WO2014127777A2 - Verfahren und vorrichtung zur bestimmung eines fahrbahnzustands - Google Patents
Verfahren und vorrichtung zur bestimmung eines fahrbahnzustands Download PDFInfo
- Publication number
- WO2014127777A2 WO2014127777A2 PCT/DE2014/200062 DE2014200062W WO2014127777A2 WO 2014127777 A2 WO2014127777 A2 WO 2014127777A2 DE 2014200062 W DE2014200062 W DE 2014200062W WO 2014127777 A2 WO2014127777 A2 WO 2014127777A2
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- image area
- vehicle
- camera
- road condition
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000001454 recorded image Methods 0.000 claims description 20
- 230000033001 locomotion Effects 0.000 claims description 18
- 230000006978 adaptation Effects 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 13
- 230000002123 temporal effect Effects 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 238000007637 random forest analysis Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 description 10
- 238000001514 detection method Methods 0.000 description 8
- 239000013598 vector Substances 0.000 description 6
- 238000003066 decision tree Methods 0.000 description 5
- 239000007787 solid Substances 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 235000004522 Pentaglottis sempervirens Nutrition 0.000 description 2
- 230000000454 anti-cipatory effect Effects 0.000 description 2
- 239000010426 asphalt Substances 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000001556 precipitation Methods 0.000 description 2
- 239000004576 sand Substances 0.000 description 2
- 238000002604 ultrasonography Methods 0.000 description 2
- 244000025254 Cannabis sativa Species 0.000 description 1
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 240000004050 Pentaglottis sempervirens Species 0.000 description 1
- 241001609370 Puschkinia scilloides Species 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 239000010868 animal carcass Substances 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000003921 oil Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000000123 paper Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
- 230000016776 visual perception Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
- H04N13/20—Image signal generators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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; CALCULATING OR 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/42—Document-oriented image-based pattern recognition based on the type of document
- G06V30/422—Technical drawings; Geographical maps
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/63—Control of cameras or camera modules by using electronic viewfinders
- H04N23/633—Control of cameras or camera modules by using electronic viewfinders for displaying additional information relating to control or operation of the camera
- H04N23/635—Region indicators; Field of view indicators
Definitions
- the invention relates to a method and an apparatus for determining a road condition by means of a driving convincing camera.
- the designation of the warning and intervention times basically based on a dry roadway with high Adhesion coefficient between tire and roadway.
- DE 10 2004 018 088 A1 shows a tramway recognition system with a temperature sensor, an ultrasound sensor and a camera.
- the temperature, roughness and image data (lane data) obtained from the sensors are filtered and compared with reference data and a degree of security for the comparison is generated.
- the condition of the road surface is determined.
- the road surface eg concrete, asphalt, dirt, grass, sand or gravel
- their condition eg dry, icy, snowy, wet
- WO 2012/110030 A2 shows a method and a device for friction coefficient estimation by means of a 3D camera, e.g. a stereo camera.
- the 3D camera captures at least one image of the surroundings of the vehicle.
- a height profile of the road surface is created in the entire vehicle apron.
- From the height profile of the expected local coefficient of friction of the road surface in the driving tool apron is estimated.
- a classification of the road surface can be made in individual cases, e.g. as snow cover or muddy dirt road done.
- the object of the present invention is therefore to provide a road condition recognition by means of a camera which, when using (only) a monocamera, ensures a reliable and robust anticipatory road condition recognition or friction coefficient estimation derived therefrom.
- the starting point of the solution according to the invention are the following considerations: A combination of algorithms of digital image processing with an intelligent adaptation and adjustment of the relevant image processing area or ROI (Region of Interest) on the respective driving situation to ensure that the analyzed image area includes the road surface with the goal to determine the road condition.
- ROI Region of Interest
- a main idea of the invention from the perspective of digital image processing is the calculation of local and global features from the image and the appropriate combination of different features within an image area but also from different image areas, and the subsequent decision by a classifier trainable from example data whose results from different time periods lead to a decision on the road condition.
- the technical advantage in the efficient processing of the camera image due to simple operations and the achievement of a high quality on the merge of various features.
- a method according to the invention for determining a road condition by means of a vehicle camera comprises the following steps:
- At least one image is taken by means of the vehicle camera
- a first area in the captured image is determined, which includes a map of the road surface
- the first image area is fed to a classifier, the classifier assigning the first image area to at least one class representing a particular roadway condition and
- the driving camera detects an environment outside the vehicle, in particular, the driving camera can be directed forward and behind the windshield be arranged approximately in the region of the inner mirror.
- the first image area which is detected to detect the road condition, may also be referred to as region-of-interest (ROI) and may be the entire image or a portion of the image.
- ROI region-of-interest
- the image area may be, for example, a simple rectangle, a region of undefined shape, or even a single pixel.
- the determination of the image detail relevant for the further image processing is particularly important in order to ensure that the analyzed first image area includes the road surface, so that the road condition can be determined from this first image area.
- At least one of the predetermined classes of lane conditions is assigned to the first image area by a classifier (or a classification system). These classes are preferably "wet lane”, “dry lane”, “snowy lane” and "icy On the basis of learned assignments of example image regions to known road conditions, the trained classifier can also assign previously unknown image contents or regions to at least one class.
- Information about the at least one roadway condition is output, preferably to further driver assistance functions, vehicle functions or even to the driver.
- the information that is output on the ascertained roadway condition may be an estimate of the friction coefficient for the roadway area that is depicted in the image area.
- the coefficient of friction also coefficient of friction, coefficient of adhesion, (static) friction coefficient or coefficient of friction indicates which force can be transmitted with respect to the wheel load between a road surface and a vehicle tire (eg in the tangential direction) and is therefore an essential measure for the road condition .
- tire properties are required to fully determine the coefficient of friction. For an estimate of the coefficient of friction from camera image data, only road condition information is typically taken into account, since in general no tire properties can be determined from camera image data.
- the inventive method for determining the road condition ensures a very robust, reliable and predictive determination of the spatially resolved road condition.
- the automatic detection of road condition information is a key element on the way to highly automated or autonomous driving in the future.
- At least one feature is extracted from the first image area and fed to the classifier.
- the feature is or the features are particularly suitable to detect the different appearance of the road surface in the camera image depending on the road condition.
- a plurality of individual features may form a feature vector that combines different information from the first image area to provide a more robust and accurate view of the roadway in the classification step. to be able to decide.
- Different feature types for an image area yield a set of feature vectors.
- the resulting set of feature vectors for an image area is called a feature descriptor. If several image areas are used, the feature descriptor can also be composed or combined from combined features of the different image areas.
- the composition of the feature descriptor can be done by simple concatenation, a weighted combination or other non-linear mapping. Not only different image areas can be used at one time in an image, but also over several times in successive images of a series of images.
- the feature descriptor is then assigned by a classification system (classifier) to at least one of the classes.
- a classifier in this case is a mapping of the feature descriptor to a discrete number identifying the classes to be recognized.
- the feature extracted from the first image area and supplied to the classifier comprises the average gray value or the mean color value (RGB) of the first image area.
- the feature type "average RGB color value” comprises three individual feature values, namely R, G and B (red, green and blue value), which can be summarized as a feature vector.
- any other information that can be extracted from an ROI or from pixels of the ROI and from which differences between the given classes can be determined is also suitable.
- feature types may be HSI values (Hue, Saturation, Intensity) or L * a * b * values (CIELAB color space) averaged over the first image area, or, for example.
- Gradient values are extracted as a feature.
- the feature vectors for single or multiple feature types extracted from one or more ROIs of an image form the feature descriptor.
- the at least one feature extracted from the first image area and fed to the classifier comprises the result or the results of a pixel-by-pixel segmentation within the first image area.
- special regions can be pinpointed. This is advantageous for the detection of local differences, for example for the detection of puddles, drying lanes on wet roads or icy lanes on snow roads. This increases the quality of detection of these facts.
- This pinpoint classification can be achieved, for example, by semantic segmentation methods in which each pixel in the image area is assigned a label of one of the given classes.
- the pixel-precise classification of images extends a rough localization of objects in images by a pinpoint classification.
- a random decision forest (Random Decision Forest or even Random Forest) is used as the classifier.
- Decision trees are hierarchically arranged classifiers that split the classification problem in a tree-like manner. Beginning in the root, the path to a leaf node is made on the basis of the decisions made, in which the final classification decision takes place. Due to the learning complexity, very simple classifiers, the so-called “decision stumps", which separate the input space orthogonally to a coordinate axis, are preferably used for the inner nodes.
- Decision forests are collections of decision trees that contain randomized elements in training the decision trees, preferably at two sites. First, each tree is trained with a random selection of training data, and second, for each binary decision, only a random selection of allowed dimensions is used. In the leaf nodes, class histograms are stored which allow a maximum likelihood estimation (estimation of the highest probability) of the feature vectors reaching the leaf nodes in training. Class histograms store the number of times a feature descriptor of a particular lane state passes through the decision tree to reach the corresponding leaf node. As a result, each class may prefer a true probability, which is calculated from the class histograms.
- the most likely class from the class histogram is preferably used as the current road condition.
- other methods may be used to transfer the information from the decision trees to a lane state decision.
- the assignment of the first image area to at least one class by the classifier for at least one recorded image is subjected to temporal filtering before the information about the at least one assigned roadway state is output.
- the classifier assigns at least one class to a recorded image or an image region thereof.
- An optimization can follow this assignment or decision per recorded image. In particular, this optimization can take temporal context into account by acting as temporal filtering.
- the assignment for the currently recorded image is compared with previously assigned road conditions. In particular, the most frequent class from a previous period can be used as a reference. Individual outliers (misallocations) can be eliminated in this way.
- the temporal filtering provides that the assignment of the first image area to at least one class by the classifier for at least one currently recorded image is compared with an assignment based on at least one previously recorded image.
- a change of the assigned FahrbahnDirectskiasse is issued only when a probability associated with the change, which is derived from the classification of the currently recorded image exceeds a threshold.
- the temporal context is preferably taken into account by applying a so-called hysteresis threshold method.
- the hysteresis threshold method the change from one road condition to the other is regulated by means of threshold values.
- One Change takes place only when the probability for the new road condition is high enough and for the old road condition is accordingly low. As a result, the classification result is stable and permanent jumps between different road conditions can be avoided.
- further information from the vehicle for example from the rain sensor, or other data provided by the vehicle can be used to check the classification by the classifier before information about the at least one assigned road condition is output.
- the position, the size and / or the shape of the first image area is adapted to a current driving situation of the own vehicle.
- the alignment (in the current image) and tracking (in subsequently recorded images) of the at least one image area adapted to the driving situation in terms of shape, size and position preferably takes place taking into account the movement of the own vehicle, possible further road users and the lane conditions.
- the alignment and tracking of the at least one in the form, size and position adapted to the driving situation image area is carried out in particular in the following manner: a)
- the first image area is the overall image of the camera, if the driving camera is directed exclusively on the road.
- the first image area is at least one fixed image area, which is preferably projected by adjustment and calibration of the driving camera in the center or in front of the left and right vehicle wheels in front of the vehicle on the road.
- the first image area is at least one dynamic image detail, which in the image in the travel tube of the vehicle, which Among other things, is calculated from the odometry data of the vehicle, projected and dynamically tracked this.
- the first image area is at least one dynamic image detail that is projected in the image into the road / lane traveled by the vehicle, which lies within two or laterally of a lane boundary line and is tracked dynamically.
- the first image area is at least one dynamic image detail, which is projected in the image into the road / lane traveled by the vehicle, which is detected with the aid of digital image processing means, and is tracked dynamically.
- the first image area is at least one dynamic image section, which is projected in the image in the estimated road course, and this dynamically tracked.
- the first image area is at least one dynamic image detail which is projected in the image into the trajectory calculated by the system, preferably as the center line of a predicted driving corridor on the basis of a predictive trajectory planning, and which is updated dynamically.
- the first image area is at least one dynamic image excerpt based on GPS driving tool data preferably according to driving speed and heading angle (or yaw angle) in the direction of the driving convincing projected in front of the vehicle and this is dynamically tracked.
- the first image area is at least one dynamic image detail, which, based on driving forceometry data, projects in the direction of the vehicle motion in front of the vehicle and is tracked dynamically.
- the first image area is at least one dynamic image detail based on vehicle position and map data in Direction of travel in front of the vehicle projected onto the road and this is tracked dynamically.
- the first image area is at least one fixed or dynamic image detail which corresponds to the intersection of the individual areas when at least two areas from a) to j) are superimposed.
- the first image area is at least one fixed or dynamic image area containing a range from a) to k), excluding image segments with detected objects such as vehicles, pedestrians or infrastructure.
- the adaptation can advantageously be made depending on the speed of the own vehicle.
- the position, size and / or shape of the second image area is adapted to the speed of the own vehicle in order to obtain a temporally uniform prediction of the expected road condition. For example, It can be determined which roadway condition will be crossed in 0.5 seconds or in one second.
- An estimate of the distance required for this purpose can also be carried out with sufficient accuracy with a monocamera with known installation height and the assumption of a flat road course over the imaging geometry.
- the distance can be determined by triangulation with greater accuracy accordingly.
- a lane on which the own vehicle is located is determined, and the first image area is adapted to include an image of the road surface of the preceding own lane.
- the at least one "dynamic" image area comprises in the image the lane / lane traveled by the vehicle, which lies within two or laterally of a traffic lane delimitation line Limitations in the lateral direction limited.
- the shape of the first image area may correspond to a trapezoid but also to a rectangle.
- this imaging area can be projected into the subsequently recorded images, so that the image area is tracked dynamically.
- aensstraj ektorie the own vehicle is predicted and calculates a driving route.
- the prediction can be based on data from the camera, other environmental sensors, vehicle sensors, navigation devices,
- the first image area is adapted to include an image of the road surface that is within the calculated travel path.
- the first image area is adapted such that the first image area contains only one image of the road surface.
- everything relevant to what the tires of your own vehicle will roll in the future or possibly roll will be relevant.
- road surface precipitation on it, pollution (leaves, paper, sand, oil, animal carcass residues), road markings that are run over.
- the first image area can be adapted such that image segments with previously recognized objects from the first image area are excluded.
- Previously recognized objects are especially different Road users, such as vehicles (including cars, trucks), cyclists or pedestrians, or infrastructure elements.
- navigation and map data and / or vehicle sensor data and / or data of further environment sensor data may preferably be taken into account.
- a second image area is determined, which includes an image of a second area of the road surface.
- the first image area may correspond to a predicted driving lane area in which the left driving wheels will roll on the road surface
- the second image area will be a predicted driving lane area in which the right driving wheels will roll.
- the second image area comprises an image of a further region of the roadway surface lying ahead.
- a preferred embodiment could therefore contain two image areas, with the first image area in the ego traffic lane lying directly in front of the ego vehicle and a second image area being positioned depending on the speed in the same lane ahead of the vehicle.
- the size of both image areas as previously described, preferably limited by lane markings or boundaries in the lateral direction.
- the first and second image areas preferably do not overlap one another and may be spatially separated from one another.
- the second image area is evaluated in particular in the same way as the first image area according to the method steps already described.
- a separate second image section offers the advantage of a higher spatial resolution compared to an enlarged individual image section.
- the position, size and / or shape of the second image area is adapted to the speed of the own vehicle in order to obtain a temporally uniform prediction (or preview) of the expected roadway condition.
- the assignment of the first image area to at least one roadway state from a currently recorded image is plausibilized by the assignment of the second image area to at least one roadway state from a previously recorded image.
- Information is output corresponding to at least one plausibility road condition. Since the second image area includes an image of a further upstream area of the road surface, its classification provides in effect a look-ahead. In a later image, the area of the road surface during forward travel is at least partially in the first image area due to the vehicle's own motion.
- the earlier class of the second image area can be considered as a "preview" for the plausibility check, thereby increasing the recognition certainty
- the two image areas are preferably transformed with the aid of odometry data of the vehicle.
- a monocular camera is used as a camera.
- Monocameras are established as driver assistance cameras and cheaper than stereo cameras.
- the method according to the invention already enables a robust and reliable road condition classification on the basis of monocamera images.
- a 3D or stereo camera is used as the camera.
- 3D or stereo cameras allow the evaluation of depth information from the image.
- the consideration of depth information profiles in the classification becomes possible.
- the invention further relates to a device for determining a road condition comprising a driving camera, an image processing unit, a classification unit and an output unit.
- the vehicle camera is designed to record at least one image of the vehicle environment.
- the image processing unit is designed to determine a first image area which comprises an image of the road surface and to supply it to a classification unit.
- the classification unit is designed to associate the first image area with at least one class that represents a specific roadway condition.
- the output unit is configured to output information about the at least one roadway condition that is assigned to the first image area by the classification unit.
- FIG. 1 shows a flow chart for illustrating the sequence of a variant embodiment of the method for determining a road condition by means of a vehicle camera
- FIG. 2 is an image of a forward vehicle environment taken with a vehicle camera
- Fig. 3 is a bird's-eye view representation of the scene represented by the image
- FIG. 6 shows a representation for determining a forward-looking adaptation horizon
- FIG. 7 shows a previous and future course of a trajectory when cornering
- FIG. 8 shows an image with a first image area and an image area shifted with respect to the lane course
- FIG. 10 shows an image with a first image area and two image areas shifted to this with consideration of a drive hose predicted for an evasive maneuver.
- Fig. 1 shows a flowchart for illustrating the sequence of a variant of the method according to the invention for determining a road condition by means of a driving camera.
- an image is taken with the driving camera in step S10. From this image, the lane can be determined in step 12, e.g. on the basis of lane markings in the image, lane boundary objects, etc. Already here, e.g. non-stationary objects are determined, which should not be considered in the determination of the road condition.
- a prediction of the trajectory or the travel tube of the own vehicle can take place.
- data from own vehicle sensors (V), eg steering angle, speed, etc., navigation system data or map data (N) or data further Environment sensors such as radar, lidar, telematics unit, etc. are taken into account.
- step 16 the ROI or a first or several image areas is determined, which includes a map of the road surface. These or these image extracts or features extracted therefrom are fed in step 18 to a classifier which associates each image region with at least one class representing a particular road condition.
- step 20 information about this at least one road condition is output, e.g. to a collision warning or an emergency brake assistant, which can adapt its warning thresholds or intervention times to the ascertained road condition.
- a collision warning or an emergency brake assistant which can adapt its warning thresholds or intervention times to the ascertained road condition.
- FIG. 2 shows, by way of example, an image (I) of a vehicle environment ahead, as recorded by a front camera (6) of a moving vehicle.
- camera-based driver assistance functions can be realized, e.g. Lane Departure Warning (LDW), Lane Keeping Assistance / System (LKA), Traffic Sign Recognition (TSR), Intelligent Headlamp Control (IHC), Collision Warning (FCW) Forward collision warning), a precipitation detection, an automatic cruise control (ACC, Adaptive Cruise Control), a parking assistance, automatic emergency brake or emergency steering systems (EBA, Emergency Brake Assist or ESA, Emergency Steering Assist).
- LDW Lane Departure Warning
- LKA Lane Keeping Assistance / System
- TSR Traffic Sign Recognition
- IHC Intelligent Headlamp Control
- FCW Collision Warning
- ACC automatic cruise control
- EBA Emergency Brake Assist or ESA, Emergency Steering Assist
- the camera image shows a roadway (1) whose surface is largely homogeneous. On the surface, lane markers are visible: a solid side line (4), which marks the left and right end of the lane, and center line segments (3) of the broken or dashed center lane mark.
- the roadway (1) could be made of asphalt or concrete. On the otherwise dry roadway (1) a puddle (2) can be seen.
- FIG. 3 is a bird's eye view of a representation of the scene represented by the image of the vehicle camera in FIG. 2.
- This representation can be determined from the camera image, where in a monocamera, preferably imaging properties of the camera (4), the built-in geometry of the camera in the vehicle (5), the actual vehicle height (due to the tire position / chassis control), pitch, yaw and / or roll angle are taken into account. It can be assumed that the road surface is flat.
- the representation can be determined directly on the basis of the acquired 3D image data, whereby further aspects can also be taken into account here.
- the representation is essentially characterized in that distances correspond to actual distances.
- the center strip segments shown are also arranged equidistantly on the real roadway.
- FIG. 3 On the representation shown in Fig. 3, the roadway (1), the puddle (2), the centerline segments (3) and the solid side boundary lines (4) of the lane mark are already included in the camera image ( Figure 2) ,
- a vehicle (5) with a camera (6) is included in the representation, the image from FIG. 2 having been taken with the camera (6).
- the dashed arrow indicates the predicted trajectory (T) of the vehicle (5).
- ROI region of interest
- FIG. 4 shows such an image area (R1) within the camera image (I).
- the center of an exemplary rectangular assumed first image area (Rl) is described within the entire camera image (I) by the image coordinates (x 0 , y 0 ) and the extent (Ax 0 , Ay 0 ). Image coordinates are indicated by lowercase letters.
- FIGS. 5 and 7 each show a second image area (R2) in addition to a first one (R1). This can be evaluated simultaneously (ie for a single image (I) to be evaluated) to the first image area (R1).
- the first image area (R1) contains information about the road condition that is reached by the vehicle (5) in a shorter time, and the second (R2) information that becomes relevant in a later time (preview for the current first image area).
- the second image area (R2) can each illustrate an adaptation of the first image area (R1) to a faster vehicle speed (or other changed driving situations).
- An example of such an adaptation of the first image area (R1) is an adaptation via the vehicle's own speed, the lane course during cornering and the predicted driving route during an evasive maneuver.
- the first image area (R1) could indicate the area of the roadway (1) which is run over by the vehicle at a speed of 50 km / h in ls. If the vehicle is traveling twice as fast, on the other hand, the area of the roadway (1), which is the second image area, would be run over in one second (R2). As the vehicle speed increases, the ROI (R2) moves further into the upper part of the image (farther from the vehicle (5)) and slightly to the left (x 10 ⁇ x 0 , y 10 > y 0 ) due to the camera's perspective (Ax 10 ⁇ Ax 0 , Ay 10 ⁇ Ay 0 ).
- FIG. 6 illustrates the determination of this adaptation on the basis of a representation in the vehicle coordinate system (X, Y). From the perspective of the own vehicle (5), CoG Veh whose center of gravity is always located at a current position XOV, a predictive adaptation horizon X p eh determined v, is a function of the traveling vehicle velocity ⁇ v eh and optionally further context information Inf Umf is:
- the environment information Inf ümf may indicate that an image area (R1, R2) should be further adjusted so that a preceding vehicle (not shown) is not displayed in that image area. This could lead to a faulty road condition classification. In order to prevent this, an image area (R1, R2) should be scaled down, cropped or shifted in this situation so that subsequently only the road surface (1, 2) to be classified is imaged therein.
- a suitable algorithm finally takes over the transformation of the determined prediction horizon (X pVeh ) into the image coordinate system (x, y) by the new position ⁇ xwr io) and expansion (Ax 10 , Ay 10 ) of the adapted or changed image region determine.
- the transformation corresponds to the transition from a representation as in FIG. 3 to a representation as in FIG. 2.
- lane markings (3, 4) can be recognized and used eg for a lane departure warning function (LDW). With knowledge of the course of the lane markings (3, 4), the course of the traffic lane traveled by the own vehicle (5) can be determined.
- LDW lane departure warning function
- Fig. 7 in the co-driving coordinate system of the previous and predicted on the basis of a lane detection course of motion (T) is shown when cornering.
- the mean curvature K c of the predicted course of motion (T dashed line) can be given as a function of the current vehicle yaw movement X " act of the previous course of motion (T solid line) as well as additional environment information, in particular the curvature of the preceding lane course.
- FIG. 8 shows for right-hand traffic how a prediction horizon determined from FIG. 7 (not shown there) can be transformed in the image (I) by adapting the image region from R1 to R2.
- the ROI moves into the left-hand top of the camera (x 20 ⁇ x 0 , 20> Yo).
- ⁇ The area of the image area decreases in accordance with the camera image.
- a trapezoidal shape was chosen here, which lies on the roadway between the median strip (3) and the right-hand lane boundary line (4).
- the driving tube is understood to be the predicted movement corridor of the ego vehicle (5) up to a distance of about 150 m. It is characterized in particular by its width, which can correspond approximately to the lane width.
- the travel tube can be calculated from camera data, data from other surroundings or vehicle sensors. If it is ensured by appropriate camera / environment sensor system and monitoring of the driver's activities that an evasive maneuver is to be carried out, the region of the road surface (1) to be imaged by the ROI is shifted as a function of an optimally planned avoidance trajectory (for example, 2nd order).
- the lateral benö the available alternative space in the X direction is S x .
- the curvature of the optimal avoidance curve K ref results from the planned avoidance trajectory according to: f "(X)
- the current curvature of the curve K act is a function of the vehicle yaw movement (see Section 2).
- the prediction horizon X pVeh is a measure of which " look- ahead" individual points (X pVs hr Y P veh) of the optimal avoidance curve become the target image coordinates (X30, Y30) for the ROI.
- Fig. 9 shows in co-driving coordinate system a previous course of motion T lst , the continuation of which would lead to a collision with an obstacle (7).
- An optimal avoidance ectorie T soll is shown as a dash-dotted curve.
- the obstacle could have been comfortably avoided.
- P act As part of an emergency maneuver can now be required by a short-term change in the yaw angle of! P act to ⁇ ⁇ a course of movement according to the dashed line in order to reach the area of the target Traj ektorie as effectively as possible.
- a road condition determination or camera-based coefficient of friction estimation is enormously important, since emergency maneuvers are braked or even steered to the friction limit.
- a puddle (2) on an otherwise dry road (1) as in Fig. 2 could lead to a collision with the obstacle can not be avoided or the own vehicle departs from the road.
- a camera image (I) is shown that a stationary obstacle (7), eg a vehicle, in its own lane in front of the own vehicle (6) images.
- a value determined from FIG. 9 prediction horizon X PVE hr Y P veh (I) in the image by adjusting the image area of Rl to Rl '' can be transformed.
- An intermediate step of adaptation (Rl 7 ) is also shown.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
- Mechanical Engineering (AREA)
Abstract
Description
Claims
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE112014000887.7T DE112014000887A5 (de) | 2013-02-19 | 2014-02-14 | Verfahren und Vorrichtung zur Bestimmung eines Fahrbahnzustands |
US14/764,782 US10147002B2 (en) | 2013-02-19 | 2014-02-14 | Method and apparatus for determining a road condition |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE102013101639.1A DE102013101639A1 (de) | 2013-02-19 | 2013-02-19 | Verfahren und Vorrichtung zur Bestimmung eines Fahrbahnzustands |
DE102013101639.1 | 2013-02-19 |
Publications (2)
Publication Number | Publication Date |
---|---|
WO2014127777A2 true WO2014127777A2 (de) | 2014-08-28 |
WO2014127777A3 WO2014127777A3 (de) | 2014-12-24 |
Family
ID=50433895
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/DE2014/200062 WO2014127777A2 (de) | 2013-02-19 | 2014-02-14 | Verfahren und vorrichtung zur bestimmung eines fahrbahnzustands |
Country Status (3)
Country | Link |
---|---|
US (1) | US10147002B2 (de) |
DE (2) | DE102013101639A1 (de) |
WO (1) | WO2014127777A2 (de) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105701444A (zh) * | 2014-12-12 | 2016-06-22 | 通用汽车环球科技运作有限责任公司 | 用于确定道路表面的状况的系统和方法 |
DE102018203807A1 (de) | 2018-03-13 | 2019-09-19 | Continental Teves Ag & Co. Ohg | Verfahren und Vorrichtung zur Erkennung und Bewertung von Fahrbahnzuständen und witterungsbedingten Umwelteinflüssen |
CN111856491A (zh) * | 2019-04-26 | 2020-10-30 | 大众汽车有限公司 | 用于确定车辆的地理位置和朝向的方法和设备 |
US20210009125A1 (en) * | 2016-04-29 | 2021-01-14 | Ford Global Technologies, Llc | System and method for controlling a vehicle steering system |
CN113687310A (zh) * | 2016-04-22 | 2021-11-23 | 安波福技术有限公司 | 用于自动化车辆的对象检测系统 |
AT524256A1 (de) * | 2020-10-08 | 2022-04-15 | Thomas Genitheim Ing Dipl Ing Fh | Verfahren zur Ermittlung eines Reibbeiwertes |
Families Citing this family (73)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102012112725A1 (de) | 2012-12-20 | 2014-06-26 | Continental Teves Ag & Co. Ohg | Reibwertschätzung aus Kamera- und Raddrehzahldaten |
DE102012112724A1 (de) | 2012-12-20 | 2014-06-26 | Continental Teves Ag & Co. Ohg | Verfahren zur Bestimmung eines Fahrbahnzustands aus Umfeldsensordaten |
DE102013223367A1 (de) | 2013-11-15 | 2015-05-21 | Continental Teves Ag & Co. Ohg | Verfahren und Vorrichtung zur Bestimmung eines Fahrbahnzustands mittels eines Fahrzeugkamerasystems |
US10325165B2 (en) * | 2014-09-30 | 2019-06-18 | Conduent Business Services, Llc | Vision-based on-street parked vehicle detection via normalized-view classifiers and temporal filtering |
JP6306735B2 (ja) * | 2014-10-24 | 2018-04-04 | 京セラ株式会社 | ステレオカメラ装置及びステレオカメラ装置を備える車両 |
US9428194B2 (en) * | 2014-12-11 | 2016-08-30 | Toyota Motor Engineering & Manufacturing North America, Inc. | Splash condition detection for vehicles |
KR101692628B1 (ko) * | 2014-12-24 | 2017-01-04 | 한동대학교 산학협력단 | 관심영역을 이용하여 차량의 후방 좌우 옆 차선 영역을 감지하는 방법 및 이를 이용한 차량용 영상 모니터링 시스템 |
WO2016183074A1 (en) * | 2015-05-10 | 2016-11-17 | Mobileye Vision Technologies Ltd. | Road profile along a predicted path |
US10691958B1 (en) * | 2015-07-30 | 2020-06-23 | Ambarella International Lp | Per-lane traffic data collection and/or navigation |
US10235817B2 (en) * | 2015-09-01 | 2019-03-19 | Ford Global Technologies, Llc | Motion compensation for on-board vehicle sensors |
CN114612877A (zh) * | 2016-01-05 | 2022-06-10 | 御眼视觉技术有限公司 | 用于估计未来路径的系统和方法 |
JP6811534B2 (ja) | 2016-02-04 | 2021-01-13 | 株式会社トプコン | 道路性状の表示方法、及び道路性状の表示装置 |
JP6745112B2 (ja) | 2016-02-04 | 2020-08-26 | 株式会社トプコン | 路面性状の評価方法、及び路面性状の評価装置 |
JP6745113B2 (ja) * | 2016-02-04 | 2020-08-26 | 株式会社トプコン | 路面性状取得方法、及び路面性状取得装置 |
CN107092920A (zh) * | 2016-02-17 | 2017-08-25 | 福特全球技术公司 | 评估其上行驶有车辆的路面的方法和装置 |
CN107563256A (zh) * | 2016-06-30 | 2018-01-09 | 北京旷视科技有限公司 | 辅助驾驶信息产生方法及装置、辅助驾驶系统 |
US11270130B2 (en) * | 2016-08-05 | 2022-03-08 | Transportation Ip Holdings, Llc | Route inspection system |
JP6776058B2 (ja) * | 2016-08-26 | 2020-10-28 | シャープ株式会社 | 自律走行車両制御装置、自律走行車両制御システム及び自律走行車両制御方法 |
US11145142B2 (en) | 2016-09-06 | 2021-10-12 | International Business Machines Corporation | Detection of road surface defects |
DE102016217916A1 (de) | 2016-09-19 | 2018-03-22 | Volkswagen Aktiengesellschaft | Verfahren, Assistenzsystem und computerlesbares Speichermedium mit Instruktionen zum Auswerten fahrwegbezogener Informationen |
US10275662B1 (en) * | 2016-09-30 | 2019-04-30 | Zoox, Inc. | Estimating friction based on image data |
DE102016218949A1 (de) * | 2016-09-30 | 2018-04-05 | Conti Temic Microelectronic Gmbh | Kameravorrichtung sowie Verfahren zur Objektdetektion in einem Umgebungsbereich eines Kraftfahrzeugs |
DE102016220308A1 (de) * | 2016-10-18 | 2018-04-19 | Continental Automotive Gmbh | System und Verfahren zur Erzeugung von digitalen Straßenmodellen aus Luft- oder Satellitenbildern und von Fahrzeugen erfassten Daten |
DE102016224539A1 (de) * | 2016-12-08 | 2018-06-14 | Brose Fahrzeugteile Gmbh & Co. Kommanditgesellschaft, Bamberg | Verfahren zur Ansteuerung einer Stellvorrichtung mit einer Einklemmschutzfunktion |
US10481609B2 (en) * | 2016-12-09 | 2019-11-19 | Ford Global Technologies, Llc | Parking-lot-navigation system and method |
JP6794243B2 (ja) * | 2016-12-19 | 2020-12-02 | 日立オートモティブシステムズ株式会社 | 物体検出装置 |
US11579574B2 (en) * | 2017-02-10 | 2023-02-14 | Nec Corporation | Control customization system, control customization method, and control customization program |
JP6666289B2 (ja) * | 2017-03-15 | 2020-03-13 | 株式会社東芝 | 移動体用空間情報算出装置及び衝突回避システム |
US10209089B2 (en) | 2017-04-03 | 2019-02-19 | Robert Bosch Gmbh | Automated image labeling for vehicles based on maps |
DE102017114571A1 (de) * | 2017-06-29 | 2019-01-03 | Volkswagen Aktiengesellschaft | Verfahren und Vorrichtung zum Bestimmen einer Beschaffenheit einer Oberfläche in der Umgebung eines Fahrzeugs |
US10331957B2 (en) * | 2017-07-27 | 2019-06-25 | Here Global B.V. | Method, apparatus, and system for vanishing point/horizon estimation using lane models |
DE102017120899A1 (de) * | 2017-09-11 | 2019-03-14 | Connaught Electronics Ltd. | Verfahren und System zum automatischen Parken eines Fahrzeugs in einer Notsituation |
DE102017216016A1 (de) * | 2017-09-12 | 2019-03-14 | Robert Bosch Gmbh | Verfahren und Vorrichtung zum Erkennen eines Umfelds eines Fahrzeugs |
DE102017122432A1 (de) | 2017-09-27 | 2019-03-28 | Valeo Schalter Und Sensoren Gmbh | Verfahren zum Erfassen einer Fahrbahnbeschaffenheit einer Fahrbahn für ein Kraftfahrzeug, Fahrerassistenzsystem sowie Kraftfahrzeug |
US10678256B2 (en) * | 2017-09-28 | 2020-06-09 | Nec Corporation | Generating occlusion-aware bird eye view representations of complex road scenes |
EP3722172A4 (de) * | 2017-12-07 | 2020-12-02 | Nissan Motor Co., Ltd. | Verfahren zur bestimmung des strassenzustandes und vorrichtung zur bestimmung des strassenzustandes |
EP3495219B1 (de) * | 2017-12-11 | 2023-07-05 | Volvo Car Corporation | Wegvorhersage für ein fahrzeug |
EP3546312A1 (de) * | 2018-03-26 | 2019-10-02 | Volvo Car Corporation | Verfahren und system zur handhabung der bedingungen einer strasse, auf der ein fahrzeug fährt |
US11124193B2 (en) | 2018-05-03 | 2021-09-21 | Volvo Car Corporation | System and method for providing vehicle safety distance and speed alerts under slippery road conditions |
US11592566B2 (en) | 2019-08-15 | 2023-02-28 | Volvo Car Corporation | Vehicle systems and methods utilizing LIDAR data for road condition estimation |
US10706294B2 (en) | 2018-05-03 | 2020-07-07 | Volvo Car Corporation | Methods and systems for generating and using a road friction estimate based on camera image signal processing |
US10800408B2 (en) * | 2018-05-24 | 2020-10-13 | Baidu Usa Llc | Determining driving paths for autonomous driving that avoid moving obstacles |
DE102018209595A1 (de) * | 2018-06-14 | 2019-12-19 | Robert Bosch Gmbh | Verfahren zum automatischen Bestimmen eines Straßenzustands |
US11699207B2 (en) * | 2018-08-20 | 2023-07-11 | Waymo Llc | Camera assessment techniques for autonomous vehicles |
US11227409B1 (en) | 2018-08-20 | 2022-01-18 | Waymo Llc | Camera assessment techniques for autonomous vehicles |
US10872419B2 (en) * | 2018-09-04 | 2020-12-22 | GM Global Technology Operations LLC | Method and apparatus for evaluating a vehicle travel surface |
US11199847B2 (en) * | 2018-09-26 | 2021-12-14 | Baidu Usa Llc | Curvature corrected path sampling system for autonomous driving vehicles |
CN109446963B (zh) * | 2018-10-19 | 2021-10-01 | 中国科学院东北地理与农业生态研究所 | 基于hsv和lbp结合的地表状态识别方法 |
US11010592B2 (en) * | 2018-11-15 | 2021-05-18 | Toyota Research Institute, Inc. | System and method for lifting 3D representations from monocular images |
JP6946605B2 (ja) * | 2018-12-27 | 2021-10-06 | 三井金属アクト株式会社 | ドア自動開閉システム |
US11472413B2 (en) | 2019-02-20 | 2022-10-18 | Steering Solutions Ip Holding Corporation | Mu confidence estimation and blending |
DE102019106625A1 (de) * | 2019-03-15 | 2020-09-17 | HELLA GmbH & Co. KGaA | Verfahren und Vorrichtung zum Ermitteln einer Gefahrenquelle auf einer Fahrbahn |
KR102587419B1 (ko) * | 2019-03-27 | 2023-10-10 | 히다치 아스테모 가부시키가이샤 | 서스펜션 제어 장치 |
DE102019108649A1 (de) * | 2019-04-03 | 2020-10-08 | Valeo Schalter Und Sensoren Gmbh | Verfahren und Fahrerassistenzsystem zum Erfassen eines Objekts |
US11361574B2 (en) * | 2019-10-23 | 2022-06-14 | Bendix Commercial Vehicle Systems Llc | System and method for monitoring for driver presence and position using a driver facing camera |
US11592304B2 (en) * | 2020-02-03 | 2023-02-28 | Bose Corporation | Surface detection for micromobility vehicles |
GB2611452A (en) | 2020-05-18 | 2023-04-05 | Roadbotics Inc | Systems and methods for creating and/or analyzing three-dimensional models of infrastructure assets |
KR20220001496A (ko) * | 2020-06-29 | 2022-01-05 | 주식회사 만도모빌리티솔루션즈 | 긴급 제동 시스템 및 방법 |
US12103539B2 (en) | 2020-08-24 | 2024-10-01 | Steering Solutions Ip Holding Corporation | Surface detection via a directed autonomous vehicle |
CN112528793B (zh) * | 2020-12-03 | 2024-03-12 | 上海汽车集团股份有限公司 | 一种车辆的障碍物检测框抖动消除方法及装置 |
US12062242B2 (en) * | 2020-12-03 | 2024-08-13 | Hl Klemove Corp. | Method and system for real-time continuous lane mapping and classification |
CN115123075A (zh) * | 2021-03-25 | 2022-09-30 | 丰田自动车株式会社 | 下车支援装置 |
CN113200052B (zh) * | 2021-05-06 | 2021-11-16 | 上海伯镭智能科技有限公司 | 一种用于无人驾驶的路况智能识别方法 |
EP4113459A1 (de) * | 2021-07-02 | 2023-01-04 | Fujitsu Technology Solutions GmbH | Ki-basierte überwachung von rennbahnen |
EP4459563A2 (de) * | 2021-07-02 | 2024-11-06 | Fujitsu Technology Solutions GmbH | Ki-basierte überwachung von rennstrecken |
US20230142305A1 (en) * | 2021-11-05 | 2023-05-11 | GM Global Technology Operations LLC | Road condition detection systems and methods |
DE102022204089A1 (de) | 2022-04-27 | 2023-11-02 | Robert Bosch Gesellschaft mit beschränkter Haftung | Verfahren zum Erkennen, ob ein Egofahrzeug von einer momentan befahrenen Fahrspur einer Fahrbahn in eine benachbarte Fahrspur wechselt oder ob es die momentan befahrene Fahrspur beibehält |
DE102022004824A1 (de) | 2022-12-20 | 2024-06-20 | Mercedes-Benz Group AG | Verfahren zur Bestimmung eines Fahrbahnzustands einer von einem Kraftwagen befahrenen Fahrbahn sowie ein Assistenzsystem |
CN116861292B (zh) * | 2023-07-10 | 2024-07-09 | 哈尔滨工业大学 | 道路监测数据有荷动力响应实时识别方法 |
CN117292349B (zh) * | 2023-11-22 | 2024-04-12 | 魔视智能科技(武汉)有限公司 | 确定路面高度的方法、装置、计算机设备及存储介质 |
CN118038284B (zh) * | 2024-04-15 | 2024-06-14 | 贵州黔通工程技术有限公司 | 一种高速公路病害智能检测方法及系统 |
CN118362604B (zh) * | 2024-06-19 | 2024-10-08 | 广汽埃安新能源汽车股份有限公司 | 一种路面结冰状态检测方法、装置、电子设备和存储介质 |
CN118570959B (zh) * | 2024-07-09 | 2024-10-01 | 四川智慧高速科技有限公司 | 一种基于传感器的道路结冰预警方法和系统 |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102004018088A1 (de) | 2003-04-09 | 2005-02-10 | Continental Teves, Inc., Auburn Hills | Fahrbahnerkennungssystem |
WO2012110030A2 (de) | 2011-02-14 | 2012-08-23 | Conti Temic Microelectronic Gmbh | Reibwertschätzung mittels einer 3d-kamera |
Family Cites Families (54)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH072448B2 (ja) | 1986-01-13 | 1995-01-18 | アイシン・エィ・ダブリュ株式会社 | 4輪駆動の制御装置 |
GB8918303D0 (en) | 1989-08-10 | 1989-09-20 | Lucas Ind Plc | Monitoring and predicting road vehicle/road surface conditions |
JPH0735522A (ja) | 1993-07-23 | 1995-02-07 | Nippon Doro Kodan | レーザーを利用した舗装路面横断プロフィル測定方法 |
US5586028A (en) * | 1993-12-07 | 1996-12-17 | Honda Giken Kogyo Kabushiki Kaisha | Road surface condition-detecting system and anti-lock brake system employing same |
US5774821A (en) | 1994-11-25 | 1998-06-30 | Itt Automotive Europe Gmbh | System for driving stability control |
JPH08263784A (ja) * | 1995-03-23 | 1996-10-11 | Honda Motor Co Ltd | 道路状況認識装置 |
EP0827127B1 (de) * | 1996-08-28 | 2006-10-04 | Matsushita Electric Industrial Co., Ltd. | Lokales Positionierungsgerät und Verfahren dafür |
DE19856510C2 (de) | 1998-02-20 | 2002-10-24 | Cegelec Anlagen Und Automatisi | Verfahren und System zur Ermittlung von Unebenheiten und Schadstellen in der Oberfläche einer Verkehrsfläche |
DE19854964A1 (de) | 1998-11-29 | 2000-06-08 | Martin Spies | Sensor zur Fahrbahnbeurteilung |
JP2001334921A (ja) | 2000-05-30 | 2001-12-04 | Fuji Heavy Ind Ltd | 車両の路面摩擦係数推定装置 |
JP3271963B1 (ja) | 2000-10-26 | 2002-04-08 | 富士重工業株式会社 | 車両の路面摩擦係数推定装置 |
DE10060333A1 (de) | 2000-12-04 | 2002-06-13 | Daimler Chrysler Ag | Vorrichtung zur Erkennung einer während des Fahrbetriebes eines Fahrzeuges auftretenden Aquaplaninggefahr |
DE10155488A1 (de) | 2001-11-13 | 2003-05-28 | Wilhelm Caspary | Verfahren zur Erfassung der Oberfläche einer Fahrbahn |
US6636258B2 (en) | 2001-10-19 | 2003-10-21 | Ford Global Technologies, Llc | 360° vision system for a vehicle |
EP2514640B1 (de) | 2001-12-21 | 2015-08-05 | Kabushiki Kaisha Bridgestone | Verfahren und Vorrichtung zur Schätzung der Straßenbedingungen und des Reifenlaufzustands sowie ABS und Fahrzeugsteuerung damit |
ES2391556T3 (es) | 2002-05-03 | 2012-11-27 | Donnelly Corporation | Sistema de detección de objetos para vehículo |
DE10256726A1 (de) | 2002-12-05 | 2004-06-24 | Conti Temic Microelectronic Gmbh | Verfahren zur fahrbahnabhängigen Signalgenerierung in einem Kraftfahrzeug |
JP4453382B2 (ja) | 2004-02-10 | 2010-04-21 | トヨタ自動車株式会社 | 車両の走行制御装置 |
DE102004016288B3 (de) | 2004-04-02 | 2005-08-18 | Daimlerchrysler Ag | Verfahren zur Bestimmung eines Reibwerts |
DE102004019337A1 (de) | 2004-04-21 | 2005-11-17 | Siemens Ag | Assistenzsystem für Kraftfahrzeuge |
DE102004055069B4 (de) | 2004-07-15 | 2007-02-15 | Daimlerchrysler Ag | Mehrdimensionale Fahrbahnvermessung |
DE102004047914A1 (de) | 2004-09-29 | 2006-03-30 | A.D.C. Automotive Distance Control Systems Gmbh | Methode zur Einschätzung des Fahrbahnzustands |
DE102004048637A1 (de) | 2004-10-04 | 2006-04-06 | Daimlerchrysler Ag | 3D-Fahrbahnmessung mit redundanten Messdaten |
DE102006012289A1 (de) | 2006-03-17 | 2007-09-20 | Man Nutzfahrzeuge Ag | Verfahren zur vorausschauenden Erkennung der Reibwertänderung eines Straßenbelags |
US8306747B1 (en) | 2007-01-19 | 2012-11-06 | Starodub, Inc. | Travel way measurement system |
DE102008047750A1 (de) | 2007-09-18 | 2009-05-07 | Continental Teves Ag & Co. Ohg | Bestimmung eines Kraftschlusses mit wenigen Sensoren |
EP2048476B1 (de) | 2007-10-08 | 2013-12-11 | Delphi Technologies, Inc. | Fahrerunterstützungsverfahren |
WO2010050300A1 (ja) * | 2008-10-30 | 2010-05-06 | 株式会社ブリヂストン | 路面状態推定方法 |
DE102009033219A1 (de) | 2009-01-23 | 2010-07-29 | Daimler Ag | Verfahren zur Ermittlung eines Fahrzeug vorausliegenden Straßenprofils einer Fahrspur |
JP5172764B2 (ja) | 2009-03-30 | 2013-03-27 | 本田技研工業株式会社 | 路面摩擦係数推定装置 |
US8395529B2 (en) | 2009-04-02 | 2013-03-12 | GM Global Technology Operations LLC | Traffic infrastructure indicator on head-up display |
KR20120050451A (ko) | 2009-07-17 | 2012-05-18 | 콘티넨탈 엔지니어링 서비시스 게엠베하 | 자동차들의 마찰 계수 분류를 위한 레이저-기반 방법 |
DE102009041566B4 (de) | 2009-09-15 | 2022-01-20 | Continental Teves Ag & Co. Ohg | Verfahren zur Klassifizierung des Fahrbahnreibwerts |
KR101089650B1 (ko) * | 2009-09-23 | 2011-12-06 | 삼성전기주식회사 | 차량 속도 제어 장치 및 방법 |
JP5325765B2 (ja) * | 2009-12-28 | 2013-10-23 | 日立オートモティブシステムズ株式会社 | 路肩検出装置及び路肩検出装置を用いた車両 |
US9092981B2 (en) * | 2010-03-03 | 2015-07-28 | Panasonic Intellectual Property Management Co., Ltd. | Road condition management system and road condition management method |
DE102010011093A1 (de) | 2010-03-11 | 2011-09-15 | Daimler Ag | Verfahren zur Bestimmung einer Fahrzeugaufbaubewegung |
DE102010013339A1 (de) | 2010-03-30 | 2011-01-05 | Daimler Ag | Vorrichtung und Verfahren zur Steuerung eines Motorlagers für ein Fahrzeug |
DE102010045162A1 (de) | 2010-09-11 | 2012-03-15 | Volkswagen Ag | Schlaglochassistent mit Umfeldwahrnehmung |
JP2012066785A (ja) | 2010-09-27 | 2012-04-05 | Fuji Heavy Ind Ltd | 車両の統合制御装置 |
DE102010063017A1 (de) | 2010-12-14 | 2012-06-14 | Robert Bosch Gmbh | Verfahren in einem Fahrerassistenzsystem zur Erkennung von Nässe auf einer Fahrbahn |
DE102011011755A1 (de) | 2011-02-18 | 2012-08-23 | Conti Temic Microelectronic Gmbh | Halbleiterschaltkreis und Verfahren in einem Sicherheitskonzept zum Einsatz in einem Kraftfahrzeug |
DE102011100907A1 (de) | 2011-05-09 | 2012-01-12 | Daimler Ag | Vorrichtung und Verfahren zur Ermittlung eines Fahrbahnzustands |
WO2013009697A1 (en) | 2011-07-08 | 2013-01-17 | Bendix Commercial Vehicle Systems Llc | Image-based vehicle detection and distance measuring method and apparatus |
DE102011081362A1 (de) | 2011-08-23 | 2013-02-28 | Robert Bosch Gmbh | Verfahren und Vorrichtung zur Ermittlung eines Oberflächenzustands einer von einem Fahrzeug befahrenen oder zu befahrenden Fahrbahn |
DE102012101085A1 (de) | 2012-02-10 | 2013-08-14 | Conti Temic Microelectronic Gmbh | Bestimmung einer Beschaffenheit einer Fahrbahnoberfläche mittels einer 3D-Kamera |
EP2852831A4 (de) * | 2012-05-23 | 2016-04-20 | Raqib Omer | Verfahren und system zur klassifizierung des strassenoberflächenzustandes |
DE102012024874B4 (de) | 2012-12-19 | 2014-07-10 | Audi Ag | Verfahren und Vorrichtung zum prädikativen Ermitteln eines Parameterwertes einer von einem Fahrzeug befahrbaren Oberfläche |
DE102012112725A1 (de) | 2012-12-20 | 2014-06-26 | Continental Teves Ag & Co. Ohg | Reibwertschätzung aus Kamera- und Raddrehzahldaten |
DE102012112724A1 (de) | 2012-12-20 | 2014-06-26 | Continental Teves Ag & Co. Ohg | Verfahren zur Bestimmung eines Fahrbahnzustands aus Umfeldsensordaten |
US8788146B1 (en) * | 2013-01-08 | 2014-07-22 | Ford Global Technologies, Llc | Adaptive active suspension system with road preview |
US9187099B2 (en) | 2013-10-17 | 2015-11-17 | Richard M. Powers | Systems and methods for predicting weather performance for a vehicle |
DE102013223367A1 (de) | 2013-11-15 | 2015-05-21 | Continental Teves Ag & Co. Ohg | Verfahren und Vorrichtung zur Bestimmung eines Fahrbahnzustands mittels eines Fahrzeugkamerasystems |
US9434388B2 (en) | 2014-10-31 | 2016-09-06 | GM Global Technology Operations LLC | Surface estimation for vehicles |
-
2013
- 2013-02-19 DE DE102013101639.1A patent/DE102013101639A1/de not_active Withdrawn
-
2014
- 2014-02-14 US US14/764,782 patent/US10147002B2/en active Active
- 2014-02-14 WO PCT/DE2014/200062 patent/WO2014127777A2/de active Application Filing
- 2014-02-14 DE DE112014000887.7T patent/DE112014000887A5/de active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102004018088A1 (de) | 2003-04-09 | 2005-02-10 | Continental Teves, Inc., Auburn Hills | Fahrbahnerkennungssystem |
WO2012110030A2 (de) | 2011-02-14 | 2012-08-23 | Conti Temic Microelectronic Gmbh | Reibwertschätzung mittels einer 3d-kamera |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105701444A (zh) * | 2014-12-12 | 2016-06-22 | 通用汽车环球科技运作有限责任公司 | 用于确定道路表面的状况的系统和方法 |
CN105701444B (zh) * | 2014-12-12 | 2019-11-29 | 通用汽车环球科技运作有限责任公司 | 用于确定道路表面的状况的系统和方法 |
CN113687310A (zh) * | 2016-04-22 | 2021-11-23 | 安波福技术有限公司 | 用于自动化车辆的对象检测系统 |
US20210009125A1 (en) * | 2016-04-29 | 2021-01-14 | Ford Global Technologies, Llc | System and method for controlling a vehicle steering system |
US11702073B2 (en) * | 2016-04-29 | 2023-07-18 | Ford Global Technologies, Llc | System and method for controlling a vehicle steering system |
DE102018203807A1 (de) | 2018-03-13 | 2019-09-19 | Continental Teves Ag & Co. Ohg | Verfahren und Vorrichtung zur Erkennung und Bewertung von Fahrbahnzuständen und witterungsbedingten Umwelteinflüssen |
WO2019174682A1 (de) | 2018-03-13 | 2019-09-19 | Continental Teves Ag & Co. Ohg | Verfahren und vorrichtung zur erkennung und bewertung von fahrbahnzuständen und witterungsbedingten umwelteinflüssen |
CN111856491A (zh) * | 2019-04-26 | 2020-10-30 | 大众汽车有限公司 | 用于确定车辆的地理位置和朝向的方法和设备 |
CN111856491B (zh) * | 2019-04-26 | 2023-12-22 | 大众汽车有限公司 | 用于确定车辆的地理位置和朝向的方法和设备 |
AT524256A1 (de) * | 2020-10-08 | 2022-04-15 | Thomas Genitheim Ing Dipl Ing Fh | Verfahren zur Ermittlung eines Reibbeiwertes |
AT524256B1 (de) * | 2020-10-08 | 2023-06-15 | Thomas Genitheim Ing Dipl Ing Fh | Verfahren zur Ermittlung eines Reibbeiwertes |
Also Published As
Publication number | Publication date |
---|---|
WO2014127777A3 (de) | 2014-12-24 |
US20150371095A1 (en) | 2015-12-24 |
DE102013101639A1 (de) | 2014-09-04 |
DE112014000887A5 (de) | 2015-11-19 |
US10147002B2 (en) | 2018-12-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2014127777A2 (de) | Verfahren und vorrichtung zur bestimmung eines fahrbahnzustands | |
WO2019174682A1 (de) | Verfahren und vorrichtung zur erkennung und bewertung von fahrbahnzuständen und witterungsbedingten umwelteinflüssen | |
EP3160813B1 (de) | Verfahren zur erstellung eines umfeldmodells eines fahrzeugs | |
EP3292510B1 (de) | Verfahren und vorrichtung zur erkennung und bewertung von fahrbahnreflexionen | |
DE112016000422B4 (de) | Geschwindigkeitsregelvorrichtung und geschwindigkeitsregelverfahren für fahrzeuge | |
DE102012104766B4 (de) | Spurermittlung mittels Spurmarkierungsidentifikation für Spurzentrierung/-haltung | |
DE102007043164B4 (de) | Nebelerkennungsvorrichtung für Kraftfahrzeuge | |
EP2888604B1 (de) | Verfahren zur bestimmung eines fahrspurverlaufs für ein fahrzeug | |
WO2016177372A1 (de) | Verfahren und vorrichtung zur erkennung und bewertung von umwelteinflüssen und fahrbahnzustandsinformationen im fahrzeugumfeld | |
WO2014094766A1 (de) | Verfahren zur bestimmung eines fahrbahnzustands aus umfeldsensordaten | |
WO2014161691A1 (de) | Verfahren und vorrichtung zum führen eines fahrzeugs im umfeld eines objekts | |
DE102012210608A1 (de) | Verfahren und Vorrichtung zum Erzeugen eines Steuerparameters für ein Abstandsassistenzsystem eines Fahrzeugs | |
DE102009012917A1 (de) | Hinderniserkennungsvorrichtung für Fahrzeuge | |
DE102008020007A1 (de) | Verfahren zum Unterstützen eines Fahrers beim Fahren mit einem Fahrzeug mit einer Fahrspurerkennung | |
DE102018104270A1 (de) | Verfahren zum Vorhersagen des Verhaltens mindestens eines Fußgängers | |
EP3627386A1 (de) | Verfahren und vorrichtung zum bereitstellen eines umfeldabbildes eines umfeldes einer mobilen einrichtung und kraftfahrzeug mit einer solchen vorrichtung | |
DE102013201796A1 (de) | Verfahren zur Bereitstellung eines Fahrkorridors für ein Fahrzeug und Fahrassistenzsystem | |
DE102017106349A1 (de) | Fahrerassistenzsystem für ein Fahrzeug zum Prognostizieren eines dem Fahrzeug vorausliegenden Fahrspurbereichs, Fahrzeug und Verfahren | |
DE102018211368A1 (de) | Verfahren zur Beschreibung einer Umgebung eines Fahrzeugs durch die Topologie der befahrenen Straße | |
EP2964503B1 (de) | Schätzung der zukünftigen geschwindigkeit und/oder entfernung eines fahrzeugs von einem referenzpunkt und schätzung der zukünftigen beschleunigung | |
DE102013021840A1 (de) | Verfahren zum Erzeugen eines Umgebungsmodells eines Kraftfahrzeugs, Fahrerassistenzsystem und Kraftfahrzeug | |
EP3655299B1 (de) | Verfahren und vorrichtung zum ermitteln eines optischen flusses anhand einer von einer kamera eines fahrzeugs aufgenommenen bildsequenz | |
DE102012221652B4 (de) | Verfahren und Vorrichtung zum Bestimmen, ob in einer Verkehrssituation Linksverkehr oder Rechtsverkehr besteht | |
DE102014209015A1 (de) | Verfahren und Vorrichtung zur Abstandsregelung für ein Fahrzeug | |
EP2696310B1 (de) | Verfahren zum Identifizieren eines Straßenrands |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 14714927 Country of ref document: EP Kind code of ref document: A2 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 14764782 Country of ref document: US |
|
WWE | Wipo information: entry into national phase |
Ref document number: 1120140008877 Country of ref document: DE Ref document number: 112014000887 Country of ref document: DE |
|
REG | Reference to national code |
Ref country code: DE Ref legal event code: R225 Ref document number: 112014000887 Country of ref document: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 14714927 Country of ref document: EP Kind code of ref document: A2 |