Centerline method for trailer hitch angle detection

Abstract

A system for detecting a coupling angle between a vehicle (14) and a trailer (12), comprising: an imaging device (34) configured to capture images of the trailer (12); a controller (38) designed to: Processing the captured images; Deriving an edge map and identifying trailer pixels therein; Defining a number of line candidates projecting from a common starting point in the edge mapping; and Determining the coupling angle based on an angle between a selected line candidate and a reference line; wherein the line candidates are derived based on a width of a vehicle rear bumper, a drawbar length, and a trailer length; wherein the reference line extends along a center column of the edge mapping and intersects a mapped coupling point between the vehicle (14) and the trailer (12).

Description

FIELD OF THE INVENTION

[0001] The present invention relates to trailer reversing assistance systems in general and, more particularly, to trailer reversing assistance systems that employ hitch angle detection by image processing. BACKGROUND OF THE INVENTION

[0002] Reversing a vehicle while towing a trailer can be challenging for many drivers, especially those who rarely tow a trailer or who tow multiple trailers. Some systems used to assist a driver in reversing a trailer rely on hitch angle measurements to determine the trailer's position relative to the vehicle. Thus, the accuracy and reliability of the hitch angle measurements can be critical to the operation of the trailer reversing assistance system.

[0003] DE 10 2004 050 149 A1 describes a method for determining at least one drawbar angle and one trailer angle of a trailer of an articulated vehicle, in which characteristic edges and lines of at least the drawbar and the front of the trailer are determined from a video stream of an imaging sensor, from whose geometric relationships and / or relative position to one another at least the drawbar angle and the trailer angle of the trailer are determined.

[0004] US 2014 / 0 324 295 A1 describes a system and method for monitoring a hitch angle. A screen displays an image scene of a trailer connection between a towing vehicle and a trailer, with a processor configured to superimpose a hitch angle limit on the image scene. A hitch angle position indicator is displayed on the screen and visually relates a current hitch angle to the hitch angle limit.

[0005] JP 2003-148938 A discloses a device for detecting a connection angle between a towing vehicle and a trailer. For this purpose, a video camera is mounted on the towing vehicle and captures images of the edge of the towed vehicle. An image processing device processes the video camera output signal to highlight the edge line. An identification device identifies angle information between the edge line highlighted by the image processing device and a pre-stored reference line and transmits this information as an electrical signal.

[0006] DE 10 2011 113 191 A1 describes a method and a device for determining a bending angle between a towing vehicle and a trailer. An image of the trailer is captured using an image capture device. The captured image is evaluated using image data analysis, and a bending angle is determined based on the image data analysis. SUMMARY OF THE INVENTION

[0007] According to one aspect of the present invention, a system for detecting a hitch angle between a vehicle and a trailer is provided. An imaging device is configured to capture images of the trailer, and a controller is configured to process the captured images. The controller derives an edge map and identifies trailer pixels therein. The controller defines a number of line candidates in the edge map, the lines projecting from a common origin, and determines the hitch angle based on an angle between a selected line candidate and a reference line. The line candidates are derived based on a width of a vehicle rear bumper, a drawbar length, and a trailer length. The reference line extends along a center column of the edge map and intersects a mapped hitch point between the vehicle and the trailer.

[0008] According to another aspect of the present invention, a method for detecting a hitch angle between a vehicle and a trailer is provided. The method includes the steps of capturing images of the trailer using an imaging device and providing a controller for processing the captured images. The controller derives an edge map and identifies trailer pixels therein. The controller generates a number of line candidates in the edge map, the line candidates projecting from a common starting point, and determines the hitch angle based on an angle between a selected line candidate and a reference line. The line candidates are derived based on a width of a vehicle rear bumper, a drawbar length, and a trailer length.The reference line extends along a center column of the edge mapping and intersects a mapped coupling point between the vehicle and the trailer.

[0009] These and other features, advantages and objects of the present invention will be better understood and appreciated by those skilled in the art by reference to the following description, claims and appended drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In the drawings: Fig. 1 is a top perspective view of a trailer mounted on a vehicle having one embodiment of a hitch angle sensor for operating a trailer backup assist system; Fig. 2 is a block diagram illustrating an embodiment of the trailer backup assist system including a steering input device, a turn control, and a trailer braking system; Fig. 3 is a flowchart for a method for detecting a hitch angle according to one embodiment. Fig. Figure 4 is a captured image showing a trailer in straight alignment with a vehicle and the presence of ground disturbances; Fig. 5 is an edge mapping of the recorded image Fig. 4 shown image; Fig. Figure 6 illustrates the blurring of ground disturbances in an averaged image; Fig. 7 is an edge mapping of the averaged Fig. 6 shown image; Fig. 8 illustrates a pendant outline of a sample image; Fig. 9 illustrates a pattern image being matched with a search image to determine a hitch angle; Fig. 10 is a search image having a proximity zone for collapse detection and a number of candidate hitch point locations around which a template image can be rotated to determine an actual imaged hitch point and a hitch angle; Fig. 11 is a flowchart for a method of detecting a hitch angle according to another embodiment; Fig. 12 is an edge map of a captured image showing a number of candidate lines, one of which is selected to determine a hitch angle based on its angular position relative to a reference line; Fig. 13 is a flowchart for a method for locating a mapped hitch point according to one embodiment; Fig. 14 and Fig. 15 are respectively captured images in which a trailer appears at a particular coupling angle and a detection window is used to scan an imaged drawbar to locate an imaged coupling point; and Fig. Figure 16 is a graph showing averaged pixel differences for a number of common pixel positions in the acquired images taken in Fig. 14 and Fig. 15 are shown. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] For the purposes of the description herein, it is to be understood that the disclosed trailer backup assist system and related methods are capable of various alternative embodiments and orientations, unless expressly stated to the contrary. Further, it is to be understood that the specific devices and processes illustrated in the appended drawings and described in the following description are simply embodiments of the inventive concepts defined in the appended claims. Although various aspects of the trailer backup assist system and related methods are described with reference to a particular illustrated embodiment, the disclosed invention is not limited to such embodiments, and additional modifications, applications, and embodiments may be practiced without departing from the disclosed invention.Therefore, specific dimensions and other physical characteristics relating to the embodiments disclosed herein are not to be considered limiting unless expressly stated to the contrary in the claims.

[0012] As used herein, the term "and / or," when used in a list of two or more elements, means that each of the listed elements may be employed alone or in any possible combination of two or more of the listed elements. For example, if a composition is described as containing components A, B, and / or C, the composition may contain A alone; B alone; C alone; A and B in combination; A and C in combination; B and C in combination; or A, B, and C in combination.

[0013] With reference to the Fig. 1 and Fig. 2, reference numeral 10 generally designates a trailer backup assist system for controlling a backup path of a trailer 12 attached to a vehicle 14 by allowing a driver of the vehicle 14 to specify a desired curved path of the backup path of the trailer 12. The vehicle 14 is implemented as a pickup truck pivotally mounted to an embodiment of the trailer 12 having a box frame 16 with an enclosed cargo area 18, a single axle 20 operably coupled to wheels 22 and 24, and a tongue 26 extending longitudinally forward from the enclosed cargo area 18. The illustrated trailer 12 also includes a trailer hitch connector in the form of a coupling assembly 28 connected to a vehicle hitch connector in the form of a hitch ball 30 and a drawbar 31.The coupling assembly 28 engages the hitch ball 30 to create a coupling pivot point 32 that allows for articulation of a hitch angle between the vehicle 14 and the trailer 12. As defined herein, the hitch angle corresponds to the angle formed between the centered longitudinal axis of the vehicle 14 and that of the trailer 12. It is understood that additional embodiments of the trailer 12 may alternatively be coupled to the vehicle 14 to provide a pivoting connection, such as by connecting to a fifth wheel connection. It is also contemplated that additional embodiments of the trailer 12 may include more than one axle and may have various shapes and sizes configured for different loads and objects, such as a boat trailer or a flatbed trailer.

[0014] The trailer backup assist system 10 includes an imaging device 34 located at the rear of the vehicle 14 and configured to image a rear vehicle scene. The imaging device 34 may be centrally located in an upper portion of the tailgate 35 such that the imaging device 34 is raised relative to the tongue 26 of the trailer 12. The imaging device 34 has a field of view 36 positioned and oriented to capture one or more images, which may include, among other things, the tongue 26 of the trailer 12 and the hitch ball 30. Captured images are provided to a controller 38 of the trailer backup assist system 10 and are processed by the controller 38 to determine the hitch angle between the vehicle 14 and the trailer 12, as will be described in more detail herein.The controller 38 is configured with a microprocessor 40 and / or other analog and / or digital circuitry for processing one or more logic routines stored in a memory 42. The logic routines may include one or more hitch angle detection routines 44 and operational routines 46. Information from the imaging device 34 or other components of the trailer backup assist system 10 may be provided to the controller 38 via a communications network of the vehicle 14, which may include a controller area network (CAN), a local area network (LIN), or other conventional protocols used in the automotive industry.It is understood that the controller 38 may be a standalone, dedicated controller, or a common controller integrated with the imaging device 34, or another component of the trailer backup assist system 10, in addition to any other conceivable onboard or off-board vehicle control systems.

[0015] With respect to the present embodiment, the controller 38 of the trailer backup assist system 10 may be configured to communicate with a variety of vehicle equipment. The trailer backup assist system 10 may include a vehicle sensor module 48 that monitors certain dynamics of the vehicle 14. The vehicle sensor module 48 may generate a plurality of signals communicated to the controller 38, which may include a vehicle speed signal generated by a speed sensor 50 and a vehicle yaw rate signal generated by a yaw rate sensor 52. A steering input device 54 may be provided to enable a driver to control or otherwise modify the desired curvature of the trailer 12's backup path.The steering input device 54 may be communicatively coupled to the controller 38 in a wired or wireless manner and provides the controller 38 with information defining the desired curvature of the return path of the trailer 12. In response, the controller 38 processes the information and generates corresponding steering commands, which are provided to a power steering system 56 of the vehicle 14. In one embodiment, the steering input device 54 includes a rotary knob 58 operable between a number of rotational positions, each providing an incremental change in the desired curvature of the return path of the trailer 12.

[0016] According to one embodiment, the controller 38 of the trailer backup assist system 10 may control the power steering system 56 of the vehicle 14 to operate the steerable wheels 60 of the vehicle 14 to move the vehicle 14 such that the trailer 12 responds in accordance with the desired curvature of the trailer's 12 reversing path. The power steering system 56 may be an electric power-assisted steering (EPAS) system that includes an electric steering motor 62 for turning the steerable wheels 60 to a steering angle based on a steering command generated by the controller 38, wherein the steering angle may be sensed by a steering angle sensor 64 of the power steering system 56 and provided to the controller 38. The steering command may be provided for autonomous steering of the vehicle 14 during a reversing maneuver and may alternatively be manually controlled via a rotational position (e.g.,a steering wheel angle) of a steering wheel 66 or a rotary knob 58. However, in some embodiments, the steering wheel 66 of the vehicle 14 is mechanically coupled to the steered wheels 60 of the vehicle 14 such that the steering wheel 66 moves in concert with the steered wheels 60 via an intrinsic torque, thereby preventing manual intervention via the steering wheel 66 during autonomous steering of the vehicle 14. In such cases, the power steering system 56 may include a torque sensor 68 that detects torque (e.g., gripping and / or slipping) at the steering wheel 66 that is not expected from autonomous control of the steering wheel 68 and thus indicates manual intervention by the driver.In some embodiments, the external torque applied to the steering wheel 66 may serve as a signal to the controller 38 that the driver has assumed manual control and for the trailer backup assist system 10 to terminate the autonomous steering functionality.

[0017] The controller 38 of the trailer backup assist system 10 may also communicate with a vehicle braking control system 70 of the vehicle 14 to receive vehicle speed information, such as individual wheel speeds of the vehicle 14. Additionally or alternatively, vehicle speed information may be provided to the controller 38 from, among other sources, a powertrain control system 72 and / or the speed sensor 50. It is contemplated that individual wheel speeds may be used to determine a vehicle yaw rate, which may be provided to the controller 38 alternatively or in addition to the vehicle yaw rate measured by the yaw rate sensor 52 of the vehicle sensor module 48. In some embodiments, the controller 38 may provide braking commands to the braking control system 70, thereby enabling the trailer backup assist system 10 to regulate the speed of the vehicle 14 during a backing maneuver of the trailer 12.It is understood that the controller 38 may additionally or alternatively control the speed of the vehicle 14 via interaction with the powertrain control system 72.

[0018] By interacting with the power steering system 56, the vehicle brake control system 70, and / or the powertrain control system 72 of the vehicle 14, the potential for unacceptable trailer backing conditions may be reduced. Examples of unacceptable trailer backing conditions include, but are not limited to, a vehicle-too-fast condition, a high hitch angle rate, dynamic hitch angle instability, a trailer collapse condition, sensor failure, and the like. Under such circumstances, the driver may not be aware of the failure until the unacceptable trailer backing condition is imminent or already in progress.Thus, it is disclosed herein that the controller 38 of the trailer backup assist system 10 may generate a warning signal corresponding to a notification of an incipient, impending, and / or anticipated unacceptable trailer backup condition and may generate a countermeasure to prevent such an unacceptable trailer backup condition prior to driver intervention.

[0019] According to one embodiment, the controller 38 may communicate with one or more devices, including a vehicle warning system 74, which may provide visual, audible, and tactile warnings. For example, vehicle brake lights 76 and vehicle hazard warning flashers may provide a visual warning, and a vehicle horn 78 and / or speakers 80 may provide an audible warning. Additionally, the controller 38 and / or the vehicle warning system 74 may communicate with a human-machine interface (HMI) 82 for the vehicle 14. The HMI 82 may include a touchscreen vehicle display 84, such as a center console-mounted navigation or entertainment display, capable of displaying images indicative of the warning. Such an embodiment may be desirable to notify the driver of the vehicle 14 that an unacceptable trailer backing condition is in progress.It is further contemplated that the controller 38 may communicate via wireless communication with one or more portable electronic devices, such as the portable electronic device 86 implemented as a smartphone. The portable electronic device 86 may include a display 88 for displaying one or more images and other information to a user. In response, the portable electronic device 86 may provide feedback information, such as visual, audible, and tactile alerts.

[0020] Referring to Fig. 3 illustrates a method for detecting a hitch angle. The method, also referred to herein as "the pattern matching method," may be executed by the controller 38 of the trailer backup assist system 10 and is shown as one embodiment of the hitch angle detection routine 44. The pattern matching method generally involves processing image information to distinguish a trailer contour from ground disturbances in images captured by the imaging device 34. The trailer contour then serves as a pattern and is matched to a search image to determine the hitch angle between the vehicle 14 and the trailer 12.

[0021] For illustrative purposes, Fig. 4 shows, by way of example, a captured image 90 illustrating the trailer 12 in a straight alignment with the vehicle 14 and the presence of ground disturbances. As defined herein, ground disturbances generally correspond to any ground structure capable of interfering with the image capture of the trailer 12. With regard to the captured image 90, candidate disturbances may include large stones (e.g., stone 92) and irregular ground surfaces (e.g., ground surface 94). As such, it may be difficult to accurately identify the trailer 12 when an image capture technique, namely edge detection, is applied to the captured image 90, as exemplified in Fig. 5. With these things in mind, the pattern matching method described here is capable of blurring ground disturbances to enable identification of one or more trailer contours. Once identified, the trailer contour(s) can be stored as a pattern image, which is matched to a search image to determine the coupling angle between the vehicle 14 and the trailer 12. In practice, this method has been found to be highly robust and benefits from relatively fast and simple calculations.

[0022] The pattern matching process may begin at step 100, where the driver or other occupant initializes the trailer backup assist system 10. This may be accomplished via user input using the display 84 of the vehicle 14 or by other conceivable means. At step 110, the driver is instructed to pull the trailer 12 in a straight direction so that the hitch angle between the vehicle 14 and the trailer 12 is substantially zero. While the vehicle 14 and the trailer 12 are locked in the straightening maneuver, at step 120, the controller 38 derives an averaged image of all images captured by the imaging device 34 during a period of time. It has been found that typically 1-3 seconds is sufficient. Note that the trailer 12 appears stationary within the images captured by the imaging device 34, whereas the ground disturbances vary from image to image.Thus, pixels associated with the trailer 12 will retain their contrast with respect to the averaged image, whereas pixels associated with the ground disturbances will be blurred. To illustrate this effect, . Fig. 6 shows an averaged image 125 as an example.

[0023] At step 130, the controller 38 derives an edge map of the averaged image by calculating the intensity gradient for each pixel of the averaged image 125. The intensity gradient, or edge value, of each pixel can range from 0 to 255. For illustrative purposes, Fig. 7 shows, by way of example, an edge map 135 in which the edge values ​​of pixels associated with ground disturbances have been significantly attenuated due to the blurring effect. At step 140, the controller 38 compares the edge value of each pixel of the edge map 135 to a threshold value (e.g., 30). Pixels with an edge value that meets or exceeds the threshold are identified as trailer pixels, whereas pixels with an edge value that does not meet or exceed the threshold are identified as ground disturbance pixels. Once the trailer pixels have been identified, the controller 38 determines one or more trailer contours at step 150. The trailer contour(s) is / are stored in the memory 42 of the controller 38 as a sample image at step 160 and may include a substantial entirety of the imaged trailer 12 or portions thereof. For illustrative purposes, Fig. 8, a trailer contour 152 is shown. As shown, the trailer contour 152 has a rectangular shape, which is generally more computationally efficient. In its current position, the trailer contour 152 can serve as a zero hitch angle reference and allows the hitch angle between the vehicle 14 and the trailer 12 to be determined in subsequent images (i.e., search images) via pattern matching at step 170.

[0024] According to one embodiment, as in Fig. 9, the hitch angle between the vehicle 14 and the trailer 12 may be determined based on a positional relationship between a template image 158 and a search image 171. In particular, the hitch angle may be determined by overlaying the template image 158 over the search image 171 such that the template image 158 is initially in a zero hitch angle position, and then rotating the template image 158 about a pivot point, preferably about the mapped hitch point 172. The direction of rotation may be predicted based on information received from the steering angle sensor 64 or other sensors, from which an initial assessment may be made regarding the angular position of the trailer 12 relative to the vehicle 14.Once the pattern image 158 has been matched to the search image 171, the angle θ by which the pattern image 158 is rotated relative to the zero hitch angle position can be correlated with the hitch angle between the vehicle 14 and the trailer 12.

[0025] According to one embodiment, the mapped coupling point 172 may be determined using an elimination process. For example, the controller 38 may, as exemplified in Fig. 10, define a number of hitch point location candidates 173a-173d positioned along a reference line 174 extending vertically across the center column of the search image 171. The reference line 174 is defined by the controller 38 and is assumed to coincide with the central longitudinal axis of an imaged drawbar 175 and to intersect the hitch point 172 of the imaged vehicle 14 and trailer 12. The hitch point location candidates 173a-173d are shown as evenly spaced along the reference line 174, but may vary in number and spacing in other embodiments.Once the template image 158 has been derived and the vehicle 14 and trailer 12 are moving along a curvilinear trajectory, the controller 38 may overlay the template image 158 on the search image 171 at the zero hitch angle position and rotate the template image 158 around each of the hitch point location candidates 173a-173d in an attempt to match the template image 158 to the search image 171. Based on the matching quality, each hitch point location candidate 173a-173d is given a confidence score, and the hitch point location candidate 173a-173d receiving the highest confidence score is selected as the hitch point.In the event that the matching quality associated with each hitch point location candidate 173a-173d is below a predetermined threshold, the controller 38 may define additional hitch point location candidates (not shown) along the reference line 174 in one or both directions from the hitch point location candidate 173a-173d that received the highest confidence rating and perform pattern matching with respect to each of the additional hitch point location candidates. This process may be iterated as many times as necessary until the predetermined threshold is met. By doing so, the location of the hitch point location candidate ultimately selected as the mapped hitch point will accurately reflect the location of the actual hitch point 172.

[0026] During the comparison of the pattern image 158 with the search image 171, the controller 38 may additionally determine the occurrence of an impending collapse scenario at step 180. Further referring to Fig. 10, the displacement of the pattern image 158 relative to a proximity zone 182 may be monitored while the pattern image 158 is rotated about the pivot point. In the illustrated embodiment, the proximity zone 182 may be defined as the space between an imaged rear bumper 184 of the vehicle 14 and a boundary line 186 defined by the controller 38 and superimposed on the search image 171. The boundary line 186 may be V-shaped and include a pair of straight segments 188 extending outward at an angle from a point 189 located on the reference line 174 and disposed between the imaged hitch point 172 and the imaged rear bumper 184. It should be understood that the boundary line 186 may take other shapes in alternative embodiments.The location and shape of the boundary line 186 can be determined based on various factors, including, but not limited to, vehicle speed, trailer length, drawbar length, imager characteristics, trailer contour, and vehicle contour. It is generally assumed that the vehicle speed, trailer length, drawbar length, and imager characteristics are known or otherwise measured and input into the trailer backup assist system 10. A vehicle contour, such as that of the depicted rear bumper 184, may be programmed at the factory.

[0027] If the pattern image 158 extends into the proximity zone 182 of the search image 171, the controller 38 determines at step 190 that an impending collapse scenario exists and initiates a collapse countermeasure. Otherwise, if it is determined that no impending collapse scenario exists, the controller 38 may proceed to determine the hitch angle between the vehicle 14 and the trailer 12, as previously discussed with reference to step 170. The collapse countermeasure may include generating an audible warning via the vehicle warning system 74, generating a visual warning via the display 84, generating a braking command to the vehicle braking control system 70, reducing the torque of the powertrain control system 72, modifying the steering angle of the vehicle 14, or a combination thereof, in addition to any other conceivable countermeasures.Because the trailer 12 is likely to be moving when the controller 38 determines that an impending collapse scenario is present, it is generally desirable to locate and size the proximity zone 182 in a manner that allows sufficient time to detect a collapse scenario, thereby minimizing the potential for an actual collapse and / or collision between the trailer 12 and the vehicle 14. Doing so also overcomes any response latency that may be inherent in the trailer backup assist system 10. Although steps 170 and 180 have been illustrated in a linear manner, it should be understood that both steps may be performed concurrently.

[0028] Referring to Fig. 11 illustrates another method for detecting a hitch angle. This method, also referred to herein as the "centerline method," may be executed by the controller 38 of the trailer backup assist system 10 and is shown as an exemplary embodiment of the hitch angle detection routine 44. The centerline method also utilizes image information obtained by processing images captured by the imaging device 34 to determine the hitch angle between the vehicle 14 and the trailer 12.The centerline method differs from the pattern matching method in that the vehicle 14 and trailer 12 do not need to be moving in a straight line prior to hitch angle detection, thus making the centerline method particularly useful in cases where no pattern image for the trailer 12 is available and the driver is prevented from pulling the trailer 12 in a straight line. Compared to the pattern matching method, the centerline method benefits from faster processing times, but is generally less reliable. Therefore, the centerline method can be said to provide a quick start for hitch angle detection and can be replaced at a later time by the pattern matching method or other suitable methods that provide more reliable hitch angle measurements.Thus, for illustrative purposes, the centerline method will be described in more detail below, assuming that no template image is available and that the vehicle 14 and trailer 12 are initially traveling on a curving trajectory.

[0029] The centerline method may begin at step 200, where the controller 38 processes successive images captured by the imaging device 34 to derive an averaged image. At step 210, the controller 38 derives an edge map by calculating an intensity gradient, or edge value, for each pixel in the averaged image. At step 220, the controller 38 identifies tag pixels in the edge map as corresponding to tag pixels by comparing the edge values ​​of each pixel to a threshold and selecting only the pixels that meet or exceed the threshold. For illustrative purposes, Fig. 12, an edge map 222 is shown by way of example in which an embodiment of the depicted trailer 12 appears slightly blurred as a result of an angular displacement of the trailer 12 relative to the vehicle 14. It is contemplated that additional thresholds may be used to distinguish between trailer pixels and vehicle pixels, since vehicle pixels generally have a higher degree of contrast relative to trailer pixels due to the blurring of the trailer 12. At step 230, the controller 38 defines a number of line candidates in the edge map 222, as exemplified in Fig. 12. The line candidates protrude from a common starting point, preferably the mapped hitch point 232. The direction in which the line candidates protrude may vary based on a width of the rear bumper of the vehicle 14, a length of the drawbar of the vehicle 14, and a length of the tongue of the trailer 12. In the illustrated embodiment, the line candidates may vary from -90 degrees to 90 degrees with respect to a reference line 234 indicating a predetermined hitch angle (e.g., a zero hitch angle) and extending vertically across the center column of the edge map 222 and intersecting the mapped hitch point 232. Although the exact location of the mapped hitch point 232 may initially be unknown, the controller 38 may define a default starting point from which the line candidates protrude.Since the hitch point 232 is assumed to be typically located along the reference line 234 and usually falls within a predictable distance (e.g., 10-20 centimeters from the rear bumper of the vehicle 14), the selection of a standard starting point that meets the above criteria is generally sufficient for the purposes of initial hitch angle detection.

[0030] At step 240, the controller 38 selects the line candidate (e.g., line candidate 242) that has approximately the same number of trailer pixels on each of its sides, or in other words, the line candidate, or centerline, about which the trailer pixels are substantially symmetrical. Once the controller 38 has made a line candidate selection, at step 250, the controller 38 may determine the hitch angle between the vehicle 14 and the trailer 12 based on the angular position of the selected line candidate 242 relative to the reference line 234. In particular, the angle θ between the line candidate 242 and the reference line 234 may be correlated with the hitch angle between the vehicle 14 and the trailer 12.As the vehicle 14 and trailer 12 continue along their course, steps 200-250 may be iterated with subsequent images captured by the imaging device 34 to continuously provide further hitch angle measurements.

[0031] With reference to Fig. 13 illustrates a method for locating a mapped hitch point in images captured by the imaging device 34. The method, also referred to herein as "the drawbar scanning method," may be performed by the controller 38 of the trailer backup assist system 10 and may be implemented as a subroutine of the hitch angle detection routine 44. The drawbar scanning method generally requires the trailer 12 to move relative to the vehicle 14 at a non-zero hitch angle to identify a mapped hitch point. As such, the drawbar scanning method may be performed to provide a suitable pivot point or origin point when performing the centerline method or the pattern matching method in instances where the vehicle 14 and trailer 12 are traveling along a curvilinear trajectory.By identifying the mapped coupling point, more accurate coupling angle measurements can be achieved.

[0032] The drawbar scanning method generally begins at step 300, where the controller 38 selects two images captured by the imaging device 34 showing the trailer 12 at different hitch angles. The two images may be consecutive or non-consecutive, depending on the frame rate of the imaging device 34. In practice, a discernible difference in hitch angles between the two images is generally preferred. At step 310, the controller 38 derives an edge map by calculating the intensity gradient, or edge value, for both images for each of their corresponding pixels. For illustrative purposes, Fig. 14 a first image 312 in which the coupling angle between the vehicle 14 and the trailer 12 is approximately zero, whereas Fig. 15 shows a second image 314 in which the coupling angle between the vehicle 14 and the trailer 12 is approximately 5 degrees relative to the Fig. 14. For clarity, the edge maps associated with both images 312, 314 are not shown. At step 320, the controller 38 defines a detection window 322 of variable height and width in both images 312, 314. Each detection window 322 is centered at a common pixel position, such as pixel position 324, located on a reference line 326 extending vertically across the center column of the corresponding image 312, 314. The reference line 326 is defined by the controller 38 and is assumed to coincide with the central longitudinal axis of an imaged drawbar 327 and to intersect an imaged coupling point 328 between the vehicle 14 and the trailer 12.

[0033] At step 330, the controller 38 determines an average pixel intensity of the pixels bounded by each detection window 322 when centered at the current pixel position, and at step 340, the controller 38 calculates an average pixel difference, defined here as the absolute value of the difference between the average pixel intensities calculated at step 330. Once the average pixel difference has been calculated, at step 350, the controller 38 translates each detection window 322 in an upward vertical direction (as specified by arrow 342) such that each detection window 322 is collectively centered at a new pixel position that is one or more pixel positions higher than the previous pixel position on the corresponding reference line 326.Thus, by performing multiple iterations of steps 330-350, the controller 38 can calculate averaged pixel differences for when each detection window 322 is collectively centered at a number of pixel positions along the reference line 326. Once this is done, at step 360 the controller 38 extrapolates the location of the coupling point 328 based on variations in the calculated averaged pixel differences.

[0034] With respect to Figures 312, 314, it is generally expected that little variation will occur between the calculated mean pixel differences associated with pixel positions that coincide with the depicted drawbar 327, in part because the depicted drawbar 327 appears in a common fixed position in both images 312, 314. In contrast, it is generally expected that greater variation will occur between the calculated mean pixel differences associated with pixel positions located on portions of the reference line 326 that extend beyond the depicted drawbar 327, in part because the trailer 12 appears in different positions in both images 312, 314. For illustrative purposes, Fig. 16 shows a graph illustrating calculated average pixel differences for a number of pixel positions along the vertical reference line 326. The pixel positions may fall within a predetermined distance at which the mapped clutch point 328 is expected to be located, thereby eliminating the need to determine averaged pixel differences for pixel positions along the vertical reference line 326 that are unlikely to correspond to the mapped clutch point 328.

[0035] As in Fig. 16, the graph generally demonstrates a relatively constant mean pixel difference between 2 and 3 when each detection window 322 is centered together at pixel positions 0-44, since these pixel positions coincide with the depicted drawbar 327. In contrast, the graph in Fig. 16 generally shows a large increase in mean pixel differences when each detection window 322 is collectively centered at pixel positions 46-70, because these pixel positions are located on portions of the reference line 326 that extend beyond the mapped drawbar 327. When the controller 38 detects this, it may select one of the pixel positions (e.g., pixel position 44 or 45) as the mapped hitch point 328, resulting in the large increase in mean pixel differences. According to one embodiment, the controller 38 may iterate steps 330-350 of the drawbar scanning method until the mean pixel difference meets or exceeds a predetermined threshold (e.g., 3.5) and select the pixel position associated with the calculated mean pixel difference that meets or exceeds the threshold as the mapped hitch point.This threshold may be determined based on a number of considerations, including, but not limited to, the size of the detection window 322, characteristics of the imaging device 34, etc. Once identified, the selected imaged hitch point should reflect the actual imaged hitch point 328 and may be used for hitch angle detection using the pattern matching method or the centerline method. Key to symbols

[0036] Fig. 2 10 TRAILER REVERSING ASSISTANCE SYSTEM 34 IMAGING DEVICE 38 CONTROL 40 MICROPROCESSOR 42 STORAGE 44 CLUTCH ANGLE DETECTION ROUTINE 46 OPERATION ROUTINE 48 VEHICLE SENSOR MODULE 50 SPEED SENSOR 52 Yaw Rate Sensor 54 STEERING INPUT DEVICE 56 POWER STEERING SYSTEM 58 ROTARY KNOB 62 ELECTRIC STEERING MOTOR 64 STEERING ANGLE SENSOR 68 TORQUE SENSOR 70 VEHICLE BRAKE CONTROL SYSTEM 72 POWERTRAIN CONTROL SYSTEM 74 VEHICLE WARNING SYSTEM 76 BRAKE LIGHTS 78 HORN 80 SPEAKERS 82 VEHICLE MMS

Claims

[1] A system for detecting a coupling angle between a vehicle (14) and a trailer (12), comprising: an imaging device (34) configured to capture images of the trailer (12); a controller (38) designed to: Processing the captured images; Deriving an edge map and identifying trailer pixels therein; Defining a number of line candidates projecting from a common starting point in the edge mapping; and Determining the coupling angle based on an angle between a selected line candidate and a reference line; wherein the line candidates are derived based on a width of a vehicle rear bumper, a drawbar length, and a trailer length; wherein the reference line extends along a center column of the edge mapping and intersects a mapped coupling point between the vehicle (14) and the trailer (12). [2] The system of claim 1, wherein the controller (38) processes successive images acquired by the imaging device (34) to derive an averaged image and derives the edge mapping by calculating an edge value for each pixel in the averaged image. [3] The system of claim 2, wherein the controller (38) identifies tag pixels by comparing the edge value of each pixel within the edge map to a threshold and selecting those pixels that exceed the threshold as corresponding to tag pixels. [4] The system of claim 1, wherein the starting point corresponds to a mapped coupling point between the vehicle (14) and the trailer (12). [5] The system of claim 1, wherein the starting point corresponds to a standard starting point and is located in the edge mapping at a location where a mapped coupling point between the vehicle (14) and the trailer (12) is believed to be located. [6] A system according to any one of claims 1 to 5, wherein the reference line indicates a predetermined coupling angle. [7] The system of any of claims 1 to 6, wherein the selected line candidate corresponds to any line candidate having approximately the same number of tag pixels on each of its sides. [8] A method for detecting a coupling angle between a vehicle (14) and a trailer (12), comprising the following steps: Capturing images of the trailer (12) using an imaging device (34); Providing a controller (38) for: Processing the captured images; Deriving an edge map and identifying trailer pixels therein; Defining a number of line candidates projecting from a common starting point in the edge mapping; and Determining the coupling angle based on an angle between a selected line candidate and a reference line; wherein the line candidates are derived based on a width of a vehicle rear bumper, a drawbar length, and a trailer length; wherein the reference line extends along a center column of the edge mapping and intersects a mapped coupling point between the vehicle (14) and the trailer (12). [9] The method of claim 8, wherein the controller (38) processes successive images acquired by the imaging device (34) to derive an averaged image and derives the edge mapping by calculating an edge value for each pixel in the averaged image. [10] The method of claim 9, wherein the controller (38) identifies tag pixels by comparing the edge value of each pixel within the edge map to a threshold and selecting those pixels that exceed the threshold as corresponding to tag pixels. [11] The method of claim 8, wherein the starting point corresponds to a mapped coupling point between the vehicle (14) and the trailer (12). [12] The method of claim 8, wherein the starting point corresponds to a standard starting point and is located in the edge mapping at a location where a mapped coupling point between the vehicle (14) and the trailer (12) is assumed to be located. [13] A method according to any one of claims 8 to 12, wherein the reference line indicates a predetermined coupling angle. [14] A method according to any one of claims 8 to 13, wherein the selected line candidate corresponds to any line candidate having approximately the same number of tag pixels on each of its sides.

Images