Dynamic Longitudinal and Lateral Line of Recognition Adjustment for Commercial Vehicle Camera Mirror Systems

Abstract

A method for 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 disposed at the trailer angle from the fixed point, determining an intersection point of the trailer line with a trajectory of a reference point on the trailer, determining a trailer end point along the trailer line and offset from the intersection point, and displaying a trailer end recognition line based on the determined trailer end point.

Description

[Technical Field]

[0001] The present disclosure relates to wheel tracking using a camera mirror system (CMS) on a commercial truck, and more particularly to a system and method for tracking wheel position while the wheels are obscured.

[0002] (CROSS-REFERENCE TO RELATED APPLICATIONS) This application claims priority to U.S. Provisional Application No. 63 / 325,788, filed March 31, 2022. [Background technology]

[0003] Mirror replacement systems, and camera systems that supplement the mirror view, are utilized in commercial vehicles to enhance the vehicle operator's ability to see the surrounding environment. Camera mirror systems (CMS) utilize one or more cameras to provide the vehicle operator with an enhanced field of view. In some instances, mirror replacement systems cover a wider field of view than traditional mirrors or include views not fully available through traditional mirrors.

[0004] Semi-autonomous driver assistance systems, camera mirror systems, electronic stability program systems, and other vehicle systems use or require knowledge of the location of various vehicle features throughout the vehicle's operation. Among these features may be the real-world location or the location in an image of one or more rear wheels of a trailer. Systems exist that track the location of the wheels while they are visible in the field of view of the cameras in a rear-facing camera mirror system. However, while the trailer is at a low trailer angle, the rear wheels are not visible in the field of view of the driver-side or passenger-side cameras, and the real-world location of the wheels and their location in the image are unknown.

[0005] It is also desirable to know the location of the trailer end, as the driver needs location awareness of this trailer feature, especially during relatively straight driving or very slight trailer angles where the trailer end is difficult to see. Summary of the Invention

[0006] In one exemplary embodiment, a method for providing a trailer end line for a tractor trailer includes determining a fixed point on a tractor, determining a trailer angle of the trailer, determining a trailer line disposed at the trailer angle from the fixed point, determining an intersection point of the trailer line with a trajectory of a reference point on the trailer, determining a trailer end point along the trailer line and offset from the intersection point, and displaying a trailer end recognition line based on the determined trailer end point.

[0007] In a further embodiment of any of the above, determining the fixed point includes estimating tractor wheel position.

[0008] In a further embodiment of any of the above, estimating the tractor wheel positions includes identifying a first set of wheel positions in at least a first image, wherein each wheel position in the first set of wheel positions is 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 primary cluster, wherein the best fit curve is a curve relating wheel positions to trailer angles; in response to the wheels being occluded in the first image, identifying an estimated wheel position by applying the determined trailer angle to the best fit curve; and outputting the estimated wheel position to at least one additional vehicle system.

[0009] In a further embodiment of any of the above, determining the trailer angle includes using a trailer angle sensor, CMS image analysis, or a combination thereof.

[0010] In a further embodiment of any of the above, the method includes adjusting the displayed trailer edge recognition line in response to changes in the determined trailer angle.

[0011] In a further embodiment of any of the above, the reference points are determined by estimating trailer wheel positions.

[0012] In a further embodiment of any of the above, the trajectory of reference points corresponds to the trailer wheel positions fitted as a parabola.

[0013] In a further embodiment of any of the above, estimating the trailer wheel position includes identifying a first set of wheel positions in at least a first image, wherein each wheel position in the first set of wheel positions is 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 primary cluster, the best fit curve being a curve relating wheel positions to trailer angles; in response to the wheels being occluded in the first image, identifying an estimated wheel position by applying a determined trailer angle to the best fit curve; and outputting the estimated wheel position to at least one additional vehicle system.

[0014] In a further embodiment of any of the above, determining the trailer end points includes calculating a relationship between the trailer end points and the intersection point in a tractor longitudinal direction y and a tractor lateral direction x.

[0015] In further embodiments of any of the above, the relationship is of the formula

number

[0016] In a further embodiment of any of the above, the displayed trailer end recognition line is spaced apart from the trailer end point.

[0017] In a further embodiment of any of the above, the trailer end recognition line is a first recognition line displayed in a first color and corresponding to a position of the trailer end projected onto the ground at a position below the trailer end, and the displaying includes displaying a second recognition line in a second color different from the first color, the second recognition line corresponding to a position on the ground a distance behind the first recognition line.

[0018] In a further embodiment of any of the above, the trailer edge recognition lines are displayed on only one side of the trailer for steering angles greater than 0° and less than a predetermined steering angle.

[0019] In a further embodiment of any of the above, the trailer end recognition lines are displayed only on the inside turning radius side of the trailer end.

[0020] In a further embodiment of any of the above, the trailer end recognition lines are displayed on both sides of the trailer for a steering angle of approximately 0°, and the trailer end recognition lines are not displayed at all for steering angles above the predetermined steering angle.

[0021] In another exemplary embodiment, a camera mirror system includes 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 and a Class IV view; a display configured to display the desired field of view; and a controller in communication with the image capture unit and the display, wherein the controller is configured to: determine a fixed point on a tractor; determine a trailer angle of a trailer; determine a trailer line disposed from the fixed point at the trailer angle; determine an intersection point of the trailer line with a trajectory of a reference point on the trailer; determine trailer end points along the trailer line and offset from the intersection point; and display a trailer end recognition line on the display based on the determined trailer end points.

[0022] In a further embodiment of any of the above, the fixed point is determined by estimating tractor wheel position.

[0023] In a further embodiment of any of the above, the trailer angle is determined using a trailer angle sensor, CMS image analysis, or a combination thereof.

[0024] In a further embodiment of any of the above, the controller is configured to adjust the displayed trailer edge recognition line in response to changes in the determined trailer angle.

[0025] In a further embodiment of any of the above, the reference points are determined by estimating trailer wheel positions. [Brief explanation of the drawings]

[0026] The present disclosure can be further understood by reference to the following detailed description taken in conjunction with the accompanying drawings.

[0027] [Figure 1A]FIG. 1 is a schematic front view of a commercial truck equipped with a camera mirror system (CMS) used to provide at least Class II and Class IV views.

[0028] [Figure 1B] FIG. 1 is a schematic top view of a commercial truck equipped with a camera mirror system providing Class II, Class IV, Class V, and Class VI views.

[0029] [Figure 2] FIG. 1 is a schematic top perspective view of a vehicle cab including a display and an interior camera.

[0030] [Figure 3A] 1 shows a view of a camera mirror system including a single view of a vehicle trailer at a medium to large trailer angle.

[0031] [Figure 3B] 1 shows a view of a camera mirror system including two views of a vehicle trailer at a low trailer angle.

[0032] [Figure 4] 1 shows a dataset of trailer wheel positions in images.

[0033] [Figure 5] The data set in Figure 4 is shown with the data grouped into clusters.

[0034] [Figure 6] We present the dataset from Figure 4 reduced to the primary clusters within each image.

[0035] [Figure 7] Best fit curves are shown for the data sets of Figures 4-7.

[0036] [Figure 8] The best fit curve isolated from the data set is shown.

[0037] [Figure 9] 4-8 show a process flow illustrating the conversion of raw wheel position data into best fit curves.

[0038] [Figure 10] 1 shows a process flow chart for providing trailer end recognition lines according to the disclosed method.

[0039] [Figure 11] FIG. 10 illustrates a method for determining the trailer end recognition line on the passenger side of a tractor trailer.

[0040] [Figure 12] FIG. 10 shows passenger and driver side trailer edge recognition lines displayed for a straight trailer, i.e., 0° steering angle.

[0041] [Figure 13] FIG. 10 illustrates passenger and driver side displays with trailer edge awareness lines for steering angles above 0° but below a predefined steering angle.

[0042] [Figure 14] 14A-14D show passenger and driver side displays with trailer edge recognition lines for steering angles greater than the steering angle shown in FIG. 13 but less than a default steering angle.

[0043] The embodiments, examples and alternatives of the preceding paragraphs, the claims, or the following description and drawings, including any of their various aspects or their respective individual features, may be taken independently or in any combination. Features described in connection with one embodiment are applicable to all embodiments, except where such features are incompatible. DETAILED DESCRIPTION OF THE INVENTION

[0044] Schematic diagrams of a commercial vehicle 10 are shown in FIGS. 1A and 1B. The vehicle 10 includes a vehicle cab or tractor 12 for towing a trailer 14. While commercial trucks are contemplated in this disclosure, the present invention may be applied to other types of vehicles. The vehicle 10 incorporates a camera mirror system (CMS) 15 (FIG. 2) with driver and passenger side camera arms 16a, 16b mounted on the exterior of the vehicle cab 12. If desired, the camera arms 16a, 16b may also include conventional mirrors integrated therewith, although the CMS 15 may be used to replace the mirrors entirely. In additional examples, multiple camera arms may be included on each side, with each arm housing one or more cameras and / or mirrors.

[0045] Each camera arm 16a, 16b includes a base fixed to, for example, the cab 12. A pivoting arm is supported by the base and may be articulated relative thereto. At least one rear-facing camera 20a, 20b is disposed within each camera arm. Each exterior camera 20a, 20b has an exterior field of view (FOV) that includes at least one of a Class II view and a Class IV view (FIG. 1b), which are legally defined views in the commercial trucking industry. EX1 , FOV EX2 If desired, multiple cameras may be used on each camera arm 16 a, 16 b to provide these views. Each arm 16 a, 16 b may also provide a housing that encloses electronics configured to provide various features of CMS 15.

[0046] First and second video displays 18a, 18b are positioned on the driver's side and passenger's side, respectively, within the vehicle cab 12 on or near the A-pillars 19a, 19b and display Class II and Class IV views on each side of the vehicle 10, which provide rear-facing views along the vehicle 10 captured by exterior cameras 20a, 20b.

[0047] If Class V and Class VI view footage is also desired, a camera housing 16c and camera 20c may be located at or near the front of the vehicle 10 to provide these views (FIG. 1b). A third display 18c located within the cab 12 near the top center of the windshield may be used to display Class V and Class VI views forward of the vehicle 10 to the driver.

[0048] If Class VIII view video is required, camera housings can be positioned on the sides and rear of vehicle 10 to provide a field of view that includes some or all of the Class VIII zone of vehicle 10. In such an example, third display 18c can include one or more frames that display the Class VIII view. Alternatively, additional displays can be added near first, second, and third displays 18a, 18b, 18c to provide a dedicated display that provides the Class VIII view. Displays 18a, 18b, 18c face toward a driver's area 24 within cab 22, where a driver sits in driver's seat 26.

[0049] 1A-2, FIG. 3A schematically illustrates the rear view displayed to the vehicle driver via the CMS described above when the trailer 14 is at a medium to high angle (e.g., greater than 10°). At a medium to high trailer angle, the trailer 14 is only slightly visible in the opposite view, and if visible at all, the opposite view is omitted. FIG. 3B schematically illustrates the trailer 14 on both the driver-side display 102 and the passenger-side display 104. When the trailer 14 is at a medium to high angle, the rearmost wheels 112 are visible in the corresponding view 104. In contrast, when the trailer 14 is at a low trailer angle (FIG. 3B), the wheels 112 are not visible. Because the wheels 112 are not visible, they are referred to as hidden. 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, but the wheels 112 are typically hidden at low angles (e.g., between 10 and -10 degrees).

[0050] To facilitate vehicle systems that rely on the position of the wheels 112, such as advanced driver assistance systems, camera mirror systems, electronic stability programs, and similar vehicle systems, the CMS monitors the views 102, 104 and identifies wheel positions 112 during any operating condition in which the wheels 112 are visible. Existing object tracking systems can identify the wheels 112 when they are visible and track their center points 114 as they move through the image. The positions within the image can then be converted back to real-world three-dimensional positions using known systems. In addition to using these monitored wheel positions, the CMS generates a dataset from each image, and each point in each dataset identifies the center point 114 of the wheels 112 in the image and adjusts the center point 114 of the wheels 112 by the angle of the trailer 14 at which the wheel position is detected. The angle of the trailer 14 is detected using either a trailer angle sensor, CMS image analysis, or a combination of these.

[0051] Based on the relationship established using the detection of the wheels 112 and the trailer angle while the wheels 112 are visible, the CMS is configured to determine a best fit curve for estimating the position of the wheels 112 while the wheel(s) 112 are obscured during the low angles shown in Figure 3B and while the wheels are obscured by other external effects, including low light and heavy rain. The estimated wheel positions are provided to any CMS or other vehicle system that uses that information, thereby providing the CMS or other vehicle system with continuous wheel positions.

[0052] With continued reference to Figures 1-3B, Figures 4-8 illustrate an on-road process for generating wheel position estimates specific to the currently attached trailer 14, and Figure 9 illustrates a flow of a process 300 for operating on the data sets of Figures 4-7. This process is able to estimate hidden wheel positions without requiring trailer parameters such as height and length. The examples in Figures 4-9 are shown using data from the driver's side view 102 and passenger's side view 104 (see Figure 3B), resulting in roughly symmetrical images, however, due to the symmetrical nature, it will be understood that a similar process can be applied to only a single view to generate similar wheel position estimates.

[0053] Initially, during vehicle operation, wheel position data is collected over time in a "raw wheel detection" step 302 to create the raw wheel position dataset 204 shown in FIG. 4. Raw wheel detection uses image analysis to identify wheel locations (i.e., the location of wheel center points within the image) within the image provided by the CMS. Once the dataset is populated enough to generate an estimated curve, the dataset 204 is referred to as a complete dataset. In some examples, the complete dataset includes, for example, at least approximately 100 to 150 wheel detections 204. In addition to the location of the center points 114 of the wheels 112 within the image, each data point 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 at the time the wheel position was captured. In some examples, once the dataset is populated enough, the process 300 stops adding data to the dataset. In other examples, the process may be continually updated with new detections as they become available, with the accuracy of the resulting estimation continually improving during vehicle use.

[0054] In some cases, erroneous wheel position determinations may occur and be added to the dataset 204, resulting in additional data points 208 that may distort or otherwise affect the resulting estimated curve. To remove erroneous detections from the dataset 204 and improve the resolution of the wheel position estimation, the raw data points 206 are clustered in a "data clustering" step 304. Clustering groups 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 exemplary systems, clustering is performed using one or more of a k-means clustering process, a density-based spatial (dbscan) 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 results in multiple distinct clusters 210, 212 of wheel detections. It can be seen that in each view 102, 104, a true wheel detection (data points 210) results in a single elongated cluster 210 having a roughly teardrop shape. An incorrect wheel detection 208 results in one or more additional clusters 212, which are randomly shaped.

[0055] Once the data is clustered, the clusters 212 associated with the erroneous wheel detections 208 are discarded in a "cluster culling" step 306. In some examples, cluster culling may discard the data points 208 entirely, while in other examples, the data points 208 may be retained and flagged as erroneous detections, with the flagged erroneous detections being ignored for the remainder of the process 300. If retained, the data points may be later reviewed to improve the wheel detection system or used for other diagnostic functions. For ease of reference, the clusters 210 containing accurate wheel detections are referred to as "primary data clusters." In examples using views 102, 104 from each side of the vehicle, such as the example shown in FIGS. 4-7, two primary data clusters 210 are present and retained. In other examples where only one side (corresponding to a single view 102, 104) is used, a single primary data cluster is retained.

[0056] After discarding the clusters 212 containing erroneous wheel detections, a single set of accurate wheel detections 206 remains, as shown in Figure 6. Process 300 determines a best-fit curve to apply to all wheel detections in both primary data clusters 210. In one example, the best-fit curve is a parabola defined by a quadratic equation that is the best fit to all data across both primary data clusters 210. In another example, the best-fit curve is a parabola defined by a cubic (cubic) equation. As used throughout, best-fit curve refers to a statistically determined curve that most closely approximates the trend of a scatter plot generated by the data.

[0057] The parabola defined by the quadratic best-fit curve extends beyond each data cluster 210, filling in gaps 222 between the low trailer angles of each data cluster. A cubic or other type of polynomial fit may also be used for the data clusters. With continued reference to FIGS. 4-7 and 9, FIG. 8 shows the parabola defining the best-fit curve 220 separated from the data, with a 0-degree trailer angle located in the center of the chart and increasing trailer angle toward the right and decreasing trailer angle toward the left. Because wheel position corresponds to trailer angle, the CMS estimates that wheel position is on the best-fit line when the trailer angle is between negative 10 degrees and positive 10 degrees. In another example, the gap 222 may be in a different location, but the estimation process may remain the same.

[0058] In yet another example, once a best fit curve is established, the wheel position can be estimated using the best fit curve 220 whenever the CMS is unable to identify the wheel position in the image. As an example, if one of the cameras generating the views 102, 104 fails or if the field of view 102, 104 is fully or partially obstructed, the estimation can continue to provide an estimated wheel position as long as the trailer angle can be determined.

[0059] The estimation systems and processes described above generate estimated wheel positions using images generated by views 102, 104. The CMS controller and / or other vehicle system controllers can convert the estimated image positions into corresponding 3D real-world positions and use the corresponding 3D positions as needed.

[0060] 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 may be a software module also located within the controller or a separate software system in communication with the CMS controller. The trailer end detection module uses the wheel positions to assist in identifying the trailer ends, which are marked on a CMS display to improve the vehicle driver's situational awareness. In another example, the CMS may also use the wheel positions to estimate the position of the entire wheelbase, which can then be used within the CMS.

[0061] Using the techniques described above, the display recognition lines (e.g., trailer edge lines and distance lines) can be adjusted and displayed as the trailer articulates during normal vehicle operation, particularly during relatively small amounts of trailer articulation.

[0062] 10 and 11, the system's controller is programmed to execute a method 400, which provides at least one trailer end recognition line for the tractor-trailer (steps 418, 420; shown in FIGS. 12-14 as lines 500, 502, 504, and / or 506). The trailer angle θ of the trailer 14 relative to the tractor 12 is determined at 402, for example, using a trailer angle sensor, CMS image analysis, or a combination thereof. During forward driving, the trailer angle θ is calculated with a kinematic model using tractor speed, steering angle, etc. The trailer angle θ corresponds to a real-world three-dimensional angle between the tractor 12 and trailer 14, which is then converted to a trailer angle in two-dimensional image space. That is, the three-dimensional trailer angle θ may have a vertical component due to tilt, while the two-dimensional value has only horizontal components x and y. The calibration point (x o , y o ) is determined using fixed points on the tractor 12, for example, by estimating the position of the tractor wheels 118 (block 404). This tractor wheel estimation may be performed as described above in connection with FIGS. 3A-9.

[0063] Geometrically, the trailer line 406 is located at a fixed calibration point (x o , y o ) to a two-dimensional trailer angle θ. Lateral and longitudinal offsets can be adjusted with this transformed two-dimensional angle. The trailer line indicates the orientation of the trailer 14 relative to the tractor 12. A reference point on the trailer 14 is determined by estimating the position of the trailer wheel 112, which may be, for example, the rearmost trailer wheel. This trailer wheel estimation can also be performed as described above in connection with FIGS. 3A-9.

[0064] The trajectory of the reference point (i.e., wheel trajectory or "WD curve" at 408 in FIG. 10) corresponds to the trailer wheel position 112 fitted as a parabola as shown in FIG. 11. The intersection of the trailer line with the trajectory of the reference point on the trailer (x i , y i ) (block 410) can be solved for the driver and / or passenger side wheel positions (at 412, 414 in FIG. 10).

[0065] The trailer end trajectory necessarily follows a predictable arc path behind the trailer wheel trajectory. t , y t) (block 416) also exists along the trailer line, the trailer end point determination step involves calculating the relationship between the intersection point and the trailer end point in the tractor longitudinal direction (y) and the tractor lateral direction (x). The trailer end trajectory is similar to the wheel trajectory, shifting (calibrated) Δy pixels upward in image space. Δy may vary between different trailers. The recognition line feature may use a default value for Δy, if desired, to simplify the calculation. That is, Δy may be input for a particular trailer, or may be determined according to any number of approaches, for example, as disclosed in U.S. Pat. No. 63 / 257,165, entitled "TRAILER END TRACKING IN A COMMERCIAL VEHICLE CAMERA MIRROR SYSTEM," which is incorporated herein by reference in its entirety. The intersection point, trailer line, and Δy may be combined to determine the relationship in the lateral direction (x t ) and vertical direction (y t ) can be calculated according to the following relationship:

number

[0066] Once the above relationships are determined, one or more trailer edge recognition lines may be displayed on one or more of displays 18a-18c within cabin 22. In the example shown in Figures 12-14, trailer edge recognition lines 500-506 are spaced apart from trailer edge point TE. During vehicle operation and articulation of trailer 14 relative to tractor 12, the displayed trailer edge recognition line(s) are adjusted according to changes in trailer angle θ determined based on the method described above. In this manner, the recognition lines are dynamically adjusted in both the lateral and longitudinal directions.

[0067] The amount of steering angle θ can be used to determine which trailer edge recognition lines are displayed to the driver and where they are displayed (i.e., on the driver-side and / or passenger-side displays 18a, 18b). For example, when the trailer angle is very small (i.e., the trailer is straight and approximately 0°), recognition lines are displayed on both the driver's and passenger's side, as shown in FIG. 12. In one example, a first trailer edge recognition line (500, 504) is used to indicate the trailer edge TE projected onto the ground as a horizontal line. A second trailer edge recognition line (502, 506) may be used behind the trailer edge TE, e.g., 30 meters, to assist the driver in overtaking vehicles or other objects in the lane or space adjacent to either side of the trailer 14. In one example, the first recognition line is displayed in a first color (e.g., red), and the second recognition line is displayed in a second color (e.g., yellow) different from the first color.

[0068] In another example, if one side of the trailer 14 is visible and the other side is not, only the recognition line for the visible side is displayed (FIGS. 13 and 14). The steering angle θ can be used to determine which side is visible and which side is not. Trailer edge recognition lines are displayed only on one side of the trailer for steering angles greater than 0° but less than a predetermined steering angle, for example. Trailer edge recognition lines are displayed only on the inside turning radius side of the trailer edge. The predetermined angle may be, for example, 10° or 15°. Trailer edge recognition lines are not displayed at all for steering angles greater than the predetermined steering angle. Knowing the trailer edge location while the trailer angle is small enhances driving safety in situations such as lane changes while driving straight on a highway, low light conditions, or heavy rain.

[0069] The disclosed method and system provides an approach for adjusting the lateral position of the recognition line at the end of the trailer based on the tractor-trailer angle, allowing the recognition line to be positioned at an appropriate lateral location for the driver's purposes of depth perception of surrounding vehicles.

[0070] While exemplary embodiments have been disclosed, those of ordinary skill in this art would recognize that certain modifications would come within the scope of the following claims, and for that reason the following claims should be studied to determine their true scope and content.

Claims

1. 1. A method of providing a trailer end line for a tractor trailer, comprising: Determining a fixed point on the tractor; determining a trailer angle of the trailer; determining a trailer line located at the trailer angle from the fixed point; determining an intersection of the trailer line with a trajectory of a reference point on the trailer; determining trailer end points along the trailer line and offset from the intersection point; and Displaying trailer edge recognition lines based on the determined trailer edge points. A method comprising:

2. The method of claim 1 , wherein determining the fixed point comprises estimating tractor wheel positions.

3. estimating the tractor wheel position identifying a first set of wheel positions within at least a first image, each wheel position within 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 within the first set of wheel positions; generating a best fit curve to be applied to the primary cluster, the best fit curve relating wheel position to trailer angle; responsive to a wheel being occluded in the first image, identifying an estimated wheel position by applying the determined trailer angle to the best fit curve; and outputting the estimated wheel positions to at least one additional vehicle system. The method of claim 2 , comprising:

4. The method of claim 1 , wherein determining the trailer angle includes using a trailer angle sensor, CMS image analysis, or a combination thereof.

5. 5. The method of claim 4, including adjusting the displayed trailer edge recognition line in response to changes in the determined trailer angle.

6. The method of claim 1 , wherein the reference points are determined by estimating trailer wheel positions.

7. The method of claim 6 , wherein the trajectory of reference points corresponds to the trailer wheel positions fitted as a parabola.

8. estimating the trailer wheel position includes: identifying a first set of wheel positions within at least a first image, each wheel position within 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 within the first set of wheel positions; generating a best fit curve to be applied to the primary cluster, the best fit curve relating wheel position to trailer angle; responsive to a wheel being occluded in the first image, identifying an estimated wheel position by applying the determined trailer angle to the best fit curve; and outputting the estimated wheel positions to at least one additional vehicle system. The method of claim 6, comprising:

9. 7. The method of claim 6, wherein determining the trailer end points includes calculating a relationship between the intersection point and the trailer end points in a tractor longitudinal direction y and a tractor lateral direction x.

10. The relationship is expressed by the formula [Equation 1] is calculated according to Here, x ｉ , y ｉ corresponds to the intersection of the wheels, and x ｔ , y ｔ 10. The method of claim 9, wherein θ corresponds to the trailer end point and θ corresponds to the steering angle.

11. The method of claim 10 , wherein the displayed trailer end recognition line is spaced from the trailer end point.

12. 2. The method of claim 1, wherein the trailer end recognition line is a first recognition line displayed in a first color and corresponds to a position of the trailer end projected onto the ground at a position below the trailer end, and wherein the displaying includes displaying a second recognition line in a second color different from the first color, the second recognition line corresponding to a position on the ground a distance behind the first recognition line.

13. 2. The method of claim 1, wherein the trailer edge recognition lines are displayed on only one side of the trailer for steering angles greater than 0 degrees and less than a predetermined steering angle.

14. The method of claim 13 , wherein the trailer end recognition lines are displayed only on the inside turning radius side of the trailer end.

15. 14. The method of claim 13, wherein the trailer edge recognition lines are displayed on both sides of the trailer for a steering angle of approximately 0°, and the trailer edge recognition lines are not displayed at all for steering angles above the predetermined steering angle.

16. 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 first view and a second view that is wider than the first view; a display configured to display the desired field of view; a controller in communication with the image capture unit and the display; Equipped with The controller Determining a fixed point on the tractor; determining a trailer angle of the trailer; determining a trailer line located at the trailer angle from the fixed point; determining an intersection of the trailer line with a trajectory of a reference point on the trailer; determining trailer end points along the trailer line and offset from the intersection point; and Displaying a trailer end recognition line on the display based on the determined trailer end points. a camera mirror system configured to:

17. 17. The system of claim 16, wherein the fixed point is determined by estimating tractor wheel position.

18. 17. The system of claim 16, wherein the trailer angle is determined using a trailer angle sensor, CMS image analysis, or a combination thereof.

19. 17. The system of claim 16, wherein the controller is configured to adjust the displayed trailer edge recognition line in response to changes in the determined trailer angle.

20. 17. The system of claim 16, wherein the reference point is determined by estimating trailer wheel positions.

Images