JPWO2021197650A5 - - Google Patents

Description

FIELD OF THE INVENTION The present invention relates generally to the field of vehicle assistance systems. More specifically, the present invention relates to a method for calculating the yaw angle of a trailer connected to a towing vehicle based on image information provided by a camera on the vehicle.

Several methods are known for calculating the angle of a trailer relative to a towing vehicle based on image information provided by a vehicle's camera.

Particularly when the images are of low quality, methods are known that are less computationally complex but do not provide robust angle information. Additionally, in known methods, the exact position of the tow ball (a type of traction device) must be known in order to determine the yaw angle.

It is an object of embodiments of the invention to provide a method for calculating the yaw angle of a trailer with high robustness and high reliability without knowing the position of the towball . This object is solved by the features of the independent claims. Preferred embodiments are set out in the dependent claims. Unless stated otherwise, embodiments of the invention are free to be combined with each other.

According to one aspect , the invention relates to a method for determining the yaw angle of a trailer relative to the longitudinal axis of a towing vehicle. This method comprises the following steps.

First, at least first and second images of the trailer are captured using a camera. The first and second images are taken such that the orientation of the trailer with respect to the vehicle is different on at least two images.

After taking the images, at least a first characteristic of the trailer is determined. The first feature must be visible in the first and second images. The first feature may be , for example, the first feature that is prominent at the first location of the trailer.

After determining that feature, a ray is set between the camera and the determined first feature on the first image, and said ray is projected onto a horizontal plane, thereby causing the first projected feature position (of the projected feature). 1st position ) is obtained. Similarly, a ray is established between the camera and the determined first feature on the second image, and said ray is projected onto said horizontal plane, thereby obtaining a second projected feature position . The projection of said features may each be carried out in the vertical direction of the rays , ie the oblique rays may be transferred to the horizontal rays without changing the azimuth.

Based on the projection of the first feature, a first perpendicular bisector is established between the location of the first projected feature location and the location of the second projected feature location . More specifically, the first perpendicular bisector is a perpendicular straight line passing through the center of the line connecting the intersection of the first ray and the horizontal plane (for example, z=1) and the location of the intersection of the second ray and the horizontal plane. It can be. The first ray is determined by converting the image coordinates of the first feature in the first image into an optical ray using camera calibration information. The second ray is determined by converting the image coordinates of the first feature in the second image into an optical ray using camera calibration information. The first perpendicular bisector may be set within a horizontal plane.

After setting the first perpendicular bisector, a first intersection between the first perpendicular bisector and the reference axis is determined . The reference axis may be the central longitudinal axis of the vehicle on which both the camera and the towball are located. This intersection therefore represents the center of rotation of the first feature.

Finally, the yaw angle of the trailer is calculated based on a first angle estimate, the first angle estimate being the first angle estimate that is continuous from the first projected feature position to the first intersection in the horizontal plane. The angle between the first line and a second line that continues from the second projected feature position to the first intersection point is used as a reference.

The method comprises: setting one or more perpendicular bisectors and calculating a yaw angle based on one or more said perpendicular bisectors; The use of one or more trailer features is advantageous because the detection of trailer features can be performed very accurately and robustly even in the case of high noise or low quality images. Additionally, since a perpendicular bisector is used to determine the yaw angle, the exact location of the tow ball may not be known.

According to one embodiment, the yaw angle of the trailer relative to the vehicle is zero on the first or second image. This allows the image to be used as a "zero pose image ", ie a reference for accurate alignment of the longitudinal axis of the vehicle and the longitudinal axis of the trailer. However , other yaw angle values can also be used as a reference. If the other yaw angle is not known , the system may calculate the change in trailer angle rather than the absolute trailer angle.

According to one embodiment, the method further comprises the following steps.
Determining a second feature of the trailer visible in the first and second images in addition to the first feature. The second feature is in a different location on the trailer than the first feature. The second feature may be , for example, a second feature that is prominent at a second location on the trailer.
Additionally, a ray of light between the camera and the determined second feature on the first image is projected onto the horizontal plane, thereby obtaining a third projected feature position . Similarly, a ray of light between the camera and the determined second feature on the second image is projected onto the horizontal plane, thereby also obtaining a fourth projected feature position .
Further , setting a second perpendicular bisector between the location of the third projected feature position and the location of the fourth projected feature position .
Based on the second perpendicular bisector, a second intersection between the second perpendicular bisector and the reference axis is determined .
A second angle estimate is established based on a second perpendicular bisector, a first line extending from a third projected feature location to the second intersection point, and a first line extending from a fourth projected feature location to the second intersection point in the horizontal plane . performing a second angle estimation based on an angle with a second line extending to the intersection point;
Finally, calculating a yaw angle based on the first and second angle estimates.

By using two or more trailer features and multiple perpendicular bisectors, noise and discrepancies in determining the turning angle between the perpendicular bisector and the reference axis can be mitigated. Wear.

According to one embodiment, in addition to the first and second features mentioned above, at least one further feature of the trailer is used for calculating the yaw angle. Using three or more features further improves the robustness and reliability of the yaw angle determination.

According to one embodiment, the yaw angle is calculated by setting a median value based on at least two angle estimates. This makes it possible to obtain a very stable yaw angle determination .

According to other embodiments, the yaw angle is calculated by setting an average value of at least two angle estimates or by using a statistical approach applied to said angle estimates.

According to one embodiment, the method further comprises the step of determining the following angular frames. The angle frame may include an upper limit and a lower limit that sandwich the yaw angle. Additionally, a set of features is determined , and the features in the feature set serve as a basis for an angle estimate located within the angle window. Said determined feature set is preferably such that only features included in said feature set are used for future yaw angle calculations . In other words , the previous yaw angle determination information determines two or more features of the trailer that lead to an angle estimate that is fairly close ( i.e. within the angle window) to the determined yaw angle, and the determined It is used to untrack features that lead to angle estimates that deviate significantly from the calculated yaw angle ( ie , outside the angle window). This can significantly reduce the computational complexity and accuracy of angle estimation.

According to one embodiment, camera calibration information is used to transform the position of the first feature and / or the second feature from a local domain of the image to a local domain of the vehicle. For example, by knowing the position of the camera using camera calibration information, the position of a particular feature on an image can be determined depending on or relative to the position where the camera is built into or installed in the vehicle. By doing so, it can be converted into location information.

According to one embodiment, the reference axis is the longitudinal axis of the towing vehicle if the camera and the towball of the vehicle are arranged in a vertical orientation plane containing the longitudinal axis of the towing vehicle. That is , in other words , the yaw angle is set based on an angle estimate, said angle estimate being based on the angle between the longitudinal axis of the towing vehicle and the obtained perpendicular bisector.

According to another embodiment, if at least one of the camera and the towball has a lateral offset with respect to the longitudinal axis of the towing vehicle, the reference axis is between the camera and the towball . is a continuous straight line. By doing so, it is possible to compensate for lateral offsets between the camera and the towball .

According to one embodiment, the camera is a rear view camera of the vehicle. By being based on a rear view camera, images of the trailer can be taken with less technical effort.

According to one embodiment, the location of the first feature is determined not only in the first and second images, but also at least in the third image. The location of the first feature in the third image is different from the location of the first feature in the first and second images. A first perpendicular bisector can be determined between the first feature in the first image and the second image. A further perpendicular bisector can be determined between the first feature in the first image and the third image. A further point of intersection may then be determined based on the point of intersection of said first perpendicular bisector and said further perpendicular bisector.

A first angle estimate is calculated based on the first perpendicular bisector. The first angle estimate is a rotation angle about the further intersection of the intersections of the first ray and the horizontal plane with respect to the intersection of the second ray and the horizontal plane. The first angle estimate corresponds to a change in the yaw angle of the trailer between the first image and the second image. That is , in other words , the point of rotation of the trailer is determined not by the intersection of the first perpendicular bisector with the reference axis , but by tracking three or more image features. It is determined by intersecting at least two perpendicular bisectors obtained.

According to a further aspect , a system for determining a yaw angle of a trailer relative to a longitudinal axis of a towing vehicle is disclosed. The system includes a camera that captures images of the trailer and a processing entity that processes the captured images. Furthermore, the system is configured to be able to perform the following steps.
- capturing at least a first image and a second image of the trailer using a camera, the orientation of the trailer relative to the vehicle being different on the at least two images ;
- determining at least a first feature of the trailer visible in the first and second images;
- projecting the ray between the camera and the first feature determined on the first image onto a horizontal plane, thereby obtaining a first projected feature position ; projecting a ray between the features onto the horizontal plane, thereby obtaining a second projected feature position ;
- establishing a first perpendicular bisector between the location of the first projected feature location and the location of the second projected feature location ;
- determining a first point of intersection between the first perpendicular bisector and the reference axis ;
- calculating a yaw angle based on a first angle estimate, the first angle estimate being a first line in the horizontal plane that is continuous from the first projected feature position to the first intersection point; , calculating a yaw angle based on the first angle estimate, the angle between the second projected feature position and a second line continuous to the first intersection point.

Any features described above as embodiments of the method are also applicable as system features in a system according to the present disclosure.

According to yet another embodiment, a vehicle is disclosed that includes a system according to any of the embodiments described above.

The term "vehicle " as used herein may mean an automobile, truck, bus, train, or other motorized vehicle.

As used herein, the term "yaw angle" may refer to the pivot angle between the longitudinal axis of the vehicle and the longitudinal axis of the trailer.

The term "median" as used herein may refer to the value that separates the upper half from the lower half of a data sample or probability distribution.

As used herein, the term " basic " or "substantially" refers to a difference of +/-10%, preferably +/-5% from the exact value and that the change This means that there is an insignificant difference with respect to at least one of the traffic regulations .

Various aspects of the present invention, including specific features and advantages, will be readily understood from the following detailed description and accompanying drawings.

FIG. 1 illustrates a top view of a vehicle towing a trailer. FIG. 2 schematically shows angle estimation based on a single feature taken by multiple camera images of different turning angles between the trailer and the towing vehicle . FIG . 3 schematically shows a plurality of angle estimates based on first and second features taken by a plurality of camera images of different turning angles between a trailer and a towing vehicle. FIG. 4 schematically shows the geometric determination of the rotation point based on the first and second perpendicular bisectors obtained from a unique trailer feature contained in three different images. FIG. 5 shows a schematic block diagram illustrating the steps of a method for determining the yaw angle of the trailer relative to the longitudinal axis of the towing vehicle.

The invention will now be described more fully with reference to the accompanying drawings, in which exemplary embodiments are shown. Although the embodiments in the figures may relate to the preferred embodiments, all elements and features described in connection with the embodiments may be incorporated, as appropriate, in other embodiments and embodiments described herein. It may be used in combination with the features, particularly in conjunction with the embodiments described in detail above. In any event, this invention should not be construed as limited to the embodiments described herein. Where applicable, like reference numbers are used throughout the following description to indicate similar elements, parts, items, or features.

The features of the invention disclosed in the description, the claims, the examples or the features of the invention disclosed in the drawings are, both individually or in any combination thereof, the invention It may be a material for implementing in various forms.

FIG. 1 shows a top view of a vehicle 1 towing a trailer 2. FIG. The vehicle 1 includes a longitudinal axis LAV passing through the center of the vehicle 1. Similarly, the trailer 2 has a longitudinal axis LAT passing through the center of the trailer 2. The trailer 2 is connected to the vehicle 1 by a trailer hitch with a tow ball 4 .

In a particular driving situation, the longitudinal axis LAV of the vehicle 1 and the longitudinal axis LAT of the trailer 2 may not be parallel or overlapping each other; is limited. In other words , the yaw angle YA defines the deviation angle of the longitudinal axis LAT of the trailer 2 with respect to the longitudinal axis LAV of the vehicle 1. The yaw angle YA may be measured on a horizontal plane including the longitudinal axis LAT of the trailer 2, similar to the longitudinal axis LAV of the vehicle 1.
Knowledge regarding the yaw angle YA is particularly advantageous, for example in trailer assistance systems .

To determine the yaw angle YA, a plurality of images of at least a portion of the trailer 2 are taken by the camera 3. The camera 3 may be , for example, a rear view camera of the vehicle for capturing images of the surroundings of the vehicle when the vehicle is traveling backwards. One of the images taken may be of a known angular positioning of the trailer 2 with respect to the towing vehicle 1. Said image may be used as a reference in the calculation of the yaw angle YA. In said known angular arrangement of the trailer 2 relative to the tow vehicle 1, the yaw angle YA may be 0° or any other angular value.

FIG. 2 shows a schematic diagram showing the angular relationship of the first feature F1 of the trailer 2 at different times when the trailer 2 has different yaw angles YA with respect to the towing vehicle 1.

The camera 3 may take two or more images at different times and with different angular positions of the trailer 2 relative to the vehicle 1. For example, a series of images may be taken .

In this example, the second image may show the orientation of the trailer relative to the vehicle at a yaw angle YA=0°.

Due to the angular movement of the trailer 2 over time, certain features detected on the trailer will appear at different positions in the first and second images. In FIG. 2, the first feature is shown as a square.

The upper representation of the first feature (associated with the ray R represented by the solid line connecting the feature and camera 3) is identified in the first image and represented by the dashed line connecting the feature and camera 3. A lower representation (associated with the ray R) is identified in the second image at a different time. Calibration information of the camera 3 may be used to correlate the location of the first feature in each image with the location of the vehicle 1, in particular with a fixed point of the vehicle 1. Specifically, the calibration information of the camera 3 may be used to determine the ray R connecting the first feature and the camera 3, and the location of the first feature in the image coordinates may be converted into a ray . In other words , in order to associate the camera position and the feature position, the location of the feature on the image and the position of the fixed point of the vehicle based on the calibration information of the camera 3 are correlated.

Features on the trailer are located and matched using feature detection and matching algorithms . For example, Harris Corner Detector, Scale-Invariant Feature Transform (SIFT) algorithm, Speeded Up Robust Features (SURF) algorithm, Binary Robust Invariant t Scalable Keypoints (BRISK) algorithm, Binary Robust Independent Elementary Features (BRIEF), Oriented FAST and Rotated BRIEF ( ORB) algorithm or another suitable feature detection and matching algorithm could be used .

Feature detection and matching algorithms will detect features of the images that are on the trailer or not on the trailer. Many different methods could be used to distinguish trailer features from non- trailer features. For example, when moving forward in a straight line, trailer features can be distinguished from non- trailer features by looking for features that remain in the same position over time. Alternatively, the motion of background features may be modeled over time using the known motion of the vehicle. This could be extracted from CAN data regarding speed and steering. In other words, features that do not apply to the epipolar constraint of the fundamental matrix can be considered to be trailer features.

After identifying the features in each image, the first features of the first and second images are projected onto a common horizontal plane. More specifically, the light ray between the camera 3 and the determined first feature on the first image is projected onto a horizontal plane, thereby obtaining the first projected feature position PFP1a. In addition, the light ray between the camera 3 and the determined first feature on the second image is likewise projected onto the horizontal plane, resulting in a second projected feature position PFP1b. It is worth mentioning here that said projection is performed in the vertical direction, so that only the elevation angle of the rays changes, but not the azimuth angle.

After determining the first and second projected feature positions PFP1a and PFP1b, a first perpendicular bisector B1 is set based on the first and second projected feature positions PFP1a and PFP1b. As shown in FIG. 2, the first perpendicular bisector B1 is perpendicular to the connecting line connecting the first and second projected feature positions PFP1a and PFP1b. In addition, the first perpendicular bisector B1 passes through the center of the connection line. In this embodiment, the first perpendicular bisector B1 intersects with the reference axis , which is the longitudinal axis of the vehicle LAV. The intersection of the first perpendicular bisector B1 and the reference axis provides a rotation point around which the trailer rotates. More specifically, said intersection provides the position of the tow ball 4.

A first angle estimate α1 is calculated based on the first perpendicular bisector B1. The first angle estimation α1 is based on a first line L1 connecting the reference axis and the intersection of the first projected feature position PFP1a and the first perpendicular bisector B1, and a second projected feature position PFP1b and the first perpendicular bisector B1. This is about the angle between the second line L2 that connects the equisector line B1 and the intersection of the reference axis . This intersection may indicate the position of the tow ball 4. More specifically, the first angle estimation α1 on the horizontal plane is determined by the location of the first feature in the first image projected onto the horizontal plane and the location of the first feature in the second image projected onto the horizontal plane. The turning angle of the trailer 2 on the horizontal plane about the first intersection point IP1 (which is the position of the tow ball 4) between the two is characterized.

The first angle estimate α1 represents the yaw angle YA of the trailer 2 centered on the actual rotation point.

FIG. 3 shows that the first and second features F1, F2 of the trailer 2 taken at different times (trailer 2 has different yaw angles YA with respect to the towing vehicle 1) are used to set the yaw angle YA. shows an embodiment similar to . A plurality of different features may be distinguishable on the image taken by the camera 3. As shown in FIG. 3, said features are identified at different angular positions relative to a fixed point of the vehicle 1. The first feature is drawn as a square, and the second feature is drawn as a triangle. Said fixed point may be the location of the camera 3 or the location of the tow ball 4.

In Figure 3, the upper pair of first and second features (indicated by PFP1a, PFP2a and associated with the solid ray connecting camera 3 and the features) are identified in the first image and (PFP1b , PFP2b and associated with the dashed ray connecting the features with camera 3) are identified in the second image at different times.

The determination of the yaw angle YA is performed in the same manner as in the embodiment of FIG. The main difference is that two angle estimates α1, α2 are set and the yaw angle of the trailer is developed based on said two angle estimates α1, α2. More specifically, a first perpendicular bisector B1 is set and obtaining a first angle estimate α1 is performed as described above.

In addition , the second angle estimation α2 sets the third projected feature position PFP2a and the fourth projected feature position PFP2b, sets the second perpendicular bisector B2 to obtain the second intersection IP2, and calculates the third projected feature position PFP2b. It is obtained by connecting the position PFP2a and the fourth projected feature position PFP2b with the second intersection point IP2. The third projected feature position PFP2a is the second feature in the first image projected onto the horizontal plane, and the fourth projected feature position PFP2b is the second feature in the second image projected onto the horizontal plane. It is. The second intersection point IP2 is a point where the second perpendicular bisector B2 intersects with the reference axis line , and in this embodiment, it may be a point where the second perpendicular bisector line B2 intersects with the longitudinal axis line of the vehicle LAV. The second angle estimate α2 is the angle formed by the first line connecting the third projected feature position PFP2a and the intersection IP2 and the second line connecting the fourth projected feature position PFP2b and the intersection IP2.

In this embodiment, since not only the camera 3 but also the tow ball 4 are located on the longitudinal axis LAV of the vehicle 1, the reference axis is the longitudinal axis LAV of the towing vehicle 1. In other embodiments, the camera 3 or the towball 4 is laterally offset with respect to the longitudinal axis LAV of the vehicle 1, or the camera 3 or the towball 4 is laterally offset with respect to the longitudinal axis LAV of the vehicle 1. If they are different, the reference axis may be formed by a straight line connecting the camera 3 and the tow ball 4.

Under ideal conditions, the first angle estimate α1 and the second angle estimate α2 should be equal (α1=α2) and represent the yaw angle YA. However, the values of the first and second angle estimates α1 and α2 may differ due to noise or mismatch .

It is noteworthy that more than two features of trailer 2 can be determined and tracked across multiple images. In addition, preferably more than two images are taken at different times in order to improve the results of the yaw angle estimation. Thereby, more than two angle estimates α1 and α2 can be set to improve the quality of yaw angle determination .

A statistical measure may be used to determine the yaw angle YA based on the first and second angle estimates α1, α2 having different values. According to a first embodiment, the median value of two or more angle estimates α1, α2 may be used to determine the yaw angle YA. According to other embodiments, statistical methods may be used to determine the yaw angle YA based on two or more angle estimates α1, α2. The statistical method can be, for example, the RANSAC algorithm (RANSAC; Random Sample Consensus) or the least squares algorithm.

Not all features visible on the captured image are equally suitable for calculating the yaw angle YA. For reduced computational complexity and robustness , features with a turning angle very close to the actual yaw angle are selected and further used to determine the yaw angle YA. For feature selection , only those features that give a turning angle α1, α2 within a predetermined frame surrounding the actual yaw angle may be tracked in future images. For example, the frame may be defined by an upper limit and a lower limit, the upper and lower limits defining an angular frame surrounding the actual yaw angle. For example, the frame may span between 2° and 10°, particularly preferably between 3° and 5°. All features that give a turning angle within said frame in the last two or more yaw angle determination steps are further tracked in the next captured image.

When tracking a particular trailer feature in multiple images, samples of said feature can be placed on a circle segment due to the movement of the trailer 2. The center of said circle segment represents the location of the tow ball 4. Therefore, by tracking specific trailer features across multiple images, the location of the towball 4 can be derived .

To mitigate noise, the location of the towball 4 may be determined by considering the characteristics of multiple trailers tracked over a period of time across multiple images. Each feature of the trailer may correspond to a circle segment with a particular center estimate. By applying statistical methods to the estimation of the plurality of centers , the actual location of the tow ball 4 can be developed . The statistical method may be, for example, a RANSAC algorithm or a least squares algorithm.

FIG. 4 shows a further embodiment in which the rotation point is determined geometrically without using the upper reference axis .

The rotation point is set by developing at least two perpendicular bisectors B1, B2 based on three images showing features at different angular positions relative to the towing vehicle 1. In FIG. 4, the first projected feature position PFP1a is a feature included in the first image projected onto a common horizontal plane, as described above. Similarly, the second projected feature position PFP1b is for the feature included in the second image, and the third projected feature position PFP1c is for the feature included in the third image.

The first perpendicular bisector B1 is a connection line connecting the first and second projected feature positions PFP1a and PFP1b. The second perpendicular bisector B2 indicates a connecting line connecting the first and third projected feature positions PFP1a and PFP1c. The intersection of the first and second perpendicular bisectors B1 and B2 defines an intersection point IP that indicates the rotation point of the trailer 2 , that is, the position of the tow ball 4 .

The intersection IP can be used to determine the yaw angle YA of the trailer as shown in the embodiments of FIGS. 2 and 3.

FIG. 5 shows a block diagram illustrating the steps of a method for determining the yaw angle YA of the trailer 2 with respect to the longitudinal axis LAV of the towing vehicle 1.

As a first step, at least first and second images of the trailer are captured using a camera (S10).

After image capture, at least one feature of the trailer visible on the first and second images is determined (S11).

After determining the features, a first projected feature position and a second projected feature position are set by feature projection (S12).

After projecting the features , a first perpendicular bisector is set (S13).

After setting the first perpendicular bisector, a first intersection between the first perpendicular bisector and the reference axis or a further perpendicular bisector is developed (S14).

Finally, the yaw angle is calculated based on the first angle estimate (S15).

It should be noted that the above description and drawings merely illustrate the principles of the proposed invention. Those skilled in the art will be able to implement various configurations not explicitly described or shown herein that may embody the principles of the invention.

1 Vehicle 2 Trailer 3 Camera 4 Towball α1 First angle estimation α2 Second angle estimation B1 First perpendicular bisector B2 Second perpendicular bisector PFP1a Projection of the first feature in the first image Feature position
PFP1b Projected feature position of the first feature in the second image
PFP1c Projected feature position of the first feature in the third image
PFP2a Projected feature position of the second feature in the first image
PFP2b Projected feature position of the second feature in the second image
IP Intersection IP1 First intersection IP2 Second intersection LAT Trailer vertical axis line
LAV Vehicle longitudinal axis
R ray
YA Yaw angle

Claims (13)

A method for determining the yaw angle (YA) of a trailer (2) with respect to the longitudinal axis (LAV) of a towing vehicle (1), said method comprising:
- taking at least a first and a second image of the trailer (2) with a camera (3), in which the orientation of the trailer (2) with respect to the vehicle ( 1) is different on at least two images; S10) and
- determining (S11) at least a first feature of said trailer (2) that is visible in a first and second image;
- projecting a ray of light between said camera (3) and a first feature determined on a first image onto a horizontal plane, thereby obtaining a first projected feature position (PFP1a); and the first feature determined on the second image onto the horizontal plane, thereby obtaining a second projected feature position (PFP1b) (S12);
- setting a first perpendicular bisector (B1) between the location of the first projected feature position (PFP1a) and the location of the second projected feature position (PFP1b) (S13) ;
- determining (S14) a first point of intersection (IP1) between the first perpendicular bisector (B1) and a reference axis or a further perpendicular bisector;
- a step (S15) of calculating a yaw angle (YA) based on a first angle estimate (α1), the first angle estimate (α1) being a first projected feature position (PFP1a ) in the horizontal plane; ) to the first intersection (IP1), and the angle between the second line that continues from the second projected feature position (PFP1b) to the first intersection (IP1). a step (S15) of calculating the yaw angle (YA) based on the first angle estimation (α1) ;
A method for determining the yaw angle (YA) of a trailer (2) with respect to the longitudinal axis (LAV) of a towing vehicle (1), comprising: 2. The yaw angle (YA) of the trailer (2) relative to the vehicle (1) on the first or second image is zero or any known yaw angle (YA ) that can be used as a reference angle . The method described in 1. - determining a second feature of said trailer (2) that is visible in first and second images, said second feature being in a different position than said first feature on said trailer (2); determining the second feature that is located ;
- projecting a ray of light between said camera (3) and said second feature determined on said first image onto said horizontal plane, thereby obtaining a third projected feature position (PFP2a); 3) and the second feature determined on the second image onto the horizontal plane, thereby obtaining a fourth projected feature position (PFP2b);
- setting a second perpendicular bisector (B2) between the location of the third projected feature position (PFP2a) and the location of the fourth projected feature position (PFP2b);
determining a second point of intersection (IP2) between a second perpendicular bisector (B2) and the reference axis ;
- calculating a second angle estimate (α2), said second angle estimate (α2) being continuous from said third projected feature position (PFP2a) to said second intersection point (IP2) in said horizontal plane ; A second angle estimation (α2), which is about the angle between the first line and the second line continuous from the fourth projected feature position (PFP2b) to the second intersection (IP2) steps to calculate,
- calculating the yaw angle (YA) based on the first and second angle estimates ( α1 , α2) ;
The method according to claim 1 or 2, further comprising : Method according to claim 3, characterized in that, in addition to the first and second features, at least one further feature of the trailer (2) is used for calculating the yaw angle (YA). 5. A method according to claim 3 or 4, wherein the yaw angle (YA) is calculated by setting a median value based on the at least two angle estimates. Claims 3 to 5, wherein the yaw angle (YA) is calculated by setting an average value of the at least two angle estimates or by using a statistical approach applied to the angle estimates. The method described in any one of the above . further comprising a step of determining an angle frame ;
the angular frame has upper and lower bounds surrounding the yaw angle (YA), the angular frame determining a set of features that lead to an angle estimation within the angular frame;
7. A method according to any one of claims 1 to 6 , wherein the determined set of features is used for calculating a future yaw angle (YA). 8. Camera calibration information according to claim 1 , wherein camera calibration information is used to transform the position of at least one of the first feature and the second feature from the local domain of the image to the local domain of the vehicle (1). The method described in any one of the above . if the camera (3) and the tow ball (4) of the vehicle (1) are arranged in a vertically oriented plane comprising the longitudinal axis (LAV) of the towing vehicle (1); 9. A method according to any one of claims 1 to 8, wherein the reference axis is the longitudinal axis (LAV) of the towing vehicle (1). If at least one of the camera (3) and the tow ball (4) has a lateral deviation with respect to the longitudinal axis (LAV) of the towing vehicle (1), the reference axis 10. The method according to claim 1 , wherein there is a continuous straight line between the tow ball (4) and the tow ball (4). 11. A method according to any one of claims 1 to 10 , wherein the camera (3) is a rear view camera of the vehicle (1). A system for determining the yaw angle (YA) of a trailer (2) with respect to the longitudinal axis (LAV) of a towing vehicle (1), said system comprising: a camera ( 3) and a processing entity that processes the captured image, the system comprising:
- taking at least a first and a second image of the trailer (2) using a camera (3), wherein the orientation of the trailer (2) with respect to the vehicle ( 1) is different on at least two images; (S10) and
- determining (S11) at least a first feature of said trailer (2) that is visible in a first and second image;
- projecting a ray of light between said camera (3) and a first feature determined on a first image onto a horizontal plane, thereby obtaining a first projected feature position (PFP1a); and the first feature determined on the second image onto the horizontal plane, thereby obtaining a second projected feature position (PFP1b) (S12);
- setting a first perpendicular bisector (B1) between the location of the first projected feature position (PFP1a) and the location of the second projected feature position (PFP1b) (S13) ;
- determining (S14) a first point of intersection (IP1) between the first perpendicular bisector (B1) and a reference axis or a further perpendicular bisector;
- a step (S15) of calculating a yaw angle (YA) based on a first angle estimate (α1), the first angle estimate (α1) being calculated from the first projection feature position (PFP1a); Regarding the angle between the first line that continues to the intersection (IP1) and the second line that continues from the second projected feature position (PFP1b) to the first intersection (IP1) in the horizontal plane. a step (S15) of calculating a certain yaw angle (YA) based on the first angle estimation (α1) ;
A system for determining a yaw angle (YA) of a trailer (2) with respect to a longitudinal axis (LAV) of a towing vehicle (1), further configured to perform. A vehicle comprising a system according to claim 12.