CN114372351A - Automatic driving simulation scene automatic generation method based on real traffic scene - Google Patents
Automatic driving simulation scene automatic generation method based on real traffic scene Download PDFInfo
- Publication number
- CN114372351A CN114372351A CN202111568464.9A CN202111568464A CN114372351A CN 114372351 A CN114372351 A CN 114372351A CN 202111568464 A CN202111568464 A CN 202111568464A CN 114372351 A CN114372351 A CN 114372351A
- Authority
- CN
- China
- Prior art keywords
- scene
- module
- lane
- automatic driving
- generation method
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to the field of automatic driving tests, and discloses an automatic generation method of an automatic driving simulation scene based on a real traffic scene, aiming at the problem of large workload of manual extraction of the automatic driving scene in the prior art, the invention provides a scheme which comprises a hardware part and a software module and is characterized in that the hardware part comprises four high-definition cameras, a high-precision positioning device and an industrial personal computer, wherein the four high-definition cameras respectively record the traffic conditions around a collection vehicle, the high-precision positioning device is arranged on the collection vehicle and used for positioning the position of the vehicle and assisting the extraction and positioning of a lane line, and the industrial personal computer is used for connecting the high-definition cameras and the high-precision positioning device and receiving and storing videos and positioning data. The invention can automatically, conveniently, efficiently and truly acquire a real traffic scene, can more truly reproduce scene traffic flow in a simulation environment, and can continuously convey relatively real simulation scenes to the simulation environment, thereby realizing data-driven simulation.
Description
Technical Field
The invention relates to the field of automatic driving test, in particular to an automatic driving simulation scene generation method based on a real traffic scene.
Background
The existing automatic driving scenes are mostly manually extracted, the workload of manual extraction is large, and the actual real traffic conditions are different to a certain extent. The accuracy and richness of the scene can be affected by the limitation of extraction efficiency and the difference from the real traffic condition. Most of the existing simulation scene standard files are in OpenX series standard formats, scene description extracted manually needs to be converted into the OpenX series standard formats, and workload is further increased.
If the real traffic scene can be automatically, conveniently, efficiently and truly collected, the scene traffic flow can be more truly reproduced in the simulation environment, relatively real simulation scenes can be continuously conveyed to the simulation environment, and data-driven simulation is realized.
Disclosure of Invention
The automatic generation method of the automatic driving simulation scene based on the real traffic scene solves the problem of large workload of manual extraction of the automatic driving scene in the prior art.
In order to achieve the purpose, the invention adopts the following technical scheme:
the automatic generation method of the automatic driving simulation scene based on the real traffic scene comprises a hardware part and a software module, wherein the hardware part comprises four high-definition cameras, a high-precision positioning device and an industrial personal computer, the four high-definition cameras are used for recording traffic conditions around a collection vehicle respectively, the high-precision positioning device is installed on the collection vehicle and used for positioning the position of the vehicle and assisting in the extraction and positioning of lane lines, and the industrial personal computer is used for connecting the high-definition cameras and the high-precision positioning device and receiving and storing videos and positioning data;
the software module includes target identification module, lane identification module, location data receiving module and scene generation module, the output of target identification module, the output of lane identification module and the output of location data receiving module all link with the input electricity of scene generation module, the hardware portion links with software module electricity, and the industrial computer is the hardware platform of software operation, saves software operation result.
Preferably, the four high-definition cameras are respectively a front high-definition camera, a rear high-definition camera, a left high-definition camera and a right high-definition camera, and the four high-definition cameras are installed on the collection vehicle and used for recording the traffic environment around the road and used for the software program to extract the lane lines and identify and extract the target objects.
Preferably, the target identification module is used for identifying and collecting vehicles, pedestrians, roadside facilities and the like in the video of the traffic environment around the vehicles, and marking, extracting and storing the vehicles, the pedestrians, the roadside facilities and the like.
Preferably, the lane recognition module is used for recognizing lane lines and constructing a virtual lane network by combining the positioning module.
Preferably, the positioning data receiving module is used for receiving the positioning data, and is combined with the lane line identification module to construct the virtual lane network.
Preferably, the scene generation module generates standard OpenX format files uniformly according to rules according to the data of the target identification module, the lane identification module and the positioning data receiving module.
In the invention:
the invention can automatically, conveniently, efficiently and truly acquire a real traffic scene, can more truly reproduce scene traffic flow in a simulation environment, and can continuously convey relatively real simulation scenes to the simulation environment, thereby realizing data-driven simulation.
Drawings
FIG. 1 is a block diagram of the present invention.
Fig. 2 is a schematic diagram of the operation of the scene generation module of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments.
Referring to fig. 1-2, the automatic generation method of the automatic driving simulation scene based on the real traffic scene comprises a hardware part and a software module, wherein the hardware part comprises four high-definition cameras, a high-precision positioning device and an industrial personal computer, the four high-definition cameras are respectively a front high-definition camera, a rear high-definition camera, a left high-definition camera and a right high-definition camera, the four high-definition cameras are installed on a collection vehicle and used for recording the traffic environment around the road and used for a software program to perform lane line extraction and target object identification extraction on the collection vehicle;
the industrial personal computer is used for connecting the high-definition camera and the high-precision positioning device, receiving and storing videos and positioning data;
the software module comprises a target identification module, a lane identification module, a positioning data receiving module and a scene generation module, wherein the output end of the target identification module, the output end of the lane identification module and the output end of the positioning data receiving module are all electrically connected with the input end of the scene generation module, the hardware part is electrically connected with the software module, an industrial personal computer is a hardware platform for software operation and stores a software operation result, the target identification module is used for identifying and collecting vehicles, pedestrians, roadside facilities and the like in a video of a traffic environment around the vehicles and marking, extracting and storing the vehicles, the lane identification module is used for identifying lane lines and is combined with the positioning module to construct a virtual lane network, the positioning data receiving module is used for receiving the positioning data and is combined with the lane line identification module to construct a virtual lane network, and the scene generation module is used for receiving the positioning data according to the target identification module, the lane identification module and the scene receiving module, and uniformly generating standard OpenX format files by the data according to rules.
The working principle is as follows: the system comprises a target identification module code which is written in advance, a lane identification module code, a positioning data receiving module code, a scene generation module code and combined debugging, wherein the target identification module code can identify vehicles on a road, pedestrians and various barriers, and roadside facilities, and can generate a time axis and a target object list on the positioning data line, and can represent positions, the lane identification module can identify the lane line, the positioning data receiving module can receive the positioning data, and sends the positioning data to the scene generation module, and the scene generation module can generate a scene file according to a standard format. The scene file that generates should be able to move in mainstream autopilot simulation software, then install 4 high accuracy cameras respectively in the front of gathering the car, back, left and right four directions, then be connected to on the industrial computer, the video signal in four directions can be accepted in the debugging on the industrial computer, and can save on the industrial computer, then install high-accuracy positioner on the car again, be connected to on the industrial computer, the debugging on the industrial computer, can receive normal locating data, and can save on the industrial computer.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (6)
1. The automatic driving simulation scene automatic generation method based on the real traffic scene comprises a hardware part and a software module, and is characterized in that the hardware part comprises four high-definition cameras, a high-precision positioning device and an industrial personal computer, wherein the four high-definition cameras respectively record traffic conditions around a collection vehicle, the high-precision positioning device is arranged on the collection vehicle and used for positioning the position of the vehicle and assisting in extracting and positioning lane lines, and the industrial personal computer is used for connecting the high-definition cameras and the high-precision positioning device and receiving and storing videos and positioning data;
the software module includes target identification module, lane identification module, location data receiving module and scene generation module, the output of target identification module, the output of lane identification module and the output of location data receiving module all link with the input electricity of scene generation module, the hardware portion links with software module electricity, and the industrial computer is the hardware platform of software operation, saves software operation result.
2. The automatic generation method of the automatic driving simulation scene based on the real traffic scene as claimed in claim 1, wherein the four high-definition cameras are a front high-definition camera, a rear high-definition camera, a left high-definition camera and a right high-definition camera, respectively, and the four high-definition cameras are installed on a collection vehicle for recording the traffic environment around the road for the software program to perform lane line extraction and target object identification extraction on the traffic environment.
3. The automatic generation method of the automatic driving simulation scene based on the real traffic scene as claimed in claim 2, wherein the target recognition module is used for recognizing and capturing vehicles, pedestrians, roadside facilities and the like in the video of the traffic environment around the vehicles, and labeling, extracting and storing the vehicles, the pedestrians, the roadside facilities and the like.
4. The automatic generation method of the driving simulation scene based on the real traffic scene as claimed in claim 3, wherein the lane recognition module is used for recognizing lane lines and combining with the positioning module to construct a virtual lane network.
5. The automatic generation method for the automatic driving simulation scene based on the real traffic scene as claimed in claim 4, wherein the positioning data receiving module is used for receiving positioning data and combining with the lane line identification module to construct the virtual lane network.
6. The automatic generation method for the automatic driving simulation scene based on the real traffic scene as claimed in claim 5, wherein the scene generation module generates the standard OpenX format file uniformly according to the data of the target recognition module, the lane recognition module and the positioning data receiving module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111568464.9A CN114372351A (en) | 2021-12-21 | 2021-12-21 | Automatic driving simulation scene automatic generation method based on real traffic scene |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111568464.9A CN114372351A (en) | 2021-12-21 | 2021-12-21 | Automatic driving simulation scene automatic generation method based on real traffic scene |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114372351A true CN114372351A (en) | 2022-04-19 |
Family
ID=81140735
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111568464.9A Pending CN114372351A (en) | 2021-12-21 | 2021-12-21 | Automatic driving simulation scene automatic generation method based on real traffic scene |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114372351A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114936515A (en) * | 2022-04-25 | 2022-08-23 | 北京宾理信息科技有限公司 | Method and system for generating simulated traffic scene file |
-
2021
- 2021-12-21 CN CN202111568464.9A patent/CN114372351A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114936515A (en) * | 2022-04-25 | 2022-08-23 | 北京宾理信息科技有限公司 | Method and system for generating simulated traffic scene file |
CN114936515B (en) * | 2022-04-25 | 2023-09-19 | 北京宾理信息科技有限公司 | Method and system for generating simulated traffic scene file |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109657355B (en) | Simulation method and system for vehicle road virtual scene | |
US20200265268A1 (en) | System and method for procedurally synthesizing datasets of objects of interest for training machine-learning models | |
CN111179585B (en) | Site testing method and device for automatic driving vehicle | |
CN107153363B (en) | Simulation test method, device, equipment and readable medium for unmanned vehicle | |
CN102867418B (en) | Method and device for judging license plate identification accuracy | |
CN112464910A (en) | Traffic sign identification method based on YOLO v4-tiny | |
CN112633535A (en) | Photovoltaic power station intelligent inspection method and system based on unmanned aerial vehicle image | |
CN113343461A (en) | Simulation method and device for automatic driving vehicle, electronic equipment and storage medium | |
CN102538762A (en) | Online inspection device of high-speed railway contact network and inspection method of online inspection device as well as high-speed rail contact network detection system formed by online inspection device | |
CN115830399B (en) | Classification model training method, device, equipment, storage medium and program product | |
CN116529784A (en) | Method and system for adding lidar data | |
CN114372351A (en) | Automatic driving simulation scene automatic generation method based on real traffic scene | |
CN113643431A (en) | System and method for iterative optimization of visual algorithm | |
Avramović et al. | Real-time large scale traffic sign detection | |
CN114415542A (en) | Automatic driving simulation system, method, server and medium | |
CN112529859A (en) | Power distribution equipment defect detection method and system | |
CN116225921A (en) | Visual debugging method and device for detection algorithm | |
CN116524210A (en) | Automatic driving data screening method, system, electronic equipment and storage medium | |
CN112950059B (en) | Test system and method for engineering quality management of intelligent vehicle road system monitoring facility | |
CN115359505A (en) | Electric power drawing detection and extraction method and system | |
CN114034260A (en) | Deep foundation pit support structure deformation diagnosis system based on streaming media and BIM | |
CN113239931A (en) | Logistics station license plate recognition method | |
CN111831570A (en) | Test case generation method oriented to automatic driving image data | |
CN117437792B (en) | Real-time road traffic state monitoring method, device and system based on edge calculation | |
CN110796024B (en) | Automatic driving visual perception test method and device for failure sample |
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 |