Dynamic longitudinal and lateral adjustment of perceived lines for commercial vehicle camera mirror system
By determining the trailer angle and wheel position of the trailer in a commercial truck, the towing line is generated, and the problem of invisibility of the trailer wheel at low angles is solved, the accurate estimation of the trailer position and dynamic adjustment of the perception line is achieved, and the driver is improved situational awareness.
Patent Information
- Application Number
- CN202380031230.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2022-03-31
- Filing Date
- 2023-03-22
- Publication Date
- 2024-11-15
AI Technical Summary
In commercial trucks, when the trailer is at a low trailer angle, the rear wheels of the trailer are not visible within the field of view of the driver or passenger side camera mirror system, resulting in unknown wheel position, affecting the driver's perception of the trailer's characteristic position, especially in Driving straight or trailer ends during difficult-to-see angles.
By determining the fixed point on the tractor and the trailer angle of the trailer, the trailer line is generated, and combined with the best fit curve for the trailer wheel position, the trailer wheel position is estimated, and the trailer end perception line is adjusted to be displayed when the trailer is hidden Provides location awareness.
It realizes that the trailer wheel can still accurately estimate its position when it is invisible and dynamically adjusts the perception line, improving the situational awareness of the vehicle operator and enhancing driving safety.
Smart Images

Figure CN118974766A_ABST
Abstract
Description
[0001] CROSS-REFERENCE TO RELATED APPLICATIONS
[0002] This application claims priority to U.S. Provisional Application No. 63 / 325,788, filed on March 31, 2022. Technical Field
[0003] The present disclosure relates to wheel tracking using a camera mirror system (CMS) of a commercial truck, and more particularly to systems and methods for tracking wheel positions when the wheels are hidden. Background Art
[0004] Rearview mirror replacement systems and camera systems for supplementing the rearview mirror view are used in commercial vehicles to enhance the vehicle operator's ability to observe the surrounding environment. A camera mirror system (CMS) utilizes one or more cameras to provide an enhanced field of view to the vehicle operator. In some examples, the rearview mirror replacement system covers a larger field of view than a conventional rearview mirror or includes views that are not fully available through a conventional rearview mirror.
[0005] Semi-autonomous driver assistance systems, camera mirror systems, electronic stability program systems, and other vehicle systems use or need to know the position of various vehicle features throughout the operation of the vehicle. These features can be real world locations or the position of one or more rear wheels of a trailer in an image. Systems exist for tracking wheel positions when the wheels are visible in the field of view of the rear view camera mirror system camera. However, when the trailer is at a low trailer angle, the trailer rear wheels are not visible in the field of view of the driver or passenger side cameras, and the position of the wheels in the real world as well as the position of the wheels in the image is unknown.
[0006] It is also desirable to know the trailer end position because the driver needs positional awareness of such trailer features, particularly during relatively straight driving or very small trailer angles where the trailer end is difficult to see. Summary of the invention
[0007] In one exemplary embodiment, a method of providing a trailer end line for a tractor-trailer includes determining a fixed point on the tractor, determining a trailer angle of the trailer, determining a trailer line arranged with the fixed point at the trailer angle, determining an intersection point between the trailer line and a locus of reference points on the trailer, determining a trailer endpoint along the trailer line and offset from the intersection point, and displaying a trailer end perception line based on the determined trailer endpoint.
[0008] In another embodiment of any of the above embodiments, the fixed point determining step includes estimating the position of the wheels of the tractor.
[0009] In another embodiment of any of the above embodiments, the tractor wheel position estimation includes identifying a first set of wheel positions in at least a first image, each wheel position in the first set of wheel positions being associated with a corresponding trailer angle, clustering the first set of wheel positions and identifying a primary cluster in the first set of wheel positions, generating a best fit curve applied to the primary cluster, the best fit curve being a curve that associates wheel positions with trailer angles, identifying an estimated wheel position by applying a determined trailer angle to the best fit curve in response to the wheel being hidden in the first image, and outputting the estimated wheel position to at least one additional vehicle system.
[0010] In another embodiment of any of the above embodiments, the trailer angle determination step includes: using a trailer angle sensor, CMS image analysis, or a combination thereof.
[0011] In another embodiment of any of the above embodiments, the method includes the step of adjusting the displayed trailer end perception line based on the determined change in the trailer angle.
[0012] In a further embodiment of any of the above embodiments, the reference point is determined by estimating trailer wheel positions.
[0013] In another embodiment of any of the above embodiments, the locus of reference points corresponds to trailer wheel positions fitted as a parabola.
[0014] In another embodiment of any of the above embodiments, the trailer wheel position estimation includes identifying a first set of wheel positions in at least a first image, each wheel position in the first set of wheel positions being associated with a corresponding trailer angle, clustering the first set of wheel positions and identifying a main cluster in the first set of wheel positions, generating a best fit curve applied to the main cluster, the best fit curve being a curve that associates wheel positions with trailer angles, identifying an estimated wheel position by applying a determined trailer angle to the best fit curve in response to the wheel being hidden in the first image, and outputting the estimated wheel position to at least one additional vehicle system.
[0015] In another embodiment of any of the above embodiments, the trailer endpoint determination step includes calculating the relationship between the intersection point and the trailer endpoint in the tractor longitudinal direction y and the tractor transverse direction x.
[0016] In another embodiment of any of the above embodiments, the relationship is according to the equation and t =y i +Δy is calculated, where x i ,yi Corresponding to the wheel intersection point, x t ,y t corresponds to the trailer endpoint, and θ corresponds to the steering angle.
[0017] In another embodiment of any of the above embodiments, the displayed trailer end sensing line is spaced apart from the trailer endpoint.
[0018] In another embodiment of any of the above embodiments, the trailer end perception line is a first perception line, the first perception line is displayed in a first color and corresponds to the position of the trailer end projected on the ground at a position below the trailer end. The displaying step includes displaying a second perception line in a second color different from the first color, and the second perception line corresponds to a position on the ground at a distance behind the first perception line.
[0019] In another embodiment of any of the above embodiments, for a steering angle greater than 0° but less than a predetermined steering angle, the trailer end sensing line is displayed only on one side of the trailer.
[0020] In another embodiment of any of the above embodiments, the trailer end sensing line is displayed only on one side of the inner turning radius of the trailer end.
[0021] In another embodiment of any of the above embodiments, for a steering angle of approximately 0°, the trailer end sensing lines are displayed on both sides of the trailer, and for steering angles above the predetermined steering angle, the trailer end sensing lines are not displayed at all.
[0022] In another exemplary embodiment, a camera mirror system includes a camera arm having a camera, a display, and a controller, wherein the camera arm has a camera, the camera has an image capture unit configured to capture a desired field of view, the desired field of view including at least one of a Class II view and a Class IV view, the display is configured to display the desired field of view, the controller communicates with the image capture unit and the display, the controller is configured to determine a fixed point on a tractor, determine a trailer angle of a trailer, determine a trailer line arranged at the trailer angle with respect to the fixed point, determine an intersection between the trailer line and a trajectory of a reference point on the trailer, determine a trailer endpoint along the trailer line and offset from the intersection, and display a trailer end perception line on the display based on the determined trailer endpoint.
[0023] In a further embodiment of any of the above embodiments, the fixed point is determined by estimating a tractor wheel position.
[0024] In another embodiment of any of the above embodiments, the trailer angle is determined using a trailer angle sensor, CMS image analysis, or a combination thereof.
[0025] In another embodiment of any of the above embodiments, the controller is configured to adjust the displayed trailer end perception line based on the determined change in the trailer angle.
[0026] In a further embodiment of any of the above embodiments, the reference point is determined by estimating trailer wheel positions. BRIEF DESCRIPTION OF THE DRAWINGS
[0027] The present disclosure may be further understood by reference to the following detailed description considered in conjunction with the accompanying drawings, in which:
[0028] Figure 1A is a schematic front view of a commercial truck having a camera mirror system (CMS) for providing at least Class II and Class IV views.
[0029] Figure 1B is a schematic top elevation view of a commercial truck with a camera mirror system providing Class II, Class IV, Class V, and Class VI views.
[0030] Figure 2 is a schematic top perspective view of a vehicle cab including a display and interior camera.
[0031] Figure 3A A camera mirror system view is illustrated that includes a single view of the vehicle trailer at medium to large trailer angles.
[0032] Figure 3B A camera mirror system view is illustrated including two views of the vehicle trailer at a low trailer angle.
[0033] Figure 4 A data set of trailer wheel positions within an image(s) is illustrated.
[0034] Figure 5 Pictured Figure 4 A dataset where data is classified into clusters.
[0035] Figure 6 Pictured Figure 4 The dataset is reduced to the main clusters within each image.
[0036] Figure 7 Pictured Figure 4-Figure 7 The best fit curve for the data set in .
[0037] Figure 8 The best fit curve separated from the data set is illustrated.
[0038] Fig. 9 Illustration of the conversion of raw wheel position data into Figure 4-Figure 8The process flow of the best fit curve is shown.
[0039] Fig.10 Depicted is a process flow diagram for providing a trailer end sensing line according to the disclosed method.
[0040] Fig.11 is a schematic diagram illustrating a method for determining a trailer end sense line on the passenger side of a tractor-trailer.
[0041] Fig.12 The displayed passenger side trailer end sense line and driver side trailer end sense line are illustrated for a straight trailer (ie, 0° steering angle).
[0042] Fig.13 Passenger and driver side displays are illustrated with trailer end awareness lines for steering angles greater than 0° but less than a predetermined steering angle.
[0043] Fig.14 The diagram shows a Fig.13 The passenger and driver side displays show the trailer end sensing line for a steering angle that is shown but still less than the predetermined steering angle.
[0044] The embodiments, examples and alternatives of the preceding paragraphs, the claims or the following description and the drawings, including their various aspects or corresponding individual features, may be adopted independently or in any combination. Features described in conjunction with one embodiment are applicable to all embodiments, unless these features are incompatible. DETAILED DESCRIPTION
[0045] exist Figure 1A and Figure 1B 1 shows a schematic diagram of a commercial vehicle 10. The vehicle 10 includes a vehicle cab or tractor 12 for towing a trailer 14. Although commercial trucks are contemplated in this disclosure, the present invention is also applicable to other types of vehicles. The vehicle 10 includes a camera mirror system (CMS) 15 ( Figure 2 ), which has a driver-side camera arm 16a and a passenger-side camera arm 16b mounted to the exterior of the vehicle cab 12. If desired, the camera arms 16a, 16b may also include traditional rearview mirrors integrated therewith, but the CMS 15 may be used to completely replace the rearview mirrors. In other examples, multiple camera arms may be included on each side, each arm housing one or more cameras and / or rearview mirrors.
[0046] Each camera arm 16a, 16b includes a base fixed to, for example, the cab 12. The pivot arm is supported by the base and can be hinged relative to the base. At least one rear-view camera 20a, 20b is arranged in each camera arm. The external cameras 20a, 20b provide an external field of view FOV EX1 FOVEX2 , external field of view FOV EX1 FOV EX2 Include at least one of the Class II and Class IV views ( Figure 1B ), which are legally required views for the commercial trucking industry. If desired, multiple cameras may also be used in each camera arm 16a, 16b to provide these views. Each arm 16a, 16b may also provide a housing that encapsulates electronics configured to provide the various features of the CMS 15.
[0047] The first video display 18a and the second video display 18b are arranged on or near the A-pillars 19a, 19b on each of the driver's side and the passenger side within the vehicle cab 12 to display Class II views and Class IV views of the corresponding sides of the vehicle 10, which provide rearward-facing side views along the vehicle 10 captured by the external cameras 20a, 20b.
[0048] If video of Class V and Class VI views is also desired, a camera housing 16c and camera 20c may be arranged at or near the front of the vehicle 10 to provide these views ( Figure 1B ). A third display 18 c disposed within the cab 12 near the top center of the windshield may be used to display Class V and Class VI views toward the front of the vehicle 10 to the driver.
[0049] If video of a Class VIII view is desired, camera housings may be provided on the sides and rear of the vehicle 10 to provide a field of view that includes part or all of the Class VIII area of the vehicle 10. In such an example, the third display 18c may include one or more frames that display a Class VIII view. Alternatively, an additional display may be added near the first display 18a, the second display 18b, and the third display 18c that provides a display dedicated to providing a Class VIII view. The displays 18a, 18b, 18c face the driver area 24 within the cab 22, where the operator sits in the driver's seat 26.
[0050] Continue to refer Figure 1A-Figure 2 , Figure 3A The rear view displayed to the vehicle operator by the CMS described above is schematically illustrated when the trailer 14 is at a medium to large angle (e.g., greater than 10 degrees). At medium to large trailer angles, the trailer 14 is minimally visible in the opposite view (if it is visible at all), and the opposite view is omitted. Figure 3B The trailer 14 is schematically illustrated in the driver-side display 102 and the passenger-side display 104. When the trailer 14 is at a medium to large angle, the rearmost wheels 112 are visible in the corresponding view 104. Conversely, when the trailer 14 is at a low trailer angle ( Figure 3B), the wheels 112 are not visible. Because the wheels 112 are not visible, the wheels 112 are said to be hidden. Although the exact angle at which the wheels 112 are hidden depends on the position of the camera generating the view and the length of the trailer 14, the wheels 112 are generally hidden at low angles (e.g., between 10 degrees and -10 degrees).
[0051] To facilitate vehicle systems that rely on the position of the wheels 112 (e.g., advanced driver assistance systems, camera mirror systems, electronic stability programs, and similar vehicle systems), the CMS monitors the views 102, 104 and identifies the wheel positions 112 under any operating conditions where the wheels 112 are visible. Existing object tracking systems can identify the wheels 112 when they are visible and track the center points 114 of the wheels 112 as they pass through the image. The positions in the images can then be converted back to real-world 3D positions using known systems. In addition to using these monitored wheel positions, the CMS generates a data set from each image, with each point in each data set identifying the center point 114 of the wheels 112 in the image and aligning the center points 114 of the wheels 112 with the angle of the trailer 14 where the wheel positions were detected. The angle of the trailer 14 is detected using one of the trailer angle sensors, CMS image analysis, or a combination of both.
[0052] Based on the relationship established using the wheel 112 detection and the trailer angle when the wheel(s) 112 are visible, the CMS is configured to determine a best fit curve for estimating the Figure 3B The positions of the wheels 112 during low angles are shown when the wheel(s) 112 are hidden and when the wheels are hidden due to other external influences, including light and heavy rain. The estimated wheel positions are provided to any CMS or other vehicle system that uses the information, thereby providing continuous wheel positions to the CMS or other vehicle system.
[0053] Continue to refer to Figure 1- Figure 3B , Figure 4-Figure 8 illustrates an on-road process for generating wheel position estimates specific to a currently attached trailer 14, Fig. 9 The diagram shows the Figure 4-Figure 7 The process 300 operates on a data set. The process is able to estimate the position of the hidden wheels without requiring trailer parameters such as height and length. Figure 4-Figure 9 The example uses images from the driver side view 102 and the passenger side view 104 (see Figure 3B ) data, resulting in an approximately symmetrical image, but it will be appreciated that due to the symmetry a similar process can be applied to only a single view and produce similar wheel position estimates.
[0054] Initially, in a “raw wheel detection” step 302, wheel position data is aggregated over time while the vehicle is in operation to generate a raw wheel position dataset 204 ( Figure 4 ). The raw wheel detections use image analysis to identify the wheel locations in the images provided by the CMS (i.e., the locations of the center points of the wheels in the images). Once a data set has been provided sufficient to generate an estimation curve, the data set 204 is referred to as a complete data set. In some examples, the complete data set includes, for example, at least approximately 100-150 wheel detections 204. In addition to the location of the center point 114 of the wheel 112 in the image, each data point also has an associated corresponding trailer angle determined by any available trailer angle detection or estimation system, where the corresponding trailer angle is the trailer angle when the wheel position was captured. In some examples, once the data set has been sufficiently provided, the process 300 stops adding data to the data set. In other examples, the process can be continuously updated with new detections as they become available, and the accuracy of the resulting estimate continues to improve throughout the use of the vehicle.
[0055] In some cases, incorrect wheel position determinations may occur and may be added to the data set 204, thereby generating additional data points 208 that may distort or otherwise affect the resulting estimated curve. In order to eliminate false detections from the data set 204 and improve the resolution of the wheel position estimate, the original data points 206 are clustered in a "data clustering" step 304. Clustering combines each data point 206 with nearby neighboring data points 206 based on the proximity of the data point 206 to other data points 206 and the density of the data points 206. In some example systems, clustering is performed using one or more of a k-means clustering process, a dbscan (density-based spatial) clustering process, a distribution-based clustering process, a fuzzy clustering process, a mean shift clustering process, and a Gaussian mixture model clustering process. The clustering process generates a plurality of different wheel detection clusters 210, 212. It will be appreciated that in each view 102, 104, a true wheel detection (data point 210) will result in a single elongated cluster 210 having a generally teardrop shape. False wheel detection 208 will generate one or more additional clusters 212 , where additional clusters 212 are of random shape.
[0056] Once the data is clustered, the cluster 212 associated with the erroneous wheel detection 208 is discarded in a "cluster down selection" step 306. In some examples, the cluster down selection may discard the data point 208 entirely, while in other examples, the data point 208 may be retained and marked as a erroneous detection, wherein the marked erroneous detection is ignored in the remainder of the process 300. When retained, the data point may be later examined to improve the wheel detection system, or the examined data point may be used for other diagnostic functions. For ease of reference, the cluster 210 including the accurate wheel detection is referred to as the "primary data cluster." In the example using the views 102, 104 of both sides of the vehicle, for example Figure 4-Figure 7 In the example shown, there are two master data clusters 210 and they are retained. In an alternative example where only a single side (corresponding to a single view 102, 104) is used, a single master data cluster is retained.
[0057] After discarding the cluster 212 containing erroneous wheel detections, a single set of accurate wheel detections 206 remains ( Figure 6 ). The process 300 determines a best fit curve for all wheel detections in the two master data clusters 210. In one example, the best fit curve is a parabola defined by a second order equation and is the best fit for all data on the two master data clusters 210. In another example, the best fit curve is a parabola defined by a third order (cubic) equation. As used throughout, a best fit curve refers to a curve that is statistically determined to be closest to the trend of the scatter plot generated by the data.
[0058] The parabola defined by the second order best fit curve extends beyond each data cluster 210 and fills in the gaps 222 between the low trailer angles for each data cluster. A cubic or other type of polynomial fit may be used for the data clusters. Figure 4-Figure 7 and Fig. 9 , Figure 8 The diagram illustrates a parabola defining a best fit curve 220 separated from the data, with 0 degree trailer angle located at the center of the graph, and trailer angle increasing toward the right side of the graph and decreasing toward the left side of the graph. Since wheel position corresponds to trailer angle, the CMS estimates that the wheel position is located on the best fit line when the trailer angle is between negative 10 degrees and positive 10 degrees. In alternative examples, the blank 222 may be located at a different location, but the estimation process may remain the same.
[0059] In another example, once the best fit curve is established, the best fit curve 220 can be used to estimate the wheel position whenever the CMS cannot identify the wheel position in the image. For example, if one of the cameras generating the views 102, 104 fails, or if the field of view 102, 104 is completely or partially obstructed, the estimation can continue to provide estimated wheel positions as long as the trailer angle can be determined.
[0060] The estimation system and process described above generates estimated wheel positions using images generated by views 102, 104. The CMS controller and / or other vehicle system controller converts the estimated image positions into corresponding three-dimensional real world positions and can use the corresponding three-dimensional positions as desired.
[0061] In at least one example, the estimated wheel positions are provided from the CMS controller to a trailer end detection module within the CMS system. The trailer end detection module can be a software module located within the controller or a separate software system that communicates with the CMS controller. The trailer end detection module uses the wheel positions to assist in identifying the trailer end and marks the trailer end position on the CMS display to improve the vehicle operator's situational awareness. In another example, the wheel positions can also be used by the CMS to estimate the position of the entire wheelbase, which can then be used within the CMS.
[0062] The above-described techniques may be used to adjust display perception lines (eg, trailer end line and distance lines) for display as the trailer articulates during normal vehicle operation, particularly during relatively slight articulation of the trailer.
[0063] refer to Fig.10 and Fig.11 The controller of the system is programmed to perform a method 400 that provides at least one trailer end sensing line (418, 420, in Figure 12-14 4. At 402, a trailer angle θ of the trailer 14 relative to the tractor 12 is determined, for example, using a trailer angle sensor, CMS image analysis, or a combination thereof. During forward travel, the trailer angle θ is calculated using a kinematic model that uses tractor speed, steering angle, etc. The trailer angle θ corresponds to a real-world 3D angle between the tractor 12 and the trailer 14, which is then converted to a 2D image space trailer angle. That is, the 3D trailer angle θ may have a vertical component due to tilt, and the 2D value has only horizontal components x and y. The calibration point (x o ,y o ) is determined, for example, by estimating the position of the tractor wheel 118 using a fixed point on the tractor 12 (block 404). The tractor wheel estimate may be combined with Figure 3A-Figure 9 Performed as described.
[0064] Geometrically, the trailer line 406 is arranged to be aligned with the fixed calibration point (x o ,y o ) into a 2D trailer angle θ. Lateral and longitudinal offsets can be adjusted using this converted 2D angle. The trailer line represents the orientation of the trailer 14 relative to the tractor 12. The reference point on the trailer 14 is determined, for example, by estimating the position of the trailer wheel 112, which may be the last trailer wheel. The trailer wheel estimate may also be combined with Figure 3A-Figure 9 Performed as described.
[0065] The trajectory of the reference point (i.e., Fig.10 The wheel trajectory or “WD curve” at 408 in FIG. 1 corresponds to the trailer wheel position 112 fitted as a parabola, such as Fig.11 The intersection point (x i ,y i ) (block 410) to obtain the driver's side wheel position and / or the passenger's side wheel position (in Fig.10 412, 414 in the figure).
[0066] The trailer end track must follow a predictable arc path behind the trailer wheel track. t ,y t )(box 416) is also located on the trailer line, so the trailer endpoint determination step includes calculating the relationship between the intersection point and the trailer endpoint in the longitudinal direction y of the tractor and the lateral direction x of the tractor. Because the trailer end track will be similar to the wheel track, there is a (calibrated) upward shift of Δy pixels in image space. Δy can vary between different trailers. If necessary, the perceived line feature can use a default value of Δy to simplify the calculation. That is, Δy can be an input for a specific trailer, or it can be determined according to any number of methods, for example, as disclosed in USSN 63 / 257,165 entitled "TRAILER END TRACKING IN ACOMMERCIAL VEHICLE CAMERA MIRROR SYSTEM", the entire contents of which are incorporated herein by reference. Combining the intersection point, trailer line, and Δy, the trailer end tracking in the lateral direction (x) can be calculated according to the following relationship t ) and vertical (y t ) direction:
[0067]
[0068] y t=y i +Δy Equation 2
[0069] In the event that the above relationship is determined, one or more trailer end sensing lines may be displayed on one or more of the displays 18a-18c within the cab 22. Figure 12-14 In the example shown, any trailer end sensing line 500-506 is spaced from the trailer end point TE. Throughout vehicle operation and during articulation of the trailer 14 relative to the tractor 12, the displayed trailer end sensing line(s) are adjusted based on changes in the trailer angle θ determined based on the above-described method. In this manner, the sensing lines are dynamically adjusted in both the lateral and longitudinal directions.
[0070] The amount of steering angle θ can be used to determine which trailer end perception lines are displayed to the driver and where those lines are displayed (i.e., driver-side and / or passenger-side displays 18a, 18b). For example, when the trailer angle is very small (i.e., the trailer is straight, approximately 0°), the perception lines are shown on both the driver side and the passenger side, as shown in FIG. Fig.12 As shown. In one example, the first trailer end perception line (500, 504) is used to indicate the trailer end TE projected onto the ground at a horizontal position. The second trailer end perception line (502, 506) can be used behind the trailer end TE (e.g., 30 meters) to help the driver pass vehicles or other objects in adjacent lanes or spaces on either side of the trailer 14. In one example, the first perception line is displayed in a first color (e.g., red), and the second perception line is displayed in a second color (e.g., yellow) different from the first color.
[0071] In another example, when one side of the trailer 14 is visible and the other side is not visible, only the visible side perception line ( Fig.13 and Fig.14 ). The steering angle θ can be used to determine which side is visible and which is not visible. For example, for steering angles greater than 0° but less than a predetermined steering angle, the (one or more) trailer end sensing lines are only displayed on one side of the trailer. The trailer end sensing lines are only displayed on one side of the inner turning radius of the trailer end. For example, the predetermined angle may be 10° or 15°. For steering angles above the predetermined steering angle, the (one or more) trailer end sensing lines are not displayed at all. Knowing the trailer end position during small trailer angles enhances driving safety in situations such as changing lanes while driving straight on the highway or in low light conditions or heavy rain.
[0072] The disclosed method and system provide a method to adjust the lateral position of a perception line at the end of a trailer based on the tractor-trailer angle. The perception line can be placed at an appropriate lateral position for the driver's depth perception purpose of surrounding vehicles.
[0073] Although exemplary embodiments have been disclosed, a worker of ordinary skill in this art would recognize that certain modifications would come within the scope of the claims. Therefore, the following claims should be studied to determine their true scope and content.
Claims
1. A method of providing a trailer end line for a tractor-trailer, the method comprising: Identify the anchoring points on the towing vehicle; Determine the trailer's tow angle; determining a trailer line arranged at the trailer angle relative to the fixed point; determining an intersection between the trailer line and a locus of reference points on the trailer; determining a trailer endpoint along the trailer line and offset from the intersection; as well as A trailer end awareness line is displayed based on the determined trailer endpoint.
2. The method according to claim 1, wherein The step of determining the fixed point includes estimating the position of the wheels of the tractor.
3. The method according to claim 2, wherein: The tractor wheel position estimation includes: identifying a first set of wheel positions in at least a first image, each wheel position in the first set of wheel positions being associated with a corresponding trailer angle; clustering the first set of wheel positions and identifying a primary cluster in the first set of wheel positions; generating a best fit curve to be applied to the master cluster, the best fit curve being a curve relating wheel position to trailer angle; identifying an estimated wheel position by applying the determined trailer angle to the best fit curve in response to the wheel being hidden in the first image; and The estimated wheel position is output to at least one additional vehicle system.
4. The method according to claim 1, wherein The trailer angle determination step includes using a trailer angle sensor, CMS image analysis, or a combination thereof.
5. The method according to claim 4, comprising: The step of adjusting a displayed trailer end sensing line based on the determined change in trailer angle.
6. The method according to claim 1, wherein The reference point is determined by estimating the trailer wheel position.
7. The method according to claim 6, wherein: The locus of reference points corresponds to the trailer wheel positions fitted as a parabola.
8. The method according to claim 6, wherein: The trailer wheel position estimation includes: identifying a first set of wheel positions in at least a first image, each wheel position in the first set of wheel positions being associated with a corresponding trailer angle; clustering the first set of wheel positions and identifying a primary cluster in the first set of wheel positions; generating a best fit curve to be applied to the master cluster, the best fit curve being a curve relating wheel position to trailer angle; identifying an estimated wheel position by applying the determined trailer angle to the best fit curve in response to the wheel being hidden in the first image; and The estimated wheel position is output to at least one additional vehicle system.
9. The method according to claim 6, wherein: The trailer endpoint determination step includes calculating the relationship between the intersection point in the tractor longitudinal direction y and the tractor transverse direction x and the trailer endpoint.
10. The method according to claim 9, wherein: The relationship is based on the equation y t =y i -Δy is calculated, where x i 、y i Corresponding to the wheel intersection point, x t 、y t corresponds to the trailer endpoint, and θ corresponds to the steering angle.
11. The method according to claim 10, wherein: The trailer end sensing line is shown spaced apart from the trailer end point.
12. The method according to claim 1, wherein The trailer end perception line is a first perception line, which is displayed in a first color and corresponds to the position of the trailer end projected on the ground at a position below the trailer end, and the displaying step includes displaying a second perception line in a second color different from the first color, and the second perception line corresponds to a position on the ground at a certain distance behind the first perception line.
13. The method according to claim 1, wherein For a steering angle greater than 0° but less than a predetermined steering angle, the trailer end sensing line is displayed only on one side of the trailer.
14. The method according to claim 13, wherein The trailer end sensing line is displayed only on one side of the inner turning radius of the trailer end.
15. The method according to claim 13, wherein: For a steering angle of approximately 0°, the trailer end sensing lines are displayed on both sides of the trailer, and for steering angles above the predetermined steering angle, the trailer end sensing lines are not displayed at all.
16. A camera mirror system comprising: a camera arm having a camera with an image capture unit configured to capture a desired field of view, the desired field of view including at least one of a Class II view and a Class IV view; a display configured to display the desired field of view; a controller in communication with the image capture unit and the display, the controller being configured to: Identify the anchoring points on the towing vehicle; Determine the trailer's tow angle; determining a trailer line arranged at the trailer angle relative to the fixed point; determining an intersection between the trailer line and a locus of reference points on the trailer; determining a trailer endpoint along the trailer line and offset from the intersection; as well as A trailer end awareness line is displayed on the display based on the determined trailer endpoint.
17. The system according to claim 16, wherein: The fixed point is determined by estimating the position of the tractor vehicle wheels.
18. The system according to claim 16, wherein: The trailer angle is determined using a trailer angle sensor, CMS image analysis, or a combination thereof.
19. The system according to claim 16, wherein: The controller is configured to adjust the displayed trailer end sensing line based on the determined change in the trailer angle.
20. The system of claim 16, wherein: The reference point is determined by estimating the trailer wheel position.
