CN107235044A - It is a kind of to be realized based on many sensing datas to road traffic scene and the restoring method of driver driving behavior - Google Patents
It is a kind of to be realized based on many sensing datas to road traffic scene and the restoring method of driver driving behavior Download PDFInfo
- Publication number
- CN107235044A CN107235044A CN201710401034.5A CN201710401034A CN107235044A CN 107235044 A CN107235044 A CN 107235044A CN 201710401034 A CN201710401034 A CN 201710401034A CN 107235044 A CN107235044 A CN 107235044A
- Authority
- CN
- China
- Prior art keywords
- data
- vehicle
- barrier
- car
- traffic
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 241001269238 Data Species 0.000 title claims abstract description 17
- 230000004888 barrier function Effects 0.000 claims abstract description 41
- 230000009467 reduction Effects 0.000 claims abstract description 28
- 238000005259 measurement Methods 0.000 claims abstract description 20
- 230000004927 fusion Effects 0.000 claims abstract description 12
- 238000001514 detection method Methods 0.000 claims description 15
- 241000894007 species Species 0.000 claims description 10
- 238000012937 correction Methods 0.000 claims description 9
- 238000013527 convolutional neural network Methods 0.000 claims description 7
- 238000009795 derivation Methods 0.000 claims description 6
- 238000007418 data mining Methods 0.000 claims description 4
- 238000007619 statistical method Methods 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 claims description 4
- 230000001351 cycling effect Effects 0.000 claims description 3
- 235000013399 edible fruits Nutrition 0.000 claims 1
- 230000007547 defect Effects 0.000 abstract description 2
- 230000006399 behavior Effects 0.000 description 23
- 238000005516 engineering process Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 3
- 238000012827 research and development Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000006735 deficit Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002441 reversible effect Effects 0.000 description 2
- PCTMTFRHKVHKIS-BMFZQQSSSA-N (1s,3r,4e,6e,8e,10e,12e,14e,16e,18s,19r,20r,21s,25r,27r,30r,31r,33s,35r,37s,38r)-3-[(2r,3s,4s,5s,6r)-4-amino-3,5-dihydroxy-6-methyloxan-2-yl]oxy-19,25,27,30,31,33,35,37-octahydroxy-18,20,21-trimethyl-23-oxo-22,39-dioxabicyclo[33.3.1]nonatriaconta-4,6,8,10 Chemical compound C1C=C2C[C@@H](OS(O)(=O)=O)CC[C@]2(C)[C@@H]2[C@@H]1[C@@H]1CC[C@H]([C@H](C)CCCC(C)C)[C@@]1(C)CC2.O[C@H]1[C@@H](N)[C@H](O)[C@@H](C)O[C@H]1O[C@H]1/C=C/C=C/C=C/C=C/C=C/C=C/C=C/[C@H](C)[C@@H](O)[C@@H](C)[C@H](C)OC(=O)C[C@H](O)C[C@H](O)CC[C@@H](O)[C@H](O)C[C@H](O)C[C@](O)(C[C@H](O)[C@H]2C(O)=O)O[C@H]2C1 PCTMTFRHKVHKIS-BMFZQQSSSA-N 0.000 description 1
- 102100034112 Alkyldihydroxyacetonephosphate synthase, peroxisomal Human genes 0.000 description 1
- 101000799143 Homo sapiens Alkyldihydroxyacetonephosphate synthase, peroxisomal Proteins 0.000 description 1
- 238000000848 angular dependent Auger electron spectroscopy Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- VIKNJXKGJWUCNN-XGXHKTLJSA-N norethisterone Chemical compound O=C1CC[C@@H]2[C@H]3CC[C@](C)([C@](CC4)(O)C#C)[C@@H]4[C@@H]3CCC2=C1 VIKNJXKGJWUCNN-XGXHKTLJSA-N 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
- B60W40/09—Driving style or behaviour
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
-
- 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
- G06V20/58—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; 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
- G06V20/58—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; 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
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
-
- 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
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/59—Context or environment of the image inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
- G06V20/597—Recognising the driver's state or behaviour, e.g. attention or drowsiness
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0001—Details of the control system
- B60W2050/0043—Signal treatments, identification of variables or parameters, parameter estimation or state estimation
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2555/00—Input parameters relating to exterior conditions, not covered by groups B60W2552/00, B60W2554/00
- B60W2555/60—Traffic rules, e.g. speed limits or right of way
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Human Computer Interaction (AREA)
- Mathematical Physics (AREA)
- Traffic Control Systems (AREA)
Abstract
Realized the invention provides a kind of based on many sensing datas to road traffic scene and the restoring method of driver driving behavior, by many sensing datas, many retrieving algorithm fusions realize the precise restoration of road traffic scene and driver driving behavior, specifically include：Multi-source data, which is mutually corrected, realizes vehicle driving trace precise restoration；The accurate measurement to barrier speed and distance is realized based on monocular vision and millimetre-wave radar；Multisource data fusion is generated<Road traffic scene, driving behavior>Data pair.Instant invention overcomes existing reduction technique data source is single, more relies on expensive device and obtain quality data, and the relatively low defect of reduction precision.
Description
Technical field
It is more particularly to a kind of to be realized based on many sensing datas to road the invention belongs to intelligent transportation and field of image recognition
Traffic scene and the restoring method of driver driving behavior.
Background technology
Automobile to realize really it is unmanned, it allows for perceiving and recognize the object of surrounding, and it is to be understood that oneself
Oneself accurate location.These two aspects is all the core of unmanned technology.A series of making for driving behaviors of driver, is in accordance with
The research of traffic environment residing at that time, either automatic Pilot algorithm, or assist driver drive, in vehicle traveling process
The environment around sensing, collects data at any time, carries out static state, the identification of dynamic object, detecting with following the trail of, and navigation instrument
Diagram data, carries out the computing and analysis of system, is all highly important.
At this stage in the unmanned research and development technology of main flow, laser radar perceptually equipment all have selected.Laser radar
Advantage is that its investigative range is wider, and detection accuracy is higher.But, the shortcoming of laser radar is it is also obvious that in poles such as sleet mists
Poor-performing under weather is held, the data volume of collection is very huge also sufficiently expensive.It is used as the indispensable core sensors of ADAS
Type, millimetre-wave radar technology relative maturity.But the shortcoming of millimetre-wave radar is also very directly perceived, and detection range is lost by frequency range
Direct restriction, can not also perceive pedestrian, and all barriers in periphery can not be modeled accurately.
Vision is the most important function means in the human cognitive world, and biological study shows, the mankind obtain external information
75% relies on vision system, and this ratio is even as high as 90% in driving environment, if it is possible to should by human visual system
Automatic Pilot field is used, the accuracy of automatic Pilot will be undoubtedly increased substantially.
For such case, in method proposed by the present invention, combine two kinds of data of monocular vision and radar and realize outside car
Scene is accurately perceived.The target detection scalability that monocular vision is realized using convolutional neural networks is higher, can not only pass through
Modification recall rate obtains more object detection results to avoid the problem of radar is to partial impairment thing None- identified, can also
By constantly training new model, different traffic scenes are adapted to, the barrier that can be recognized is continuously increased；By millimetre-wave radar
Precise information, it is possible to achieve the reverse correction to camera parameters in monocular vision, improves ranging and range rate arithmetic accuracy, while auxiliary
Help the target detection of monocular vision.Existing track of vehicle retrieving algorithm, its precision depends on high-quality data, for this
Situation, the present invention realizes the fusion of two and three dimensions retrieving algorithm, while built by monocular vision data and gps data
Kalman filter, realizes the correction of the result to data de-noising and reduction, and the precision of track reduction result is higher.
The automatic Pilot Decision Control system realized towards complex environment can be studied on the basis of the data pair that reduction is obtained
System depth learning technology, so that automated driving system gradually forms good driving habit by the self-study of data-driven, together
When can help improve driver driving custom, can also as research and development manufacturer's work out development strategy and relevant department's policy making and
The important reference foundation implemented.
The content of the invention
The subject matter that the present invention is solved is all kinds of sensing equipments by being laid on vehicle, and collection storage vehicle is in reality
Various driving contextual datas during the road driving of border, using the big data knowledge such as statistical analysis, data mining, from data dimension
The multi-angle such as degree, vehicle dimension, time dimension, region dimension, analyses in depth, compares user's driving behavior, find driving behavior
General character and individual character.Understood using the image scene based on deep learning, further data are labeled by radar data, also
The outer traffic scene of former car, is ultimately formed<Traffic scene, driving behavior>Data pair.Overcome existing reduction technique data source list
One, more rely on expensive device and obtain quality data, and the relatively low defect of reduction precision is based on many sensing datas there is provided one kind
Realize to road traffic scene and the restoring method of driver driving behavior.
The technology of the present invention solution：One kind is realized to road traffic scene and driver driving behavior based on many sensing datas
Restoring method, by many sensing datas, the fusion of many retrieving algorithms realizes the essence of road traffic scene and driver driving behavior
Really reduction, is specifically included：Multi-source data, which is mutually corrected, realizes vehicle driving trace precise restoration；Based on monocular vision and millimeter wave
Radar realizes the accurate measurement to barrier speed and distance；Multisource data fusion is generated<Road traffic scene, driving behavior>
Data pair.
It is implemented as follows：
(1) based on gyroscope, accelerometer, gps data, monocular cam data are as auxiliary, by two peacekeepings three
Dimension retrieving algorithm is combined, and carries out the mutual correction between gps data and gyroscope accelerometer data, accomplishes that vehicle travels rail
The precise restoration of mark, obtains the driving trace of vehicle；
(2) on the basis of CAN data and OBD data, concrete operations of the reduction driver under various scenes, including
Play lamp, steering wheel control, throttle and brake control；
(3) by monocular cam and radar, using convolutional neural networks, the target for completing to participate in traffic outside car thing is examined
Survey, obtain the species of vehicle-surroundings barrier；
(4) by monocular cam data, using method of geometry relation, the bigness scale amount to obstacle distance is realized, by milli
Metre wave radar data, obtain the accurate distance of barrier and this car, and herein on the basis of distance reversely to camera parameters
Demarcation, at the same by the parallel relation of lane line also can the calibrating camera angle of pitch, two kinds of calibration results are mutually authenticated, and obtain standard
The true video camera angle of pitch, for the measurement of other obstacle distances, finally give vehicle-surroundings barrier and this car it is accurate away from
From；
(5) measurement to barrier speed in the unidirectional track of vehicle front is realized based on monocular cam data, with
Based on millimetre-wave radar, the tachometric survey of thing is participated in the traffic outside the unidirectional track in front, vehicle-surroundings barrier is obtained
With the relative velocity of this car；
(6) vehicle driving trace for obtaining step (1), driver's concrete operations behavior that step (2) is obtained, step (3)
The species of obtained barrier, the distance of the barrier that step (4) is obtained and this car, the barrier that step (5) is obtained and this car
Relative velocity carry out the fusions of many reduction results, generation<Traffic scene, driving behavior>Data pair, the traffic scene refers to：
The various traffic of vehicle-surroundings participate in the species of thing, including pedestrian, vehicle, the people of cycling, traffic sign；Traffic participates in thing
State, includes the distance and relative velocity of moving object, the topology information of road, traffic sign；The driving behavior refers to driver
Concrete operations in the car, including beat lamp, steering wheel control, throttle and brake control and vehicle driving trace.
The step (1) implements down：
(11) on three dimension scale, parsing vehicle axis system parses vehicle with respect to the position relation between reference frame
Coordinate system uses Quaternion Method with respect to the position relation between reference frame, and Quaternion Method is mutually tied with Kalman filter algorithm
Close, improve SINS attitude algorithm accuracy and real-time；
(12) Kalman filter built by monocular vision data and gps data, is realized to data de-noising and reduction
Result correction, obtain more accurate vehicle driving trace.
The step (2) implements down：
The various running informations that can be got based on CAN and OBD interfaces, including speed, oil consumption, steering wheel, turn
To lamp, throttle, brake pedal, these data are uploaded onto the server by terminal, and the big data using statistical analysis, data mining is known
Know, how reduction driver controls vehicle by the operation to steering wheel, brake pedal, gas pedal, steering indicating light, other light
Each concrete operations was marked the upper correspondence time by traveling, convenient with subsequently being merged with other data.
The step (3) implements down：
(31) by Faster-RCNN convolutional neural networks, four steps of target detection, i.e. candidate region are generated,
Feature extraction, classification and Bounding Box are returned, within unification to a depth network frame, and realization is joined to traffic in the visual field
With the target detection of thing, marked with correspondence rectangle frame, and obtain confidence level；
(32) millimetre-wave radar identification obtains vehicle-surroundings barrier, and records the correspondence time.
The step (4) implements down：
(41) according to video camera projection model, obtained by geometry derivation between road surface coordinate system and image coordinate system
Relation, it is the plane domain in trapezoid area, corresponding flat coordinate system that video camera, which shoots obtained road plane, road surface coordinate system with
Point between plane coordinate system is corresponded；
(42) plane of delineation coordinate on barrier rectangle frame base is asked for respectively and the image at plane of delineation base midpoint is put down
Areal coordinate, and road surface plane coordinates is derived as by geometrical relationship；
(43) the two road surface coordinates obtained in step (42) are applied mechanically into 2 range formulas, obtain between 2 points away from
From；
(44) the accurate measurement to a certain obstacle distance is realized using millimetre-wave radar, it is anti-by geometrical relationship derivation
To solution, camera parameters are re-started with demarcation, camera parameters refer to the video camera angle of pitch, try to achieve accurate video camera and bow
The elevation angle；
(45) simultaneously, traffic lane line in the plane of delineation is obtained using machine vision algorithm, recycles at 2 points and determines one
The method of bar straight line, determines the straight line corresponding to traffic lane line on road plane in image, by the relation of two straight line parallels
Solve the video camera angle of pitch；
(46) camera parameters for obtaining step (44), (45) are mutually authenticated, and Real-time solution obtains accurately video camera
The angle of pitch, in the measurement of other obstacle distances, obtaining the accurate distance of barrier and this car.
The step (5) implements down：
(51) side for using claim 1 step (4) not, obtains front vehicles in nth frame image and N+K two field pictures
When, with two of this car apart from S1, S2；
(52) according to this car speed, the time difference T between nth frame image and N+K two field pictures calculates this car traveling
Apart from S3；
(53) front truck operating range S=S2+S3-S1 is calculated；
(54) vehicle velocity V=S/T is calculated；Thing is participated in for the traffic not before vehicle into track, the measurement of speed is relied on
Millimetre-wave radar, finally gives the relative velocity of vehicle-surroundings barrier and this car.
The step (6) implements down：
(61) by obtained vehicle driving trace, driver's concrete operations behavior, the species of periphery barrier, barrier with
The distance of this car, the relative velocity of barrier and this car carries out time mark respectively；
(62) by above-mentioned reduction result, it is attached using the time as unique major key, the time, identical data fusion was one
Rise, formed<Traffic scene, driving behavior>Data pair.
The advantage of the present invention compared with prior art is：
Traffic scene restoring method proposed by the present invention based on many sensing datas, can be ultimately formed<Traffic scene, drives
Sail behavior>Data pair, and reduction precision it is higher.
In track of vehicle reduction, the fusion of two and three dimensions retrieving algorithm is realized, while by monocular vision data
The Kalman filter built with gps data, realizes the correction of the result to data de-noising and reduction, the essence of track reduction result
Du Genggao.In the measurement of target detection and obstacle distance speed, while monocular vision and millimetre-wave radar are make use of, a side
Face, the target detection scalability that monocular vision is realized using convolutional neural networks is higher, not only can be by changing recall rate
More object detection results are obtained to avoid the problem of radar is to partial impairment thing None- identified, can also be by constantly instructing
Practice new model, adapt to different traffic scenes, be continuously increased the barrier that can be recognized；On the other hand, by millimetre-wave radar
Precise information, it is possible to achieve the reverse correction to camera parameters in monocular vision, improves ranging and range rate arithmetic accuracy.
Meanwhile, the automatic Pilot decision-making control realized towards complex environment can be studied on the basis of the data pair that reduction is obtained
System depth learning art processed, is practised so that automated driving system gradually forms good driving by the self-study of data-driven
Used, generation meets the dynamic response and ability of making decisions on one's own of Chinese transportation feature and driving habit, lifts the safety of automatic Pilot
Property and validity；Driver driving custom can be helped improve；Research and development manufacturer's work out development strategy and relevant department can also be used as
Policy making and the important reference foundation implemented.
Brief description of the drawings
Fig. 1 is the schematic diagram of the inventive method；
Fig. 2 is the track reduction flow chart in the present invention；
Fig. 3 is video camera projection model in the present invention, wherein upper figure is projection relation, figure below is projection plane.
Embodiment
As shown in figure 1, in driving procedure, making for driver's sequence of operations, is the traffic conditions according to periphery at that time,
As periphery main traffic participates in the motion state of thing, traffic sign, traffic lights, weather condition, road conditions etc..The present invention
Function essentially consist in：Based on CAN, OBD, gyroscope, accelerometer, GPS/BD, millimetre-wave radar and monocular cam
Deng multi-sensor data, the reduction to the reduction of road traffic scene and driver driving behavior outside car is realized, is formed<Traffic
Scape, driving behavior>Data pair.Traffic scene mainly includes：The various traffic of vehicle-surroundings participate in the species of things, such as pedestrian, vehicle,
The people of cycling, traffic sign；Traffic participates in the state of thing, the distance and relative velocity of such as moving object, the topology of road
Information, traffic sign.Driver driving behavior mainly includes：The concrete operations of driver in the car, such as play lamp, steering wheel control, oil
Door and brake control, and vehicle driving trace.
1. vehicle driving trace is reduced
(1) on three dimension scale, parsing vehicle axis system is with respect to the position relation between reference frame.At present, SINS
Described in carrier movement coordinate system mainly have Euler's horn cupping, direction cosines with respect to the method for position relation between reference frame
Method, trigonometric function method, Rodrigues parametric methods, Quaternion Method and equivalent rotating vector method, are focused on Quaternion Method
Face, and Quaternion Method is combined with Kalman filter algorithm, improve SINS attitude algorithm accuracy and real-time；
(2) Kalman filter built by monocular vision data and gps data, is realized to data de-noising and reduction
As a result correction, obtains more accurate vehicle driving trace.
2. based on CAN and OBD data analysis driver driving behaviors
The various running informations that can be got based on CAN and OBD interfaces, such as speed, oil consumption, steering wheel, steering
Lamp, throttle, brake pedal etc., these data can be uploaded onto the server by terminal, utilize the number greatly such as statistical analysis, data mining
It is reported that knowing, how reduction driver is controlled by the operation to steering wheel, brake pedal, gas pedal, steering indicating light, other light etc.
Vehicle traveling processed.Each concrete operations was marked into the upper correspondence time, it is convenient with subsequently being merged with other data.
3. the accurate measurement adjusted the distance is realized based on monocular camera machine vision and millimetre-wave radar
(1) by Faster-RCNN convolutional neural networks, four steps of target detection, (candidate region is generated, feature
Extract, classification and Bounding Box are returned) it is unified within a depth network frame, realize and thing is participated in traffic in the visual field
Target detection, with correspondence rectangle frame mark；
(2) according to video camera projection model, obtained by geometry derivation between road surface coordinate system and image coordinate system
Relation.As shown in Figure 3.In the upper figures of Fig. 3, plane ABU represents road plane, and ABCD is the ladder in the road plane that video camera is photographed
Shape region, O points are camera lens central point, and OG is camera optical axis, and G points are camera optical axis and the intersection point of road plane, I points
For the upright projection in the plane of O Dian roads.In the coordinate system of road surface, G points are defined as the origin of coordinates, vehicle forward direction definition
For Y direction.Corresponding points of the GABCD each points in the plane of delineation are as shown in Fig. 3 figure below, and abcd is four ends of image plane rectangle
Point, H and W are respectively the height and width of image plane.The midpoint g for defining image rectangle is the origin of coordinates of photo coordinate system, y-axis generation
Table vehicle forward direction；
(3) plane of delineation coordinate on barrier rectangle frame base and the plane of delineation at plane of delineation base midpoint are asked for respectively
Coordinate, and road surface plane coordinates is derived as by geometrical relationship；
(4) the two road surface coordinates obtained in (3) are applied mechanically into 2 range formulas, obtains at the distance between 2 points；
(5) the accurate measurement to a certain obstacle distance is realized using millimetre-wave radar, it is anti-by geometrical relationship derivation
To solution, camera parameters are re-started with demarcation, camera parameters refer to the video camera angle of pitch, try to achieve accurate video camera and bow
The elevation angle；
(6) simultaneously, in real road environment, because markings are parallel lines, therefore can be first with machine vision algorithm
To obtain traffic lane line in the plane of delineation, 2 points of methods for determining straight line are recycled, traffic lane line in image is determined
Straight line on corresponding road plane, the video camera angle of pitch is solved by the relation of two straight line parallels, and is not using just always
The video camera angle of pitch that beginningization markers is set；
(7) camera parameters for obtaining step (5), (6) are mutually authenticated, and Real-time solution obtains accurately video camera pitching
Angle, in the measurement of other obstacle distances, obtaining the accurate distance of barrier and this car.
4. the accurate measurement to speed is realized based on monocular camera machine vision and millimetre-wave radar
By shooting forward object of which movement image sequence, then to these image sequences are using image procossing and regard
Feel that e measurement technology is analyzed, calculate measurement and obtain real-time displacement of the objects in front between two field pictures, and then calculating is obtained
Object real time kinematics speed.
(1) by the distance-finding method in step 3, front vehicles are obtained in nth frame image and N+K two field pictures, with this
Two of car are apart from S1, S2；
(2) according to this car speed, the time difference T between nth frame image and N+K two field pictures calculates this car traveling
Apart from S3；
(3) front truck operating range S=S2+S3-S1 is calculated；
(4) vehicle velocity V=S/T is calculated.
(5) by millimetre-wave radar, correct velocity value is obtained, for correcting the time in monocular vision tachometric survey algorithm
Deviation and range deviation, while realizing the measurement for the speed that thing is participated in the traffic not before vehicle into track, finally give
The relative velocity of vehicle-surroundings barrier and this car.
5. data fusion, generation<Traffic scene, driving behavior data>Data pair.
(1) by obtained vehicle driving trace, driver's concrete operations behavior, the species of periphery barrier, barrier with
The distance of this car, the relative velocity of barrier and this car carries out time mark respectively；
(2) by above-mentioned reduction result, it is attached using the time as unique major key, the time, identical data fusion was one
Rise, formed<Traffic scene, driving behavior>Data pair.
Above example is provided just for the sake of the description purpose of the present invention, and is not intended to limit the scope of the present invention.This
The scope of invention is defined by the following claims.The various equivalent substitutions that do not depart from spirit and principles of the present invention and make and repair
Change, all should cover within the scope of the present invention.
Claims (7)
1. a kind of realize that to road traffic scene and the restoring method of driver driving behavior its feature exists based on many sensing datas
In：Comprise the following steps：
(1) based on gyroscope, accelerometer, gps data, monocular cam data are as auxiliary, by two and three dimensions also
Former algorithm is combined, and is carried out the mutual correction between gps data and gyroscope accelerometer data, is accomplished vehicle driving trace
Precise restoration, obtains the driving trace of vehicle；
(2) on the basis of CAN data and OBD data, concrete operations of the reduction driver under various scenes, including beat
Lamp, steering wheel control, throttle and brake control；
(3) by monocular cam and radar, using convolutional neural networks, complete to participate in traffic outside car the target detection of thing,
Obtain the species of vehicle-surroundings barrier；
(4) by monocular cam data, using method of geometry relation, the bigness scale amount to obstacle distance is realized, by millimeter wave
Radar data, obtains the accurate distance of barrier and this car, and the demarcation on the basis of distance reversely to camera parameters herein,
Simultaneously by the parallel relation of lane line also can the calibrating camera angle of pitch, two kinds of calibration results are mutually authenticated, and obtain accurately
The video camera angle of pitch, for the measurement of other obstacle distances, finally gives the accurate distance of vehicle-surroundings barrier and this car；
(5) measurement to barrier speed in the unidirectional track of vehicle front is realized based on monocular cam data, with millimeter
Based on ripple radar, the tachometric survey of thing is participated in the traffic outside the unidirectional track in front, vehicle-surroundings barrier and this is obtained
The relative velocity of car；
(6) vehicle driving trace for obtaining step (1), driver's concrete operations behavior that step (2) is obtained, step (3) is obtained
Barrier species, the distance of barrier that step (4) is obtained and this car, the phase of barrier and this car that step (5) is obtained
The fusion of many reduction results, generation are carried out to speed<Traffic scene, driving behavior>Data pair, the traffic scene refers to：Vehicle
The various traffic in periphery participate in the species of thing, including pedestrian, vehicle, the people of cycling, traffic sign；Traffic participates in the shape of thing
State, includes the distance and relative velocity of moving object, the topology information of road, traffic sign；The driving behavior refers to driver and existed
In-car concrete operations, including beat lamp, steering wheel control, throttle and brake control and vehicle driving trace.
A kind of realized 2. according to claim 1 based on many sensing datas to road traffic scene and driver driving behavior
Restoring method, it is characterised in that：The step (1) implements down：
(11) on three dimension scale, parsing vehicle axis system parses vehicle coordinate with respect to the position relation between reference frame
Position relation between the relative reference frame of system uses Quaternion Method, and Quaternion Method is combined with Kalman filter algorithm,
Improve SINS attitude algorithm accuracy and real-time；
(12) Kalman filter built by monocular vision data and gps data, realizes the knot to data de-noising and reduction
The correction of fruit, obtains more accurate vehicle driving trace.
A kind of realized 3. according to claim 1 based on many sensing datas to road traffic scene and driver driving behavior
Restoring method, it is characterised in that：The step (2) implements down：
The various running informations that can be got based on CAN and OBD interfaces, including speed, oil consumption, steering wheel, steering indicating light,
Throttle, brake pedal, these data are uploaded onto the server by terminal, using the big data knowledge of statistical analysis, data mining, also
How former driver controls vehicle to travel by the operation to steering wheel, brake pedal, gas pedal, steering indicating light, other light,
Each concrete operations was marked into the upper correspondence time, it is convenient with subsequently being merged with other data.
A kind of realized 4. according to claim 1 based on many sensing datas to road traffic scene and driver driving behavior
Restoring method, it is characterised in that：The step (3) implements down：
(31) by Faster-RCNN convolutional neural networks, four steps of target detection, i.e. candidate region are generated, feature
Extract, classification and Bounding Box are returned, within unification to a depth network frame, are realized and are participated in thing to traffic in the visual field
Target detection, marked with correspondence rectangle frame, and obtain confidence level；
(32) millimetre-wave radar identification obtains vehicle-surroundings barrier, and records the correspondence time.
A kind of realized 5. according to claim 1 based on many sensing datas to road traffic scene and driver driving behavior
Restoring method, it is characterised in that：The step (4) implements down：
(41) according to video camera projection model, the pass between road surface coordinate system and image coordinate system is obtained by geometry derivation
System, it is the plane domain in trapezoid area, corresponding flat coordinate system that video camera, which shoots obtained road plane, and road surface coordinate system is with putting down
Point between areal coordinate system is corresponded；
(42) plane of delineation coordinate on barrier rectangle frame base is asked for respectively and the plane of delineation at plane of delineation base midpoint is sat
Mark, and road surface plane coordinates is derived as by geometrical relationship；
(43) the two road surface coordinates obtained in step (42) are applied mechanically into 2 range formulas, obtains at the distance between 2 points；
(44) the accurate measurement to a certain obstacle distance is realized using millimetre-wave radar, is reversely asked by geometrical relationship derivation
Camera parameters are re-started demarcation, camera parameters refer to the video camera angle of pitch, try to achieve accurate video camera pitching by solution
Angle；
(45) simultaneously, traffic lane line in the plane of delineation is obtained using machine vision algorithm, recycles determine one directly at 2 points
The method of line, determines the straight line corresponding to traffic lane line on road plane in image, is solved by the relation of two straight line parallels
The video camera angle of pitch；
(46) camera parameters for obtaining step (44), (45) are mutually authenticated, and Real-time solution obtains accurately video camera pitching
Angle, in the measurement of other obstacle distances, obtaining the accurate distance of barrier and this car.
A kind of realized 6. according to claim 1 based on many sensing datas to road traffic scene and driver driving behavior
Restoring method, it is characterised in that：The step (5) implements down：
(51) side for using claim 1 step (4) not, obtains front vehicles in nth frame image and N+K two field pictures, with
Two of this car are apart from S1, S2；
(52) according to this car speed, the time difference T between nth frame image and N+K two field pictures calculates the distance of this car traveling
S3；
(53) front truck operating range S=S2+S3-S1 is calculated；
(54) vehicle velocity V=S/T is calculated；Thing is participated in for the traffic not before vehicle into track, the measurement of speed relies on millimeter
Ripple radar, finally gives the relative velocity of vehicle-surroundings barrier and this car.
A kind of realized 7. according to claim 1 based on many sensing datas to road traffic scene and driver driving behavior
Restoring method, it is characterised in that：The step (6) implements down：
(61) by obtained vehicle driving trace, driver's concrete operations behavior, the species of periphery barrier, barrier with this car
Distance, the relative velocity of barrier and this car carries out time mark respectively；
(62) by above-mentioned reduction result, be attached using the time as unique major key, time identical data fusion together, shape
Into<Traffic scene, driving behavior>Data pair.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710401034.5A CN107235044B (en) | 2017-05-31 | 2017-05-31 | A kind of restoring method realized based on more sensing datas to road traffic scene and driver driving behavior |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710401034.5A CN107235044B (en) | 2017-05-31 | 2017-05-31 | A kind of restoring method realized based on more sensing datas to road traffic scene and driver driving behavior |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107235044A true CN107235044A (en) | 2017-10-10 |
| CN107235044B CN107235044B (en) | 2019-05-28 |
Family
ID=59984711
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710401034.5A Active CN107235044B (en) | 2017-05-31 | 2017-05-31 | A kind of restoring method realized based on more sensing datas to road traffic scene and driver driving behavior |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107235044B (en) |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107499262A (en) * | 2017-10-17 | 2017-12-22 | 芜湖伯特利汽车安全系统股份有限公司 | ACC/AEB systems and vehicle based on machine learning |
| CN108196535A (en) * | 2017-12-12 | 2018-06-22 | 清华大学苏州汽车研究院（吴江） | Automated driving system based on enhancing study and Multi-sensor Fusion |
| CN108227707A (en) * | 2017-12-25 | 2018-06-29 | 清华大学苏州汽车研究院（吴江） | Automatic Pilot method based on laser radar and end-to-end deep learning method |
| CN108596081A (en) * | 2018-04-23 | 2018-09-28 | 吉林大学 | A kind of traffic detection method merged based on radar and video camera |
| CN108960183A (en) * | 2018-07-19 | 2018-12-07 | 北京航空航天大学 | A kind of bend target identification system and method based on Multi-sensor Fusion |
| CN108983219A (en) * | 2018-08-17 | 2018-12-11 | 北京航空航天大学 | A kind of image information of traffic scene and the fusion method and system of radar information |
| CN109002800A (en) * | 2018-07-20 | 2018-12-14 | 苏州索亚机器人技术有限公司 | The real-time identification mechanism of objective and recognition methods based on Multi-sensor Fusion |
| CN109061706A (en) * | 2018-07-17 | 2018-12-21 | 江苏新通达电子科技股份有限公司 | A method of the vehicle drive behavioural analysis based on T-Box and real-time road map datum |
| CN109263649A (en) * | 2018-08-21 | 2019-01-25 | 北京汽车股份有限公司 | Object identification method and object identification system under vehicle and its automatic driving mode |
| CN109606374A (en) * | 2018-12-28 | 2019-04-12 | 北汽福田汽车股份有限公司 | The method and apparatus of vehicle, fuel consumption data for verifying electronic horizon |
| CN109720312A (en) * | 2017-10-30 | 2019-05-07 | 现代摩比斯株式会社 | Autonomous emergency braking apparatus and its control method |
| CN109974687A (en) * | 2017-12-28 | 2019-07-05 | 周秦娜 | Co-located method, apparatus and system in a kind of multisensor room based on depth camera |
| CN110068818A (en) * | 2019-05-05 | 2019-07-30 | 中国汽车工程研究院股份有限公司 | The working method of traffic intersection vehicle and pedestrian detection is carried out by radar and image capture device |
| CN110309741A (en) * | 2019-06-19 | 2019-10-08 | 百度在线网络技术（北京）有限公司 | Obstacle detection method and device |
| CN110751836A (en) * | 2019-09-26 | 2020-02-04 | 武汉光庭信息技术股份有限公司 | Vehicle driving early warning method and system |
| CN110853393A (en) * | 2019-11-26 | 2020-02-28 | 清华大学 | Intelligent network vehicle test field data acquisition and fusion method and system |
| CN110901638A (en) * | 2018-08-28 | 2020-03-24 | 大陆泰密克汽车系统（上海）有限公司 | Driving assistance method and system |
| CN111267863A (en) * | 2018-12-04 | 2020-06-12 | 广州汽车集团股份有限公司 | Driver driving type identification method and device, storage medium and terminal equipment |
| CN111564051A (en) * | 2020-04-28 | 2020-08-21 | 安徽江淮汽车集团股份有限公司 | Safe driving control method, device and equipment for automatic driving automobile and storage medium |
| CN111681422A (en) * | 2020-06-16 | 2020-09-18 | 衢州量智科技有限公司 | Management method and system for tunnel road |
| CN111879314A (en) * | 2020-08-10 | 2020-11-03 | 中国铁建重工集团股份有限公司 | Multi-sensor fusion roadway driving equipment real-time positioning system and method |
| CN112298196A (en) * | 2019-07-26 | 2021-02-02 | 丰田自动车株式会社 | Annunciator information management system |
| WO2021036083A1 (en) * | 2019-08-26 | 2021-03-04 | 格物汽车科技(苏州)有限公司 | Driver behavior model development method and device for automatic driving, and storage medium |
| CN113379945A (en) * | 2021-07-26 | 2021-09-10 | 陕西天行健车联网信息技术有限公司 | Vehicle driving behavior analysis device, method and system |
| CN113494938A (en) * | 2020-04-02 | 2021-10-12 | 三菱电机株式会社 | Object recognition device and object recognition method |
| CN113642548A (en) * | 2021-10-18 | 2021-11-12 | 氢山科技有限公司 | Abnormal driving behavior detection device and device for hydrogen energy transport vehicle and computer equipment |
| CN113947893A (en) * | 2021-09-03 | 2022-01-18 | 网络通信与安全紫金山实验室 | Method and system for restoring driving scene of automatic driving vehicle |
| EP3927588A4 (en) * | 2019-02-21 | 2022-11-09 | Zoox, Inc. | Motion prediction based on appearance |
| CN116204791A (en) * | 2023-04-25 | 2023-06-02 | 山东港口渤海湾港集团有限公司 | Construction and management method and system for vehicle behavior prediction scene data set |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010014090A (en) * | 2008-07-07 | 2010-01-21 | Toyota Motor Corp | Control device for vehicle |
| CN101908272A (en) * | 2010-07-20 | 2010-12-08 | 南京理工大学 | Traffic safety sensing network based on mobile information |
| US20150019088A1 (en) * | 2013-07-10 | 2015-01-15 | Kia Motors Corporation | Apparatus and method of processing road data |
| KR20170028631A (en) * | 2015-09-04 | 2017-03-14 | (주) 이즈테크놀로지 | Method and Apparatus for Detecting Carelessness of Driver Using Restoration of Front Face Image |
-
2017
- 2017-05-31 CN CN201710401034.5A patent/CN107235044B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010014090A (en) * | 2008-07-07 | 2010-01-21 | Toyota Motor Corp | Control device for vehicle |
| CN101908272A (en) * | 2010-07-20 | 2010-12-08 | 南京理工大学 | Traffic safety sensing network based on mobile information |
| US20150019088A1 (en) * | 2013-07-10 | 2015-01-15 | Kia Motors Corporation | Apparatus and method of processing road data |
| KR20170028631A (en) * | 2015-09-04 | 2017-03-14 | (주) 이즈테크놀로지 | Method and Apparatus for Detecting Carelessness of Driver Using Restoration of Front Face Image |
Non-Patent Citations (1)
| Title |
|---|
| 张文娜 李军: "基于潜变量的驾驶员路径选择行为分析", 《科学技术与工程》 * |
Cited By (43)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107499262A (en) * | 2017-10-17 | 2017-12-22 | 芜湖伯特利汽车安全系统股份有限公司 | ACC/AEB systems and vehicle based on machine learning |
| CN109720312B (en) * | 2017-10-30 | 2021-08-10 | 现代摩比斯株式会社 | Autonomous emergency brake device and control method thereof |
| CN109720312A (en) * | 2017-10-30 | 2019-05-07 | 现代摩比斯株式会社 | Autonomous emergency braking apparatus and its control method |
| CN108196535A (en) * | 2017-12-12 | 2018-06-22 | 清华大学苏州汽车研究院（吴江） | Automated driving system based on enhancing study and Multi-sensor Fusion |
| CN108227707A (en) * | 2017-12-25 | 2018-06-29 | 清华大学苏州汽车研究院（吴江） | Automatic Pilot method based on laser radar and end-to-end deep learning method |
| CN108227707B (en) * | 2017-12-25 | 2021-11-26 | 清华大学苏州汽车研究院（吴江） | Automatic driving method based on laser radar and end-to-end deep learning method |
| CN109974687A (en) * | 2017-12-28 | 2019-07-05 | 周秦娜 | Co-located method, apparatus and system in a kind of multisensor room based on depth camera |
| CN108596081A (en) * | 2018-04-23 | 2018-09-28 | 吉林大学 | A kind of traffic detection method merged based on radar and video camera |
| CN108596081B (en) * | 2018-04-23 | 2021-04-20 | 吉林大学 | Vehicle and pedestrian detection method based on integration of radar and camera |
| CN109061706A (en) * | 2018-07-17 | 2018-12-21 | 江苏新通达电子科技股份有限公司 | A method of the vehicle drive behavioural analysis based on T-Box and real-time road map datum |
| CN108960183A (en) * | 2018-07-19 | 2018-12-07 | 北京航空航天大学 | A kind of bend target identification system and method based on Multi-sensor Fusion |
| CN108960183B (en) * | 2018-07-19 | 2020-06-02 | 北京航空航天大学 | Curve target identification system and method based on multi-sensor fusion |
| CN109002800A (en) * | 2018-07-20 | 2018-12-14 | 苏州索亚机器人技术有限公司 | The real-time identification mechanism of objective and recognition methods based on Multi-sensor Fusion |
| CN108983219A (en) * | 2018-08-17 | 2018-12-11 | 北京航空航天大学 | A kind of image information of traffic scene and the fusion method and system of radar information |
| CN109263649A (en) * | 2018-08-21 | 2019-01-25 | 北京汽车股份有限公司 | Object identification method and object identification system under vehicle and its automatic driving mode |
| CN110901638B (en) * | 2018-08-28 | 2021-05-28 | 大陆泰密克汽车系统（上海）有限公司 | Driving assistance method and system |
| CN110901638A (en) * | 2018-08-28 | 2020-03-24 | 大陆泰密克汽车系统（上海）有限公司 | Driving assistance method and system |
| CN111267863A (en) * | 2018-12-04 | 2020-06-12 | 广州汽车集团股份有限公司 | Driver driving type identification method and device, storage medium and terminal equipment |
| CN111267863B (en) * | 2018-12-04 | 2021-03-19 | 广州汽车集团股份有限公司 | Driver driving type identification method and device, storage medium and terminal equipment |
| CN109606374A (en) * | 2018-12-28 | 2019-04-12 | 北汽福田汽车股份有限公司 | The method and apparatus of vehicle, fuel consumption data for verifying electronic horizon |
| CN109606374B (en) * | 2018-12-28 | 2020-07-10 | 智博汽车科技(上海)有限公司 | Vehicle, method and device for verifying fuel consumption data of electronic horizon |
| EP3927588A4 (en) * | 2019-02-21 | 2022-11-09 | Zoox, Inc. | Motion prediction based on appearance |
| CN110068818A (en) * | 2019-05-05 | 2019-07-30 | 中国汽车工程研究院股份有限公司 | The working method of traffic intersection vehicle and pedestrian detection is carried out by radar and image capture device |
| CN110309741A (en) * | 2019-06-19 | 2019-10-08 | 百度在线网络技术（北京）有限公司 | Obstacle detection method and device |
| CN112298196A (en) * | 2019-07-26 | 2021-02-02 | 丰田自动车株式会社 | Annunciator information management system |
| CN112298196B (en) * | 2019-07-26 | 2024-05-28 | 丰田自动车株式会社 | Annunciator information management system |
| WO2021036083A1 (en) * | 2019-08-26 | 2021-03-04 | 格物汽车科技(苏州)有限公司 | Driver behavior model development method and device for automatic driving, and storage medium |
| CN110751836A (en) * | 2019-09-26 | 2020-02-04 | 武汉光庭信息技术股份有限公司 | Vehicle driving early warning method and system |
| CN110853393B (en) * | 2019-11-26 | 2020-12-11 | 清华大学 | Intelligent network vehicle test field data acquisition and fusion method and system |
| CN110853393A (en) * | 2019-11-26 | 2020-02-28 | 清华大学 | Intelligent network vehicle test field data acquisition and fusion method and system |
| CN113494938A (en) * | 2020-04-02 | 2021-10-12 | 三菱电机株式会社 | Object recognition device and object recognition method |
| CN113494938B (en) * | 2020-04-02 | 2024-05-17 | 三菱电机株式会社 | Object recognition device and object recognition method |
| CN111564051B (en) * | 2020-04-28 | 2021-07-20 | 安徽江淮汽车集团股份有限公司 | Safe driving control method, device and equipment for automatic driving automobile and storage medium |
| CN111564051A (en) * | 2020-04-28 | 2020-08-21 | 安徽江淮汽车集团股份有限公司 | Safe driving control method, device and equipment for automatic driving automobile and storage medium |
| CN111681422A (en) * | 2020-06-16 | 2020-09-18 | 衢州量智科技有限公司 | Management method and system for tunnel road |
| CN111879314A (en) * | 2020-08-10 | 2020-11-03 | 中国铁建重工集团股份有限公司 | Multi-sensor fusion roadway driving equipment real-time positioning system and method |
| CN111879314B (en) * | 2020-08-10 | 2022-08-02 | 中国铁建重工集团股份有限公司 | Multi-sensor fusion roadway driving equipment real-time positioning system and method |
| CN113379945A (en) * | 2021-07-26 | 2021-09-10 | 陕西天行健车联网信息技术有限公司 | Vehicle driving behavior analysis device, method and system |
| CN113947893A (en) * | 2021-09-03 | 2022-01-18 | 网络通信与安全紫金山实验室 | Method and system for restoring driving scene of automatic driving vehicle |
| CN113642548A (en) * | 2021-10-18 | 2021-11-12 | 氢山科技有限公司 | Abnormal driving behavior detection device and device for hydrogen energy transport vehicle and computer equipment |
| CN113642548B (en) * | 2021-10-18 | 2022-03-25 | 氢山科技有限公司 | Abnormal driving behavior detection device and device for hydrogen energy transport vehicle and computer equipment |
| CN116204791A (en) * | 2023-04-25 | 2023-06-02 | 山东港口渤海湾港集团有限公司 | Construction and management method and system for vehicle behavior prediction scene data set |
| CN116204791B (en) * | 2023-04-25 | 2023-08-11 | 山东港口渤海湾港集团有限公司 | Construction and management method and system for vehicle behavior prediction scene data set |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107235044B (en) | 2019-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107235044B (en) | A kind of restoring method realized based on more sensing datas to road traffic scene and driver driving behavior | |
| US8791996B2 (en) | Image processing system and position measurement system | |
| CN111448478B (en) | System and method for correcting high-definition maps based on obstacle detection | |
| EP2372308B1 (en) | Image processing system and vehicle control system | |
| CN105260699B (en) | A kind of processing method and processing device of lane line data | |
| KR102595897B1 (en) | Method and apparatus of determining road line | |
| JP5468108B2 (en) | Method and system for detecting road terrain for a driver assistance system | |
| US8428362B2 (en) | Scene matching reference data generation system and position measurement system | |
| US8369577B2 (en) | Vehicle position recognition system | |
| US8452103B2 (en) | Scene matching reference data generation system and position measurement system | |
| CN102208036B (en) | Vehicle position detection system | |
| CN110531376A (en) | Detection of obstacles and tracking for harbour automatic driving vehicle | |
| KR102091580B1 (en) | Method for collecting road signs information using MMS | |
| US20110242319A1 (en) | Image processing system and position measurement system | |
| CN109583415A (en) | A kind of traffic lights detection and recognition methods merged based on laser radar with video camera | |
| Shunsuke et al. | GNSS/INS/on-board camera integration for vehicle self-localization in urban canyon | |
| CN112861748B (en) | Traffic light detection system and method in automatic driving | |
| CN106446785A (en) | Passable road detection method based on binocular vision | |
| CN109583312A (en) | Lane detection method, apparatus, equipment and storage medium | |
| CN114808649B (en) | Highway scribing method based on vision system control | |
| WO2022230739A1 (en) | Object tracking device | |
| US20230314162A1 (en) | Map generation apparatus | |
| US20230314163A1 (en) | Map generation apparatus | |
| US20220307861A1 (en) | Map generation apparatus | |
| CN116802581A (en) | Automatic driving perception system testing method, system and storage medium based on aerial survey data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210824 Address after: 100191 045, 2f, commercial garage, No. 17, Zhichun Road, Haidian District, Beijing Patentee after: Chuangketianxia (Beijing) Technology Development Co.,Ltd. Address before: 100191 No. 37, Haidian District, Beijing, Xueyuan Road Patentee before: BEIHANG University |
|
| TR01 | Transfer of patent right | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20171010 Assignee: Beijing Zhimou Technology Development Co.,Ltd. Assignor: Chuangketianxia (Beijing) Technology Development Co.,Ltd. Contract record no.: X2023990000843 Denomination of invention: A Method for Restoring Road Traffic Scenarios and Driver Driving Behavior Based on Multi sensor Data Granted publication date: 20190528 License type: Exclusive License Record date: 20231008 |
|
| EE01 | Entry into force of recordation of patent licensing contract |