Display method of vehicle perception result on perception reality interface, vehicle perception system and storage medium

Abstract

A method for stably displaying a vehicle perception result in a perception reality interface, a vehicle perception system and a storage medium, comprising: obtaining position information of a rear target object based on vehicle perception data, and obtaining current position data of the target object; taking a vehicle coordinate system as a reference coordinate system, performing coordinate system conversion on the rendering target, and performing image rendering according to the current position data of the rendering target object; determining whether the rendering target object is a pre-warning target object according to the coordinates of the rendering target object; and using a fixed position of the display image to display a warning, wherein the display image is configured to display a yellow warning icon at the fixed position of the display image when the pre-warning target object appears, the yellow warning icon is displayed in a flashing manner when the current longitudinal coordinate of the pre-warning target object gradually decreases, and the flashing frequency of the yellow warning icon is increased when the change rate of the current longitudinal coordinate of the pre-warning target object increases.

Description

Technical Field

[0001] This invention relates to the technical field of display methods for vehicle perception reality interfaces, specifically to a method for displaying vehicle perception results on a perception reality interface, a vehicle perception system, and a storage medium. Background Technology

[0002] Currently, the level of intelligent driving in vehicles is gradually improving, and L2 and higher levels of assisted driving functions are gradually being made available to users. However, intelligent driving functions cannot perfectly replicate the real world and cannot cover some high-risk driving scenarios. In such scenarios, users need to monitor the intelligent driving system in real time and take over in dangerous situations. Furthermore, the instability of intelligent driving perception data and the inconsistency between the visualized interface and the real world are increasing users' "trust anxiety" regarding intelligent driving information in navigation systems.

[0003] There are currently two main approaches to vehicle perception reconstruction interfaces: The first approach uses perceived data as the input source to reconstruct the road elements and near-field targets that can be perceived, and displays the relative positional relationship between other targets and the vehicle in real time. However, in scenarios with navigation, it is impossible to display the road that the vehicle should be traveling on in the perception interface, resulting in limited information display capabilities. Furthermore, the large amount of vehicle perception content and the lack of processing of the positional relationship between the vehicle and the road lead to a cluttered overall interface, making it inefficient for users to obtain key information in driving scenarios. The second method is based on high-precision maps. By transmitting vehicle perception signals to a map engine, the map engine matches the perceived vehicle targets with the lanes. Finally, the near-field perceived targets and corresponding intelligent driving status of the vehicle are displayed in the lanes within the high-precision map boundary. At the same time, navigation guidance information can also be displayed. This method relies on high-precision maps and is costly. The map rendering engine anchors the vehicle's lane position based on high-precision positioning data, and then matches other targets into the lanes on the map based on the relative positional relationship between the vehicle and other targets. This method is overly dependent on high-precision positioning. In scenarios with a large number of buildings obstructing the view or in tunnels, when there are errors in high-precision positioning, the rendering relationship between the targets in the lane and the lane position will show a large deviation. Summary of the Invention

[0004] To address at least one aspect of the aforementioned problems, the present invention provides a method for stably displaying vehicle perception results in a perception reality interface, comprising: acquiring the position information of a rear target based on vehicle perception data; determining the rear target as a rendering target when it appears for three consecutive frames; acquiring the current position data of the rendering target; using the vehicle's coordinate system as a reference coordinate system, performing coordinate system transformation on the rendering target, and rendering a display image based on the current position data of the rendering target; taking the vehicle as the origin, the vehicle's length direction as the ordinate, the vehicle's travel direction as the negative ordinate direction, and the vehicle's width direction as the abscissa; determining the rendering target as a warning target when the absolute value of the abscissa of the rendering target is less than a preset width value, and the difference between the current ordinate of the rendering target and the ordinate of the previous frame is less than zero; displaying the warning at a fixed position in the display image, wherein the display image is configured such that when the warning target appears, a yellow warning icon appears at the fixed position in the display image; the yellow warning icon flashes as the current ordinate of the warning target gradually decreases; and the flashing frequency of the yellow warning icon increases as the rate of change of the current ordinate of the warning target increases.

[0005] Preferably, the preset width value includes a first width value and a second width value, the first width value is greater than the second width value, the road level where the vehicle is located is obtained, and when the road level is a highway or a road, the preset width value is equal to the first width value.

[0006] Preferably, the flashing frequency includes a first frequency, a second frequency, and a third frequency. When the rate of change of the current ordinate of the warning target is greater than zero and less than a first threshold, the flashing frequency of the yellow warning icon is equal to the first frequency. When the rate of change of the current ordinate of the warning target is greater than the first threshold and less than a second threshold, the flashing frequency of the yellow warning icon is equal to the second frequency. When the rate of change of the current ordinate of the warning target is greater than the second threshold, the flashing frequency of the yellow warning icon is equal to the third frequency.

[0007] Preferably, when the rendered target object disappears within the perspective distance of the displayed image, the current ordinate of the rendered target object is set to be greater than the perspective distance.

[0008] Preferably, the method further includes: filtering the frequency of vehicle perception data, queuing and storing the vehicle perception data, obtaining the location information of the target object to be rendered using a fixed frequency of 10Hz, and rendering the display image using a frequency of 10Hz.

[0009] On the other hand, a vehicle perception system is provided, including a processor and a memory, the memory including a computer program, and the processor for running the computer program in the memory to implement the method of stably displaying the vehicle perception results in a perception reality interface as described in any one of claims 1-5.

[0010] On the other hand, a computer-readable storage medium is provided, including a computer program, which is executed by a processor at runtime, to stably display vehicle perception results in a perception reality interface as described above.

[0011] The method for stably displaying vehicle perception results in a perception reality interface according to embodiments of the present invention has the following beneficial effects: It does not rely on high-precision positioning, and can accurately express the matching relationship between perceived targets around the vehicle and the road where it is located. Through location data preprocessing, it can accurately depict surrounding targets in accurate lane positions. The perception signal target filtering algorithm ensures smooth and stable initial display and disappearance of targets on the map. In scenarios where the perception signal has unstable output, the data stabilization filtering scheme can ensure that the targets depicted on the map are continuously and smoothly displayed dynamically. Attached Figure Description

[0012] To better understand the above and other objects, features, advantages, and functions of the present invention, reference can be made to the embodiments shown in the accompanying drawings. The same reference numerals in the drawings refer to the same parts. Those skilled in the art should understand that the drawings are intended to schematically illustrate preferred embodiments of the invention and do not limit the scope of the invention in any way; the parts in the drawings are not drawn to scale.

[0013] Figure 1 A flowchart illustrating a method for stably displaying vehicle perception results in a perception reality interface according to an embodiment of the present invention is shown.

[0014] Figure 2 The illustration shows a method for stably displaying vehicle perception results in a perception reality interface according to an embodiment of the present invention. Detailed Implementation

[0015] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0016] The term "comprising" and its variations as used herein signify open inclusion, i.e., "including but not limited to". Unless otherwise stated, the term "or" means "and / or". The term "based on" means "at least partially based on". The terms "one example embodiment" and "one embodiment" mean "at least one example embodiment". The term "another embodiment" means "at least one additional embodiment". The terms "first", "second", etc., may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0017] In order to at least partially solve one or more of the above problems and other potential problems, embodiments of this disclosure propose a method for stably displaying vehicle perception results in a perception reality interface, including: step S1, obtaining the position information of a rear target object based on vehicle perception data, and when the rear target object appears for three consecutive frames, determining the rear target object as a rendering target object, and obtaining the current position data of the rendering target object.

[0018] Specifically, the Reality Perception Interface (SR) is rendered by processing and summarizing information about the vehicle's surroundings obtained by sensors such as cameras and LiDAR. Simply put, it is the processing of perception data collected by onboard sensors into display images for the user to see.

[0019] The location information of targets behind the vehicle is extracted based on vehicle perception data. For example, the target behind the vehicle is identified and marked by the license plate information contained in the image of the vehicle perception data. The location information of the identified target behind the vehicle is stored and analyzed. If the same target behind the vehicle is found in three consecutive frames of vehicle sensing data, then the target behind the vehicle is confirmed as a stable target.

[0020] The target object stabilization filtering algorithm determines that a target object is considered stable after three consecutive frames of stable data output, and the rendering is performed based on the last position data of the target object.

[0021] Step S2: Using the vehicle's coordinate system as a reference coordinate system, perform coordinate system transformation on the rendering target, and render the display image based on the current position data of the rendering target.

[0022] Specifically, such as Figure 2 As shown, the displayed image is an SR interface image output by the vehicle perception system based on vehicle perception data. The coordinate system of the rendered target object and the vehicle is unified by determining the relative positions of the rendered target object and the vehicle itself in the vehicle perception data. In some real-time examples, the boundary of the displayed image is determined based on the effective perception range of the vehicle perception data, and the rendered target objects within the perception range are displayed through the rendered image. For example, the displayed image uses the vehicle as a point on the center line of the bottom edge, and the position information of the rendered target objects is rendered in the displayed image according to a proportional scaling. Alternatively, in other embodiments, the vehicle is the midpoint of the displayed image, and the rendered target objects determine their rendering positions relative to the vehicle in the displayed image based on their respective position information.

[0023] In step S3, taking the host vehicle as the origin, the length direction of the host vehicle as the ordinate, the traveling direction of the host vehicle as the negative ordinate direction, and the width direction of the host vehicle as the abscissa, when the absolute value of the abscissa of the rendering target is less than the preset width value, and the difference between the current ordinate of the rendering target and the ordinate of the previous frame is less than zero, the rendering target is determined to be a warning target.

[0024] Specifically, the method for displaying an unfixed target at a lateral rear position includes: firstly acquiring vehicle perception data, and identifying a target according to the vehicle perception data; secondly, when a rear target signal is identified, analyzing the position of the rear target.

[0025] Taking the center point of the rear of the host vehicle as the origin coordinate (0,0), when the lateral position of the rear target satisfies -X1<X<0, it is determined as a left rear target; when the lateral position of the rear target satisfies X1>X>0, the target is determined to be a right rear target. For the longitudinal distance, the change trend of the longitudinal distance is judged. If the longitudinal distance keeps approaching, the ordinate Y value of the target gradually decreases, and Y2-Y1<0, the rendering target belongs to the warning target; if the Y value increases, and Y2-Y1>=0, the rendering target does not belong to the warning target.

[0026] In some embodiments, the preset width value includes a first width value and a second width value, the first width value is greater than the second width value, the road grade where the host vehicle is located is acquired, and when the road grade is an expressway or a first-class road, the preset width value is equal to the first width value.

[0027] Specifically, the preset width value can be set according to actual requirements. For example, the first width value is 5.25m, and the second width value is 5m. When the road grade where the host vehicle is located is an expressway and a first-class road, the preset width value X1 is 5.25m. When the road grade where the host vehicle is located is an ordinary road, the preset width value X1 is 5m. For example, when the lateral position of the rear target satisfies -5<X<0 (the value for expressways and first-class roads is -5.25<X<0), it is determined as a left rear target; when the lateral position of the rear target satisfies 5>X>0 (the value for expressways and first-class roads is 5.25>X>0), the target is determined to be a right rear target. For the longitudinal distance, the change trend of the longitudinal distance is judged. If the longitudinal distance keeps approaching, the Y value gradually decreases, and Y2-Y1<0, the target belongs to the warning target; if the Y value increases, and Y2-Y1>=0, the target does not belong to the warning target.

[0028] In step S4, the warning is displayed at a fixed position of the display image, and the display image is configured such that when a warning target appears, a yellow warning icon appears at the fixed position of the display image, the yellow warning icon blinks when the current ordinate of the warning target gradually decreases, and the blinking frequency of the yellow warning icon increases when the change rate of the current ordinate of the warning target increases.

[0029] Specifically, a warning display is provided for targets to the side and rear: the target is displayed in a fixed position on the map. When the target appears, a yellow warning icon appears on the map. When the longitudinal distance continues to approach, the icon flashes. When the acceleration of the longitudinal distance approach increases (the time when the Y-axis distance is 0, 0~0.3~1~3), the flashing frequency increases, and the flashing level is divided into 3 levels.

[0030] In some embodiments, the flashing frequency includes a first frequency, a second frequency, and a third frequency. When the rate of change of the current ordinate of the warning target is greater than zero and less than a first threshold, the flashing frequency of the yellow warning icon is equal to the first frequency. When the rate of change of the current ordinate of the warning target is greater than the first threshold and less than a second threshold, the flashing frequency of the yellow warning icon is equal to the second frequency. When the rate of change of the current ordinate of the warning target is greater than the second threshold, the flashing frequency of the yellow warning icon is equal to the third frequency.

[0031] In some embodiments, when a rendered target object disappears within the perspective distance of the displayed image, the current ordinate of the rendered target object is set to be greater than the perspective distance.

[0032] Specifically, when a rendered target object disappears, a sudden disappearance will cause the image to jump. If the rendered target object in the perception data disappears within the perspective distance (perspective distance = L) of the displayed image, then the vertical coordinate Y of the rendered target object is set to Y>L, and the interrupted target object can disappear smoothly.

[0033] In some embodiments, the method further includes: filtering the frequency of vehicle perception data, queuing and storing the vehicle perception data, acquiring the location information of the target object to be rendered using a fixed frequency of 10Hz, and rendering the display image using a frequency of 10Hz.

[0034] Specifically, when the frequency of the sensing data output is unstable, the SR filters the unstable data frequency, renders the image at a frequency of 10Hz, stores the sensing data in a queue in advance, and the SR retrieves the latest position information of the sensing target at a fixed frequency of 10Hz.

[0035] On the other hand, a vehicle perception system is provided, including a processor and a memory, the memory including a computer program, and the processor for running the computer program in the memory to implement a method for stably displaying vehicle perception results in a perception reality interface as described above.

[0036] Specifically, the processor can be a central processing unit, or other general-purpose processors, digital signal processors, application-specific integrated circuits, field-programmable gate arrays, etc. General-purpose processors can be microprocessors, etc.

[0037] Memory can include various storage units, such as read-only memory (ROM) and permanent storage devices. ROM is used to store static data or instructions required by the processor or other modules of the computer. Permanent storage devices can be read-write storage devices or non-volatile storage devices. Alternatively, permanent storage devices may use magnetic or optical discs, flash memory, etc.

[0038] Furthermore, the memory includes any combination of computer-readable storage media, including various types of semiconductor memory chips; magnetic disks and / or optical disks may also be used. The memory may include removable storage devices that are readable and / or writable, such as read-only digital versatile optical discs, read-only Blu-ray discs, ultra-high-density optical discs, flash memory cards, magnetic floppy disks, etc. Computer-readable storage media do not contain carrier waves or transient electronic signals transmitted wirelessly or via wired connections.

[0039] The memory stores computer programs, which, when processed by a processor, can cause the processor to execute some or all of the methods described above.

[0040] Furthermore, the method according to this application can also be implemented as a computer-readable storage medium, including a computer program, which is executed by a processor to stably display the vehicle perception results in a perception reality interface as described above.

[0041] The various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or technical improvements to the embodiments in the market, or to enable others skilled in the art to understand this document.

Claims

1. A method for stably displaying vehicle perception results in a perception reality interface, characterized in that, include: The location information of the target object behind is obtained based on vehicle perception data. When the target object behind appears for three consecutive frames, it is determined that the target object behind is the rendering target object, and the current position data of the rendering target object is obtained. Using the vehicle's coordinate system as a reference coordinate system, the target object is transformed into a different coordinate system, and the image is rendered based on the current position data of the target object. With the vehicle as the origin, the length direction of the vehicle as the vertical coordinate, the direction of travel of the vehicle as the negative direction of the vertical coordinate, and the width direction of the vehicle as the horizontal coordinate, when the absolute value of the horizontal coordinate of the rendered target is less than the preset width value, and the difference between the current vertical coordinate of the rendered target and the vertical coordinate of the previous frame is less than zero, the rendered target is judged to be a warning target. The warning is displayed at a fixed position on the image. The image is configured to display a yellow warning icon at the fixed position when the warning target appears. The yellow warning icon flashes as the current ordinate of the warning target gradually decreases. The flashing frequency of the yellow warning icon increases as the rate of change of the current ordinate of the warning target increases.

2. The method according to claim 1, characterized in that, The preset width value includes a first width value and a second width value. The first width value is greater than the second width value. The road level where the vehicle is located is obtained. When the road level is a highway or a road, the preset width value is equal to the first width value.

3. The method according to claim 2, characterized in that, The flashing frequency includes a first frequency, a second frequency, and a third frequency. When the rate of change of the current vertical coordinate of the warning target is greater than zero and less than the first threshold, the flashing frequency of the yellow warning icon is equal to the first frequency. When the rate of change of the current vertical coordinate of the warning target is greater than the first threshold and less than the second threshold, the flashing frequency of the yellow warning icon is equal to the second frequency. When the rate of change of the current vertical coordinate of the warning target is greater than the second threshold, the flashing frequency of the yellow warning icon is equal to the third frequency.

4. The method according to claim 3, characterized in that, If the rendered target object disappears within the perspective distance of the displayed image, then the current ordinate of the rendered target object is set to be greater than the perspective distance.

5. The method according to claim 4, characterized in that, Also includes: The vehicle perception data frequency is filtered, the vehicle perception data is queued and stored, the position information of the rendering target object is obtained at a fixed frequency of 10Hz, and the display image is rendered at a frequency of 10Hz.

6. A vehicle perception system, characterized in that, The processor and memory, the memory including a computer program, the processor being configured to run the computer program in the memory to implement the method for stably displaying vehicle perception results in a perceptual reality interface as described in any one of claims 1-5.

7. A computer-readable storage medium, characterized in that, Includes a computer program, which is executed by a processor at runtime, to stably display the vehicle perception results in a perception reality interface as described in any one of claims 1-5.

Images