EP4364093A1 - Objektverfolgung basierend auf einem bewegungsmodell - Google Patents
Objektverfolgung basierend auf einem bewegungsmodellInfo
- Publication number
- EP4364093A1 EP4364093A1 EP22738374.2A EP22738374A EP4364093A1 EP 4364093 A1 EP4364093 A1 EP 4364093A1 EP 22738374 A EP22738374 A EP 22738374A EP 4364093 A1 EP4364093 A1 EP 4364093A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- tracked
- point
- movement
- state
- sensor data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
- G06T7/251—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments involving models
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/277—Analysis of motion involving stochastic approaches, e.g. using Kalman filters
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/62—Extraction of image or video features relating to a temporal dimension, e.g. time-based feature extraction; Pattern tracking
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
- B60W2420/40—Photo, light or radio wave sensitive means, e.g. infrared sensors
- B60W2420/403—Image sensing, e.g. optical camera
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
- B60W2420/40—Photo, light or radio wave sensitive means, e.g. infrared sensors
- B60W2420/408—Radar; Laser, e.g. lidar
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/40—Dynamic objects, e.g. animals, windblown objects
- B60W2554/404—Characteristics
- B60W2554/4044—Direction of movement, e.g. backwards
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
Definitions
- the present invention relates to a method for object tracking, wherein a first state of an object to be tracked is estimated by means of at least one computing unit using a predefined movement model for the object to be tracked, the first state containing a first direction of movement of a point to be tracked, whose position with respect to the to be tracked object is specified and environment sensor data are generated by means of an environment sensor system, which represent the object to be tracked.
- the invention also relates to a method for at least partially automatically guiding an ego vehicle, an electric vehicle guidance system and a computer program product.
- the object tracking from the perspective of the ego vehicle is important, with the object being, for example, other road users or other vehicles in the vicinity of the vehicle Ego vehicle is a key task to ensure a safe and reliable automatic or partially automatic driving or driver support.
- iterative methods are used, for example, which require known motion models that approximately describe the dynamic behavior of the object to be tracked.
- a possible and widespread movement model is the so-called single-track model.
- Kalman filter methods or derivatives thereof for example an extended Kalman filter method, an unscented Kalman filter method and so on, are used for state prediction and verification or refinement. It is an object of the present invention to increase the accuracy of object tracking based on a motion model, in particular tracking external vehicles from the perspective of an ego vehicle based on a motion model.
- the invention is based on the idea of moving a point of the object to be tracked, which is tracked using the motion model or whose state is estimated using the motion model, so that the resulting direction of movement of the shifted point better matches a geometric orientation of the object to be tracked, such as it is given on the basis of environment sensor data, matches.
- a method for object tracking is specified.
- At least one computing unit in particular an ego vehicle, is used to estimate a first state of an object to be tracked, which is located in particular in the vicinity of the ego vehicle, using a predefined movement model for the object to be tracked.
- the first state includes a first direction of movement of a point to be tracked.
- a surroundings sensor system in particular of the ego vehicle, is used to generate surroundings sensor data which represent the object to be tracked.
- a geometric orientation of the object to be tracked is determined by means of the at least one computing unit based on the surroundings sensor data.
- the point to be tracked is shifted by means of the at least one computing unit depending on a first deviation of the geometric orientation from the first direction of movement.
- a second state of the object to be tracked is determined by means of the at least one computing unit as a function of the first state and the shifted point.
- the point to be tracked has a predefined position with respect to the object to be tracked.
- the point to be tracked can be on or in the object, but can also be outside of the object. It is therefore in particular a virtual point that is tracked using the motion model.
- the state, in particular the first and the second state, of the object to be tracked contains the corresponding direction of movement of the object to be tracked and possibly further model parameters, for example a speed, acceleration and/or position of the point to be tracked and so on.
- the direction of movement of the state ie in particular the first state, corresponds to the direction of movement of the point to be tracked.
- this point is transferred to the shifted point, so that the second state contains, for example, the direction of movement of the shifted point instead of the direction of movement of the point to be tracked.
- the direction of movement of the object to be tracked represents a particularly well-suited model parameter.
- the direction of movement can be estimated within the framework of the movement model on the one hand and measured directly or indirectly using the environment sensor system of the ego vehicle, for example using cameras, lidar systems or radar systems, on the other hand.
- computer vision algorithms or other algorithms for automated perception can be used for this purpose in order to obtain corresponding measured values for the direction of movement based on the environmental sensor data.
- the movement of the point to be tracked consists of a translational movement and a rotational movement.
- the first direction of movement can be understood in particular as the direction of movement of the translational movement of the point to be tracked.
- the first direction of movement and the geometric orientation can be given, for example, by corresponding angles in a known coordinate system.
- the first deviation therefore corresponds in particular to an angular difference or an absolute value of the corresponding angular difference.
- the geometric orientation of the object to be tracked can be given, for example, by a constant direction that is firmly predetermined with respect to the object to be tracked.
- the geometric orientation of a vehicle can be given, for example, by its longitudinal axis or the direction of the longitudinal axis. This can be determined, for example, at least approximately by the alignment or orientation of a delimiting figure, also referred to as a delimiting box (English: "Bounding Box"), which the at least one computing unit is based on can determine the environment sensor data.
- the delimiting figure can correspond to a rectangle or a cuboid, for example, which encloses the object to be tracked in the representation by the environment sensor data, ie for example in a corresponding camera image or in a corresponding lidar or radar point cloud.
- the direction of movement of the points is generally different given a general movement of the object to be tracked. Accordingly, the direction of movement of the point to be tracked generally deviates from the geometric orientation, so that the first deviation is generally non-zero.
- the shifting of the point to be tracked in order to obtain the shifted point can be greater, for example, the greater the first deviation.
- the first state can be estimated, for example, using a Kalman filter algorithm or based on another mathematical estimation algorithm, in particular an iterative estimation algorithm.
- Such methods usually include estimating a state of the object to be tracked, in particular based on the movement model, and refining or improving the estimated state taking into account measured values, in particular the environmental sensor data.
- the motion model can be used as a basis, but corresponding actual measured values can also be recorded in order to take into account deviations from the ideal or expected behavior.
- the first state can then correspond, for example, to the state estimated using the motion model and the second state to the state improved or refined using the environmental sensor data.
- the first and the second state relate in particular to the same time segment or the same iteration step.
- the refinement step ie the step for determining the second state of the object to be tracked, is not based on the point to be tracked, its direction of movement as the first direction of movement and part of the first State was estimated, but performed based on the shifted point.
- a second deviation of the direction of movement of the shifted point from the geometric orientation can be smaller than the first deviation or ideally equal to zero. In this way, a better match between the refined estimated state and the motion model is achieved.
- an error in the object tracking can be reduced and accordingly the accuracy and reliability of the object tracking can be increased, particularly when the method steps mentioned are repeated iteratively.
- this increases the security of a driver assistance function or a function for automatically or partially automatically driving the ego vehicle, which is based on the output of the object tracking method.
- the improvement in accuracy by the invention is all the greater, the greater the first deviation of the first movement direction from the geometric orientation of the object to be tracked.
- the improvement in accuracy can be greater as the object is larger.
- the environment sensor system can contain one or more subsystems, for example one or more cameras, one or more lidar sensor systems and/or one or more radar sensor systems.
- the environmental sensor data may include one or more camera images, one or more lidar point clouds, and/or one or more radar point clouds.
- a current radius of movement of the point to be tracked is determined, in particular by means of the at least one computing unit, based on the first state.
- the shifting of the point to be followed then takes place depending on the current radius of movement.
- Both the point to be followed and the shifted point lie on a circular arc that corresponds to the current radius of movement.
- the at least one computing unit can determine a center point of the circular arc and the current radius of movement based on the first state.
- the displacement of the point to be followed is dependent on the first deviation and dependent on the current radius of movement.
- the greater the first deviation and the greater the instantaneous radius of movement the greater the displacement.
- the deviation of the geometric orientation from a second direction of movement of the point to be tracked can be at least partially compensated for in relation to the first deviation of the geometric orientation from the first direction of movement of the point to be tracked.
- the first state contains a translation speed of the object to be tracked, in particular of the point to be tracked, and an angular speed of the point to be tracked.
- the current radius of movement is determined, in particular by means of the at least one computing unit, as the ratio of the translational speed to the angular speed, ie as the quotient of the translational speed and the angular speed.
- the translation speed is in particular parallel to the first direction of movement and the angular speed corresponds to an angular speed around the center of the circle corresponding to the instantaneous radius of movement. In this way, the current radius of movement can be reliably determined or estimated.
- the point to be tracked is moved along an arc of a circle having a radius equal to the current radius of movement.
- the point to be tracked and the point moved lie on an arc of a circle.
- the first deviation is determined as the first angular difference between the geometric orientation and the first direction of movement.
- the second state includes the second direction of movement of the displaced point.
- the second deviation of the geometric orientation from the second direction of movement is smaller than the first deviation, in particular equal to zero or approximately equal to zero.
- the second direction of movement is equal to the geometric orientation or approximately equal to the geometric orientation.
- the second deviation is at least approximately equal to zero in this case. In this way, a good agreement with the motion model can be achieved.
- a point cloud is generated based on the surroundings sensor data or the surroundings sensor data contain the point cloud.
- a portion of the point cloud that represents the object to be tracked is identified.
- a delimiting figure is determined, in particular by means of the at least one computing unit, which encloses the part of the point cloud, the delimiting figure having a predefined geometric shape.
- the geometric orientation of the object to be tracked corresponds to a spatial alignment of the boundary figure.
- the geometric orientation can be clearly defined according to the spatial orientation of the delimiting figure.
- the delimiting figure is a rectangle or a cuboid.
- an aspect ratio of the rectangle or the cuboid can be predetermined or variable.
- the point cloud corresponds in particular to a lidar point cloud or a radar point cloud.
- the point cloud contains a large number of points.
- the part of the point cloud that represents the object to be tracked corresponds to a subset of the point cloud.
- the determination or identification of the part of the point cloud that represents the object to be tracked can be achieved, for example, by using a cluster method.
- Such embodiments have the advantage that corresponding limiting figures can be determined using known methods, so that the first deviation can be precisely determined and compensated for.
- a reproducible and reliable result of the determination of the geometric orientation can be achieved by using a rectangular or cuboid delimitation figure.
- a camera image is generated based on the surroundings sensor data or the surroundings sensor data contain the camera image.
- a boundary figure is determined which encloses the representation of the object to be tracked in the camera image, the boundary figure having a predefined shape.
- the geometric orientation of the object to be tracked corresponds to a spatial alignment of the boundary figure.
- the delimiting figure can be determined, for example, using an object recognition algorithm using the at least one computing unit.
- This can, for example, be an algorithm based on machine learning, for example a
- Algorithm based on a trained artificial neural network. Numerous architectures are known for this, for example corresponding to the so-called YOLO algorithm. According to at least one embodiment, a method based on a Kalman filter is used to determine the second state.
- the method based on the Kalman filter can, for example, correspond to a Kalman filter method, an extended Kalman filter method, an unscented Kalman filter method or some other derivative of the Kalman filter method.
- the first state is first estimated, which is also referred to as prediction.
- a Kalman gain factor or the like is then determined, for example, and this is used to improve the prediction, in particular depending on the corresponding measured values, here the surroundings sensor data, in order to determine the second state, which can also be referred to as refinement.
- refinement is not based on the original point to be traced, but on the point that has been moved. In this way, established methods based on the Kalman filter or the like can be enabled to achieve more accurate object tracking.
- a method for at least partially automatically driving an ego vehicle which is in particular a motor vehicle, is specified.
- a method according to the invention for object tracking is carried out by means of the ego vehicle, in particular an electronic vehicle guidance system of the ego vehicle, which contains the environment sensor system and the at least one computing unit.
- a control unit of the ego vehicle, in particular the electronic vehicle guidance system, for example the at least one computing unit, generates at least one control signal for at least partially automatic guidance of the ego vehicle depending on the second state of the object to be tracked.
- the at least one control signal is fed to at least one corresponding actuator of the ego vehicle, which then at least partially automatically guides the ego vehicle based on the at least one control signal or can implement the at least partially automatic guidance.
- the at least one control signal can also be used for driver assistance for a driver of the ego vehicle.
- an electronic vehicle guidance system for an ego vehicle has at least one computing unit that is set up to estimate a first state of an object to be tracked, in particular in the vicinity of the ego vehicle, using a predefined movement model for the object to be tracked, the first state having a first direction of movement of a point to be tracked.
- the electronic vehicle guidance system has an environment sensor system for the ego vehicle, which is set up to generate environment sensor data which represent the object to be tracked.
- the at least one computing unit is set up to determine a geometric orientation of the object to be tracked based on the surroundings sensor data, to move the point to be tracked as a function of a first deviation of the geometric orientation from the first direction of movement, and to determine a second state of the object to be tracked depending on the first state and the shifted point.
- an electronic vehicle guidance system according to the invention is set up to carry out a method according to the invention or carries out such a method.
- a computer program with instructions is provided. If the commands are executed by an electronic vehicle guidance system according to the invention, in particular by the at least one computing unit of the electronic vehicle guidance system, the commands cause the electronic vehicle guidance system to implement a method according to the invention for object tracking or a method according to the invention for at least partially automatically guiding an ego vehicle to perform.
- a computer-readable storage medium which stores a computer program according to the invention.
- the computer program according to the invention and the computer-readable storage medium according to the invention can be understood as respective computer program products with the commands.
- An electronic vehicle guidance system can be understood to mean an electronic system that is set up to guide or control the motor vehicle fully automatically or fully autonomously, in particular without the driver having to intervene in a control system.
- the motor vehicle or the electronic vehicle guidance system carries out all necessary functions, such as steering, braking and/or acceleration maneuvers that may be necessary, the observation and recording of road traffic and the associated necessary reactions, automatically and fully automatically.
- the electronic vehicle guidance system can be used to implement a fully automatic or fully autonomous driving mode of the motor vehicle according to level 5 of the classification according to SAE J3016.
- Under an electronic vehicle guidance system can also a driver assistance system (English: “advanced driver assistance system", ADAS) are understood, which supports the driver in a partially automated or partially autonomous driving of the motor vehicle.
- ADAS advanced driver assistance system
- the electronic vehicle guidance system can be used to implement a partially automated or partially autonomous driving mode of the motor vehicle according to one of levels 1 to 4 according to the SAE J3016 classification.
- SAE J3016 refers to the corresponding standard in the June 2018 version.
- the at least partially automatic vehicle guidance can therefore include guiding the motor vehicle according to a fully automatic or fully autonomous driving mode of level 5 according to SAE J3016.
- the at least partially automatic vehicle guidance can also include guiding the motor vehicle according to a partially automated or partially autonomous driving mode according to one of levels 1 to 4 according to SAE J3016.
- a computing unit can be understood in particular as a data processing device, so the computing unit can in particular process data for carrying out computing operations. This may also include operations to perform indexed accesses to a data structure, for example a look-up table (LUT).
- LUT look-up table
- the processing unit can contain one or more computers, one or more microcontrollers and/or one or more integrated circuits, for example one or more application-specific integrated circuits, ASIC (English: “application-specific integrated circuit”), one or more field-programmable gate Arrays, FPGA, and/or one or more single-chip systems, SoC (English: "System on a Chip”).
- the processing unit can also have one or more processors, for example one or more microprocessors, one or more central processing units, CPU (central processing unit), one or more graphics processor units, GPU and/or contain one or more signal processors, in particular one or more digital signal processors, DSP.
- the computing unit can also contain a physical or a virtual network of computers or other of the units mentioned.
- the computing unit includes one or more hardware and/or software interfaces and/or one or more memory units.
- a memory device can be configured as volatile data storage, such as dynamic random access memory (DRAM), or static random access memory (SRAM), or non-volatile Data memory, for example as a read-only memory, ROM, as a programmable read-only memory, PROM, as an erasable read-only memory, EPROM (erasable read-only memory) ), as electrically erasable read-only memory, EEPROM (English: “electrically erasable read-only memory”), as flash memory or flash EEPROM, as ferroelectric memory with random access, FRAM (English: “ferroelectric random access memory”), as magnetoresistive random access memory (MRAM) or phase change random access memory (PCRAM). random access memory”).
- DRAM dynamic random access memory
- SRAM static random access memory
- non-volatile Data memory for example as a read-only memory, ROM, as a programmable read-only memory,
- a component of the electronic vehicle guidance system according to the invention in particular the at least one computing unit or the control unit of the electronic vehicle guidance system, is set up, configured, designed or the like to perform or realize a specific function, a specific To achieve an effect or to serve a specific purpose, this can be understood in such a way that the component, beyond the basic or theoretical usability or suitability of the component for this function, effect or purpose, through a corresponding adaptation, programming, physical design and so on is specifically and actually capable of performing or realizing the function, achieving the effect, or serving the purpose.
- An object recognition algorithm can be understood as a computer algorithm that is able to identify one or more objects within a provided input image by defining corresponding bounding figures or bounding boxes (English: "bounding boxes") and assigning each of the bounding boxes a corresponding object class, where the object classes can be selected from a predefined set of object classes.
- the assignment of an object class to a bounding box can be understood in such a way that a corresponding confidence value or a probability for the object identified within the bounding box belonging to the corresponding object class is provided.
- the algorithm may have such a confidence value or a provide probability.
- Object class assignment may include, for example, selecting or providing the object class with the highest confidence or probability.
- the algorithm can only specify the bounding boxes without assigning a corresponding object class.
- FIG. 1 a schematic representation of an ego vehicle with an exemplary embodiment of an electronic vehicle guidance system according to the invention.
- FIG. 2 shows a schematic flowchart of an exemplary embodiment of a method for object tracking according to the invention.
- FIG. 1 schematically shows an ego vehicle 1 which has an exemplary embodiment of an electronic vehicle guidance system 2 according to the invention. Furthermore, an object 5 to be tracked is shown in the vicinity of the ego vehicle 1 .
- the object 5 to be tracked is, in particular, another vehicle that is only shown schematically as a rectangle.
- the electronic vehicle guidance system 2 includes a computing unit 3, which can be designed, for example, as a control unit, ECU, of the ego vehicle 1 or can be part of a control unit.
- the electronic vehicle guidance system 2 has also an environment sensor system 4a, 4b, for example a camera 4b and/or a lidar system 4a and/or a radar system (not shown).
- the vehicle guidance system 2 is able to carry out a method according to the invention for object tracking.
- a corresponding flow chart of such a method is shown schematically in FIG.
- step S1 of the method for example, an initial state of the object 5 to be tracked is determined using a predefined movement model, for example a single-track model.
- the processing unit 3 can use, for example, surroundings sensor data from the surroundings sensor system 4a, 4b.
- step S2 a first state of the object 5 to be tracked is estimated or predicted using the predefined movement model by the computing unit 3, the first state containing a first movement direction 6a of a point 8a to be tracked of the object 5 to be tracked.
- surroundings sensor data representing the object 5 to be tracked are generated by means of the surroundings sensor system 4a, 4b.
- step S3 the computing unit 3 determines a geometric orientation of the object 5 to be tracked based on the environmental sensor data.
- the computing unit 3 can, for example, apply an object recognition algorithm to a camera image of the camera 4b and/or a cluster algorithm to a point cloud of the lidar system 4a. In this way, the computing unit 3 can determine a boundary figure that encloses the object 5 to be tracked.
- a rectangle is shown as the delimiting figure 7 in FIG.
- the geometric orientation then corresponds to a predetermined spatial orientation of the delimiting figure 7, for example the geometric orientation is parallel to one side of the delimiting figure 7, in particular to the longer side of the rectangle.
- the computing unit 3 also determines, based on the surroundings sensor data, an instantaneous movement radius of the object to be tracked, which corresponds to a radius of a circle 9 .
- R corresponds to the radius of the circle 9
- D corresponds to an angular difference between the first direction of movement 6a of the point 8a to be tracked and the geometric orientation of the point to be tracked Object 5.
- the second direction of movement 6b of the shifted point 8b is then also approximately equal to the geometric orientation.
- step S4 the computing unit can calculate a correction factor based on the shifted point 8b and in particular the second direction of movement 6b. If, for example, an approach based on a Kalman filter is followed, then the correction factor can correspond to a corresponding Kalman amplification factor. In step S4, the state of the object 5 to be tracked is then updated depending on the correction factor, which in turn is determined depending on the shifted point 8b.
- the second direction of movement 6b which is used to update the state of the object to be tracked, corresponds at least approximately to the geometric orientation of the object 5 to be tracked, so that a more precise object tracking is made possible.
- the point to be tracked is shifted to a point that, in particular, has no transverse velocity, ie corresponds to a point that moves in the geometric orientation direction of the object to be tracked.
- the object to be tracked is in particular a vehicle, for example a motor vehicle with two axles.
- the shifted point can be, for example, on a non-steerable axle, ie an axle with non-steerable wheels, of the vehicle.
- the shifted point may be between the two axles.
- the shifted point can also lie outside the vehicle.
- the shifted point can be determined by minimizing the deviation between the geometric orientation of the object to be tracked from the direction of motion based on the motion model.
- an object filter such as an extended Kalman filter, based on a corresponding state vector may be used.
- the state vector may include two-dimensional location coordinates of a point to be tracked, a translational velocity, a yaw rate, a yaw angle, and so on.
- the computing unit can determine the current radius of movement based on the movement model or based on the ratio of the translation speed to the angular speed of the object.
- the center of the corresponding circle can also be determined, with the line connecting the center of the circle and the point to be tracked being perpendicular to the direction of movement of the point to be tracked.
- the point to be tracked can then be shifted on the circle by an angle corresponding to the angular difference between the geometric orientation and the direction of movement, so as to determine an optimal shifted point for tracking.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Automation & Control Theory (AREA)
- Human Computer Interaction (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| DE102021116693.4A DE102021116693A1 (de) | 2021-06-29 | 2021-06-29 | Objektverfolgung basierend auf einem Bewegungsmodell |
| PCT/EP2022/066939 WO2023274795A1 (de) | 2021-06-29 | 2022-06-22 | Objektverfolgung basierend auf einem bewegungsmodell |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| EP4364093A1 true EP4364093A1 (de) | 2024-05-08 |
Family
ID=82446467
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP22738374.2A Pending EP4364093A1 (de) | 2021-06-29 | 2022-06-22 | Objektverfolgung basierend auf einem bewegungsmodell |
Country Status (6)
| Country | Link |
|---|---|
| US (1) | US20240412381A1 (de) |
| EP (1) | EP4364093A1 (de) |
| JP (1) | JP7717858B2 (de) |
| KR (1) | KR20240023621A (de) |
| DE (1) | DE102021116693A1 (de) |
| WO (1) | WO2023274795A1 (de) |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8126642B2 (en) * | 2008-10-24 | 2012-02-28 | Gray & Company, Inc. | Control and systems for autonomously driven vehicles |
| DE102013018310A1 (de) * | 2013-10-31 | 2015-04-30 | Daimler Ag | Verfahren zur Bestimmung einer Bewegung eines Objekts |
| US10037613B1 (en) * | 2017-03-30 | 2018-07-31 | Uber Technologies, Inc. | Systems and methods to track vehicles proximate perceived by an autonomous vehicle |
| US10816344B2 (en) * | 2018-03-07 | 2020-10-27 | Aptiv Technologies Limited | Method and system for determining the pointing angle of a moving object |
| US11550061B2 (en) * | 2018-04-11 | 2023-01-10 | Aurora Operations, Inc. | Control of autonomous vehicle based on environmental object classification determined using phase coherent LIDAR data |
| JP2021067647A (ja) * | 2019-10-28 | 2021-04-30 | ロベルト・ボッシュ・ゲゼルシャフト・ミト・ベシュレンクテル・ハフツングRobert Bosch Gmbh | 車両追跡装置 |
| JP7383451B2 (ja) * | 2019-10-28 | 2023-11-20 | ロベルト・ボッシュ・ゲゼルシャフト・ミト・ベシュレンクテル・ハフツング | 車両追跡装置 |
| DE102020105192B4 (de) * | 2020-02-27 | 2022-03-10 | Bayerische Motoren Werke Aktiengesellschaft | Verfahren zum Detektieren bewegter Objekte in einer Fahrzeugumgebung und Kraftfahrzeug |
| US12110042B1 (en) * | 2020-10-14 | 2024-10-08 | Aurora Operations, Inc. | Systems and methods for generating physically realistic trajectories |
| EP3985411B1 (de) * | 2020-10-19 | 2025-03-19 | Aptiv Technologies AG | Verfahren und vorrichtung zur erkennung von objekten |
-
2021
- 2021-06-29 DE DE102021116693.4A patent/DE102021116693A1/de active Pending
-
2022
- 2022-06-22 US US18/575,695 patent/US20240412381A1/en active Pending
- 2022-06-22 JP JP2023580486A patent/JP7717858B2/ja active Active
- 2022-06-22 WO PCT/EP2022/066939 patent/WO2023274795A1/de not_active Ceased
- 2022-06-22 EP EP22738374.2A patent/EP4364093A1/de active Pending
- 2022-06-22 KR KR1020247002041A patent/KR20240023621A/ko active Pending
Also Published As
| Publication number | Publication date |
|---|---|
| JP2024527543A (ja) | 2024-07-25 |
| US20240412381A1 (en) | 2024-12-12 |
| DE102021116693A1 (de) | 2022-12-29 |
| KR20240023621A (ko) | 2024-02-22 |
| WO2023274795A1 (de) | 2023-01-05 |
| JP7717858B2 (ja) | 2025-08-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| DE112018006161B4 (de) | System und Verfahren zum Steuern eines Fahrzeugs | |
| DE102019112413B4 (de) | Verfahren und vorrichtung zur multi-sensor-datenfusion für automatisierte und autonome fahrzeuge | |
| DE102019116569A1 (de) | LOKALISIERUNG FÜR AUTONOME FAHRZEUGE UNTER VERWENDUNG VON GAUßSCHEN VERMISCHUNGSMODELLEN | |
| DE102017118808A1 (de) | Verfahren und Systeme für Fahrzeugpositionierungs-Rückmeldung | |
| DE102009004415B4 (de) | Verfahren und Systeme zum Berechnen der Gierverstärkung für die Verwendung bei der Steuerung eines Fahrzeugs | |
| WO2024041833A1 (de) | Visuelle wahrnehmung mit einem fahrzeug basierend auf einem kamerabild und einer ultraschallkarte | |
| EP4153943B1 (de) | Verfahren zum ermitteln einer ausgangspose eines fahrzeugs | |
| DE102020109883A1 (de) | Vorrichtung zur ausweichlenkungsunterstützung, system damit und verfahren davon | |
| WO2025012194A1 (de) | Verfahren zum betreiben eines assistenzsystems eines zumindest teilweise assistiert betriebenen kraftfahrzeugs, computerprogrammprodukt, computerlesbares speichermedium sowie assistenzsystem | |
| DE102014215245B4 (de) | Bahnplanung für komplexe Dynamiken | |
| DE102020127051A1 (de) | Verfahren zur Bestimmung von sicherheitskritischen Ausgabewerten mittels einer Datenanalyseeinrichtung für eine technische Entität | |
| DE102023100599A1 (de) | Rechnerisch effizientes unüberwachtes dnn-vortraining | |
| WO2023274795A1 (de) | Objektverfolgung basierend auf einem bewegungsmodell | |
| DE102017104357A1 (de) | Verfahren, vorrichtung und computerlesbares speichermedium mit instruktionen zur bewegungsplanung für ein kraftfahrzeug | |
| EP4526842B1 (de) | Verfahren zum steuern einer robotervorrichtung | |
| DE102022125766A1 (de) | Berechnung von Höheninformationen eines Bordsteins in einer Umgebung einesFahrzeugs | |
| DE102021126527A1 (de) | Radarbasierte Objektverfolgung | |
| DE102022124085A1 (de) | Darstellung von Bilddaten in einem Fahrzeug abhängig von Sensordaten | |
| DE102025109746B3 (de) | Modellprädiktive Steuerung für automatisiertes Fahren in komplexen Geometrien | |
| DE112020007133T5 (de) | Fahrzeugrelativpositionsberechnungsvorrichtung und Fahrzeugregelvorrichtung | |
| DE102022111559A1 (de) | Positionierung eines Fahrzeugs bezüglich eines Anhängers | |
| DE102023105962A1 (de) | Modellierung eines Umrisses eines Objekts | |
| DE102024109531B3 (de) | Verfahren zur Kalibrierung eines Kamerasystems sowie Kamerasystem mit Prozessoreinheit | |
| DE102022114097A1 (de) | Bewertung einer möglichen Kollision eines Fahrzeugs mit einem Objekt | |
| DE102024126730A1 (de) | Auswählen eines Zielfahrzeugs zur Längssteuerung eines Ego-Fahrzeugs |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: UNKNOWN |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
| PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
| 17P | Request for examination filed |
Effective date: 20231219 |
|
| AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
| DAV | Request for validation of the european patent (deleted) | ||
| DAX | Request for extension of the european patent (deleted) | ||
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |