An abnormality perception ground object filtering method and device

Abstract

The application relates to an abnormal perception ground object filtering method and device, which comprises the following steps: acquiring real-time perception ground object data and high-precision map ground object data of a current position; pairing each perception ground object with each ground object in a high-precision map to obtain one or more ground object pairs; filtering the one or more ground object pairs based on a first preset distance and consistency; layering the filtered one or more ground object pairs based on a second preset distance and a lane number; and filtering the ground object pairs in the layer with the largest number of ground object pairs based on the uniqueness between the ground object pairs. The application filters the matched abnormal ground objects by pairing the real-time perception ground objects with the ground objects in the high-precision map, and retains the accurate and reliable perception ground objects to improve the system stability and safety.

Description

Technical Field

[0001] This invention belongs to the field of high-precision mapping and intelligent driving technology, specifically relating to an anomaly detection ground feature filtering method and device. Background Technology

[0002] With the widespread application of ground object sensing in the field of intelligent driving, playing a crucial role in modules such as positioning, planning, and control, the accuracy of ground object sensing directly impacts the performance of intelligent driving. Due to the complexity of real-world scenarios, some anomalies inevitably occur in ground object sensing. Filtering out abnormal ground object sensing is an indispensable part of intelligent driving, and accurate and reliable methods for filtering abnormal ground object sensing can effectively improve the stability and safety of intelligent driving. Summary of the Invention

[0003] To improve the accuracy of anomaly detection feature identification, a first aspect of the present invention provides an anomaly detection feature filtering method, comprising: acquiring real-time detected feature data and high-precision map feature data of the current location; pairing each detected feature with each feature in the high-precision map to obtain one or more feature pairs; filtering the one or more feature pairs based on a first preset distance and consistency; stratifying the filtered one or more feature pairs based on a second preset distance and lane number; and filtering the feature pairs in the layer with the most feature pairs based on the uniqueness between feature pairs.

[0004] In some embodiments of the present invention, filtering the one or more feature pairs based on a first preset distance and consistency includes: filtering all feature pairs based on a first preset distance; and filtering the filtered one or more feature pairs based on the consistency of feature data subtypes.

[0005] Furthermore, the step of filtering all feature pairs based on a first preset distance includes: filtering all feature pairs based on a first preset distance, and filtering out feature pairs whose pairing distance is higher than the first preset distance.

[0006] In some embodiments of the present invention, the step of stratifying the filtered one or more feature pairs based on a second preset distance and the number of lanes includes: stratifying the filtered one or more feature pairs in ascending order based on integer multiples of lane distances.

[0007] In some embodiments of the present invention, filtering the feature pairs in the layer with the most feature pairs based on the uniqueness between feature pairs includes: counting the number of feature pairs in each layer, determining the layer with the most feature pairs; and filtering the features in the layer with the most feature pairs based on the uniqueness between feature pairs.

[0008] Furthermore, the filtering of features in the layer with the most feature pairs based on the uniqueness of feature pairs includes: retaining unique feature pairs based on the uniqueness of feature pairs; and filtering non-unique feature pairs in ascending order based on the number of times each feature is paired with other features.

[0009] A second aspect of the present invention provides an anomaly sensing ground feature filtering device, comprising: an acquisition module for acquiring real-time sensing ground feature data and high-precision map ground feature data of the current location; pairing each sensing ground feature with each ground feature in the high-precision map to obtain one or more ground feature pairs; a first filtering module for filtering the one or more ground feature pairs based on a first preset distance and consistency; a second filtering module for stratifying the filtered one or more ground feature pairs based on a second preset distance and the number of lanes; and a third filtering module for filtering the ground feature pairs in the stratum with the most ground feature pairs based on the uniqueness between the ground feature pairs.

[0010] A third aspect of the present invention provides an electronic device comprising: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the anomaly detection ground feature filtering method provided in the first aspect of the present invention.

[0011] In a fourth aspect, the present invention provides a computer-readable medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the anomaly-sensing ground feature filtering method provided in the first aspect of the present invention.

[0012] The beneficial effects of this invention are:

[0013] This invention relates to a method and apparatus for filtering abnormal sensing features. The method includes: acquiring real-time sensing feature data and high-precision map feature data of the current location; pairing each sensing feature with each feature in the high-precision map to obtain one or more feature pairs; filtering the one or more feature pairs based on a first preset distance and consistency; stratifying the filtered one or more feature pairs based on a second preset distance and lane number; and filtering the feature pairs in the stratum with the most feature pairs based on the uniqueness between feature pairs. Therefore, this invention proposes an abnormal sensing feature filtering method that uses a high-precision map as a reference, pairs real-time sensing features with features in the high-precision map, filters out abnormally matched features, and retains accurate and reliable sensing features to improve system stability and security. Attached Figure Description

[0014] Figure 1This is a schematic diagram of the basic process of the anomaly detection ground feature filtering method in some embodiments of the present invention;

[0015] Figure 2 This is a schematic diagram of the specific process of the anomaly detection ground feature filtering method in some embodiments of the present invention;

[0016] Figure 3 This is a schematic diagram of the structure of an anomaly sensing ground feature filtering device in some embodiments of the present invention;

[0017] Figure 4 This is a schematic diagram of the structure of an electronic device in some embodiments of the present invention. Detailed Implementation

[0018] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.

[0019] refer to Figure 1 and Figure 2 In a first aspect of the present invention, an anomaly sensing ground feature filtering method is provided, comprising: S100. acquiring real-time sensing ground feature data and high-precision map ground feature data of the current location; pairing each sensing ground feature with each ground feature in the high-precision map to obtain one or more ground feature pairs; S200. filtering the one or more ground feature pairs based on a first preset distance and consistency; S300. stratifying the filtered one or more ground feature pairs based on a second preset distance and the number of lanes; S400. filtering the ground feature pairs in the stratum with the most ground feature pairs based on the uniqueness between ground feature pairs.

[0020] In step S100 of some embodiments of the present invention, acquiring real-time sensed ground feature data and high-precision map ground feature data of the current location; pairing each sensed ground feature with each ground feature in the high-precision map to obtain one or more ground feature pairs includes:

[0021] Specifically, it receives and saves real-time sensing data of ground features; acquires and saves high-precision map features of the current location; and sequentially calculates the distance from the center of each sensing ground feature to the center of each high-precision map feature, recording the feature ID and pairing distance.

[0022] In step S200 of some embodiments of the present invention, filtering the pairing of one or more land features based on a first preset distance and consistency includes:

[0023] S201. Filter all land feature pairs based on the first preset distance;

[0024] S202. Based on the consistency of the subtype of land cover data, filter one or more land cover pairs after screening.

[0025] Specifically, all pairing distances are filtered to remove matching pairs that exceed a set range; the matching pairs that meet the requirements in step S201 are filtered to remove matching pairs with inconsistent subtypes.

[0026] Furthermore, in step S201, the filtering of all feature pairs based on the first preset distance includes: filtering all feature pairs based on the first preset distance, and filtering out feature pairs whose pairing distance is higher than the first preset distance.

[0027] It is understandable that the first preset distance is used for "initial screening" of ground features and the second preset distance is used for "refined screening" of ground features. Therefore, the first preset distance is not less than the second preset distance.

[0028] In step S300 of some embodiments of the present invention, the step of stratifying the filtered one or more feature pairs based on the second preset distance and the number of lanes includes: stratifying the filtered one or more feature pairs in ascending order based on integer multiples of lane distances.

[0029] Specifically, the matching pairs in step S200 are layered by pairing distance, and layered by distance of 1 lane, 2 lanes, and 3 lanes.

[0030] In step S400 of some embodiments of the present invention, filtering the feature pairs in the layer with the most feature pairs based on the uniqueness between feature pairs includes: S401. Counting the number of feature pairs in each layer and determining the layer with the most feature pairs; S402. Filtering the features in the layer with the most feature pairs based on the uniqueness between feature pairs.

[0031] Furthermore, in step S402, filtering the features in the layer with the most feature pairs based on the uniqueness of feature pairs includes: retaining unique feature pairs based on the uniqueness of feature pairs; and filtering non-unique feature pairs in ascending order based on the number of times each feature is paired with other features.

[0032] Specifically, count the number of matching pairs in each layer, select the layer with the most matching pairs, and filter the rest; perform one-to-one matching judgment on the filtered matching pairs, retain the unique matching pairs, prioritize assigning non-unique matching features to features with only one candidate set and retaining them, and filter out the rest, and so on, traversing all matching pairs; output the sensed features in the matching pairs retained in step eight as reliable sensed features, for subsequent positioning and planning control applications.

[0033] refer to Figure 2 In a specific embodiment of the present invention, the following steps are included: Step 1: Receive and save the sensed ground feature data in real time;

[0034] Step 2: Obtain and save high-precision map features of the current location;

[0035] Step 3: Calculate the distance from each perceived ground feature center to each high-precision map ground feature center in sequence, and record the ground feature ID and pairing distance;

[0036] Step 4: Filter all pairing distances, removing matching pairs that exceed the set range;

[0037] Step 5: Perform subtype consistency screening on the matching pairs that meet the requirements in Step 4, filtering out matching pairs with inconsistent subtypes;

[0038] Step Six: Layer the matching pairs from Step Five by pairing distance, according to the distance of 1 lane, 2 lanes, and 3 lanes;

[0039] Step 7: Count the number of matching pairs in each layer, select the layer with the most matching pairs, and filter the rest;

[0040] Step 8: Perform one-to-one matching judgment on the matching pairs selected in Step 7. Keep the unique matching pairs, prioritize assigning non-unique matching features to features with only one candidate set and keep them, and filter out the rest. Repeat this process to traverse all matching pairs.

[0041] Step 9: Output the sensed features retained in Step 8 as reliable sensed features for subsequent positioning and planning control applications.

[0042] Example 2

[0043] refer to Figure 3 In a second aspect, the present invention provides an anomaly sensing ground feature filtering device 1, comprising: an acquisition module 11, configured to acquire real-time sensing ground feature data and high-precision map ground feature data of the current location; pairing each sensing ground feature with each ground feature in the high-precision map to obtain one or more ground feature pairs; a first filtering module 12, configured to filter the one or more ground feature pairs based on a first preset distance and consistency; a second filtering module 13, configured to stratify the filtered one or more ground feature pairs based on a second preset distance and the number of lanes; and a third filtering module 14, configured to filter the ground feature pairs in the stratum with the most ground feature pairs based on the uniqueness between the ground feature pairs.

[0044] Furthermore, the first filtering module 12 includes: a filtering unit for filtering all feature pairs based on a first preset distance; and a filtering unit for filtering one or more feature pairs after filtering based on the consistency of feature data subtypes.

[0045] Example 3

[0046] refer to Figure 4 A third aspect of the present invention provides an electronic device comprising: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the anomaly sensing ground feature filtering method of the first aspect of the present invention.

[0047] Electronic device 500 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 502 or a program loaded from storage device 508 into random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of electronic device 500. The processing unit 501, ROM 502, and RAM 503 are interconnected via bus 504. An input / output (I / O) interface 505 is also connected to bus 504.

[0048] Typically, the following devices can be connected to I / O interface 505: input devices 506 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 507 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 508 including, for example, hard disks; and communication devices 509. Communication device 509 allows electronic device 500 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 4 An electronic device 500 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 4 Each box shown can represent a device or multiple devices as needed.

[0049] Specifically, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by a processing device 501, it performs the functions defined in the methods of embodiments of this disclosure. It should be noted that the computer-readable medium described in embodiments of this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0050] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more computer programs, which, when executed by the electronic device, cause the electronic device to:

[0051] Computer program code for performing the operations of embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, C++, and Python—and conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0052] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0053] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An anomaly detection ground feature filtering method, characterized in that, include: Acquire real-time sensing ground feature data and high-precision map ground feature data of the current location; Each perceived ground feature is paired with each ground feature in the high-precision map to obtain one or more ground feature pairs; Based on a first preset distance and consistency, the pairings of one or more ground features are filtered; Based on the second preset distance and the number of lanes, the filtered one or more land feature pairs are layered; The step of stratifying the filtered pairing of one or more ground features based on a second preset distance and the number of lanes includes: Based on integer multiples of lane distance, in ascending order, the filtered pairs of one or more ground features are layered; Based on the uniqueness of feature pairs, feature pairs in the layer with the most feature pairs are filtered. The filtering of land feature pairs in the layer with the most pairs based on the uniqueness of land feature pairs includes: Count the number of feature pairs in each layer and determine the layer with the most feature pairs; Based on the uniqueness of feature pairs, features in the layer with the most feature pairs are filtered. The filtering of land features in the layer with the most land feature pairs based on the uniqueness of land feature pairs includes: Based on the uniqueness of feature pairs, retain unique feature pairs; Based on the number of times each feature is paired with other features simultaneously, non-unique feature pairings are filtered in ascending order of quantity.

2. The anomaly sensing ground feature filtering method according to claim 1, characterized in that, The filtering of the one or more land feature pairs based on a first preset distance and consistency includes: All ground features are matched and filtered based on a first preset distance; Based on the consistency of the subtypes of land cover data, one or more land cover pairs after screening are filtered.

3. The anomaly sensing ground feature filtering method according to claim 2, characterized in that, The filtering of all land cover pairs based on a first preset distance includes: All feature pairs are filtered based on a first preset distance, and feature pairs with a distance greater than the first preset distance are filtered out.

4. An anomaly sensing ground feature filtering device applying the anomaly sensing ground feature filtering method as described in any one of claims 1-3, characterized in that, include: The acquisition module is used to acquire real-time sensed ground feature data and high-precision map ground feature data of the current location; Each perceived ground feature is paired with each ground feature in the high-precision map to obtain one or more ground feature pairs; The first filtering module is used to filter the pairing of one or more ground features based on a first preset distance and consistency. The second filtering module is used to stratify one or more filtered land feature pairs based on a second preset distance and the number of lanes. The third filtering module is used to filter the feature pairs in the layer with the most feature pairs based on the uniqueness of the feature pairs.

5. The anomaly sensing ground feature filtering device according to claim 4, characterized in that, The first filtering module includes: The filtering unit is used to filter all land feature pairs based on a first preset distance; The filtering unit is used to filter one or more feature pairs after screening based on the consistency of the feature data subtype.

6. An electronic device, comprising: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the anomaly-aware ground feature filtering method as described in any one of claims 1 to 3.

7. A computer-readable medium having a computer program stored thereon, wherein, When the computer program is executed by the processor, it implements the anomaly sensing ground feature filtering method as described in any one of claims 1 to 3.

Images