CN111413692B - Camera transverse position estimation self-calibration method based on roadside stationary object - Google Patents
Camera transverse position estimation self-calibration method based on roadside stationary object Download PDFInfo
- Publication number
- CN111413692B CN111413692B CN202010191503.7A CN202010191503A CN111413692B CN 111413692 B CN111413692 B CN 111413692B CN 202010191503 A CN202010191503 A CN 202010191503A CN 111413692 B CN111413692 B CN 111413692B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- distance
- transverse distance
- camera
- near target
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S11/00—Systems for determining distance or velocity not using reflection or reradiation
- G01S11/12—Systems for determining distance or velocity not using reflection or reradiation using electromagnetic waves other than radio waves
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
- G06T2207/30256—Lane; Road marking
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Electromagnetism (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to the technical field of automobile control, in particular to a lateral position estimation self-calibration method of a camera based on a roadside static object. The intelligent camera is used for identifying the static objects on the roadside, recording the observed transverse distance and the observed longitudinal distance of the static objects, the camera transmits data to a control system of the vehicle through communication connection, the control system calculates and obtains a compensation coefficient of the observed transverse distance and the actual transverse distance in the driving process of the vehicle, a lookup table of the compensation coefficient and the observed longitudinal distance is formed, when the vehicle meets a near target again, the control system obtains the compensation coefficient from the observed longitudinal distance of the near target to the vehicle through the lookup table, automatically compensates the observed transverse distance of the near target to obtain the actual transverse distance of the near target, and determines the transverse position of the near target. The method is extremely simple, can eliminate the distortion of the visual angle of the camera when observing the near target, and accurately obtains the transverse position of the near target.
Description
Technical Field
The invention relates to the technical field of automobile control, in particular to a lateral position estimation self-calibration method of a camera based on a roadside static object.
Background
The emergency braking function of the Advanced Driver Assistance System (ADAS) is extremely sensitive to the accuracy of the lateral position estimation of nearby objects. Generally, the distance estimation of the center of the visual field of the camera is more accurate, and the distance estimation has larger error due to larger distortion of the edge of the visual field. The nearby lane target is usually at the edge of the field of view, so the lateral distance estimation error is large. The phenomena of false alarm and missed alarm of an Advanced Driver Assistance System (ADAS) can be caused, and the driving experience of a user is greatly influenced.
Disclosure of Invention
The present invention is directed to solve the above mentioned technical problems in the background art, and provides a method for estimating and self-calibrating a lateral position of a camera based on a stationary object on a road.
The technical scheme of the invention is as follows: a lateral position estimation self-calibration method of a camera based on a roadside static object is characterized by comprising the following steps: the intelligent camera is used for identifying a static object on the roadside, recording the observation transverse distance and the observation longitudinal distance of the static object from a vehicle in the camera, transmitting data to a control system of the vehicle through communication connection by the camera, calculating and obtaining a compensation coefficient of the observation transverse distance and the actual transverse distance in the driving process of the vehicle by the control system, forming a lookup table of the compensation coefficient and the observation longitudinal distance, obtaining the compensation coefficient by the control system through the lookup table and the observation longitudinal distance of the near target from the vehicle when the vehicle meets the near target again, automatically compensating the observation transverse distance of the near target through the compensation coefficient to obtain the actual transverse distance of the near target, and determining the transverse position of the near target.
The method for identifying the roadside stationary object through the intelligent camera further comprises the following steps: the intelligent camera identifies street lamps or trees on the roadside as static objects.
The method for calculating and obtaining the compensation coefficient of the observed transverse distance and the actual transverse distance in the running process of the vehicle by the control system comprises the following steps: when the control system judges that the vehicle is in a straight-going state, according to the principle that the actual transverse distance between the static object and the vehicle is unchanged when the vehicle is in the straight-going state, the relation between the observed transverse distance between the static object and the vehicle in the intelligent camera and the actual transverse distance can be obtained, and therefore the compensation coefficient of the observed transverse distance and the actual transverse distance is obtained.
The method for judging that the vehicle is in the straight-going state by the control system comprises the following steps: the intelligent camera with the lane recognition function is used for judging whether the current driving lane of the vehicle is in a straight lane or not, and the control system is used for collecting the course angular speed in the driving movement process of the vehicle so as to judge whether the vehicle is in a straight-going state or not.
Further, the near target is a static target or a moving target.
Further, after the vehicle has obtained the lookup table of the compensation coefficient and the observation longitudinal distance, when the vehicle encounters the near target again, the vehicle may be in a straight-ahead state or a non-straight-ahead state at this time, and the actual transverse distance of the near target may be obtained through the lookup table and the observation longitudinal distance.
The invention has the advantages that: 1. according to the method, the transverse distance of the intelligent camera for observing the static target is calibrated in advance, namely, the relation between the observed transverse distance and the actual transverse distance is compensated, so that a lookup table between the longitudinal distance observed by the camera and a compensation coefficient is formed, and then the actual transverse position of the next near target can be obtained based on the lookup table, so that the problems of large estimation error of the transverse distance of the camera and distortion of visual angles at two sides of the camera are solved, the observation precision of a control system on the targets at two sides of a road in the automobile driving process is improved, the phenomena of false alarm and missed alarm of an advanced assisted driving system (ADAS) are avoided, and the driving experience of a user is greatly improved;
2. the street lamp or the tree on the roadside is identified as the static object through the intelligent camera, the identification mode is simple, the sample is sufficient, the identification precision is higher, and the subsequent data processing is convenient;
3. the compensation coefficient is determined based on that the transverse distance between a static object and the automobile is always constant in the process that the automobile is in a straight-going state, but the transverse distance observed can change along with the change of the longitudinal distance of the automobile because the static object moves from the middle position of the visual angle of the camera to the two side edges of the visual angle in the moving process of the camera, so that the change relation between the observed transverse distance and the actual transverse distance can be found out, and the compensation coefficient is obtained;
4. the method for judging whether the vehicle runs straight through two steps, namely judging whether the vehicle is in a straight lane through the intelligent camera, judging whether the vehicle is in a straight state through observing a running signal of the vehicle through the control system, and accurately judging the straight state of the vehicle through the two steps, is extremely simple and efficient, has a reasonable logical judgment mode, and has extremely accurate judgment result;
5. after the lookup table is obtained, the method does not need to consider whether the near target is in a static state or whether the vehicle is in a straight-going state for judging the transverse distance of the near target again, so that the use state can greatly improve the vehicle judgment mode range, can deal with various situations occurring in the actual driving process, and greatly expands the application scene of the method.
The method is very simple, can eliminate the distortion of the visual angle of the camera when observing the near target by obtaining the lookup table of the compensation coefficient and the longitudinal distance, accurately obtains the transverse position of the near target, avoids the phenomena of false alarm and missed alarm of an Advanced Driver Assistance System (ADAS), greatly improves the driving experience of a user, and has great popularization value and wide application scenes.
Drawings
FIG. 1: the invention discloses a vehicle running schematic diagram.
Detailed Description
The invention is described in further detail below with reference to the figures and the specific embodiments.
In this embodiment, the intelligent camera (the Mobileye Q3 forward camera) is calibrated first, and the compensation coefficient between the observed lateral distance and the actual lateral distance of the intelligent camera is obtained. The intelligent camera of the embodiment has a lane recognition function, the intelligent camera judges whether the vehicle is in a straight lane or not through the lane recognition function, when the vehicle is judged to be in the straight lane, the control system receives a running signal of the vehicle, such as a running signal which can judge whether the vehicle deflects or not, for example, the course angular velocity and the like, and when the control system receives the running signal and judges that the vehicle is in a straight state, calibration of the intelligent camera can be started at the moment, namely, a compensation coefficient of the observed transverse distance and the actual transverse distance of the camera is calculated.
When the vehicle is in a straight-ahead state, it can be determined that the lateral distance between the roadside stationary object and the vehicle is always kept unchanged, but because the stationary object moves from the center of the view angle of the intelligent camera to the edge positions at both sides of the view angle in the driving process of the vehicle, the stationary object is displayed on the data information of the intelligent camera, namely the observed lateral distance between the stationary object and the vehicle changes, and therefore the change relationship between the observed lateral distance and the actual lateral distance needs to be obtained, and the compensation coefficient between the observed lateral distance and the actual lateral distance is obtained. The static object of the embodiment is a target such as a street lamp and a tree which can be identified by the intelligent camera.
After obtaining the compensation coefficient between the observed lateral distance and the actual lateral distance, it can be found that the compensation coefficient actually has a certain relationship with the observed longitudinal distance between the vehicle and the stationary object. The camera has a precision area, when the longitudinal distance between the camera and the observation object is in the precision area, the error between the actual transverse distance of the camera and the observation transverse distance is minimum, namely the compensation coefficient is minimum at the moment, when the longitudinal distance between the camera and the observation object is far away from the precision area, the farther the distance from the precision area is, the larger the compensation coefficient is, and otherwise, the smaller the compensation coefficient is. Therefore, calibration is carried out through a large number of experiments, the ratio of the actual transverse distance to the observed transverse distance is used as a compensation coefficient, and a lookup table between the compensation coefficient of the intelligent camera and the observed longitudinal distance can be formed by obtaining the corresponding relation between the observed longitudinal distance and the compensation coefficient. The observed longitudinal distance of the present embodiment refers to the longitudinal distance of the vehicle from the stationary object observed by the camera, and the observed longitudinal distance is equal to the actual longitudinal distance when the vehicle is in a straight-ahead state.
After the lookup table between the compensation coefficient of the intelligent camera and the observation longitudinal distance is obtained, when the vehicle meets a near target again, whether the near target is in a static state or not and whether the vehicle is in a straight-going state or not at the moment, the intelligent camera obtains the observation longitudinal distance of the near target, based on the lookup table, the corresponding compensation coefficient can be obtained, then the actual transverse distance between the near target and the vehicle can be obtained through the observation transverse distance between the near target and the vehicle, which is obtained through the intelligent camera, and therefore the transverse position of the near target can be accurately judged.
Taking a vehicle of a certain model as an example, the vehicle is provided with an intelligent camera of a certain model, and the intelligent camera has a lane recognition function. When the vehicle runs for the first time, the intelligent camera is calibrated. As shown in fig. 1, when the vehicle runs in a straight lane and is in a straight state, the intelligent camera observes a street lamp on the front roadside, at this time, the actual lateral distance of the vehicle from the street lamp is 2.46m, and the observed lateral distance of the vehicle from the street lamp, which is acquired by the intelligent camera, is L1When the distance between the vehicle and the observation longitudinal distance of the street lamp A is 20m, the compensation coefficient of the intelligent camera to the actual transverse distance and the observation longitudinal distance of the vehicle is 1.02. The vehicle continues to run, the intelligent camera obtains that the longitudinal distance change of the vehicle from the street lamp A is 8m, and the transverse distance of the vehicle from the street lamp A obtained by the intelligent camera is L2Because the vehicle is in a straight-ahead state, the actual transverse distance between the vehicle and the street lamp a is also 2.46m, and the compensation coefficient of the intelligent camera to the actual transverse distance and the observed longitudinal distance of the vehicle is 1.29 at the moment. And sequentially recording the compensation coefficient and the observation longitudinal distance to form a lookup table, wherein the lookup table is as shown in the following table:
table 1: corresponding table of compensation coefficient and observation longitudinal distance of intelligent camera of certain vehicle
After the lookup table is obtained, when a red light runner appears on the roadside in front of the vehicle in the driving process of the vehicle, the intelligent camera observes that the observation longitudinal distance from the red light runner to the vehicle is 1.1m and the observation longitudinal distance from the red light runner to the vehicle is 12m, finds out that the corresponding compensation coefficient is 1.20 by consulting the lookup table, calculates the actual transverse distance from the red light runner to the vehicle at the moment to be 1.32m, feeds back the information to an advanced assistant driving system (ADAS), and judges whether to take emergency braking measures or not by the advanced assistant driving system (ADAS).
The longitudinal direction of the present embodiment refers to the direction in which the vehicle travels, i.e., the up-down direction in fig. 1, and the lateral direction refers to the direction perpendicular to the direction in which the vehicle travels, i.e., the left-right direction in fig. 1.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are given by way of illustration of the principles of the present invention, and that various changes and modifications may be made without departing from the spirit and scope of the invention as defined by the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (5)
1. A lateral position estimation self-calibration method of a camera based on a roadside static object is characterized by comprising the following steps: the method comprises the steps that a static object on the roadside is identified through an intelligent camera, the observation transverse distance and the observation longitudinal distance between the static object and a vehicle are recorded in the camera, the camera transmits data to a control system of the vehicle through communication connection, the control system calculates and obtains a compensation coefficient of the observation transverse distance and the actual transverse distance in the driving process of the vehicle, a lookup table of the compensation coefficient and the observation longitudinal distance is formed, when the vehicle meets a near target again, the control system obtains the compensation coefficient through the lookup table and the observation longitudinal distance between the near target and the vehicle, then the observation transverse distance of the near target is automatically compensated through the compensation coefficient, the actual transverse distance of the near target is obtained, and the transverse position of the near target is determined;
the method for calculating and obtaining the compensation coefficient of the observed transverse distance and the actual transverse distance in the running process of the vehicle by the control system comprises the following steps: when the control system judges that the vehicle is in a straight-going state, according to the principle that the actual transverse distance between the static object and the vehicle is unchanged when the vehicle is in the straight-going state, the relation between the observed transverse distance between the static object and the vehicle in the intelligent camera and the actual transverse distance can be obtained, and therefore the compensation coefficient of the observed transverse distance and the actual transverse distance is obtained.
2. The method for self-calibration of the lateral position estimation of the camera based on the roadside stationary object as claimed in claim 1, wherein: the method for identifying the roadside stationary object through the intelligent camera comprises the following steps: the intelligent camera identifies street lamps or trees on the roadside as static objects.
3. The method for self-calibration of the lateral position estimation of the camera based on the roadside stationary object as claimed in claim 1, wherein: the method for judging that the vehicle is in the straight-going state by the control system comprises the following steps: the intelligent camera with the lane recognition function is used for judging whether the current driving lane of the vehicle is in a straight lane or not, and the control system is used for collecting the course angular speed in the driving movement process of the vehicle so as to judge whether the vehicle is in a straight-going state or not.
4. The method for self-calibration of the lateral position estimation of the camera based on the roadside stationary object as claimed in claim 1, wherein: the near target is a static target or a moving target.
5. The method for self-calibration of the lateral position estimation of the camera based on the roadside stationary object as claimed in claim 1, wherein: when the vehicle encounters the near target again after the vehicle has obtained the lookup table of the compensation coefficient and the observation longitudinal distance, the vehicle can be in a straight-going state or a non-straight-going state at this time, and the actual transverse distance of the near target can be obtained through the lookup table and the observation longitudinal distance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010191503.7A CN111413692B (en) | 2020-03-18 | 2020-03-18 | Camera transverse position estimation self-calibration method based on roadside stationary object |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010191503.7A CN111413692B (en) | 2020-03-18 | 2020-03-18 | Camera transverse position estimation self-calibration method based on roadside stationary object |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111413692A CN111413692A (en) | 2020-07-14 |
| CN111413692B true CN111413692B (en) | 2022-03-18 |
Family
ID=71491186
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010191503.7A Active CN111413692B (en) | 2020-03-18 | 2020-03-18 | Camera transverse position estimation self-calibration method based on roadside stationary object |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111413692B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112130152B (en) * | 2020-09-16 | 2023-09-05 | 东风汽车集团有限公司 | Method for correcting transverse distance between automobile and target object |
| CN115980787B (en) * | 2023-03-16 | 2023-05-23 | 安徽科创中光科技股份有限公司 | Pollution monitoring and positioning method based on particulate radar |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2576216A1 (en) * | 1999-10-29 | 2001-05-17 | Safegate International Ab | Aircraft identification and docking guidance systems |
| EP1577682A1 (en) * | 2004-03-20 | 2005-09-21 | Robert Bosch Gmbh | Object locating system for vehicles to recognize lane change |
| CN101089917A (en) * | 2007-06-01 | 2007-12-19 | 清华大学 | A Fast Recognition Method for Target Vehicles in Lane Changing Conditions |
| CN103712573A (en) * | 2013-12-27 | 2014-04-09 | 华南师范大学 | Method for correcting space matching of area array imaging sensors in two-channel interferometry |
| CN107703528A (en) * | 2017-09-25 | 2018-02-16 | 武汉光庭科技有限公司 | Low precision GPS vision positioning method and system is combined in automatic Pilot |
| CN108627175A (en) * | 2017-03-20 | 2018-10-09 | 现代自动车株式会社 | The system and method for vehicle location for identification |
| CN109733390A (en) * | 2018-12-29 | 2019-05-10 | 江苏大学 | An adaptive lane change warning method based on driver characteristics |
| CN110320517A (en) * | 2019-05-31 | 2019-10-11 | 惠州市德赛西威汽车电子股份有限公司 | A kind of trailer-mounted radar recognition methods |
| CN110555407A (en) * | 2019-09-02 | 2019-12-10 | 东风汽车有限公司 | pavement vehicle space identification method and electronic equipment |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6154973A (en) * | 1998-03-27 | 2000-12-05 | Franz Plasser Bahnbaumaschinen-Industriegesellschaft M.B.H. | Method for correcting the track geometry of a track |
| US7573402B2 (en) * | 2005-08-25 | 2009-08-11 | Herbert William J | Dual laser beam guidance and parking device |
| CN104359408B (en) * | 2014-11-25 | 2017-03-22 | 麦特汽车服务股份有限公司 | Automotive chassis data measurement method based on two-dimension dip angle self-compensation |
| WO2018094647A1 (en) * | 2016-11-24 | 2018-05-31 | Baidu.Com Times Technology (Beijing) Co., Ltd. | Method and system for steering control of an autonomous vehicle using proportional, integral, and derivative (pid) controller |
| CN107389026B (en) * | 2017-06-12 | 2019-10-01 | 江苏大学 | A kind of monocular vision distance measuring method based on fixed point projective transformation |
| CN110706271B (en) * | 2019-09-30 | 2022-02-15 | 清华大学 | A vehicle vision real-time multi-vehicle target horizontal and vertical distance estimation method |
-
2020
- 2020-03-18 CN CN202010191503.7A patent/CN111413692B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2576216A1 (en) * | 1999-10-29 | 2001-05-17 | Safegate International Ab | Aircraft identification and docking guidance systems |
| EP1577682A1 (en) * | 2004-03-20 | 2005-09-21 | Robert Bosch Gmbh | Object locating system for vehicles to recognize lane change |
| CN101089917A (en) * | 2007-06-01 | 2007-12-19 | 清华大学 | A Fast Recognition Method for Target Vehicles in Lane Changing Conditions |
| CN103712573A (en) * | 2013-12-27 | 2014-04-09 | 华南师范大学 | Method for correcting space matching of area array imaging sensors in two-channel interferometry |
| CN108627175A (en) * | 2017-03-20 | 2018-10-09 | 现代自动车株式会社 | The system and method for vehicle location for identification |
| CN107703528A (en) * | 2017-09-25 | 2018-02-16 | 武汉光庭科技有限公司 | Low precision GPS vision positioning method and system is combined in automatic Pilot |
| CN109733390A (en) * | 2018-12-29 | 2019-05-10 | 江苏大学 | An adaptive lane change warning method based on driver characteristics |
| CN110320517A (en) * | 2019-05-31 | 2019-10-11 | 惠州市德赛西威汽车电子股份有限公司 | A kind of trailer-mounted radar recognition methods |
| CN110555407A (en) * | 2019-09-02 | 2019-12-10 | 东风汽车有限公司 | pavement vehicle space identification method and electronic equipment |
Non-Patent Citations (1)
| Title |
|---|
| "高速公路汽车防撞预警系统的开发研究";应世杰;《中国优秀博硕士学位论文全文数据库（硕士）工程科技||辑》;20060415;第C035-21页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111413692A (en) | 2020-07-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9208389B2 (en) | Apparatus and method for recognizing current position of vehicle using internal network of the vehicle and image sensor | |
| JP3822770B2 (en) | Vehicle front monitoring device | |
| JP3671825B2 (en) | Inter-vehicle distance estimation device | |
| CN109791598A (en) | The image processing method of land mark and land mark detection system for identification | |
| WO2019167531A1 (en) | Stereo camera device | |
| US20030002713A1 (en) | Vision-based highway overhead structure detection system | |
| JP5949955B2 (en) | Road environment recognition system | |
| US20150332100A1 (en) | Moving Object Location/Attitude Angle Estimation Device and Moving Object Location/Attitude Angle Estimation Method | |
| CN102806913A (en) | Novel lane line deviation detection method and device | |
| CN113859263B (en) | Scheduled travel route setting device and scheduled travel route setting method | |
| CN108957413A (en) | Sensor target positional accuracy test method | |
| CN111413692B (en) | Camera transverse position estimation self-calibration method based on roadside stationary object | |
| US10554951B2 (en) | Method and apparatus for the autocalibration of a vehicle camera system | |
| CN113029185A (en) | Road marking change detection method and system in crowdsourcing type high-precision map updating | |
| GB2370706A (en) | Determining the position of a vehicle | |
| CN111959482A (en) | Autonomous driving device and method | |
| CN114084129A (en) | Fusion-based vehicle automatic driving control method and system | |
| JP6649859B2 (en) | Vehicle position estimation device and vehicle position estimation method | |
| JP6834914B2 (en) | Object recognition device | |
| JP3440956B2 (en) | Roadway detection device for vehicles | |
| JP5446559B2 (en) | Vehicle position calculation device and vehicle position calculation method | |
| JP2024177451A (en) | Measurement device, measurement method, and program | |
| CN115214681A (en) | Method and system for determining ground level by means of artificial neural network | |
| JP6604052B2 (en) | Runway boundary estimation device and runway boundary estimation method | |
| JP2024038322A (en) | Measuring device, measuring method and program |
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 |