EP4176378A1 - Verfahren zur umgebungserfassung mit wenigstens zwei unabhängigen bildgebenden umgebungserfassungssensoren, vorrichtung zur durchführung des verfahrens, fahrzeug sowie entsprechend ausgelegtes computerprogramm - Google Patents
Verfahren zur umgebungserfassung mit wenigstens zwei unabhängigen bildgebenden umgebungserfassungssensoren, vorrichtung zur durchführung des verfahrens, fahrzeug sowie entsprechend ausgelegtes computerprogrammInfo
- Publication number
- EP4176378A1 EP4176378A1 EP21742742.6A EP21742742A EP4176378A1 EP 4176378 A1 EP4176378 A1 EP 4176378A1 EP 21742742 A EP21742742 A EP 21742742A EP 4176378 A1 EP4176378 A1 EP 4176378A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- sensor
- environment detection
- rcdr
- surroundings
- reliability range
- 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
- 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
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/254—Fusion techniques of classification results, e.g. of results related to same input data
- G06F18/256—Fusion techniques of classification results, e.g. of results related to same input data of results relating to different input data, e.g. multimodal recognition
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/776—Validation; Performance evaluation
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
-
- 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
- G06V20/582—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of traffic signs
-
- 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 invention relates to the technical field of systems for detecting surroundings, in particular in vehicles.
- Such systems play an increasingly important role in the vehicle sector and are used for both autonomous driving systems and driver assistance systems.
- the relevant driver assistance systems and automatic driving functions also have an autonomy level and are dependent on the environment detection sensors producing reliable data.
- driver assistance systems that relieve the driver of certain tasks.
- driver assistance systems are a blind spot warning assistant, an emergency brake assistant, a parking assistant, a turning assistant, a lane departure warning system, a cruise control assistant, etc.
- completely autonomous driving is also mentioned, in which a completely autonomous driving function is implemented with a correspondingly powerful computer.
- the data obtained in this way about the environment can thus be used as a basis for system-based driving recommendations, warnings, automatic driving maneuvers, etc.
- displays / warnings are conceivable about the direction in which (possibly in your own trajectory ) another it wants to turn the surrounding vehicle.
- an automatic braking maneuver can be carried out when an adaptive speed warning assistant detects that a certain distance from a vehicle in front is not reached.
- traffic sign recognition is also mentioned as an application in order to inform the driver of the legal framework. These traffic signs must also be observed by automatic driving systems or driver assistance systems and can trigger automatic braking or acceleration processes.
- a particularly important example is an AEBS emergency braking system, corresponding to the Advanced Emergency Braking System.
- Such systems can be designed for various combinations of environmental detection sensors. Accordingly, adjustments are required with regard to the availability of the assistance system, the triggering of the various warnings from the driver, and the braking behavior, etc.
- autonomous driving sometimes also Automatic driving, automated driving or piloted driving
- autonomous driving is to be understood as the locomotion of vehicles, mobile robots and driverless transport systems that behave largely autonomously.
- autonomous driving is also used when there is still a driver in the vehicle who may only be responsible for monitoring the automatic driving process.
- transport organizations in Germany the Federal Highway Research Institute was involved
- Level 0 “Driver only”, the driver drives himself, steers, accelerates, brakes, etc. An emergency braking function can also intervene at this level.
- Level 1 Certain assistance systems help to operate the vehicle (including a distance control system - Automatic Cruise Control ACC).
- Level 2 partial automation. Automatic parking, lane keeping function, general longitudinal guidance, acceleration, braking, etc. are taken over by the assistance systems (including traffic jam assistant).
- Level 3 high automation. The driver does not have to constantly monitor the system. The vehicle independently performs functions such as triggering the indicator, changing lanes and keeping in lane. The driver can focus on other things, but if necessary, the system prompts the system to take the lead within a warning period. This form of autonomy is technically feasible on motorways. Legislators are working to allow Level 3 vehicles. The legal framework for this has already been created.
- Level 4 full automation. The system is permanently in charge of the vehicle. If the system can no longer handle the driving tasks, the driver can be asked to take the lead.
- Level 5 No driver required. No human intervention is required other than setting the destination and starting the system. Automated driving functions from level 3 relieve the driver of the responsibility for controlling the vehicle.
- the VDA issued a similar classification of the various levels of autonomy, which can also be used.
- the Society of Automotive Engineers also has a specification for the classification of the levels of autonomy. It is the specification “S ⁇ E J3016 TM: Taxonomy and Definitions for Terms Related to On-Road Motor Vehicle Automated Drivinq Systems”. Even according to this specification, the emergency braking function can intervene at level 0.
- a very important aspect is that the surroundings of the moving vehicle must be recorded very precisely.
- sensor data fusion in which the accuracy of the environment detection is increased by the fact that the object recognitions of several different environment detection sensors are related to one another, with the resulting data being merged.
- a sensor data fusion can consist, for example, in the fusion of camera and radar data in order to classify objects and to increase the object recognition performance of the sensor system.
- a vehicle-based system for recognizing traffic signs is known from US 2016/0170414 A1.
- Environmental sensors such as LIDAR sensors, RADAR sensors and cameras are used. The position of the vehicle is also recorded via GPS. The recognized traffic signs are reported externally with their position and entered there in a database.
- the known solutions have various disadvantages. This was recognized within the scope of the invention. With the image acquisition methods known today for use in the driver assistance sector, there is the problem that their detection performance decreases when an environmental sensor supplies unreliable data, for example due to the environmental conditions. It can happen quickly. The environmental conditions also include the weather conditions. These strongly influence the visibility conditions. Daylight is also mentioned in this context. In twilight, rain, fog and at night, the images recorded by the camera can no longer be used so well for object recognition. The boundaries are fluid.
- the object of the invention is to find such an approach.
- the technology of sensor data fusion should be used as extensively as possible, since it has proven itself in increasing the accuracy of object recognition.
- This object is achieved by a method for environment detection with at least two independent imaging environment detection sensors, which include cameras as well as RADAR and LIDAR sensors, according to claim 1, a device for carrying out the method according to claim 11 and a vehicle for use in the method according to claim 1 Claim 15 and a computer program according to Claim 16 achieved.
- the inventors have recognized that there is a decrease in the functional accuracy of the driver assistance system when a Environment detection sensor is exposed to adverse conditions, although another environment detection sensor is not impaired.
- the functional accuracy can be impaired if one of the environmental detection sensors is exposed to adverse conditions. Therefore, it is provided according to the invention to monitor the function of the environment detection sensors.
- the invention consists in a method for capturing the surroundings with at least two independent imaging sensors for capturing the surroundings, the images of the sensors capturing the surroundings being evaluated with respective object recognition algorithms.
- the at least two environment detection sensors have different characteristics with regard to the object detection as a function of the distance of the object from the environment detection sensor. Because the environment detection sensors move, multiple successive object detection for the respective environment sensor takes place for dynamic object detection. The multiple successive object identifications are entered in an object list, the object identifications being related to one another in the object lists of the environment detection sensors. With the help of the sensor data fusion, the accuracy of the object identifications of the object identifications that are related to one another is increased. In addition, however, due to the problems mentioned above, the function of the environment detection sensors is monitored.
- the method has the advantage that the accuracy of the object detection by the environment detection sensors is increased overall.
- the reliability range is determined by the fact that in this range the object recognition rate and / or the object tracking rate is in a nominal value range that is required for reliable object recognition.
- the nominal range of values can be determined through experiments.
- An example of a required nominal range of values is in the range of 80-90% object detection rate and 90-100% object tracking rate.
- An advantageous variant consists in that the reliability range is continuously redefined in order to enable a dynamic definition of the reliability range. This enables quick adaptation to changing environmental conditions, such as changing light conditions or changing weather conditions.
- This also enables dynamic adaptation of the control behavior of the driver assistance system or the automatic driving function. This can relate to various aspects of the driver assistance system. In addition to the control behavior, the availability of the driver assistance system and the type of warning given to the driver are also mentioned as examples.
- the method can be used particularly advantageously with environment detection sensors for environment detection for a vehicle, one environment detection sensor being a RADAR sensor or a LIDAR sensor and the other environment detection sensor being a camera.
- stationary objects in particular traffic signs or stationary vehicles, are also detected as objects by the environmental sensors. These objects are extremely important for safe driver assistance systems and automatic speed steps.
- a trajectory is determined for object tracking, on which the positions of the continuous object recognition of the object lie.
- the determination of the trajectory is advantageous for controlling the sensor data fusion.
- the reliability range is dependent on the object and the position of the object relative to the sensor.
- the trajectory can be divided into sections which indicate the actual calculation of the position of a person using the measurement data of which environment detection sensor or which environment detection sensors Object recognition should take place.
- the invention in another embodiment, relates to a device for carrying out the method, having at least two independent imaging environment detection sensors, the at least two environment detection sensors having different characteristics with regard to object detection depending on the distance of the object from the environment detection sensor.
- the device further includes a computing device and a storage device, the computing device being designed to calculate an exact position for object recognition by the at least two imaging sensors for the environment by means of sensor fusion.
- a special feature is that the computing device is designed to dynamically determine a reliability range with regard to the object detection of at least one environment detection sensor and to limit the implementation of the sensor data fusion for the corresponding object detections of the at least two environment detection sensors to the reliability range and, outside the reliability range, to limit the object localization based on to calculate the object detections of the other environment detection sensor for which the specific reliability range does not apply.
- the method according to the invention can thus be implemented in a device.
- Such a computing device can be used particularly advantageously as part of a control device in a driver assistance system of a vehicle.
- driver assistance systems rely on the fact that they receive reliable object recognition from surroundings detection sensors.
- the reliability of the object recognition can be checked and the accuracy of the object recognition can be increased in certain areas.
- An advantageous development of the device consists in that the computing device is equipped with a degradation function which is designed to dynamically adapt the function of the driver assistance system as a function of the determination of the reliability range. This can be done in such a way that, for example, the control behavior is adapted. This can go as far as the complete shutdown of the driver assistance system. The driver can also be warned in stages.
- the environment detection sensors consist of a video camera and a LIDAR or RADAR sensor.
- Another embodiment of the invention consists in a vehicle with a device according to the invention.
- FIG. 2 shows a block diagram of the on-board electronics of a vehicle
- Fig. 3 is a block diagram of a control unit of a
- FIG. 5 shows a basic illustration in which an object tracking lane for a static object is drawn in in the form of a traffic sign and the current reliability range for a camera sensor; and
- FIG. 6 shows a flowchart for a computer program with which the method according to the invention for environment detection with at least two independent imaging environment detection sensors can be implemented.
- Fig. 1 shows a typical traffic situation on a six-lane motorway.
- the reference number 10 denotes a utility vehicle. It can be a bus or a truck, for example.
- the commercial vehicle 10 is equipped with environment detection sensors and a driver assistance system that is based on the object detection that results from the evaluation of the data of the environment detection sensors.
- the driver assistance system relates to an emergency braking assistance system.
- Vehicles traveling ahead are denoted by the reference number 12.
- the commercial vehicle 10 moves in the middle lane.
- a traffic sign 16 is shown on the right-hand side of the road. It is a speed limit traffic sign.
- Oncoming vehicles 14 move in the lanes of the opposite lane. As is customary on motorways, the two lanes for the different directions are structurally separated.
- FIG. 2 schematically shows a block diagram of the on-board electronics of the commercial vehicle 10.
- the infotainment system of the commercial vehicle 10 is shown in the upper area.
- a touch-sensitive display unit 20, a computing device 40, an input unit 50 and a memory 60 are used to operate the infotainment system.
- the display unit 20 is connected to the computing device 40 via a data line 70.
- the data line can be designed according to the LVDS standard, corresponding to low voltage differential signaling.
- the display unit 20 receives control data for controlling the display surface of the touchscreen 20 from the computing device 40 via the data line 70. Control data of the commands entered are also transmitted from the touchscreen 30 to the computing device 40 via the data line 70.
- the input unit is denoted by the reference number 50. Associated with it are operating elements such as buttons, rotary controls, sliders or rotary push-button controls, with the help of which the operator can make entries via the menu navigation.
- the memory device 60 is connected to the computing device 40 via a data line 80.
- pictogram directories and / or symbol directories can be stored with the pictograms and / or symbols for the possible insertion of additional information.
- the other parts of the infotainment system interior camera 150, radio 140, navigation device 130, telephone 120 and instrument cluster 110 are connected to the device for operating the infotainment system via the data bus 100.
- a bus system based on Ethernet technology such as BroadR-Reach, can be used as the data bus 100. Further examples are the MOST bus (Media Oriented System Transport) or the D2B bus (Domestic Digital Bus).
- a communication module 160 is also connected to the data bus 100. This is used for internal and external communication. For this purpose, the communication module 160 is equipped with an Ethernet interface for internal communication.
- an LTE (Long Term Evolution) or 5G is in the communication module 160 Modem provided with which data can be received and sent via cellular radio.
- sections of a constantly updated, highly accurate map can be loaded via cellular network.
- the interior camera 150 can be designed as a conventional video camera. In this case, it records 25 frames / s, which corresponds to 50 fields / s in the interlace recording mode.
- An engine control unit is denoted by the reference number 151.
- Reference numeral 152 corresponds to an ESC control unit (Electronic Stability Control) and reference numeral 153 denotes a transmission control unit.
- Further control devices such as an additional brake control device, can be present in the commercial vehicle 10.
- Such control devices are typically networked with the CAN bus system (Controller Area Network) 104, which is standardized as an ISO standard, mostly as ISO 11898-1.
- the communication bus 100 of the infotainment system is connected to a gateway 30.
- the other parts of the on-board electronics are also connected to it.
- the communication bus 104 of the drive train and on the other hand the communication bus 102 for driver assistance systems, which can be designed in the form of the FlexRay bus.
- An emergency brake assistant 184 is shown here.
- This emergency braking assistant is known internationally as the Advanced Emergency Braking System (AEBS).
- AEBS Advanced Emergency Braking System
- further driver assistance systems could also be connected to it, including, for example, a control unit for automatic distance control ACC in accordance with Adaptive Cruise Control, a driver assistance system DCC for adaptive chassis control, in accordance with Dynamic Chassis Control.
- the surroundings detection sensors, a RADAR sensor 186, corresponding to radio detection and ranging, and a front camera 182 are also connected to this bus 102. Their function is discussed in more detail below.
- a communication bus 106 is also connected to the gateway 30. This connects the gateway 30 with an on-board diagnostic interface 190. The task of the gateway 30 is to carry out the format conversions for the various communication systems 100, 102, 104, 106 so that data can be exchanged with one another.
- the emergency braking assistance system 184 makes use of a highly precise map of the surroundings for the emergency braking function. The map of the surroundings can be stored in advance in a memory of the emergency braking assistance system.
- the gateway 30 For this purpose, it is usually loaded via the communication module 160, forwarded by the gateway 30 and written to the memory of the emergency braking assistance system 184.
- the gateway 30 In another variant, only a section of a map of the surroundings is loaded and written into the memory of the emergency braking assistance system.
- the loaded map of the surroundings still has to be supplemented by the observations of the surroundings detection sensors 182 and 186.
- a stereo camera, range 500m, is used to capture a 3D map, used for an automatic emergency brake assistant, lane change assistant, traffic sign recognition and an adaptive cruise control.
- Camera range 100 m
- Camera is used to capture a 3D map, used for an automatic emergency braking assistant, lane change assistant, traffic sign recognition, adaptive cruise control, front impact warning, automatic light control and a parking assistant.
- Radar sensor range 20 cm to 100 m, used for an automatic emergency braking assistant, for automatic speed control, an adaptive cruise control, a blind spot assistant, a cross traffic alarm
- Lidar sensor range 100 m
- the front camera 182 can be designed as a special camera that records more images / s in order to increase the accuracy of the object detection in the case of faster moving objects.
- the front camera 182 is mainly used for object recognition.
- Typical objects that are to be recognized are traffic signs, vehicles driving ahead / surrounding / parked and other road users, intersections, turning points, potholes, etc.
- the image evaluation takes place in the computing unit of the emergency brake assistant 184.
- Known algorithms for object recognition can be used for this purpose.
- the object recognition algorithms are processed by the computing unit of the emergency brake assistant 184. How many images can be analyzed per second depends on the performance of this processing unit.
- the reference number 184-1 denotes a computing unit. It is a powerful arithmetic unit that is able to perform the necessary arithmetic operations for the aforementioned sensor data fusion. For this, it can be equipped with several computing cores in order to carry out parallel computing operations.
- Reference numeral 184-2 denotes a storage unit. It can contain several different memory modules. Including RAM memory, EPROM memory and FEPROM memory.
- Reference numeral 184-6 denotes an Ethernet interface. This establishes the connection to the communication bus 102.
- Reference numeral 184-3 denotes an object list in which the successive object recognitions of an object recognized by the RADAR sensor 186 are recorded.
- This object list is received from the RADAR sensor 186 via the communication bus 102.
- Reference numeral 184-4 denotes an object list in which the successive object recognitions of an object recognized by the camera sensor 182 are recorded. These too Object list is received from camera sensor 182 via communication bus 102. Both object lists 184-3 and 184-4 relate to the same object that is observed by the two different environment detection sensors 182, 186 at the same time.
- Reference numeral 184-5 denotes a resulting object list in which the accuracy of the object localizations is increased by means of sensor data fusion.
- the RADAR sensor 186 has its strengths in distance measurement and object recognition at night, while the front camera 182 has its strengths in object recognition in daylight.
- the nominal object recognition areas are shown in FIG. 4.
- the nominal object detection area of the front camera 182 is marked with the reference symbol NCDR.
- the nominal object detection range of the RADAR sensor 186 is marked with the reference symbol NRDR. Nominally under ideal conditions, the object detection range of the front camera 182 extends as far as that of the RADAR sensor 186. Under deteriorated conditions, the object detection range of the front camera can deviate significantly from the nominal object detection range. In FIG.
- RCDR a currently valid reliability range of the object recognition for the front camera.
- object tracking tracks for the followed vehicles 12 in front are also shown. With them, the reliability range can be easily determined.
- the object tracking tracks are divided into different sections.
- the section labeled COT relates to the part of the object tracking track in which, with the aid of object recognition algorithms, which are based on the image data from the front camera 182 can be applied, the preceding vehicle 12 could be localized.
- the section labeled RED relates to the part of the object tracking lane in which the vehicle 12 traveling ahead could be localized with the aid of object recognition algorithms which are applied to the image data of the RADAR sensor 186.
- the RADAR sensor 186 also delivers object identifications in the COT section.
- the reference symbol 1 RDP denotes the point of the first object detection by the RADAR sensor 186.
- the reference symbol 1CDP denotes the point of the first object detection by the front camera 182.
- the reference symbol LCDP denotes the point of the last object detection by the front camera 182 under the given ambient conditions.
- the COT section is significantly longer and approaches the end of the nominal object detection area NCDR. This could be due to the fact that the vehicle 12 traveling ahead is larger or has a different shape that is easier to recognize. However, it would also be possible that visibility is better in that direction, for example because there are fewer clouds of fog there, or because there are no shadows in this direction.
- an object detection rate and an object tracking rate along the object tracking track over the distance between the environmental sensor and the object are calculated. Both rates form a simple criterion with which the reliability range can be determined quantitatively.
- the reliability range RCDR is determined by the fact that in this range the object recognition rate and / or the object tracking rate is in a nominal value range that is required for reliable object recognition.
- the nominal range of values can be determined through experiments.
- a An example of a required nominal value range is in the range of 80-90% object detection rate and 90-100% object tracking rate.
- An advantageous variant consists in that the reliability range is continuously redefined in order to enable a dynamic definition of the reliability range RCDR. This enables quick adaptation to changing environmental conditions, such as changing light conditions or changing weather conditions.
- FIG. 5 shows a basic illustration of the detection of the surroundings by the utility vehicle 10, a static object in the form of a traffic sign 16 being tracked as the object.
- the same reference symbols in FIG. 5 denote the same components as in FIG. 4.
- a difference is that the first object recognition at point 1 RDP by the RADAR sensor 186 occurs when the traffic sign 16 is the furthest away.
- the traffic sign 16 moves towards the commercial vehicle 10 in the recorded image because the commercial vehicle 10 is moving toward the traffic sign 16.
- the same situation would also arise with the detection of dynamic objects when the commercial vehicle 10 approaches them.
- a typical situation in which the emergency brake assistant is to be activated relates, for example, to the low-speed approach of the commercial vehicle 10 to the end of a traffic jam.
- the first object recognition would take place at the distant end of the object recognition area NCDR and NRDR and the last recognition would take place in the vicinity of the commercial vehicle 10.
- FIG. 6 shows a flowchart with which the method according to the invention for detecting the surroundings with at least two independent imaging sensors 182, 186 can be carried out.
- the program is executed by the arithmetic unit 184-1 in the control unit of the emergency brake assistant 184.
- the program start is denoted by the reference number 202.
- the object lists 184-3 and 184-4 are received in program step 204.
- the position of the recognized object is also indicated in the object lists.
- the image evaluations therefore find in the environment detection sensors 182 and 186 themselves.
- the image data can be transmitted to the emergency braking assistant 184, the image evaluations then having to be carried out in the computing unit 184-1.
- the image evaluation involves typical object recognition algorithms that perform pattern recognition on the basis of patterns stored in a table.
- All valid traffic signs are known and their patterns can be saved in a table. Typically, the pattern recognition is improved by a convolution operation in which the recorded images are folded with the known patterns. Such algorithms are known to the person skilled in the art and are available. If a traffic sign has been recognized in this way, the recognition distance to the traffic sign is also determined and stored. Corresponding algorithms exist for object recognition in the case of moving objects.
- the object identifications are related to one another. From the positions in the object lists 184-3 and 184-4, the distances of the objects 12, 16 to the surroundings detection sensor 182, 186 can also be calculated in each case. The object identifications in the two object lists 184-3, 184-4 can be assigned to one another via this and via the times at which the respective image was recorded. Statistical methods, such as the calculation of the covariances between object identifications, can also be used to determine whether the object identifications correspond.
- the received object lists 184-3 and 184-4 are evaluated.
- the history of the object lists which is still stored in the memory 184-2, can also be used for this purpose.
- the aim of the evaluation is to carry out a cross-check as to whether the two object lists 184-3 and 184-4 correspond. At points where the object lists do not correspond, the evaluation will show which of the two sensors has delivered an object recognition and which has not. It can be seen in FIG. 3 that the object list 184-4 of the front camera 182 is the The object only contains three times, while the object list 184-3 of the RADAR sensor 186 contains the object five times.
- program step 210 the operation of the sensor data fusion of the corresponding object identifications in the reliability range RCDR of the front camera 182 then takes place. Outside the RCDR reliability range, the object identifications are entered by the RADAR sensor 186 in the merged object list 184-5. This takes place in program step 212.
- the result is a common object list 184-5 for a recognized object.
- the object can be, for example, one of the vehicles 12 in front or the traffic sign 16, as shown in FIGS.
- the common object list 184-5 is used by the control program of the emergency braking assistant 184.
- the letter F indicates which objects in the object list were determined by sensor data fusion.
- the letter R indicates which objects were determined exclusively from the data of the RADAR sensor 186.
- the emergency braking process is carried out in order to prevent a collision with the object.
- the determination of the position of the objects can be supported with GNSS signals and odometry signals that the commercial vehicle has ready.
- the image quality will vary greatly with the time of day. A distinction should at least be made between day and night times.
- the traffic conditions can also have an influence on the accuracy of the object recognition.
- a distinction can be made here as to whether the Vehicle moved in city traffic, on the highway, on the country road, etc. In city traffic, it is particularly important to record the traffic signs precisely.
- specialty processors can include application specific integrated circuits (ASICs), reduced instruction set computers (RISC), and / or field programmable gate arrays (FPGAs).
- ASICs application specific integrated circuits
- RISC reduced instruction set computers
- FPGAs field programmable gate arrays
- the proposed method and the device are preferably implemented as a combination of hardware and software.
- the software is preferably installed as an application program on a program storage device. Typically, it is a machine based on a computer platform that has flardware, such as one or more central processing units (CPU), a random access memory (RAM) and one or more input / output (I / O) interfaces.
- An operating system is also typically installed on the computer platform.
- the invention can also be used for remote-controlled devices such as drones and robots, where image evaluation is very important.
- Other possible uses relate to a smartphone, a tablet computer, a personal assistant or data glasses.
- LCDP last object detection position camera sensor
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| DE102020117340.7A DE102020117340A1 (de) | 2020-07-01 | 2020-07-01 | Verfahren zur Umgebungserfassung mit wenigstens zwei unabhängigen bildgebenden Umgebungserfassungssensoren, Vorrichtung zur Durchführung des Verfahrens, Fahrzeug sowie entsprechend ausgelegtes Computerprogramm |
| PCT/EP2021/067790 WO2022002901A1 (de) | 2020-07-01 | 2021-06-29 | Verfahren zur umgebungserfassung mit wenigstens zwei unabhängigen bildgebenden umgebungserfassungssensoren, vorrichtung zur durchführung des verfahrens, fahrzeug sowie entsprechend ausgelegtes computerprogramm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| EP4176378A1 true EP4176378A1 (de) | 2023-05-10 |
Family
ID=76958922
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP21742742.6A Pending EP4176378A1 (de) | 2020-07-01 | 2021-06-29 | Verfahren zur umgebungserfassung mit wenigstens zwei unabhängigen bildgebenden umgebungserfassungssensoren, vorrichtung zur durchführung des verfahrens, fahrzeug sowie entsprechend ausgelegtes computerprogramm |
Country Status (5)
| Country | Link |
|---|---|
| US (1) | US12423989B2 (de) |
| EP (1) | EP4176378A1 (de) |
| CN (1) | CN116034359A (de) |
| DE (1) | DE102020117340A1 (de) |
| WO (1) | WO2022002901A1 (de) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US12179797B2 (en) * | 2020-10-28 | 2024-12-31 | Toyota Research Institute, Inc. | Layered architecture for availability of advanced driver assistance features |
| EP4174799B1 (de) * | 2021-10-26 | 2026-04-01 | Zenseact AB | Wahrgenommene freiraumverifizierung eines werbeanzeigewahrnehmungssystems |
| CN114919548B (zh) * | 2022-04-27 | 2023-10-20 | 一汽奔腾轿车有限公司 | 一种基于毫米波雷达的自适应制动控制方法 |
| DE102022206345A1 (de) * | 2022-06-23 | 2023-12-28 | Robert Bosch Gesellschaft mit beschränkter Haftung | Verfahren und Netzwerk zur Sensordatenfusion |
| WO2024110295A1 (en) * | 2022-11-22 | 2024-05-30 | Continental Autonomous Mobility Germany GmbH | Environment perception system and method for perceiving an environment of a vehicle |
| DE102023117817A1 (de) | 2023-07-06 | 2025-01-09 | Bayerische Motoren Werke Aktiengesellschaft | Verfahren und Assistenzsystem zum Unterstützen einer automatisierten Fahrzeuglängsführung und entsprechend eingerichtetes Kraftfahrzeug |
| JP2025010839A (ja) * | 2023-07-10 | 2025-01-23 | トヨタ自動車株式会社 | 自動運転システム |
| JP2025089866A (ja) * | 2023-12-04 | 2025-06-16 | トヨタ自動車株式会社 | 車両運転支援装置、車両運転支援方法及びそのプログラム |
| DE102024114787A1 (de) * | 2024-05-27 | 2025-11-27 | HELLA GmbH & Co. KGaA | System zur Fahrerassistenz oder zum autonomen Fahren eines Fahrzeugs, Fahrzeug und Verfahren zum Betreiben des Systems |
Family Cites Families (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4858574B2 (ja) * | 2009-05-19 | 2012-01-18 | トヨタ自動車株式会社 | 物体検出装置 |
| GB2529997B (en) * | 2014-05-01 | 2019-01-02 | Jaguar Land Rover Ltd | Vehicle communication system with occupant monitoring |
| US9726577B2 (en) * | 2014-06-03 | 2017-08-08 | Honeywell Internataionl Inc. | Vehicle mission capability prediction system and method |
| EP3016352B1 (de) * | 2014-11-03 | 2019-02-06 | Fujitsu Limited | Verfahren zum Verwalten eines Sensornetzwerksystems |
| US20160162743A1 (en) * | 2014-12-05 | 2016-06-09 | Magna Electronics Inc. | Vehicle vision system with situational fusion of sensor data |
| US9459626B2 (en) | 2014-12-11 | 2016-10-04 | Here Global B.V. | Learning signs from vehicle probes |
| CN105973619A (zh) | 2016-04-27 | 2016-09-28 | 厦门大学 | 结构健康监测系统下基于影响线的桥梁局部损伤识别方法 |
| US10453213B2 (en) * | 2016-08-29 | 2019-10-22 | Trifo, Inc. | Mapping optimization in autonomous and non-autonomous platforms |
| JP7206583B2 (ja) * | 2016-11-25 | 2023-01-18 | 株式会社リコー | 情報処理装置、撮像装置、機器制御システム、移動体、情報処理方法およびプログラム |
| JP6805992B2 (ja) | 2017-07-18 | 2020-12-23 | トヨタ自動車株式会社 | 周辺監視装置 |
| CN108151806B (zh) * | 2017-12-27 | 2020-11-10 | 成都西科微波通讯有限公司 | 基于目标距离的异类多传感器数据融合方法 |
| JP6968722B2 (ja) * | 2018-02-02 | 2021-11-17 | フォルシアクラリオン・エレクトロニクス株式会社 | 車載装置、インシデント監視方法 |
| DE112019000049T5 (de) * | 2018-02-18 | 2020-01-23 | Nvidia Corporation | Für autonomes fahren geeignete objekterfassung und erfassungssicherheit |
| US10884119B2 (en) | 2018-06-08 | 2021-01-05 | Ford Global Technologies, Llc | Object tracking in blind-spot |
| DE102018123779A1 (de) | 2018-09-26 | 2020-03-26 | HELLA GmbH & Co. KGaA | Verfahren und Vorrichtung zum Verbessern einer Objekterkennung eines Radargeräts |
| JP6937855B2 (ja) * | 2020-01-29 | 2021-09-22 | 本田技研工業株式会社 | 車両制御装置、車両、車両制御方法及びプログラム |
| US12299077B2 (en) * | 2020-09-24 | 2025-05-13 | Intel Corporation | Perception system error detection and re-verification |
| US20250095344A1 (en) * | 2023-09-18 | 2025-03-20 | Qualcomm Incorporated | Image interpolation for multi-sensor training of feature detection models |
-
2020
- 2020-07-01 DE DE102020117340.7A patent/DE102020117340A1/de active Pending
-
2021
- 2021-06-29 CN CN202180043034.7A patent/CN116034359A/zh active Pending
- 2021-06-29 EP EP21742742.6A patent/EP4176378A1/de active Pending
- 2021-06-29 WO PCT/EP2021/067790 patent/WO2022002901A1/de not_active Ceased
- 2021-06-29 US US18/002,488 patent/US12423989B2/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| US20230334836A1 (en) | 2023-10-19 |
| WO2022002901A1 (de) | 2022-01-06 |
| CN116034359A (zh) | 2023-04-28 |
| US12423989B2 (en) | 2025-09-23 |
| DE102020117340A1 (de) | 2022-01-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022002901A1 (de) | Verfahren zur umgebungserfassung mit wenigstens zwei unabhängigen bildgebenden umgebungserfassungssensoren, vorrichtung zur durchführung des verfahrens, fahrzeug sowie entsprechend ausgelegtes computerprogramm | |
| DE102018118220B4 (de) | Verfahren zur Schätzung der Lokalisierungsgüte bei der Eigenlokalisierung eines Fahrzeuges, Vorrichtung für die Durchführung von Verfahrensschritten des Verfahrens, Fahrzeug sowie Computerprogramm | |
| DE102017221191B4 (de) | Verfahren zur Anzeige des Verlaufs einer Sicherheitszone vor einem Fahrzeug oder einem Objekt mit einer Anzeigeeinheit, Vorrichtung zur Durchführung des Verfahrens sowie Kraftfahrzeug und Computerprogramm | |
| EP3160813B1 (de) | Verfahren zur erstellung eines umfeldmodells eines fahrzeugs | |
| DE102014008578B4 (de) | Verfahren zur Ermittlung von Positionsdaten zur Nutzung beim Betrieb eines Fahrzeugsystems eines Kraftfahrzeugs und Positionsdatenermittlungs- und-verteilssystem | |
| EP2149132B1 (de) | Verfahren und vorrichtung zur erkennung von verkehrsrelevanten informationen | |
| DE112012006226B4 (de) | Fahrassistenzvorrichtung | |
| DE102018219665B4 (de) | Steuereinheit zum Betreiben eines autonomen Fahrzeugs | |
| DE102014205953A1 (de) | Verfahren zur Analyse einer Verkehrsumfeldsituation eines Fahrzeugs | |
| DE102017100013A1 (de) | Bestimmen der fahrerabsicht an strassenverkehrskreuzungen zum vermeiden der kollision von automobilen | |
| DE102018125207A1 (de) | Fahrzeuginterne verkehrsassistenz | |
| DE102022115718A1 (de) | Verfahren und Vorrichtung zum automatisierten Anfahren eines Fahrzeugs an einer Signalisierungseinheit | |
| DE102021200636B4 (de) | Verfahren zum Erzeugen einer Fahrspurwechselempfehlung, Spurwechselassistenzsystem sowie Kraftfahrzeug mit einem Spurwechselassistenzsystem | |
| EP3609755B1 (de) | Fahrerassistenzsystem für ein fahrzeug | |
| DE102015015277A1 (de) | Technik zum automatisierten Anhalten eines Fahrzeugs in einem Zielbereich | |
| DE102014202385A1 (de) | Verfahren zur Erkennung eines Fahrerausweichwunsches in einem Fahrerassistenzsystem für Kraftfahrzeuge | |
| WO2019233777A1 (de) | Fahrassistenzsystem | |
| WO2023036545A1 (de) | Verfahren und steuerschaltung zum überprüfen, ob ein aktuell aktiver fahrmodus innerhalb seiner odd betrieben wird, sowie system und backend-server | |
| DE102013212360A1 (de) | Vorhersage des zukünftigen Fahrpfades eines Fahrzeuges | |
| DE102007002197A1 (de) | Gemeinsamer Kontroller für verschiedene Fahrerassistenzsysteme | |
| DE102017205495A1 (de) | Vorrichtung und Verfahren zum Fokussieren von Sensoren im fahrdynamischen Grenzbereich für ein Kraftfahrzeug | |
| DE102014214505B4 (de) | Verfahren zur Erstellung eines Umfeldmodells eines Fahrzeugs | |
| DE102014214507B4 (de) | Verfahren zur Erstellung eines Umfeldmodells eines Fahrzeugs | |
| DE102011083777A1 (de) | Fahrerassistenzsystem und Verfahren zum Betreiben eines Fahrerassistenzsystems | |
| DE102016224074A1 (de) | Verfahren und Vorrichtung zum Betreiben eines 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: 20230201 |
|
| 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 |
|
| 17Q | First examination report despatched |
Effective date: 20250616 |