Method and system for deriving lane distribution from vehicle trajectory

Abstract

A method and system for deriving a lane distribution from a vehicle trajectory is provided. The method includes: (1) for a set of vehicle trajectories, sequentially applying windows to each of the set of vehicle trajectories in a right-to-left traversal order based at least in part on sizes of the windows to form a plurality of lane configurations; (2) for each of the plurality of formed lane configurations, calculating a configuration score for the lane configuration based on a vehicle trajectory covered by each window included in the lane configuration, and selecting the lane configuration with the highest configuration score as a basis for lane derivation; and (3) deriving a lane based on the selected lane configuration.

Description

Technical Field

[0001] The present invention relates to lane derivation, and more particularly, to a method and system for deriving lane distribution based on vehicle trajectories. Background Art

[0002] With the development of vehicle navigation technology, when a vehicle is on a road without clear lane markings or even without lane markings, an in-vehicle system or a navigation system can infer lanes based on the driving trajectories of other vehicles. For example, after fitting the trajectories of most vehicles to generate a reference curve, the in-vehicle system or the navigation system can obtain the road shape. However, how the lanes on this road are distributed still needs to be calculated and derived. Generally speaking, calculating and deriving lane distribution is called "lane finding".

[0003] On a road with unclear lane markings, it is extremely important to guide a vehicle to drive in the correct lane to avoid collisions between vehicles moving in the same direction and / or in opposite directions. Therefore, a solution for improving the accuracy of lane finding is needed. Summary of the Invention

[0004] The following Summary of the Invention is provided to introduce a few concepts in a simplified form that will be further described in the Detailed Description below. The Summary of the Invention is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to help determine the scope of the claimed subject matter.

[0005] According to an embodiment of the present invention, there is provided a method for deriving lane distribution based on vehicle trajectories, including: (1) for a set of vehicle trajectories, applying a window to each of the set of vehicle trajectories in a left-to-right traversal order at least partially based on the size of the window to form a plurality of lane configurations; (2) for each of the formed plurality of lane configurations, calculating a configuration score for the lane configuration based on the vehicle trajectories covered by each window included in the lane configuration, and selecting the lane configuration with the highest configuration score as the basis for lane derivation; and (3) deriving lanes based on the selected lane configuration.

[0006] According to another embodiment of the present invention, there is provided a system for deriving lane distribution based on vehicle trajectories, including a lane configuration selection module and a lane derivation module, wherein the lane configuration selection module is configured to: (1) for a set of vehicle trajectories, apply a window to each of the set of vehicle trajectories in a traversal order from right to left at least partially based on the size of the window to form a plurality of lane configurations; (2) for each of the formed plurality of lane configurations, calculate a configuration score for the lane configuration based on the vehicle trajectories covered by each window included in the lane configuration, and select the lane configuration with the highest configuration score as the basis for lane derivation; wherein, the lane derivation module is configured to derive lanes based on the selected lane configuration.

[0007] These and other features and advantages will become apparent by reading the following detailed description and referring to the associated drawings. It should be understood that the foregoing general description and the following detailed description are illustrative only and do not limit the aspects claimed. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to understand in detail the manner in which the above-described features of the present invention are used, the above briefly summarized content may be described in more detail with reference to the various embodiments, some aspects of which are shown in the drawings. However, it should be noted that the drawings only show some typical aspects of the present invention and should not be considered as limiting its scope, since the description may allow other equally effective aspects.

[0009] Figure 1 FIG. 1 shows a block diagram of a system 100 for deriving lane distribution based on vehicle trajectories according to an embodiment of the present invention;

[0010] Figure 2 FIG. 2 shows a diagram 200 of a traversal process for lane configuration selection according to an embodiment of the present invention;

[0011] Figure 3 FIG. 3 shows a flowchart of a method 300 for deriving lane distribution based on vehicle trajectories according to an embodiment of the present invention; and

[0012] Figure 4 FIG. 4 shows a block diagram of an exemplary computing device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0013] The present invention will be described in detail below with reference to the accompanying drawings, and the features of the present invention will be further revealed in the following detailed description.

[0014] The following detailed description refers to the accompanying drawings that illustrate exemplary embodiments of the present invention. However, the scope of the present invention is not limited to these embodiments, but is defined by the appended claims. Therefore, embodiments outside those shown in the drawings, such as modified versions of the illustrated embodiments, are still encompassed by the present invention.

[0015] References in this specification to "an embodiment", "embodiment", "exemplary embodiment", etc., mean that the embodiment may include a particular feature, structure, or characteristic, but every embodiment may not necessarily include the particular feature, structure, or characteristic. Moreover, these phrases do not necessarily refer to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with an embodiment, it is to be understood that it is within the knowledge of those skilled in the relevant art to implement the particular feature, structure, or characteristic in connection with other embodiments, whether or not explicitly described.

[0016] For ease of explanation, only the embodiments of applying the technical solution of the present invention to "lanes" are described in detail herein. However, those skilled in the art can fully understand that the technical solution of the present invention can be applied to fields such as waterways. Unless otherwise specified, the term "A or B" used in this specification refers to "A and B" and "A or B", rather than A and B being exclusive.

[0017] Generally speaking, "lane finding" involves the following processes: 1. Calculate all vehicle trajectories that are similar to the road shape. 2. Sort these vehicle trajectories according to the lateral offset, that is, the rightmost vehicle trajectory is the first trajectory candidate. 3. Find the best road configuration. In the third step, traverse all the vehicle trajectory candidates, from the rightmost vehicle trajectory to the leftmost vehicle trajectory, and assume in turn that some vehicle trajectories represent different lanes, and see how meaningful the assumption is based on the normal lane width and the quality of each vehicle trajectory (for example, the higher the standard deviation, the lower the quality). In this process, some vehicle trajectories may not be able to participate in the lane fusion, resulting in inaccuracies in lane finding.

[0018] Ideally, all vehicle trajectories (matching the road shape) should contribute to a certain lane. Otherwise, lane deviation cannot well reflect the object trajectory, resulting in inaccurate lane deviation and lane deviation jumps, or lanes being too close. In the lane configuration selection stage of the present invention (i.e., determining how many lanes, which vehicle trajectories serve as the baseline for a certain lane, etc.), a traversal method based on a "window" is used, that is, not only the vehicle trajectories on the left side are calculated, but also the vehicle trajectories on the right side are calculated; in the lane derivation stage, when determining which vehicle trajectories contribute to which lane, in addition to the vehicle trajectories in a small range on both the left and right sides (for example, the size of the window), for vehicle trajectories beyond this range, the offset differences are also compared, and the closer vehicle trajectory is selected, so that some vehicle trajectories are not wasted, and all vehicle trajectories can be taken into account, thereby improving the accuracy of lane finding.

[0019] Figure 1 FIG. shows a block diagram of a system 100 for deriving lane distribution according to vehicle trajectories according to an embodiment of the present invention. According to an embodiment of the present invention, the system 100 can be integrated into an existing navigation system or application (for example, a navigation application downloadable to a mobile device, an in-vehicle navigation system, etc.) to provide a lane finding function. According to another embodiment of the present invention, the system 100 can operate separately from an existing navigation system or application (for example, be implemented on a remote device, a cloud service, etc.) to independently provide a lane finding function or work in cooperation with an existing navigation system to provide a lane finding function.

[0020] As Figure 1 shown, the system 100 may include a lane configuration selection module 101 and a lane derivation module 102. Those skilled in the art can fully understand that the present invention is only for the purpose of clarity. The functions of one or more of the above modules can be combined into a single module or split into multiple modules. And, one or more of the above modules can be implemented in software, hardware, or a combination thereof. And, the data transfer method between the modules can be in a manner known in the art, which is not within the scope of discussion of the present invention.

[0021] According to an embodiment of the present invention, the lane configuration selection module 101 can be configured to apply a window to each of a set of vehicle trajectories in a traversal order from right to left at least partially based on the size of the window to form a plurality of lane configurations; for each of the formed plurality of lane configurations, calculate a configuration score for the lane configuration based on the vehicle trajectories covered by each window included in the lane configuration, and select the lane configuration with the highest configuration score as the basis for lane derivation.

[0022] According to an embodiment of the present invention, a set of vehicle trajectories can be formed as follows: Select vehicle trajectories that match the road shape and are frequently traversed by vehicles within a predetermined time period (e.g., within 1 week, within 1 day, within 1 hour, etc.), and sort these vehicle trajectories horizontally from right to left to form a set of vehicle trajectories.

[0023] According to an embodiment of the present invention, a lane configuration can indicate the window distribution for a set of vehicle trajectories and the configuration score of the lane configuration. Specifically, for example, the lane configuration can include information indicating: the central vehicle trajectory of each window, the vehicle trajectories covered by each window, the number of applied windows, the configuration score of the lane configuration, etc. Among them, the central vehicle trajectory of the window refers to the vehicle trajectory that the window covers to the left and right with this as the center.

[0024] Specifically, the lane configuration selection module 101 can be further configured to traverse each vehicle trajectory in the order from right to left starting from the rightmost vehicle trajectory in a set of vehicle trajectories, use the currently traversed vehicle trajectory as the center to apply the first window (i.e., the rightmost window applied to the set of vehicle trajectories), and generate the configuration score of the lane configuration corresponding to using the currently traversed vehicle trajectory as the center of the first window according to the following steps: (1) Apply the first window to the currently traversed vehicle trajectory to use the currently traversed vehicle trajectory as the first central vehicle trajectory of the first window; (2) Select, according to the predetermined size of the window, the vehicle trajectory that is greater than the predetermined size and the nearest to the first central vehicle trajectory to the left as the second central vehicle trajectory of the second window, and apply the second window to form a first sub-lane configuration including the first window and the second window; (3) If there is a vehicle trajectory to the left of the second central vehicle trajectory, move the second window continuously to the vehicle trajectory to the left of the second central vehicle trajectory to use the nearest vehicle trajectory to the left of the second central vehicle trajectory as the second central vehicle trajectory of the second window, thereby forming a second sub-lane configuration including the first window and the second window; (4) Repeat step (3) until the second window can no longer move to the left, finally forming one or more second sub-lane configurations each including the first window and the second window; (5) Calculate the sub-configuration score for the sub-lane configuration based on the number and / or quality of the vehicle trajectories covered within each window included in the first sub-lane configuration and / or each of the one or more second sub-lane configurations, thereby obtaining one or more sub-configuration scores corresponding to the first sub-lane configuration and / or the one or more second sub-lane configurations; (6) Select the highest sub-configuration score among the one or more sub-configuration scores as the configuration score of the lane configuration with the currently traversed vehicle trajectory as the center of the first window.

[0025] In the above manner, for a set of vehicle trajectories, the configuration scores of lane configurations corresponding to each vehicle trajectory in the set of vehicle trajectories as the center of the first window can be obtained.

[0026] Further, the lane configuration selection module 101 can be configured to: select the highest configuration score from the corresponding configuration scores of multiple lane configurations, and use the lane configuration corresponding to the highest configuration score as the basis for lane derivation.

[0027] Figure 2 Fig. 200 shows a traversal process diagram of lane configuration selection according to an embodiment of the present invention. In Fig. 200, 6 vehicle trajectories numbered 0 - 5 are shown, so 6 traversals can be performed. The first traversal is marked as A, the second traversal is marked as B, the third traversal is marked as C, the fourth traversal is marked as D, the fifth traversal is marked as E, and the sixth traversal is marked as F. Among them, in Fig. 200, according to the general width of the lane, the size of the window is defined as 2 meters. In practice, different window sizes can be adopted with reference to specific requirements.

[0028] See Figure 2-1 , which shows the 1st traversal. In the 1st traversal, the rightmost vehicle trajectory 0 is used as the center vehicle trajectory of window i (i.e., the first window described above), and the nearest vehicle trajectory 3 that is more than the window size (i.e., 2 meters) away from vehicle trajectory 0 is used as the center vehicle trajectory of the second window (window j). Thus, in this 1st traversal, the first sub - lane configuration may include Figure 2-1 the windows i and j shown, where window i covers vehicle trajectories 0 and 1, and window j covers vehicle trajectories 2, 3, and 4.

[0029] For this first sub - lane configuration, its sub - configuration score can be the score of window i + the score of window j. Among them, in one way, the number of vehicle trajectories covered in the window can be used as the calculation standard to calculate the score of each window. For example, the score of window i can be 2, and the score of window j can be 3, that is, the sub - configuration score of the first sub - lane configuration is 5.

[0030] In another way, the average score of the quality scores of the vehicle trajectories covered by the window can be calculated based on the quality of the vehicle trajectories (such as the clarity, length, integrity, etc. of the vehicle trajectory), and thus used as the score of this window. For example, for window i, the score of window i can be obtained by (the quality score of vehicle trajectory 0 + the quality score of vehicle trajectory 1) / 2.

[0031] Those skilled in the art can fully understand that the calculation method of the above scores can vary according to actual needs. In this example, the score calculation is first carried out according to the number of vehicle trajectories covered by the window.

[0032] After that, the second window, window j, is moved to the left to take the vehicle trajectory 4 on the left of vehicle trajectory 3 as the central vehicle trajectory of the second window (window j), thereby obtaining the second sub-lane configuration for the first traversal. Although Figure 2-1 not shown in [reference], it can be understood that in the second sub-lane configuration, window i covers vehicle trajectory 0 and vehicle trajectory 1, and window j covers vehicle trajectory 3, vehicle trajectory 4, and vehicle trajectory 5 (assuming the distance between vehicle trajectory 3 and vehicle trajectory 4 is less than 1 meter, and the distance between vehicle trajectory 4 and vehicle trajectory 5 is less than 1 meter). As described above, the score for this second sub-lane configuration can be the score of window i (i.e., 2) + the score of window j (i.e., 3) = 5.

[0033] After that, the second window is continuously moved to the left to take vehicle trajectory 5 as the center of the second window (window j), thereby obtaining the third sub-lane configuration for the first traversal. Although Figure 2-1 not shown in [reference], it can be understood that in the third sub-lane configuration, window i still covers vehicle trajectory 0 and vehicle trajectory 1, and window j covers vehicle trajectory 4 and vehicle trajectory 5. As described above, the score for this third sub-lane configuration can be the score of window i (i.e., 2) + the score of window j (i.e., 2) = 4.

[0034] In the first traversal, it can be obtained that the configuration scores of the first sub-lane configuration and the second sub-lane configuration are the same, both being 5. In this case, in one example, the first sub-lane configuration and the second sub-lane configuration can be further compared according to the quality scores of the vehicle trajectories as described above to obtain the sub-lane configuration with the highest score as the configuration score for the first traversal. According to another example, the 5 points of the first sub-lane configuration and the second sub-lane configuration can be used as the configuration score for the first traversal to be further compared with the configuration scores obtained from other traversals.

[0035] Refer to Figure 2-2 , which shows the second traversal. In the second traversal, starting from vehicle trajectory 0 and moving to the left, vehicle trajectory 1 is taken as the central vehicle trajectory of window i (i.e., the first window described above), and the nearest vehicle trajectory 4 that is more than the window size (i.e., 2 meters) away from vehicle trajectory 1 is taken as the central vehicle trajectory of the second window (window j). Thus, in this second traversal, the first sub-lane configuration can include as Figure 2-2The shown window i and window j, where window i covers vehicle trajectories 0, vehicle trajectory 1, and vehicle trajectory 2, and window j covers vehicle trajectories 3, vehicle trajectory 4, and vehicle trajectory 5. According to the calculation method based on the number of vehicle trajectories within the window described above, the sub - configuration score of this first sub - lane configuration is the score of window i (i.e., 3) + the score of window j (i.e., 3), which is 6.

[0036] After that, move the second window to the left so that vehicle trajectory 5 to the left of vehicle trajectory 4 becomes the central vehicle trajectory of the second window (window j), thus obtaining the second sub - lane configuration for this second traversal. Although Figure 2-2 not shown in [], it can be understood that in the second sub - lane configuration, window i covers vehicle trajectories 0, vehicle trajectory 1, and vehicle trajectory 2, and window j covers vehicle trajectories 4 and vehicle trajectory 5. As described above, the score for this second sub - lane configuration can be the score of window i (i.e., 3) + the score of window j (i.e., 2) = 5.

[0037] Therefore, the configuration score for the second traversal is the configuration score of the first sub - lane configuration (i.e., 6).

[0038] And so on. For example, Figure 2-3 shows the third traversal, where it moves left from vehicle trajectory 1, with vehicle trajectory 2 as the central vehicle trajectory of window i (i.e., the first window described above). Figure 2-4 shows the fourth traversal, moving left from vehicle trajectory 2, with vehicle trajectory 3 as the central vehicle trajectory of window i (i.e., the first window described above). Figure 2 -5 shows the fifth traversal, moving left from vehicle trajectory 3, with vehicle trajectory 4 as the central vehicle trajectory of window i (i.e., the first window described above). Figure 2 -6 shows the sixth traversal, moving left from vehicle trajectory 4, with vehicle trajectory 5 as the central vehicle trajectory of window i (i.e., the first window described above).

[0039] Among them, from Figure 2-3 to Figure 2 -6, it can be seen that there is only one window in the third traversal to the sixth traversal because there are no vehicle trajectories that are more than the window's predetermined size (i.e., 2 meters) away from the first central vehicle trajectory of window i. Therefore, there is only one sub - lane configuration in the third traversal to the sixth traversal, and the score of this sub - lane configuration is the score of window i. For example, the scores of the lane configurations in the third traversal to the fifth traversal are all 3, and the score of the lane configuration in the sixth traversal is 2.

[0040] After 6 traversals, it can be seen that the configuration score 6 of the first sub-lane configuration in the second traversal is the highest score. Then, this first sub-lane configuration (i.e., window i covers vehicle trajectory 0, vehicle trajectory 1, and vehicle trajectory 2, and window j covers vehicle trajectory 3, vehicle trajectory 4, and vehicle trajectory 5) is selected as the basis for subsequent lane derivation.

[0041] According to an embodiment of the present invention, the lane derivation module 102 may be configured to derive lanes based on the lane configurations selected by the lane configuration selection module 101.

[0042] According to an embodiment of the present invention, for each window in the lane configuration, the lane derivation module 102 may fuse the lanes covered by the window to form the lane represented by the window. For example, for the above-selected lane configuration, the lane derivation module 102 may fuse vehicle trajectory 0, vehicle trajectory 1, and vehicle trajectory 2 in window i to form the lane represented by window i, and fuse vehicle trajectory 3, vehicle trajectory 4, and vehicle trajectory 5 in window j to form the lane represented by window j. Thus, two lanes are finally formed.

[0043] According to an embodiment of the present invention, the vehicle generation module 102 may also incorporate vehicle trajectories outside the window into the fusion to utilize as many vehicle trajectories as possible to form a more accurate lane. For example, assume Figure 2-1 the first sub-lane configuration (where window i covers vehicle trajectory 0 and vehicle trajectory 1, and window j covers vehicle trajectory 2, vehicle trajectory 3, and vehicle trajectory 4) is selected. Then, when deriving a lane based on window j, vehicle trajectory 5 outside window j may be fused with vehicle trajectory 2, vehicle trajectory 3, and vehicle trajectory 4 in window j, so as not to waste vehicle trajectories.

[0044] Again, for example, in the case where there are multiple vehicle trajectories outside the window that are not covered by other windows, the vehicle trajectory closest to the window may be selected to be fused with the vehicle trajectories in the window. For example, referring to Figure 2-4 , vehicle trajectory 5 may be fused with vehicle trajectory 2, vehicle trajectory 3, and vehicle trajectory 4 within window i to form a lane.

[0045] Figure 3 FIG. 300 shows a flowchart of a method 300 for deriving a lane distribution according to vehicle trajectories according to an embodiment of the present invention.

[0046] At 305, for a set of vehicle trajectories, windows are sequentially applied to each of the vehicle trajectories in the set in a left-to-right traversal order at least partially based on the size of the window to form multiple lane configurations.

[0047] According to an embodiment of the present invention, step 305 further includes: (1) applying a first window to the currently traversed vehicle trajectory to use the currently traversed vehicle trajectory as the first central vehicle trajectory of the first window; (2) selecting, based on the predetermined size of the window, the vehicle trajectory that is greater than the predetermined size and the nearest to the first central vehicle trajectory to the left as the second central vehicle trajectory of the second window, and applying the second window, thereby forming a first sub-lane configuration including the first window and the second window; (3) if there is a vehicle trajectory to the left of the second central vehicle trajectory, moving the second window continuously to the vehicle trajectory to the left of the second central vehicle trajectory to use the nearest vehicle trajectory to the left of the second central vehicle trajectory as the second central vehicle trajectory of the second window, thereby forming a second sub-lane configuration including the first window and the second window; (4) repeating step (3) until the second window can no longer move to the left, finally forming one or more second sub-lane configurations including the first window and the second window.

[0048] At 310, for each of the formed multiple lane configurations, based on the vehicle trajectories covered by each window included in the lane configuration, calculate a configuration score for the lane configuration, and select the lane configuration with the highest configuration score as the basis for lane derivation.

[0049] According to an embodiment of the present invention, step 310 further includes: (5) calculating a sub-configuration score for the sub-lane configuration based on the number and / or quality of the vehicle trajectories covered within each window included in the first sub-lane configuration and / or each of the one or more second sub-lane configurations, thereby obtaining one or more sub-configuration scores corresponding to the first sub-lane configuration and / or the one or more second sub-lane configurations; (6) selecting the highest sub-configuration score among the one or more sub-configuration scores as the configuration score for the lane configuration with the currently traversed vehicle trajectory as the center of the first window.

[0050] At 315, derive lanes based on the selected lane configuration.

[0051] According to an embodiment of the present invention, step 315 further includes: for each window in the selected lane configuration, fusing the lanes covered by the window to form the lane represented by the window.

[0052] According to another embodiment of the present invention, step 315 further includes: for each window in the selected lane configuration, fusing the lanes covered by the window and the lanes near the window to form the lane represented by the window.

[0053] Figure 4A block diagram of an exemplary computing device according to an embodiment of the present invention is shown, and the computing device is an example of a hardware device applicable to various aspects of the present invention.

[0054] Referring Figure 4 , a computing device 400 will now be described. The computing device 400 is an example of a hardware device applicable to various aspects of the present invention. The computing device 400 can be any machine configured to perform processing and / or computing, and can be, but is not limited to, a workstation, a server, a desktop computer, a laptop computer, a tablet computer, a personal digital assistant, a smartphone, an in-vehicle computer, or any combination thereof. The foregoing various methods / devices / servers / client devices can be implemented in whole or at least in part by the computing device 400 or a similar device or system.

[0055] The computing device 400 may include components that can be connected or communicate via one or more interfaces and a bus 402. For example, the computing device 400 may include a bus 402, one or more processors 404, one or more input devices 406, and one or more output devices 408. The one or more processors 404 can be any type of processor and may include, but are not limited to, one or more general-purpose processors and / or one or more dedicated processors (e.g., specialized processing chips). The input device 406 can be any type of device capable of inputting information into the computing device and may include, but are not limited to, a mouse, a keyboard, a touch screen, a microphone, and / or a remote controller. The output device 408 can be any type of device capable of presenting information and may include, but are not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The computing device 400 may also include a non-transitory storage device 410 or be connected to the non-transitory storage device. The non-transitory storage device can be any storage device that is non-transitory and capable of implementing data storage, and the non-transitory storage device may include, but are not limited to, a disk drive, an optical storage device, a solid-state memory, a floppy disk, a flexible disk, a hard disk, a magnetic tape, or any other magnetic medium, an optical disk, or any other optical medium, a ROM (read-only memory), a RAM (random access memory), a cache memory, and / or any storage chip or cartridge, and / or any other medium from which a computer can read data, instructions, and / or code. The non-transitory storage device 410 can be separated from the interface. The non-transitory storage device 410 may have data / instructions / code for implementing the above methods and steps. The computing device 400 may also include a communication device 412. The communication device 412 can be any type of device or system capable of enabling communication with internal devices and / or communication with a network and may include, but are not limited to, a modem, a network card, an infrared communication device, a wireless communication device, and / or a chipset, such as a Bluetooth device, an IEEE 1302.11 device, a WiFi device, a WiMax device, a cellular communication device, and / or similar devices.

[0056] When the computing device 400 is used as an in-vehicle device, it can also be connected to external devices (e.g., a GPS receiver, sensors for sensing different environmental data (such as an acceleration sensor, a wheel speed sensor, a gyroscope, etc.)). In this way, for example, the computing device 400 can receive positioning data and sensor data indicating the vehicle condition. When the computing device 400 is used as an in-vehicle device, it can also be connected to other devices for controlling the driving and operation of the vehicle (e.g., an engine system, a windshield wiper, an anti-lock braking system, an electronic control unit, etc.).

[0057] In addition, the non-transitory storage device 410 may have map information and software components, so that the processor 404 can implement route guidance processing. In addition, the output device 408 may include a display for displaying a map, a positioning marker of the vehicle, and an image indicating the driving status of the vehicle. The output device 408 may also include a speaker or a headphone jack for audio guidance.

[0058] The bus 402 may include, but is not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MCA) bus, an Enhanced ISA (EISA) bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus. In particular, for in-vehicle devices, the bus 402 may also include a Controller Area Network (CAN) bus or other architectures designed for automotive applications.

[0059] The computing device 400 may also include a working memory 414, which can be any type of working memory capable of storing instructions and / or data beneficial to the operation of the processor 404 and may include, but is not limited to, random access memory and / or read-only storage devices.

[0060] The software components may be located in the working memory 414, and these software components include, but are not limited to, an operating system 416, one or more application programs 418, drivers, and / or other data and code. The instructions for implementing the above methods and steps may be included in the one or more application programs 418, and the modules / units / components of the foregoing various devices / servers / client devices may be implemented by the processor 404 reading and executing the instructions of the one or more application programs 418.

[0061] It should also be recognized that changes can be made according to specific requirements. For example, custom hardware may also be used, and / or specific components may be implemented in hardware, software, firmware, middleware, microcode, hardware description language, or any combination thereof. In addition, connections with other computing devices, such as network input / output devices, etc., may be adopted. For example, part or all of the disclosed methods and devices may be implemented by programming hardware (such as programmable logic circuits including Field Programmable Gate Arrays (FPGAs) and / or Programmable Logic Arrays (PLAs)) with assembly language or a hardware programming language (such as VERILOG, VHDL, C++) using the logic and algorithms according to the present invention.

[0062] Although aspects of the present invention have been described so far with reference to the accompanying drawings, the above methods, systems, and devices are merely examples, and the scope of the present invention is not limited to these aspects, but is defined only by the appended claims and their equivalents. Various components may be omitted or may also be replaced by equivalent components. Additionally, the steps may be implemented in an order different from the order described in the present invention. Furthermore, the various components may be combined in various ways. It is also important that, as technology develops, many of the components described may be replaced by equivalent components that emerge later.

Claims

1. A method for deriving lane distribution based on vehicle trajectories, comprising: (1) For a set of vehicle trajectories, applying a window to each of the set of vehicle trajectories in a traversal order from right to left at least partially based on the size of the window to form a plurality of lane configurations; (2) For each of the formed plurality of lane configurations, calculating a configuration score for the lane configuration based on the vehicle trajectories covered by each window included in the lane configuration, and selecting the lane configuration with the highest configuration score as the basis for lane derivation; And (3) Deriving lanes based on the selected lane configuration.

2. The method according to claim 1, wherein The set of vehicle trajectories is formed as follows: Selecting vehicle trajectories that match the road shape and are frequently traversed by vehicles within a predetermined time, and sorting the vehicle trajectories horizontally from right to left to form the set of vehicle trajectories.

3. The method according to claim 1, characterized in that, Step (1) further includes: (a) Applying a first window to the currently traversed vehicle trajectory to use the currently traversed vehicle trajectory as the first central vehicle trajectory of the first window, (b) Selecting, to the left according to the predetermined size of the window, the vehicle trajectory that is greater than the predetermined size and closest to the first central vehicle trajectory as the second central vehicle trajectory of the second window, and applying the second window, thereby forming a first sub-lane configuration including the first window and the second window; (c) If there is a vehicle trajectory to the left of the second central vehicle trajectory, moving the second window further to the vehicle trajectory to the left of the second central vehicle trajectory to use the closest vehicle trajectory to the left of the second central vehicle trajectory as the central vehicle trajectory of the second window, thereby forming a second sub-lane configuration including the first window and the second window; (d) Repeating step (c) until the second window can no longer move to the left, finally forming one or more second sub-lane configurations each including the first window and the second window.

4. The method according to claim 3, characterized in that Step (2) further includes: (e) Calculating a sub-configuration score for the sub-lane configuration based on the number and / or quality of the vehicle trajectories covered within each window included in the first sub-lane configuration and / or each of the one or more second sub-lane configurations, thereby obtaining one or more sub-configuration scores corresponding to the first sub-lane configuration and / or the one or more second sub-lane configurations; (f) Selecting the highest sub-configuration score among the one or more sub-configuration scores as the configuration score for the lane configuration with the currently traversed vehicle trajectory as the central vehicle trajectory of the first window.

5. The method according to claim 1, characterized in that Step (3) further includes: For each window in the selected lane configuration, fusing the lanes covered by the window to form the lane represented by the window.

6. The method according to claim 1, characterized in that Step (3) further includes: For each window in the selected lane configuration, fusing the lanes covered by the window and the lanes near the window to form the lane represented by the window.

7. A system for deriving lane distribution based on vehicle trajectories, comprising: Lane configuration selection module, which is configured to: (1) For a set of vehicle trajectories, apply a window to each of the set of vehicle trajectories in a left-to-right traversal order at least partially based on the size of the window to form multiple lane configurations; (2) For each of the formed multiple lane configurations, calculate a configuration score for the lane configuration based on the vehicle trajectories covered by each window included in the lane configuration, and select the lane configuration with the highest configuration score as the basis for lane derivation; And Lane derivation module, which is configured to: Derive lanes based on the selected lane configuration.

8. The system according to claim 7, wherein: The lane configuration selection module is further configured to: (a) Apply a first window to the currently traversed vehicle trajectory to use the currently traversed vehicle trajectory as the first central vehicle trajectory of the first window, (b) select, according to the predetermined size of the window, the vehicle trajectory that is greater than the predetermined size and the nearest to the first central vehicle trajectory to the left as the second central vehicle trajectory of the second window, and apply the second window, thereby forming a first sub-lane configuration including the first window and the second window; (c) if there is a vehicle trajectory to the left of the second central vehicle trajectory, move the second window continuously to the vehicle trajectory to the left of the second central vehicle trajectory to use the nearest vehicle trajectory to the left of the second central vehicle trajectory as the central vehicle trajectory of the second window, thereby forming a second sub-lane configuration including the first window and the second window; (d) repeat step (c) until the second window can no longer move to the left, and finally form one or more second sub-lane configurations each including the first window and the second window.

9. The system according to claim 8, wherein The lane configuration selection module is further configured to: (e) Calculate a sub-configuration score for the sub-lane configuration based on the number and / or quality of the vehicle trajectories covered within each window included in the first sub-lane configuration and / or each of the one or more second sub-lane configurations, thereby obtaining one or more sub-configuration scores corresponding to the first sub-lane configuration and / or the one or more second sub-lane configurations; (f) select the highest sub-configuration score among the one or more sub-configuration scores as the configuration score for the lane configuration with the currently traversed vehicle trajectory as the central vehicle trajectory of the first window.

10. The system according to claim 7, wherein The lane derivation module is further configured to: For each window in the selected lane configuration, fuse the lanes covered by the window to form the lane represented by the window; or For each window in the selected lane configuration, fuse the lanes covered by the window and the lanes near the window to form the lane represented by the window.

Images