditional probability; the conditional probability of not identifying ground features when they are absent is taken as the fourth conditional probability. The probability of ground features existing at the previously determined target location is taken as the second prior probability. The probability of ground features existing when they are not identified is taken as the second posterior probability. Formulas (3) and (4) are used for calculation.
[0058] P(!Report)=P(!Report|Exist)*P(Exist)+P(!Report|!Exist)*P(!Exist)(3)
[0059]
[0060] Where P(!Report|Exist) represents the conditional probability that no feature is identified when the feature exists; P(!Report|!Exist) represents the conditional probability that no feature is identified when the feature does not exist; P(Exist) represents the probability that a feature exists at the target location; P(Exist|!Report) represents the probability that a feature exists when no feature is identified; P(!Exist) represents the probability that no feature exists at the target location, and P(!Exist) = 1 - P(Exist).
[0061] It should be noted that the probability of the existence of a ground feature when it is not identified in the current calculation can be used as the prior probability for the next calculation, and so on for iterative calculation.
[0062] Optionally, the feature is a point feature, or the feature is a line feature that is divided into lines with a length not greater than a first threshold.
[0063] The first threshold can be specifically defined as needed, for example, it can be 1m. Ground features can be divided into point features and linear features. For example, road signs are point features. Point features can be directly identified. Longer road markings, however, are linear features. In this case, the markings can be discretized, divided into multiple segments, each segment being identified as an independent object. For example, when the markings are long, they can be divided into 1m segments, and each segment can be identified separately. Due to the instability of the data acquisition equipment, if parts are missed when identifying long objects, it will affect the determination of the entire object's existence. Dividing long linear features into multiple objects and identifying them separately can avoid this problem.
[0064] Optionally, when the first posterior probability is less than the first threshold, the first posterior probability is used as the prior probability for the next posterior probability calculation.
[0065] When the first posterior probability is less than the first threshold, the first posterior probability is used as the prior probability for the next posterior probability calculation. In this way, iterative calculations can be performed in subsequent calculations to update the probability of the presence of ground features at the target location each time.
[0066] The following section uses land feature elements as an example to introduce a specific method for extracting land feature elements.
[0067] Set the initial prior probability, which is the probability that a sign exists at the target location. Specifically, it can be set to 0.5, i.e., P(Exist) = 0.5, then P(!Exist) = 1 - P(!Exist) = 0.5.
[0068] The conditional probability is determined based on the accuracy and recognition capability of the data acquisition equipment. Assuming the accuracy and recognition capability of the equipment are low, P(Report|Exist) = 0.4, P(Report|!Exist) = 0.1, then P(!Report|Exist) = 1 - P(Report|Exist) = 0.6.
[0069] P(!Report|!Exist)=1-P(Report|!Exist)=0.9.
[0070] Assuming that after the initial data collection, the identification result is the identification of ground features, and P(Exist) = 0.5,
[0071] P(!Exist) = 0.5, P(Report|Exist) = 0.4, and P(Report|!Exist) = 0.1, substitute them into formula (1)
[0072] The posterior probability P(Exist|Report) = 0.8 was calculated using (2).
[0073] Assuming that the identification result after the second information collection is that the feature was not identified, and the posterior probability of 0.8 calculated in the first collection is used as the prior probability P(Exist) = 0.8 for this collection, then...
[0074] P(!Exist)=1-P(!Exist)=0.2; Substituting P(Exist)=0.8, P(!Exist)=0.2, P(!Report|Exist)=0.6 and P(!Report|!Exist)=0.9 into formulas (3) and (4), we obtain the posterior probability P(Exist|!Report)=0.727.
[0075] Assuming that the identification result after the third information collection is that the feature is identified, the posterior probability of 0.727 calculated in the second time is taken as the prior probability P(Exist) = 0.727. Then P(!Exist) = 1 - P(!Exist) = 0.273. The posterior probability is calculated according to formulas (1) and (2).
[0076] This process is repeated iteratively, and after each calculation, the posterior probability is compared with the first threshold.
[0077] Assuming that after the sixth data collection, the calculated posterior probability is P(Exist|Report) = 0.998, and when the first threshold is set to 0.997, the posterior probability 0.998 > 0.997, it is considered that the feature can be extracted and the map can be updated in a timely manner.
[0078] It should be noted that, for ease of description, the examples above assume that the accuracy and recognition accuracy of the data acquisition devices are the same for each data collection session. If the accuracy and recognition accuracy of the data acquisition devices differ for each data collection session, then P(Report|Exist) and P(Report|!Exist) (or P(!Report|Exist) and P(!Report|!Exist)) need to be determined for each calculation.
[0079] Based on the same idea, embodiments of this specification also provide apparatus corresponding to the above methods.
[0080] Figure 2 This is a schematic diagram of the structure of a computer device provided as an embodiment of this specification. Figure 2 As shown, it includes:
[0081] The first acquisition module 201 is used to acquire a first identification result; the first identification result is the result obtained by identifying the information collected by the first acquisition device at the target location at a first moment;
[0082] The second acquisition module 202 is used to acquire a first preset conditional probability parameter and a first prior probability of the first acquisition device when the first identification result indicates that ground features exist at the target location based on the acquisition information of the first acquisition device; the first prior probability is obtained based on the information acquired by the second acquisition device at the target location at a second time; the second time is earlier than the first time.
[0083] The first calculation module 203 is used to calculate the first posterior probability based on the first preset conditional probability parameter and the first prior probability.
[0084] The first extraction module 204 is used to extract the ground features when the first posterior probability is not less than the first threshold.
[0085] Optionally, the first preset conditional probability parameter includes a first conditional probability and a second conditional probability; the first conditional probability is the conditional probability of identifying the existence of a ground feature when the ground feature exists, and the second conditional probability is the conditional probability of identifying the existence of a ground feature when the ground feature does not exist.
[0086] The first calculation module is specifically used to calculate the first posterior probability using Bayes' theorem based on the first conditional probability, the second conditional probability, and the first prior probability.
[0087] Optionally, when the first identification result indicates that no ground features were identified at the target location based on the information collected by the first acquisition device,
[0088] The second acquisition module is specifically used to acquire the second preset conditional probability parameter and the second prior probability of the first acquisition device; the second prior probability is obtained based on the information acquired by the third acquisition device at the target location at a third time; the third time is earlier than the first time;
[0089] The first calculation module is specifically used to calculate the second posterior probability based on the second preset conditional probability parameter and the second prior probability.
[0090] Optionally, the second preset conditional probability parameter includes a third conditional probability and a fourth conditional probability; the third conditional probability is the conditional probability that no feature is identified when the feature exists, and the fourth conditional probability is the conditional probability that no feature is identified when the feature does not exist.
[0091] The first calculation module is specifically used to calculate the second posterior probability using Bayes' theorem based on the third conditional probability, the fourth conditional probability, and the second prior probability.
[0092] Optionally, the device further includes:
[0093] The first determining module is used to use the first posterior probability as the prior probability for the next posterior probability calculation when the first posterior probability is less than the first threshold.
[0094] Based on the same idea, embodiments of this specification also provide computer devices / equipment / systems corresponding to the above methods.
[0095] Figure 3 This is a schematic diagram illustrating the structure of a computer device / equipment / system provided for embodiments of this specification. (See attached diagram.) Figure 3 As shown, the computer device / equipment / system 300 may include a memory 330, a processor 310, and a computer program 320 stored in the memory, the processor executing the computer program to implement the steps of any of the methods described above.
[0096] Based on the same idea, embodiments of this specification also provide a computer-readable storage medium corresponding to the above methods, on which a computer program / instruction is stored, which, when executed by a processor, implements the steps of any of the methods described above.
[0097] Based on the same idea, embodiments of this specification also provide computer program products corresponding to the above methods, including computer programs / instructions, which, when executed by a processor, implement the steps of any of the methods described above.
[0098] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on its differences from other embodiments. In particular, for... Figure 3 As the device shown is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.
[0099] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many methodological improvements today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that a methodological improvement cannot be implemented using hardware physical modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program a digital system themselves to "integrate" it onto a PLD, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should understand that by simply performing some logic programming on the method flow using one of these hardware description languages and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.
[0100] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the memory's control logic. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, ASICs, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means that can be included within it to implement various functions can also be considered as structures within the hardware component. Alternatively, the means that can be used to implement various functions can be considered as both software modules implementing the method and structures within the hardware component.
[0101] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.
[0102] For ease of description, the above devices are described separately by function as various units. Of course, in implementing this application, the functions of each unit can be implemented in one or more software and / or hardware.
[0103] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (which may include, but are not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0104] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, produce a machine that can be used to implement the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0105] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture that may include instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0106] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that can be used to implement a process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0107] In a typical configuration, a computing device may include one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0108] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.
[0109] Computer-readable media can include both permanent and non-permanent, removable and non-removable media, and information storage can be achieved by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media can include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital character versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media cannot include transient computer-readable media, such as modulated data signals and carrier waves.
[0110] It should also be noted that the terms "may include," "comprise," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that may include a list of elements may include not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "may include a…" does not exclude the presence of other identical elements in the process, method, article, or apparatus that may include said element.
[0111] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (which may include, but are not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0112] This application can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules can include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.
[0113] The above description is merely an embodiment of this application and should not be construed as limiting the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.
Claims
1. A method for extracting a ground feature element based on crowd-sourced data, characterized in that, include: Obtain the first recognition result; The first identification result is the result obtained by identifying the information collected by the first acquisition device at the target location at the first moment; When the first identification result indicates that ground features exist at the target location based on the information collected by the first acquisition device, the first preset conditional probability parameter and the first prior probability of the first acquisition device are obtained. The first preset conditional probability parameter is determined based on the accuracy and recognition capability of the first acquisition device, and is used to represent the confidence level of identifying the existence of ground features; the first prior probability is obtained based on the information collected by the second acquisition device at the target location at the second time; the second time is earlier than the first time; The first posterior probability is calculated based on the first preset conditional probability parameter and the first prior probability. When the first posterior probability is not less than the first threshold, the ground feature is extracted; When the land feature is a linear feature, the linear feature is divided into multiple linear features with a length not greater than a first threshold, and each segmented linear feature is identified as an independent object.
2. The method of claim 1, wherein, The first preset conditional probability parameter includes a first conditional probability and a second conditional probability; the first conditional probability is the conditional probability of identifying the existence of a ground feature when the ground feature exists, and the second conditional probability is the conditional probability of identifying the existence of a ground feature when the ground feature does not exist. The step of calculating the first posterior probability based on the first preset conditional probability parameter and the first prior probability specifically includes: The first posterior probability is calculated using Bayes' theorem based on the first conditional probability, the second conditional probability, and the first prior probability.
3. The method of claim 1, wherein, When the first identification result indicates that no ground features were identified at the target location based on the information collected by the first acquisition device, the method further includes: The second preset conditional probability parameter and the second prior probability of the first acquisition device are obtained; the second prior probability is obtained based on the information acquired by the third acquisition device at the target location at a third time; the third time is earlier than the first time. The second posterior probability is calculated based on the second preset conditional probability parameter and the second prior probability.
4. The method of claim 3, wherein, The second preset conditional probability parameter includes a third conditional probability and a fourth conditional probability; the third conditional probability is the conditional probability that no ground feature is identified when the ground feature exists, and the fourth conditional probability is the conditional probability that no ground feature is identified when the ground feature does not exist. The step of calculating the second posterior probability based on the second preset conditional probability parameter and the second prior probability specifically includes: The second posterior probability is calculated using Bayes' theorem based on the third conditional probability, the fourth conditional probability, and the second prior probability.
5. The method of claim 1, wherein, The geographic features also include point features.
6. The method of claim 1, wherein, When the first posterior probability is less than the first threshold, the first posterior probability is used as the prior probability for the next posterior probability calculation.
7. A computer apparatus, comprising: include: The first acquisition module is used to acquire the first recognition result; The first identification result is the result obtained by identifying the information collected by the first acquisition device at the target location at the first moment; The second acquisition module is used to acquire the first preset conditional probability parameter and the first prior probability of the first acquisition device when the first identification result indicates that ground features exist at the target location based on the acquisition information of the first acquisition device. The first preset conditional probability parameter is determined based on the accuracy and recognition capability of the first acquisition device and is used to represent the confidence level of identifying the existence of ground features; The first prior probability is obtained based on information collected by the second acquisition device at the target location at a second time point; the second time point is earlier than the first time point. The first calculation module is used to calculate the first posterior probability based on the first preset conditional probability parameter and the first prior probability. The first extraction module is used to extract the ground features when the first posterior probability is not less than the first threshold. The device is also used to, when the feature is a linear feature, divide the linear feature into multiple linear features with a length not greater than a first threshold, and identify each of the divided linear features as an independent object.
8. A computer device comprising a memory, a processor, and a computer program stored on the memory, wherein the computer program comprises instructions that, when executed by the processor, cause the processor to perform the method of any one of claims 1-7. The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 6.
9. A computer-readable storage medium having stored thereon computer program instructions, wherein, When the computer program / instructions are executed by the processor, they implement the steps of the method according to any one of claims 1 to 6.
10. A computer program product comprising computer program instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method according to any one of claims 1 to 6.