Method and apparatus for determining marker position and orientation - Patents.com

Abstract

The method and apparatus for determining the position and orientation of a marker having encoded information includes acquiring images of the marker with a stereo camera. A center of the marker is determined, and then a position of the marker is determined based on the center of the marker. A number of vertices are then determined about the center of the marker. The number of vertices are used to determine the pitch, roll and orientation of the marker. The orientation of the marker is determined based on the pitch, roll and orientation of the marker. The method and / or apparatus for determining the position and orientation of a marker can be used in a range of applications for determining the position and orientation of an object on which the marker is placed.

Description

[Technical field]

[0001] The present disclosure relates generally to methods and apparatus for determining position, and more particularly, to methods and apparatus for determining the position and orientation of a marker. [Background technology]

[0002] There is often a need to determine the position and attitude of an object for various reasons. For example, a situation may arise where the position and attitude of an agricultural sprayer towed behind a tractor is needed to determine where liquid is being sprayed in a field and whether local or national regulations are being complied with. A machine such as an agricultural sprayer may be towed behind a vehicle such as a tractor. The towed machine is typically pivotally connected to the tractor via a hitch that allows the towed machine to rotate behind the tractor. That is, the position and attitude of the tractor is not the same as the position and attitude of the towed machine, and determining the position and attitude of the tractor alone may not be sufficient to determine, for example, compliance with regulations. Electronic devices and other types of devices can be installed on the towed machine to determine the position and attitude of a particular machine. However, the cost of installing electronic devices on each machine can be expensive. Furthermore, a user may need to know the position of multiple machines simultaneously, which may require the use of multiple electronic devices at even greater cost. Summary of the Invention

[0003] In one embodiment, a method and apparatus for determining a position and pose of a marker includes acquiring images of the marker with a stereo camera. The marker has encoded information. Based on the images, a position of the marker is determined in a local coordinate system of the stereo camera. Based on the position of the marker, a position of an object is determined in the local coordinate system of the stereo camera. In one embodiment, the encoded information identifies the object and may also identify where the marker is located on the object. In one embodiment, a position of the stereo camera in a global coordinate system may be determined and based on the position of the object in the local coordinate system and the position of the stereo camera in the global coordinate system, a position of the object in the global coordinate system may be determined. In one embodiment, a center of the marker may be determined and then a position of the marker may be determined based on the center of the marker. A number of vertices on the marker around the center of the marker are then determined. The number of vertices are used to determine the pitch, roll and pose of the marker. The pose of the marker is determined based on the pitch, roll and pose of the marker.

[0004] The method and apparatus for determining the position and orientation of a marker can be used in a variety of applications to determine the position and orientation of an object on which the marker is placed, including determining the position and orientation of a bulldozer blade based on the position and orientation of a marker, determining the position and orientation of an implement towed behind a tractor, controlling the motion of a vehicle, determining the position and orientation of a vehicle, parking a vehicle, etc. A stereo camera arrangement can be used to determine the location of the marker and the location of the object or machine on which the marker is placed based on the stereo camera arrangement. [Brief description of the drawings]

[0005] [Figure 1] FIG. 1 shows a system located on a vehicle, for determining the position and orientation of a marker, according to one embodiment.

[0006] [Diagram 2]FIG. 2 shows a marker according to one embodiment.

[0007] [Diagram 3] FIG. 3 illustrates the coordinate system of a stereo camera, its video sensor, and the two-dimensional projection of a marker on the sensor according to one embodiment.

[0008] [Figure 4] FIG. 4 shows a flow chart of a method for determining the position and orientation of a marker according to one embodiment.

[0009] [Diagram 5] FIG. 5 illustrates an example application of the method of FIG. 4 to determining the position and attitude of a blade of a construction machine.

[0010] [Figure 6] FIG. 6 illustrates an example application of the method of FIG. 4 to determining the position and orientation of a towed implement.

[0011] [Figure 7] FIG. 7 illustrates an example application of the method of FIG. 4 to control vehicle motion based on the position and orientation of markers in an environment.

[0012] [Figure 8] FIG. 8 illustrates an example application of the method of FIG. 4 in which markers are placed on an automated or autonomous vehicle to determine the vehicle's position and attitude.

[0013] [Figure 9] FIG. 9 illustrates an example application of the method of FIG. 4 in which markers are installed at parking spaces to enable an automated or autonomous vehicle to identify and position itself in a designated parking space. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] The method for determining the position and orientation of the markers utilizes components including a stereo camera that is used to capture images of the markers located within its field of view (FOV). Each marker has a unique geometric shape, color, and size that facilitates finding and highlighting each marker within the left and right camera frames of the stereo camera. The unique geometric shape of each marker comprises coded information. In one embodiment, the coded information can be used to identify the marker. Triangulation techniques can be used to determine the three-dimensional (3D) position and orientation of the markers located within the coordinate system of the stereo camera. The term "position" as used herein means the position of the marker or object in the local coordinate system of the stereo camera (described in more detail below). By placing markers on multiple objects, the positions and orientations of the objects can be determined based on the positions and orientations of corresponding markers placed on the objects. The positions and orientations of the markers located within the environment in which the autonomous vehicle or machine (also referred to as "autonomous vehicle or machine") can be used to control the autonomous vehicle.

[0015] FIG. 1 illustrates an embodiment of a system 100 for determining the position and orientation of a marker, in which a stereo camera 102 is mounted on a vehicle 104. In one embodiment, the stereo camera 102 has multiple lenses, each lens having a separate imager. In various embodiments, the stereo camera 102 can be a Stereolabs ZED2i, a Framos D435e, a StereoCam 3D Stereo Camera (2MP), or the like. Each lens is configured to generate a slightly different field of view from the field of view of the other lens. These differences in field of view can be used to determine the location of an object captured in an image relative to the stereo camera. The stereo camera 102 communicates with a controller 106, which receives images from the stereo camera 102. In one embodiment, the stereo camera 102 communicates with the controller 106 via an Ethernet or USB3 connection. In various embodiments, the controller 106 can be a Rugged Embedded System powered by NVIDIA Jetson AGX / NX Xavier, or an Orin. The controller 106 is also in communication with a navigation system 108 that provides location and orientation information to the controller 106. In one embodiment, the navigation system 108 is a Global Navigation Satellite System (GNSS). The navigation system 108 may be any other type of location and orientation system, such as a system using triangulation or other location determination methods. The term "location" here refers to the location of a marker, object, machine, or camera in a large coordinate system compared to the local coordinate system of the stereo camera. The large coordinate system may be a global coordinate system. The global coordinate system may be any type of global coordinate system, such as a spherical coordinate system or an ellipsoidal coordinate system using geodetic data (e.g., World Geodetic System 1984 (WGS84)). The controller 106 is also in communication with a vehicle control system 110 that monitors and controls the operation of the vehicle 104.In one embodiment, the controller 106 communicates with the vehicle control system 110 via one of an RS232 connection, CAN, Ethernet, etc. In one embodiment, the controller 106 includes a processor 1004 that controls the operation of the controller 106 by executing computer program instructions that define the overall operation of the controller 106. The computer program instructions may be stored in a storage device 1012, or other computer readable medium (e.g., magnetic disk, CD ROM, etc.) and loaded into the memory 1010 when execution of the computer program instructions is desired. That is, the method steps of FIG. 4 (described in more detail below) may be defined by computer program instructions stored in the memory 1010 and / or the storage device 1012 and controlled by the processor 1004 executing the computer program instructions. For example, the computer program instructions may be embodied as computer executable code programmed by one of ordinary skill in the art to execute the algorithm defined by the method steps of FIG. 4. By executing the computer program instructions in this manner, the processor 1004 executes the algorithm defined by the method steps of FIG. 4. The controller 106 also includes one or more network interfaces 1006 for communicating with other devices over a network. The controller 106 also includes input / output devices 1008 (e.g., a display, keyboard, mouse, speakers, buttons, etc.) that allow user interaction with the controller 106. Those skilled in the art will recognize that an actual controller implementation may include other components, and that the description of the controller 106 herein is for illustrative purposes a high-level representation of some of the components of such a controller.

[0016] In one embodiment, the controller 106 analyzes images received from the stereo camera 102 in order to identify markers, such as marker 200, that are shown in images captured within the field of view of the stereo camera 102. In one embodiment, the controller 106 determines the position and orientation of the marker relative to the stereo camera based on the images.

[0017] FIG. 2 depicts a marker 200 in the local coordinate system of the stereo camera 102. In one embodiment, the marker 200 has a unique shape and is encoded with information. In one embodiment, the encoded information identifies the object on which the marker 200 is placed and may also identify where the marker is placed on the object. In one embodiment, the marker 200 may be a two-dimensional barcode that is painted directly on the object or printed on a material that can be applied to the object, such as a decal with an adhesive backing. In one embodiment, each marker may contain up to 12 bits of encoded information. In one embodiment, the marker 200 is an AprilTag target. AprilTag is a system that uses markers (i.e., AprilTag targets) that are encoded with information captured by one or more cameras. In one embodiment, one of the AprilTag targets is used: the square tag36h11 (comprising 587 unique tags) and the round tag49h12 (comprising 65535 unique tags). Based on images of the AprilTag target captured using one or more cameras, the position and orientation of the AprilTag target can be determined. As shown in FIG. 2, the marker 200 has four vertices mP1, mP2, mP3, and mP4, which together form a flat rectangle located approximately at the center of the marker. In one embodiment, the four vertices are located at the corners of the flat rectangle. The four vertices are used to define three axes of the marker 200. Axis Xm is defined as the line formed by vertices mP3 and mP4. Axis Ym is defined as the line formed by vertices mP1 and mP4. Axis Zm is perpendicular to both axes Xm and Ym, and intersects with vertex mP4. Rotation about each axis is defined as follows: Roll is defined as a clockwise rotation about axis Zm. Pitch is defined as a clockwise rotation about axis Xm. Azimuth is defined as a clockwise rotation about axis Ym.

[0018] FIG. 3 illustrates a local coordinate system 300 of the stereo camera 102, according to one embodiment. The stereo camera 102 is located at a point O where the axes X, Y, and Z intersect. Point O is defined as the upper left corner of the left video sensor 302 of the stereo camera 102. The horizontal axis X is orthogonal to the vertical axis Y, and both axes X and Y lie in the plane of the left video sensor and are orthogonal to the axis Z. In one embodiment, the position and orientation of the marker 200 are determined with reference to the local coordinate system 300 of the stereo camera 102. The local coordinate system 300 allows the position of the marker or object to be determined with respect to the stereo camera 102 without using a larger coordinate system, such as a global coordinate system. The position of any point can be described with reference to the stereo camera 102 using the local coordinate system. If the position and orientation of the stereo camera 102 in the larger coordinate system, such as a global coordinate system, is known, the position of the object, whose position is known in the local coordinate system, can be determined with respect to the larger coordinate system.

[0019] The stereo camera parameters affect various aspects of marker detection. The maximum detection / recognition distance of a marker of a particular size from the camera depends on the angular resolution of the camera. The better the angular resolution of the camera, the greater the maximum distance between the camera and the marker at which the marker can be found. In one embodiment, the exposure mode of the camera uses a global shutter mode to avoid spatial distortion of the shape of the marker, which may move at high speeds relative to the camera. The width of the baseline of the stereo camera affects the accuracy of the marker localization. In one embodiment, to use sub-pixel resolution, a base width of 10 centimeters is required for a maximum distance of 6 meters between the camera and the marker. A base of 15 centimeters can be used for a maximum distance of 10 meters between the camera and the marker and to maintain centimeter-level accuracy of the marker localization. The angular resolution of the camera generally depends on the lens characteristics (e.g., field of view) and the sensor resolution of the camera. The approach described here is capable of achieving millimeter-level precision and centimeter-level accuracy in the localization (limited by the calibration of the stereo camera). This approach can provide sub-degree accuracy for the pose determination of the marker.

[0020] 4 illustrates a flow chart of a method 400 for determining the position and orientation of a marker 200. In one embodiment, the controller 106 executes the steps of the method 400. In step 402, the stereo camera 102 captures an image of the marker 200. In one embodiment, the marker contains encoded information, and the image captured by the stereo camera 102 consists of two frames, one frame for each lens of the stereo camera 102.

[0021] In steps 402a and 402b, the marker 200 is identified and multiple vertices in the planar projection 304 of the marker 200 are determined separately for each of the left and right frames of the stereo camera 102. In one embodiment, the identification of the marker and the determination of each vertex can be performed by various techniques, such as a technique that involves identification and vertex determination by each AprilTag. In one embodiment, an AprilTag detector is used to detect each AprilTag.

[0022] In step 404, each vertex mP1, mP2, mP3, mP4 of the marker 200 can be calculated using a camera local coordinate system using triangulation based on the information about the 2D projections 304 of the marker vertices in both frames calculated in the previous step and the camera characteristics (e.g., stereo baseline and calibration data). In the local camera coordinate system 300, mP[0] is the value for the x coordinate, mP[1] is the value for the y coordinate, and mP[2] is the value for the z coordinate, where index 0 in the array is the x coordinate, index 1 is the y coordinate, and index 2 is the z coordinate.

[0023] In step 406, the center cP of the marker 200 is determined in the camera local coordinate system. In one embodiment, the center of the marker 200 in the coordinate system 300 shown in FIG. cP[0]=(mP1[0]+mP2[0]+mP3[0]+mP4[0]) / 4 cP[1]=(mP1[1]+mP2[1]+mP3[1]+mP4[1]) / 4 cP[2]=(mP1[2]+mP2[2]+mP3[2]+mP4[2]) / 4 where mP1, mP2, mP3, and mP4 are calculated in step 404.

[0024] In step 408, the pitch, roll, and heading of the marker 200 are determined. In one embodiment, the pitch, roll, and heading of the marker 200 are determined based on the vertices mP1, mP2, mP3, and mP4 (computed in step 404) as follows:

[0025] The roll of the marker 200 is expressed as an angle, and in one embodiment is determined using all four vertices as follows: role1 = atan2(mP2[1]-mP1[1],mP2[0]-mP1[0]) role2 = atan2(mP3[1]-mP4[1],mP3[0]-mP4[0]) Roll = (Roll 1 + Roll 2) / 2 where mP1, mP2, mP3, and mP4 are calculated in step 404.

[0026] In one embodiment, intermediate three-dimensional coordinates iP1, iP2, iP3, iP4 for each of the four vertices of the marker 200 are calculated prior to calculating the orientation of the marker 200. In one embodiment, the intermediate three-dimensional coordinates are calculated as follows: iP1[0] = mP1[0] * cos(roll) + mP1[1] * sin(roll) iP1[1] = -mP1[0] * sin(roll) + mP1[1] * cos(roll) iP1[2]=mP1[2] iP2[0] = mP2[0] * cos(roll) + mP2[1] * sin(roll) iP2[1] = -mP2[0] * sin(roll) + mP2[1] * cos(roll) iP2[2]=mP2[2] iP3[0] = mP3[0] * cos(roll) + mP3[1] * sin(roll) iP3[1] = -mP3[0] * sin(roll) + mP3[1] * cos(roll) iP3[2]=mP3[2] iP4[0] = mP4[0] * cos(roll) + mP4[1] * sin(roll) iP4[1] = -mP4[0] * sin(roll) + mP4[1] * cos(roll) iP4[2]=mP4[2] where mP1, mP2, mP3, and mP4 are calculated in step 404.

[0027] The orientation of the marker 200 is expressed as an angle and, in one embodiment, is determined as follows. Direction 1=-atan2(iP2[2]-iP1[2],iP2[0]-iP1[0]) Direction 2=-atan2(iP3[2]-iP4[2],iP3[0]-iP4[0]) Direction = (Direction 1 + Direction 2) / 2 In one embodiment, intermediate three-dimensional coordinates jP1, jP2, jP3, jP4 for each of the four vertices of the marker 200 are calculated prior to calculating the pitch of the marker 200. In one embodiment, the intermediate three-dimensional coordinates are calculated as follows: jP1[0]=iP1[0]*cos(azimuth)-iP1[2]*sin(azimuth) jP1[1]=iP1[1] jP1[2]=iP1[0]*sin(azimuth)+iP1[2]*cos(azimuth) jP2[0]=iP2[0]*cos(azimuth)-iP2[2]*sin(azimuth) jP2[1]=iP2[1] jP2[2]=iP2[0]*sin(azimuth)+iP2[2]*cos(azimuth) jP3[0]=iP3[0]*cos(azimuth)-iP3[2]*sin(azimuth) jP3[1]=iP3[1] jP3[2]=iP3[0]*sin(azimuth)+iP3[2]*cos(azimuth) jP4[0]=iP4[0]*cos(azimuth)-iP4[2]*sin(azimuth) jP4[1]=iP4[1] jP4[2]=iP4[0]*sin(azimuth)+iP4[2]*cos(azimuth) where iP1, iP2, iP3, and iP4 are calculated in the previous step.

[0028] The pitch of the marker 200 is expressed as an angle and, in one embodiment, is determined as follows: pitch1=atan2(jP1[2]-jP4[2], jP1[1]-jP4[1]) Pitch 2 = atan2(jP2[2]-jP3[2], jP2[1]-jP3[1]) pitch = (pitch1 + pitch2) / 2

[0029] At step 410, the position and orientation of the stereo camera 102 is determined. In one embodiment, the position and orientation of the stereo camera 102 is determined based on information received by the controller 106 from the navigation system 108. In one embodiment, the navigation system 108 determines its position and orientation and transmits these data to the controller 106. In one embodiment, these data are the longitude, latitude, altitude coordinates and direction angles (pitch, roll, heading) of the vehicle 104, which specify the position and orientation of the navigation system 108. The position and orientation of the stereo camera 102 is determined based on its position and orientation on the vehicle 104 with respect to the navigation system 108. In one embodiment, the relative position and orientation of the stereo camera 102 with respect to the navigation system 108 is stored in the controller 106, and the controller 106 can determine the position and orientation of the stereo camera 102 based on the position information received from the navigation system 108.

[0030] In step 412, the position of the marker 200 in the global coordinate system is determined. In one embodiment, the position of the marker 200 is determined based on the position of the center of the marker 200 determined in step 406. The position of the center of the marker 200 is known in the coordinate system 300 of the stereo camera 102. Since the position and orientation of the stereo camera 102 are known in step 410 and the position of the center of the marker 200 relative to the stereo camera 102 is known, the position of the marker 200 can also be determined. In the same step, the pose of the marker 200 is determined based on the pitch, roll and heading of the marker 200 determined in step 408. Since the position and orientation of the stereo camera 102 are known in step 410 and the pose of the marker 200 relative to the stereo camera 102 is known in step 408, the pose of the marker 200 in the global coordinate system can also be determined. It is noted that the method 400 is a non-contact method for determining the position and pose of a marker.

[0031] The determined position and orientation of the markers can be used to determine the position and orientation of an object on which one or more markers are disposed. The method 400 for determining the position and orientation of the markers 200 can be used in a variety of applications. For example, one application may use one or more markers to determine the position and / or orientation of an object on which the markers are disposed. Some such applications are described below.

[0032] FIG. 5 illustrates an example of application of the method 400 for determining the position and orientation of each marker when multiple markers are placed on a construction machine. The bulldozer 500 has a blade 504 that can be used to perform earth grading and other surface modification operations. Markers 502a and 502b are placed on the blade 504 within the field of view 506 of a stereo camera 508 located on the bulldozer 500. Using the techniques described above, the position and orientation of the blade 504 in the local coordinate system of the stereo camera 102 can be determined based on the position and orientation of the markers 502a and 502b located on the blade 504. Based on the placement of the bulldozer 500 in the local coordinate system and the position and orientation of the blade 504, the position and orientation of the blade 504 in the global coordinate system can be determined. In one embodiment, the stereo camera 102 may be placed on a mast configured such that each moving marker is placed within the field of view of the camera. The non-contact nature of method 400 allows for the calculation of the three-dimensional position and orientation of the machine and machine implements, the estimation of the amount of material prism (e.g., soil prism) to prevent its progression through the blade, and the determination of the tracked vehicle's speed compared to the vehicle's speed to calculate a coefficient characterizing the vehicle's slipperiness when moving under different conditions (e.g., heavy loads).

[0033] 6 illustrates an example application of method 400 for determining the position and orientation of each marker when multiple markers are placed on a towed implement 602. A tractor 600 pulls a towed implement 602 configured to perform an agricultural task. The position and orientation of the towed implement 602 are determined based on the position and orientation of markers 604a and 604b located within a field of view 606 of a stereo camera 608 mounted on the tractor 600. In one embodiment, the method described herein can be used to estimate the altitude of the towed implement 602. This allows for determination of the depth of a plow into the ground, or other tasks that require monitoring of the altitude of the markers.

[0034] 7 shows an example of application of the method 400 for determining the position and orientation of a plurality of markers placed in an environment in which the vehicle is driving, to control the movement of the vehicle 700 (e.g., an asphalt paver). The vehicle 700 shown here is moving in a tunnel with markers 704a, 704b, 704c, 704d placed on a fixed object in the environment (e.g., one wall of the tunnel) and markers 706a, 706b, 706c, 706d placed on an opposite fixed object in the environment (e.g., the opposite wall of the tunnel). These markers are detected by one or more stereo cameras 708a and 708b (e.g., one stereo camera pointing to one side of the vehicle 700 and one stereo camera pointing to the opposite side of the vehicle 700). The markers 704b and 704c shown here are placed in the field of view 702a of the stereo camera 708a pointing to one side of the vehicle 700. Markers 706b and 706c are shown positioned within the field of view 702b of stereo camera 708b pointing to opposite sides of the vehicle 700. In one embodiment, the placement of each marker is based on the field of view of each stereo camera, so that at least one marker on each tunnel wall is included within the field of view of each moving stereo camera. In one embodiment, the position of each marker relative to the start of the tunnel is encoded into the shape of the marker. For example, the marker ID reflects the distance of the marker in meters relative to the start of the tunnel. Using the position and orientation of each marker placed within the field of view of each stereo camera, the position and orientation of the vehicle relative to each marker is determined based on the position and orientation of each stereo camera. The movement of the vehicle (e.g., speed and direction) is controlled based on the determined placement of the vehicle and each marker. Thus, the method is useful for managing the movement and operation of autonomous vehicles and / or when a GNSS system is not available (e.g., when GNSS signals cannot be received in a tunnel). In one embodiment, these markers may be placed near the perimeter of an area (eg, on the walls surrounding a room) for the purpose of determining the placement of machines within the area.For example, if the position of one or more markers in the local coordinate system is known, it is possible to determine the local coordinates of the machine within the room by triangulation.

[0035] 8 shows an example application of the method 400 for determining the position and orientation of each marker when multiple markers are placed on multiple autonomous or automated vehicles. The multiple markers placed on each vehicle allow other vehicles to identify and determine the position and orientation of each vehicle. The combine 800 shown here has markers 802 that allow other autonomous or automated vehicles to identify the vehicle and localize its position and orientation. This information can be used for collision avoidance systems when multiple autonomous or automated vehicles are used in a fleet.

[0036] FIG. 9 illustrates an example application of the method 400 for determining the position and orientation of each marker when multiple markers are placed in a parking spot where an automated or autonomous vehicle is parked (e.g., painted or painted on the parking space). The tractor 900 has a stereo camera 908 for capturing images of the multiple markers. Vehicle parking spaces P9 and P10 are identified using markers 902 and 904, respectively. The stereo camera 908 of the tractor 900 captures images of each marker located within the field of view 906 of the stereo camera. The markers 902 and 904 identify each parking space, allowing the tractor 900 to move into the designated space based on the position and orientation of each marker. In one embodiment, the autonomous vehicle performs an approach 910 to the parking space P9 while simultaneously attempting to minimize the distance between the camera and the marker 902 and the roll angle relative to the marker 902.

[0037] The foregoing detailed description is to be understood in all respects as illustrative and illustrative, but not restrictive, and the scope of the inventive concepts disclosed herein should be interpreted with the fullest breadth permitted by the respective patent laws. The embodiments shown and described herein are merely illustrative of the principles of the inventive concepts, and those skilled in the art will appreciate that various modifications may be made without departing from the scope and spirit of the invention. Those skilled in the art will appreciate that other combinations of the various features may be made without departing from the scope and spirit of the inventive concepts.

Claims

1. acquiring images of markers on an object with a stereo camera, the markers comprising coded information; determining a position of the marker relative to a local coordinate system of the stereo camera based on the images; and determining a position of the object relative to the local coordinate system of the stereo camera based on the positions of the markers; The method according to claim 1, further comprising:

2. The method of claim 1 , wherein the encoded information identifies the object.

3. The method of claim 2 , wherein the encoded information identifies where the marker is located on the object.

4. determining the position and orientation of the stereo camera in a global coordinate system; and determining a location of the object in the global coordinate system based on the position of the object relative to the local coordinate system and the location of the stereo camera in the global coordinate system; 2. The method of claim 1, further comprising:

5. determining a center of the marker based on the image; The method of claim 1 , wherein the determining of the position of the marker relative to the local coordinate system of the stereo camera is further based on the center of the marker.

6. determining a roll of the marker; determining an orientation of the marker; determining the pitch of the marker; and determining an attitude of the marker based on the pitch, the roll, and the heading of the marker; 2. The method of claim 1, further comprising:

7. determining a pose of the object based on the pose of the marker; 7. The method of claim 6, further comprising:

8. determining a plurality of vertices around a center of the marker; The method of claim 6 , wherein the determining of the pose of the marker is further based on the plurality of vertices.

9. 4. The method of claim 3, wherein the determination of the location of the object is further based on where the marker is located on the object.

10. The method of claim 1 , wherein the stereo camera is mounted on a machine and the object is an implement mounted on the machine.

11. The method of claim 10, wherein the machine is a bulldozer and the implement is a blade.

12. 11. The method of claim 10, wherein the machine is a tractor and the object is a pulled machine.

13. The method of claim 1 , wherein the stereo camera is mounted on a first vehicle and the object is a second vehicle.

14. acquiring images of markers from a stereo camera attached to a machine, the markers being located in an environment in which the machine is located and comprising coded information; determining a position of the marker relative to a local coordinate system of the stereo camera based on the images; and determining a location of the machine relative to a global coordinate system based on the encoded information and the positions of the markers relative to a local coordinate system of the stereo camera; The method according to claim 1, further comprising:

15. The method of claim 14 , wherein the encoded information identifies the location of the marker within the environment relative to the global coordinate system.

16. 16. The method of claim 15, wherein the machine is an asphalt paver and the markers are disposed on fixed objects within the environment.

17. 16. The method of claim 15, wherein the machine is a vehicle and the marker is located on a fixed object.

18. 16. The method of claim 15, wherein the machine is a first vehicle and the marker is located on a second vehicle.

19. A stereo camera and a controller communicating with the stereo camera; The controller: acquiring images of markers on an object with the stereo camera, the markers comprising coded information; determining a position of the marker relative to a local coordinate system of the stereo camera based on the images; and determining a position of the object relative to the local coordinate system of the stereo camera based on the positions of the markers; 23. An apparatus configured to perform the operations of:

20. 20. The apparatus of claim 19, wherein the encoded information identifies the object.

21. 21. The apparatus of claim 20, wherein the encoded information identifies where the marker is located on the object.

22. 22. The apparatus of claim 21, wherein the determination of the position of the object is further based on where the marker is located on the object.

23. The operation includes: determining a position of the stereo camera in a global coordinate system; and determining a location of the object in the global coordinate system based on the position of the object relative to the local coordinate system and the location of the stereo camera in the global coordinate system; 20. The apparatus of claim 19 further comprising:

24. The operation includes: determining a roll of the marker; determining an orientation of the marker; determining the pitch of the marker; and determining an attitude of the marker based on the pitch, the roll, and the heading of the marker; 20. The apparatus of claim 19 further comprising:

Images