CN110780287A - Distance measurement method and distance measurement system based on monocular camera - Google Patents
Distance measurement method and distance measurement system based on monocular camera Download PDFInfo
- Publication number
- CN110780287A CN110780287A CN201911091971.0A CN201911091971A CN110780287A CN 110780287 A CN110780287 A CN 110780287A CN 201911091971 A CN201911091971 A CN 201911091971A CN 110780287 A CN110780287 A CN 110780287A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- target object
- information
- distance
- camera
- 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.)
- Withdrawn
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
Abstract
The invention provides a distance measuring method and a distance measuring system based on a monocular camera, wherein target object information is obtained through a camera unit, the camera unit comprises a vehicle-mounted camera, and the target object information comprises position information of a target object; acquiring lane information according to the position information of the target object, and acquiring the vertical distance between the vehicle-mounted camera and the target object according to the lane information and the internal reference proportion coefficient of the vehicle-mounted camera; acquiring a deviation angle of the target object compared with a coordinate system of the vehicle-mounted camera according to the position information of the vehicle-mounted camera and the position information of the target object, and acquiring a horizontal distance between the vehicle-mounted camera and the target object according to the deviation angle and a vertical distance between the vehicle-mounted camera and the target object so as to acquire vehicle distance information, wherein the vehicle distance information comprises the vertical distance between the vehicle and the target object and the horizontal distance between the vehicle and the target object; the distance measuring method has the advantages of simple algorithm, accuracy, high efficiency, low cost and suitability for popularization and application.
Description
Technical Field
The invention relates to the technical field of distance measuring methods, in particular to a distance measuring method and a distance measuring system based on a monocular camera.
Background
With the development of the automatic driving technology, the automatic driving vehicle gradually enters the public visual field, and in the driving scene of the automatic driving vehicle, the identification and detection of the obstacles are indispensable links. In order to recognize and detect an obstacle, an autonomous vehicle is generally operated using a sensor such as a laser radar or a camera disposed in the vehicle. Among them, the cost is high if the laser radar is used, for example, only one 64-line laser radar is tens of thousands yuan, and the laser radar has a disadvantage that the object class cannot be recognized, such as: efficient tracking and motion law estimation cannot be performed for vehicles or pedestrians traveling in front or behind. In addition, cameras generally require binocular cameras to extract features to estimate depth because of lack of depth information, and cannot be efficiently utilized in outdoor scenes.
Patent document CN106708084B discloses an unmanned aerial vehicle automatic obstacle detection and obstacle avoidance method in a complex environment, which includes: acquiring images in real time by using a binocular camera arranged on an unmanned aerial vehicle, matching and calculating based on the acquired left and right images to generate a disparity map and preprocessing the disparity map; based on the disparity map information, carrying out clustering division on the contour and the gray value of the disparity map to obtain an area block with a clear structure, and removing noise interference of the area block to obtain a potential obstacle area; comparing corresponding potential obstacle regions in the front and rear frames of disparity maps, and screening to obtain a final obstacle region according to the distance between the unmanned aerial vehicle and the potential obstacle region and the area of the potential obstacle region by combining the amplification characteristics of the obstacle; outputting an action instruction of obstacle avoidance of the unmanned aerial vehicle based on the obtained final obstacle region; but this method is computationally intensive.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a distance measuring method and a distance measuring system based on a monocular camera.
The invention provides a distance measurement method based on a monocular camera, which comprises the following steps:
a target object acquisition step: acquiring target object information through a camera unit, wherein the camera unit comprises a vehicle-mounted camera, and the target object information comprises position information of a target object;
a vertical distance obtaining step: acquiring lane information according to the position information of the target object, and acquiring the vertical distance between the vehicle-mounted camera and the target object according to the lane information and the internal reference proportion coefficient of the vehicle-mounted camera;
a vehicle distance acquisition step: and obtaining vehicle distance information according to the vertical distance between the vehicle-mounted camera and the target object, wherein the vehicle distance information comprises the vertical distance between the vehicle and the target object.
Preferably, the method further comprises the step of acquiring the horizontal distance: and obtaining a deviation angle of the target object compared with a coordinate system of the vehicle-mounted camera according to the position of the vehicle-mounted camera and the position information of the target object, and obtaining the horizontal distance between the vehicle-mounted camera and the target object according to the deviation angle and the vertical distance between the vehicle-mounted camera and the target object.
Preferably, the vehicle distance acquiring step can also acquire vehicle distance information according to the horizontal distance between the vehicle-mounted camera and the target object; wherein the vehicle distance information includes a horizontal distance of the vehicle from the target object.
Preferably, the method further comprises a feedback guiding step, wherein the feedback guiding step feeds back the vehicle distance information to a vehicle guiding party;
the vehicle guiding part controls the vehicle through the obtained vehicle distance information.
Preferably, the lane information includes lane line information;
the lane line information is lane line information of an area where the target object is located or lane line information of an area where the vehicle is located.
Preferably, the feedback guidance step is capable of feeding back vehicle distance information to the target vehicle;
the target vehicle is a vehicle where the vehicle-mounted camera is located and/or a vehicle in an adjacent lane line area.
Preferably, the vehicle guiding party is a driver or an intelligent terminal.
According to the distance measuring system based on the monocular camera, the distance measuring method based on the monocular camera is adopted, and comprises a first running vehicle;
the first running vehicle comprises a vehicle-mounted camera, a first control system and a first audio and video system;
the first control system can receive information acquired by the vehicle-mounted camera and inform a vehicle guiding party or inform the vehicle guiding party through a first audio and video system.
Preferably, a second traveling vehicle is further included;
the second running vehicle includes a second control system;
the first control system is in communication connection with the second control system;
the first running vehicle is capable of notifying the second control system of the received information of the onboard camera;
and the second running vehicle informs the vehicle guiding party of the second running vehicle of the received information of the first running vehicle through the second control system.
Preferably, the second running vehicle further comprises a second audio-visual system;
and the second running vehicle informs the vehicle guiding party of the second running vehicle of the received information of the first running vehicle through a second audio-video system.
Compared with the prior art, the invention has the following beneficial effects:
1. the invention adopts the monocular camera to efficiently and reliably complete the distance measurement between the vehicle and the target object, and has strong practicability.
2. The algorithm is simple and the cost is low.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:
FIG. 1 is a schematic diagram of the principles of the present invention;
FIG. 2 is a schematic diagram of the arrangement of the vehicle-mounted camera and the target object;
FIG. 3 is a schematic diagram of an internal reference system of the onboard camera.
Detailed Description
The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the invention, but are not intended to limit the invention in any way. It should be noted that it would be obvious to those skilled in the art that various changes and modifications can be made without departing from the spirit of the invention. All falling within the scope of the present invention.
According to the monocular camera-based ranging method provided by the invention, the camera unit is used for acquiring the target object information, wherein the camera unit comprises a vehicle-mounted camera, such as a monocular camera, the target object information comprises the position information of the target object, and the target object is a vehicle adjacent to the vehicle in the driving process or other target objects, such as pedestrians, automobiles, bicycles and the like on the road; and acquiring lane information according to the position information of the target object, wherein the lane information comprises lane line information, and the lane line information is lane line information of an area where the target object is located or lane line information of an area where the vehicle is located. Acquiring the vertical distance between the vehicle-mounted camera and the target object according to the lane information and the internal reference proportion coefficient of the vehicle-mounted camera; obtaining a deviation angle of the target object compared with a coordinate system of the vehicle-mounted camera according to the position information of the vehicle-mounted camera and the position information of the target object, and obtaining a horizontal distance between the vehicle-mounted camera and the target object according to the deviation angle and a vertical distance between the vehicle-mounted camera and the target object; obtaining vehicle distance information according to the vertical distance obtaining step and the horizontal distance obtaining step, wherein the vehicle distance information comprises the vertical distance between the vehicle and the target object and the horizontal distance between the vehicle and the target object, the horizontal distance and the vertical distance between the vehicle and the target object, which are obtained by the vehicle through a vehicle-mounted camera, and the vertical distance between the vehicle and the target object and the horizontal distance between the vehicle and the target object are obtained by combining the size information of the vehicle and the installation position of the vehicle-mounted camera on the vehicle; and feeding back the vehicle distance information to a vehicle guiding party, and controlling the traveling direction and the traveling speed of the vehicle by the vehicle guiding party through the obtained vehicle distance information. The invention adopts the monocular camera to efficiently and reliably complete the distance measurement between the vehicle and the target object, and has low cost and strong practicability.
Specifically, the feedback guidance step can feed back the vehicle distance information to the target vehicle; the target vehicle may be a vehicle where a vehicle-mounted camera is located; or a target; or vehicles in the adjacent lane line area.
In particular, the vehicle instructor is a driver or an intelligent terminal, such as a driver driving a vehicle, for example: the intelligent terminal is installed on the unmanned vehicle.
Specifically, as shown in fig. 2, a deviation angle θ of the object from the coordinate system of the vehicle-mounted camera is obtained according to the position of the vehicle-mounted camera and the object, and a horizontal distance L between the vehicle-mounted camera and the object is obtained according to the deviation angle θ. In a preferred embodiment, a camera coordinate system is established, for example, a vertical line passing through an optical center of the vehicle-mounted camera and perpendicular to the image plane is taken as a Z-axis, a deviation included angle of the target object relative to the Z-axis is a calculated deviation angle θ, and the horizontal distance L is obtained through calculation according to the vertical distance H and the deviation angle θ.
Further, the vertical distance and the horizontal distance between the vehicle and the target object are obtained through the vertical distance and the horizontal distance between the vehicle-mounted camera and the target object, and vehicle distance information, namely the vertical distance and the horizontal distance between the vehicle and the target object is obtained according to the position of the vehicle-mounted camera on the vehicle and relevant parameters such as the length and the width of the vehicle body.
Specifically, the vehicle feeds back the vehicle distance information to the vehicle guiding party through the feedback guiding step and guides the vehicle of the vehicle guiding party to drive, in a preferred example, the vehicle guiding party is a driver, and the vehicle informs the driver through a multimedia video or sound mode and the like; in a variation, the vehicle guiding party is an intelligent terminal of the unmanned vehicle, and the vehicle is fed back to the intelligent terminal in a communication manner, for example, the unmanned vehicle can use the vehicle distance information for vehicle control under the control of the intelligent terminal, and automatically adjust the traveling speed and the traveling direction of the vehicle, so as to avoid traffic accidents.
According to the distance measuring system based on the monocular camera, provided by the invention, the embodiment of the distance measuring method based on the monocular camera can be understood as comprising a first running vehicle, wherein the first running vehicle comprises a vehicle-mounted camera, a first control system and a first audio and video system; the first control system can receive information of a vertical distance between the vehicle-mounted camera and a target object and a horizontal distance between the vehicle-mounted camera and the target object, further obtain the vertical distance between the vehicle-mounted camera and a first running vehicle and the horizontal distance between the vehicle-mounted camera and the first running vehicle, and then inform a vehicle guiding party of the information of the vertical distance between the first running vehicle and the horizontal distance between the first running vehicle through a first audio-video system, and the vehicle guiding party drives the vehicle according to the obtained distance information, for example, when the target object is a second vehicle, the vehicle guiding party can inform the second vehicle in a whistle mode.
Specifically, the system further comprises a second running vehicle, for example, the second running vehicle is a target object, and the second running vehicle comprises a second control system and a second audio and video system; the first running vehicle can inform the second control system of the received information of the vertical distance of the first running vehicle and the horizontal distance of the first running vehicle to the vehicle-mounted camera; and the information obtained by the second running vehicle through the second control system informs a vehicle guiding party of the second running vehicle through a second audio and video system.
The method comprises the following steps of utilizing a pinhole camera model to explain a reference coefficient matrix and definition in the vehicle-mounted camera: let the coordinates of a point P in space under the camera coordinate system model be: (x)
c,y
c,z
c) Then, the image coordinate system (u, v) projected onto the vehicle-mounted camera phase plane has:
wherein the K matrix is called as an internal parameter matrix of the camera, f is the focal length of the camera, and the unit is mm; dx and dy are pixel sizes; c. C
x,c
yIs the coordinate offset of the optical center on the image coordinate system.
The matrix is derived from camera calibration, and is called the normalized focal length on the x-axis and the y-axis, respectively.
Specifically, a vehicle-mounted camera is arranged on a vehicle, information of a target object is acquired through the vehicle-mounted camera, and lane information is further acquired according to the information of the target object. The method comprises the steps that information of a target object such as a vehicle, a pedestrian and the like can be collected and recognized through a vehicle-mounted camera, lane information such as lane line information is further obtained according to the position of the target object, and the vertical distance between the vehicle-mounted camera and the target object is obtained according to the actual width of a lane, the width between lane lines obtained on an image and a camera internal reference coefficient. The camera's internal reference scale factor is either f/dx (wide) or f/dy (high). Where f is the focal length of the camera, and dx and dy refer to the size of each pixel of the camera area array, and the unit is meter. Let fx be f/dx, which is one of the internal scaling factors of the camera, and is derived from calibration, as shown in fig. 3:
fx/L＝x/w，
wherein, L refers to the horizontal distance of the camera from the vehicle-mounted camera of the target object, unit: rice; x refers to the width (pixel) of an object on the image; w is the actual width of the object, in units: and (4) rice.
According to the existing lane line identification technology and vehicle identification technology, the lane where the front vehicle is located and lane lines on two sides of the front vehicle can be obtained on the image. The actual distance of the lane is known as the normalized distance, for example: 3 m, the width of the horizontal line (perpendicular to the lane line) where the target rear wheel is located on the image can also be obtained.
And d is w × fx/x, that is, the target depth is the lane distance multiplied by fx divided by the lane line width of the position of the target on the image.
After the depth is found, the yaw bearing of the vehicle can also be found as: and yaw is d tan θ. Wherein, theta is an included angle between a ray from the optical center of the camera to the center of the target vehicle and the z-axis of the coordinate system of the camera, and the included angle theta can be obtained by combining the image coordinates of the center of the vehicle and the internal parameters of the camera:
camera intrinsic parameter matrix:
K＝[fx 0 cx,
0 fy cy,
0 0 1]
then: ifx ═ 1/fx
icx＝-cx*ifx
θ＝arctan(ct
x*ifx+icx,1)
Wherein (ct)
x，ct
y) Refers to the pixel coordinate value of the target center point on the image coordinate system, where only ct is used
xAnd i represents an inversion operation.
The invention provides a distance measuring method and a distance measuring system based on a monocular camera, lane information is obtained according to a camera unit, and the vertical distance between a vehicle-mounted camera and a target object is obtained according to the lane information and the internal reference coefficient of the vehicle-mounted camera; acquiring a deviation angle of the target object compared with a coordinate system of the vehicle-mounted camera according to the position information of the vehicle-mounted camera and the position information of the target object, and acquiring a horizontal distance between the vehicle-mounted camera and the target object according to the deviation angle and a vertical distance between the vehicle-mounted camera and the target object so as to acquire vehicle distance information, wherein the vehicle distance information comprises the vertical distance between the vehicle and the target object and the horizontal distance between the vehicle and the target object; the distance measuring method is accurate and efficient, has low cost, reliably realizes the distance measurement between the vehicle and the target object, and effectively guides the vehicle control of a vehicle guiding party.
In the description of the present application, it is to be understood that the terms "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience in describing the present application and simplifying the description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the present application.
Those skilled in the art will appreciate that, in addition to implementing the systems, apparatus, and various modules thereof provided by the present invention in purely computer readable program code, the same procedures can be implemented entirely by logically programming method steps such that the systems, apparatus, and various modules thereof are provided in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Therefore, the system, the device and the modules thereof provided by the present invention can be considered as a hardware component, and the modules included in the system, the device and the modules thereof for implementing various programs can also be considered as structures in the hardware component; modules for performing various functions may also be considered to be both software programs for performing the methods and structures within hardware components.
The foregoing description of specific embodiments of the present invention has been presented. It is to be understood that the present invention is not limited to the specific embodiments described above, and that various changes or modifications may be made by one skilled in the art within the scope of the appended claims without departing from the spirit of the invention. The embodiments and features of the embodiments of the present application may be combined with each other arbitrarily without conflict.
Claims (10)
1. A distance measurement method based on a monocular camera is characterized by comprising the following steps:
a target object acquisition step: acquiring target object information through a camera unit, wherein the camera unit comprises a vehicle-mounted camera, and the target object information comprises position information of a target object;
a vertical distance obtaining step: acquiring lane information according to the position information of the target object, and acquiring the vertical distance between the vehicle-mounted camera and the target object according to the lane information and the internal reference proportion coefficient of the vehicle-mounted camera;
a vehicle distance acquisition step: and obtaining vehicle distance information according to the vertical distance between the vehicle-mounted camera and the target object, wherein the vehicle distance information comprises the vertical distance between the vehicle and the target object.
2. The monocular camera-based ranging method according to claim 1, further comprising a horizontal distance acquiring step of: and obtaining a deviation angle of the target object compared with a coordinate system of the vehicle-mounted camera according to the position of the vehicle-mounted camera and the position information of the target object, and obtaining the horizontal distance between the vehicle-mounted camera and the target object according to the deviation angle and the vertical distance between the vehicle-mounted camera and the target object.
3. The monocular camera-based ranging method according to claim 2, wherein the vehicle distance obtaining step is further capable of obtaining vehicle distance information according to a horizontal distance between the vehicle-mounted camera and a target object; wherein the vehicle distance information includes a horizontal distance of the vehicle from the target object.
4. The monocular camera-based ranging method according to claim 3, further comprising a feedback guidance step of feeding back the vehicle distance information to a vehicle guidance party;
the vehicle guiding part controls the vehicle through the obtained vehicle distance information.
5. The monocular camera-based ranging method of claim 1, wherein the lane information includes lane line information;
the lane line information is lane line information of an area where the target object is located or lane line information of an area where the vehicle is located.
6. The monocular camera-based ranging method of claim 4, wherein the feedback guidance step is capable of feeding back vehicle distance information to a target vehicle;
the target vehicle is a vehicle where the vehicle-mounted camera is located and/or a vehicle in an adjacent lane line area.
7. The monocular camera-based ranging method of claim 4, wherein the vehicle instructor is a driver or a smart terminal.
8. A monocular camera-based ranging system, characterized in that the monocular camera-based ranging method of any one of claims 1 to 7 is employed, comprising a first traveling vehicle;
the first running vehicle comprises a vehicle-mounted camera, a first control system and a first audio and video system;
the first control system can receive information acquired by the vehicle-mounted camera and inform a vehicle guiding party or inform the vehicle guiding party through a first audio and video system.
9. The monocular camera-based ranging system of claim 8, further comprising a second traveling vehicle;
the second running vehicle includes a second control system;
the first control system is in communication connection with the second control system;
the first running vehicle is capable of notifying the second control system of the received information of the onboard camera;
and the second running vehicle informs the vehicle guiding party of the second running vehicle of the received information of the first running vehicle through the second control system.
10. The monocular camera-based ranging system of claim 9, wherein the second moving vehicle comprises a second audio-visual system;
and the second running vehicle informs the vehicle guiding party of the second running vehicle of the received information of the first running vehicle through a second audio-video system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911091971.0A CN110780287A (en) | 2019-11-08 | 2019-11-08 | Distance measurement method and distance measurement system based on monocular camera |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911091971.0A CN110780287A (en) | 2019-11-08 | 2019-11-08 | Distance measurement method and distance measurement system based on monocular camera |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110780287A true CN110780287A (en) | 2020-02-11 |
Family
ID=69390237
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911091971.0A Withdrawn CN110780287A (en) | 2019-11-08 | 2019-11-08 | Distance measurement method and distance measurement system based on monocular camera |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110780287A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111591284A (en) * | 2020-05-28 | 2020-08-28 | 东软睿驰汽车技术（沈阳）有限公司 | Visual field blind area obstacle avoidance method and device based on monocular recognition |
| CN111965383A (en) * | 2020-07-28 | 2020-11-20 | 禾多科技（北京）有限公司 | Vehicle speed information generation method and device, electronic equipment and computer readable medium |
| CN112268538A (en) * | 2020-10-20 | 2021-01-26 | 中国人民解放军陆军工程大学 | Geometric optical distance measurement method suitable for small unmanned vehicle |
| CN116503491A (en) * | 2023-06-26 | 2023-07-28 | 安徽大学 | Robot dog obstacle ranging and obstacle avoidance method based on camera calibration and vision |
-
2019
- 2019-11-08 CN CN201911091971.0A patent/CN110780287A/en not_active Withdrawn
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111591284A (en) * | 2020-05-28 | 2020-08-28 | 东软睿驰汽车技术（沈阳）有限公司 | Visual field blind area obstacle avoidance method and device based on monocular recognition |
| CN111965383A (en) * | 2020-07-28 | 2020-11-20 | 禾多科技（北京）有限公司 | Vehicle speed information generation method and device, electronic equipment and computer readable medium |
| CN112268538A (en) * | 2020-10-20 | 2021-01-26 | 中国人民解放军陆军工程大学 | Geometric optical distance measurement method suitable for small unmanned vehicle |
| CN116503491A (en) * | 2023-06-26 | 2023-07-28 | 安徽大学 | Robot dog obstacle ranging and obstacle avoidance method based on camera calibration and vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11719788B2 (en) | Signal processing apparatus, signal processing method, and program | |
| CN109920246B (en) | Collaborative local path planning method based on V2X communication and binocular vision | |
| EP3751455A2 (en) | Image fusion for autonomous vehicle operation | |
| Gandhi et al. | Vehicle surround capture: Survey of techniques and a novel omni-video-based approach for dynamic panoramic surround maps | |
| Broggi et al. | Terramax vision at the urban challenge 2007 | |
| CN110780287A (en) | Distance measurement method and distance measurement system based on monocular camera | |
| CN111815641A (en) | Camera and radar fusion | |
| JP2020525809A (en) | System and method for updating high resolution maps based on binocular images | |
| US20090073258A1 (en) | Device intended to support the driving of a motor vehicle comprising a system capable of capturing stereoscopic images | |
| CN212220188U (en) | Underground parking garage fuses positioning system | |
| CN114419098A (en) | Moving target trajectory prediction method and device based on visual transformation | |
| Ponsa et al. | On-board image-based vehicle detection and tracking | |
| EP3364336A1 (en) | A method and apparatus for estimating a range of a moving object | |
| Lim et al. | Implementation of semantic segmentation for road and lane detection on an autonomous ground vehicle with LIDAR | |
| Na et al. | RoadPlot-DATMO: Moving object tracking and track fusion system using multiple sensors | |
| CN212220070U (en) | Vehicle real-time positioning system based on visual semantic segmentation technology | |
| Yang | Estimation of vehicle's lateral position via the Lucas-Kanade optical flow method | |
| CN113838060A (en) | Perception system for autonomous vehicle | |
| CN110727269A (en) | Vehicle control method and related product | |
| CN110794821A (en) | Vehicle-mounted control device, field end positioning device, vehicle control system and vehicle | |
| Oniga et al. | A fast ransac based approach for computing the orientation of obstacles in traffic scenes | |
| US20230098440A1 (en) | Imaging device, imaging system, and imaging method | |
| CN114677658A (en) | Billion-pixel dynamic large-scene image acquisition and multi-target detection method and device | |
| CN110775054B (en) | Vehicle-mounted control device, field end positioning device, vehicle control system and vehicle | |
| CN113884090A (en) | Intelligent platform vehicle environment sensing system and data fusion method thereof |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200211 |
|
| WW01 | Invention patent application withdrawn after publication |