CN111091066B - Automatic driving automobile ground state assessment method and system - Google Patents
Automatic driving automobile ground state assessment method and system Download PDFInfo
- Publication number
- CN111091066B CN111091066B CN201911162569.7A CN201911162569A CN111091066B CN 111091066 B CN111091066 B CN 111091066B CN 201911162569 A CN201911162569 A CN 201911162569A CN 111091066 B CN111091066 B CN 111091066B
- Authority
- CN
- China
- Prior art keywords
- ground state
- ground
- acquiring
- vehicle
- image information
- 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
Classifications
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a ground state evaluation method and system for an automatic driving automobile, belongs to the technical field of automatic driving automobiles, and solves the problem that in the prior art, road surface state evaluation is not accurate enough. An automatic driving automobile ground state assessment method comprises the following steps: acquiring first ground image information, and acquiring ground state characteristics according to the first ground image information; adjusting light rays when the image is acquired, acquiring second ground image information, and acquiring ground state characteristics according to the second ground image information; comparing whether the ground state features acquired in two times are consistent, if so, determining the ground state by the ground state features acquired in any time, otherwise, readjusting the light rays when acquiring the image, acquiring the ground image information, acquiring the ground state features until the ground state features acquired in two times are consistent, and determining the ground state by the ground state features acquired in any time. A more accurate evaluation of the road surface condition is achieved.
Description
Technical Field
The invention relates to the technical field of automatic driving automobiles, in particular to a ground state assessment method and system for an automatic driving automobile.
Background
Along with popularization and use of the unmanned technology, the unmanned vehicle is gradually popularized and applied, but currently in the running of the unmanned vehicle, the road surface state has great influence on the safety and reliability of the running of the vehicle, when the running state of the vehicle such as the speed, the steering radius and the like is poor in matching with the road surface state, on one hand, the running comfort of the vehicle is relatively poor, on the other hand, the safety accident is easily caused when the vehicle runs, and aiming at the problem, a road condition assessment method capable of carrying out the mutual matching between the whole road condition state and the running of the vehicle along with the running of the vehicle is lacking, so that the running of the automatic driving vehicle has great potential safety hazard, and therefore, aiming at the current situation, an automatic driving vehicle running road surface state assessment method is needed to meet the requirement of actual use, and the existing road surface state assessment method is not accurate enough in road surface state assessment.
Disclosure of Invention
The invention aims to at least overcome the technical defect and provides a method and a system for evaluating the ground state of an automatic driving automobile.
In one aspect, the invention provides a method for evaluating the ground state of an automatic driving automobile, which comprises the following steps:
acquiring first ground image information in a vehicle running path, and acquiring ground state characteristics in the vehicle running path according to the first ground image information;
adjusting light rays when the image is acquired, acquiring second ground image information in a vehicle running path, and acquiring ground state characteristics in the vehicle running path according to the second ground image information;
comparing whether the ground state characteristics in the two obtained vehicle driving paths are consistent, if so, obtaining the ground state characteristics in the vehicle driving paths at any time to determine the ground state,
otherwise, readjusting the light rays when the images are acquired, acquiring the ground image information in the vehicle driving path, acquiring the ground state characteristics in the vehicle driving path until the ground state characteristics in the vehicle driving path acquired twice are consistent, and acquiring the ground state characteristics in the vehicle driving path at any one time to determine the ground state.
Further, the adjusting the light ray when the image is acquired specifically includes acquiring illumination intensity information of an area where the vehicle is running, and determining the size of the light ray adjustment when the image is acquired according to the illumination intensity information.
Further, the step of obtaining the ground state characteristics in the vehicle driving path at any one time to determine the ground state specifically comprises the steps of inputting the ground state characteristics in the vehicle driving path at any one time into a convolutional neural network model to determine the ground state.
Further, the method for evaluating the ground state of the automatic driving automobile further comprises the steps of constructing a convolutional neural network model, specifically comprising,
collecting image information data of a test vehicle in the running process of different floors to form a training database; and constructing a convolutional neural network by using the training database, and training the constructed convolutional neural network according to a back propagation algorithm to form a convolutional neural network model based on ground state assessment.
On the other hand, the invention also provides an automatic driving automobile ground state evaluation system, which comprises a first ground state feature acquisition module, a second ground state feature acquisition module and a ground state acquisition module;
the first ground state feature acquisition module is used for acquiring first ground image information in a vehicle running path and acquiring ground state features in the vehicle running path according to the first ground image information;
the second ground state feature acquisition module is used for adjusting light rays when images are acquired, acquiring second ground image information in a vehicle running path and acquiring ground state features in the vehicle running path according to the second ground image information;
the ground state acquisition module is used for comparing whether the ground state characteristics in the twice acquired vehicle running paths are consistent, if so, the ground state characteristics in the vehicle running paths are obtained at any time to determine the ground state,
otherwise, readjusting the light rays when the images are acquired, acquiring the ground image information in the vehicle driving path, acquiring the ground state characteristics in the vehicle driving path until the ground state characteristics in the vehicle driving path acquired twice are consistent, and acquiring the ground state characteristics in the vehicle driving path at any one time to determine the ground state.
Further, the automatic driving automobile ground state assessment system further comprises a light adjustment module, wherein the light adjustment module is used for wholly acquiring light rays when the image is acquired, and specifically comprises the steps of acquiring illumination intensity information of an area where the automobile runs, and determining the size of light ray adjustment when the image is acquired according to the illumination intensity information.
Further, the ground state acquisition module acquires the ground state characteristics in the vehicle driving path at any one time to determine the ground state, and specifically comprises inputting the ground state characteristics in the vehicle driving path at any one time into a convolutional neural network model to determine the ground state.
Further, the automatic driving automobile ground state assessment system also comprises a convolutional neural network model construction module, which is used for constructing a convolutional neural network model and specifically comprises,
collecting image information data of a test vehicle in the running process of different floors to form a training database; and constructing a convolutional neural network by using the training database, and training the constructed convolutional neural network according to a back propagation algorithm to form a convolutional neural network model based on ground state assessment.
Compared with the prior art, the invention has the beneficial effects that: acquiring first ground image information in a vehicle driving path, and acquiring ground state characteristics in the vehicle driving path according to the first ground image information; adjusting light rays when the image is acquired, acquiring second ground image information in a vehicle running path, and acquiring ground state characteristics in the vehicle running path according to the second ground image information; comparing whether the ground state features in the two acquired vehicle driving paths are consistent, if so, acquiring the ground state features in the vehicle driving paths at any time, determining the ground state, otherwise, readjusting the light rays when acquiring the images, acquiring the ground image information in the vehicle driving paths, acquiring the ground state features in the vehicle driving paths until the ground state features in the two acquired vehicle driving paths are consistent, and determining the ground state by acquiring the ground state features in the vehicle driving paths at any time. A more accurate evaluation of the road surface condition is achieved.
Drawings
Fig. 1 is a flow chart of a method for evaluating the ground state of an automatic driving automobile according to embodiment 1 of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Example 1
The invention provides a ground state assessment method of an automatic driving automobile, which comprises the following steps:
acquiring first ground image information in a vehicle running path, and acquiring ground state characteristics in the vehicle running path according to the first ground image information;
adjusting light rays when the image is acquired, acquiring second ground image information in a vehicle running path, and acquiring ground state characteristics in the vehicle running path according to the second ground image information;
comparing whether the ground state characteristics in the two obtained vehicle driving paths are consistent, if so, obtaining the ground state characteristics in the vehicle driving paths at any time to determine the ground state,
otherwise, readjusting the light rays when the images are acquired, acquiring the ground image information in the vehicle driving path, acquiring the ground state characteristics in the vehicle driving path until the ground state characteristics in the vehicle driving path acquired twice are consistent, and acquiring the ground state characteristics in the vehicle driving path at any one time to determine the ground state.
It should be noted that the autopilot comprises at least one camera and may comprise a plurality of cameras, the light-adjusting device when capturing the image may be a light-generating device, e.g. a Light Emitting Diode (LED), a flash, a laser, etc. camera may comprise a device adapted for use with an image recognition application and the device is capable of capturing an electronic image and transferring and saving the image to a storage device.
In one implementation, comparing the two obtained ground state characteristics in the vehicle running path to be consistent, and obtaining the ground state characteristics in the vehicle running path at any one time to determine the ground state; at this time, the light rays in the process of acquiring the image do not need to be readjusted; otherwise, the light rays when the image is acquired need to be readjusted to acquire the ground state characteristics in the running path of the vehicle again.
Preferably, the adjusting the light ray when the image is acquired specifically includes acquiring illumination intensity information of an area where the vehicle is running, and determining the size of the light ray adjustment when the image is acquired according to the illumination intensity information.
Preferably, the step of obtaining the ground state characteristics in the vehicle running path at any one time to determine the ground state specifically comprises the steps of inputting the ground state characteristics in the vehicle running path at any one time into a convolutional neural network model to determine the ground state.
Preferably, the method for evaluating the ground state of the automatic driving automobile further comprises the steps of constructing a convolutional neural network model, and specifically comprises the steps of collecting image information data of a test vehicle in the running process of different grounds to form a training database; and constructing a convolutional neural network by using the training database, and training the constructed convolutional neural network according to a back propagation algorithm to form a convolutional neural network model based on ground state assessment.
It should be noted that, in the embodiment of the present invention, the ground state is determined by using a convolutional neural network model, where the convolutional neural network is a deep feedforward artificial neural network, and the artificial neural network uses a variant of a multi-layer sensor designed to require minimum preprocessing; convolutional neural networks use relatively little preprocessing compared to other network models, which allows convolutional neural networks to learn filters. The ground state according to the embodiment of the present invention includes a ground type and a ground condition, and the classifier in the convolutional neural network model may be defined as one of a asphalt road, a cement road, a gravel road, a clay road, and a pit, and one of dry, wet, or snow.
Example 2
The invention also provides an automatic driving automobile ground state evaluation system, which comprises a first ground state feature acquisition module, a second ground state feature acquisition module and a ground state acquisition module;
the first ground state feature acquisition module is used for acquiring first ground image information in a vehicle running path and acquiring ground state features in the vehicle running path according to the first ground image information;
the second ground state feature acquisition module is used for adjusting light rays when images are acquired, acquiring second ground image information in a vehicle running path and acquiring ground state features in the vehicle running path according to the second ground image information;
the ground state acquisition module is used for comparing whether the ground state characteristics in the twice acquired vehicle running paths are consistent, if so, the ground state characteristics in the vehicle running paths are obtained at any time to determine the ground state,
otherwise, readjusting the light rays when the images are acquired, acquiring the ground image information in the vehicle driving path, acquiring the ground state characteristics in the vehicle driving path until the ground state characteristics in the vehicle driving path acquired twice are consistent, and acquiring the ground state characteristics in the vehicle driving path at any one time to determine the ground state.
The system comprises a vehicle driving area, a light adjusting module and a control module, wherein the light adjusting module is used for obtaining light rays when an image is obtained, and specifically comprises the steps of obtaining illumination intensity information of the vehicle driving area and determining the light ray adjusting size when the image is obtained according to the illumination intensity information.
Preferably, the ground state acquisition module acquires the ground state characteristics in the vehicle driving path at any one time to determine the ground state, and specifically includes inputting the ground state characteristics in the vehicle driving path at any one time to a convolutional neural network model to determine the ground state.
Preferably, the automatic driving automobile ground state assessment system further comprises a convolutional neural network model construction module, wherein the convolutional neural network model construction module is used for constructing a convolutional neural network model and specifically comprises,
collecting image information data of a test vehicle in the running process of different floors to form a training database; and constructing a convolutional neural network by using the training database, and training the constructed convolutional neural network according to a back propagation algorithm to form a convolutional neural network model based on ground state assessment.
The invention discloses a method and a system for evaluating the ground state of an automatic driving automobile, which are characterized in that the ground state characteristics in the running path of the automobile are obtained according to first ground image information in the running path of the automobile; adjusting light rays when the image is acquired, acquiring second ground image information in a vehicle running path, and acquiring ground state characteristics in the vehicle running path according to the second ground image information; comparing whether the ground state features in the two acquired vehicle driving paths are consistent, if so, acquiring the ground state features in the vehicle driving paths at any time, determining the ground state, otherwise, readjusting the light rays when acquiring the images, acquiring the ground image information in the vehicle driving paths, acquiring the ground state features in the vehicle driving paths until the ground state features in the two acquired vehicle driving paths are consistent, and determining the ground state by acquiring the ground state features in the vehicle driving paths at any time. A more accurate evaluation of the road surface condition is achieved.
Those skilled in the art will appreciate that all or part of the flow of the methods of the embodiments described above may be accomplished by way of a computer program to instruct associated hardware, where the program may be stored on a computer readable storage medium. Wherein the computer readable storage medium is a magnetic disk, an optical disk, a read-only memory or a random access memory, etc.
The above-described embodiments of the present invention do not limit the scope of the present invention. Any other corresponding changes and modifications made in accordance with the technical idea of the present invention shall be included in the scope of the claims of the present invention.
Claims (8)
1. An automatic driving automobile ground state assessment method is characterized by comprising the following steps:
acquiring first ground image information in a vehicle running path, and acquiring ground state characteristics in the vehicle running path according to the first ground image information;
adjusting light rays when the image is acquired, acquiring second ground image information in a vehicle running path, and acquiring ground state characteristics in the vehicle running path according to the second ground image information;
comparing whether the ground state characteristics in the two obtained vehicle driving paths are consistent, if so, obtaining the ground state characteristics in the vehicle driving paths at any time to determine the ground state,
otherwise, readjusting the light rays when the image is acquired, acquiring the ground image information in the vehicle driving path, acquiring the ground state characteristics in the vehicle driving path until the ground state characteristics in the vehicle driving path acquired twice are consistent, acquiring the ground state characteristics in the vehicle driving path at any time, and determining the ground state, wherein the ground state comprises the ground type and the ground condition, and the ground type is defined as one of asphalt road, cement road, gravel road, clay road and pothole.
2. The method for evaluating the ground state of an automatic driving automobile according to claim 1, wherein the adjusting the light rays when the image is acquired comprises acquiring illumination intensity information of an area where the automobile is driven, and determining the size of the light ray adjustment when the image is acquired according to the illumination intensity information.
3. The method for evaluating the ground state of an automatically driven automobile according to claim 1, wherein the ground state is determined by obtaining the ground state characteristics in the running path of the automobile at any one of the above steps, in particular, by inputting the ground state characteristics in the running path of the automobile at any one of the above steps into a convolutional neural network model, and determining the ground state.
4. The method for evaluating the ground state of the automatic driving automobile according to claim 3, further comprising the steps of constructing a convolutional neural network model, specifically comprising the steps of collecting image information data of a test vehicle in the running process of different grounds to form a training database; and constructing a convolutional neural network by using the training database, and training the constructed convolutional neural network according to a back propagation algorithm to form a convolutional neural network model based on ground state assessment.
5. The ground state evaluation system of the automatic driving automobile is characterized by comprising a first ground state feature acquisition module, a second ground state feature acquisition module and a ground state acquisition module; the first ground state feature acquisition module is used for acquiring first ground image information in a vehicle running path and acquiring ground state features in the vehicle running path according to the first ground image information; the second ground state feature acquisition module is used for adjusting light rays when images are acquired, acquiring second ground image information in a vehicle running path and acquiring ground state features in the vehicle running path according to the second ground image information; the ground state acquisition module is used for comparing whether the ground state characteristics in the twice acquired vehicle running paths are consistent, if so, the ground state characteristics in the vehicle running paths are obtained at any time, and the ground state is determined, otherwise, the light rays when the images are acquired are readjusted, the ground image information in the vehicle running paths is acquired, the ground state characteristics in the vehicle running paths are acquired until the ground state characteristics in the twice acquired vehicle running paths are consistent, and if so, the ground state characteristics in the vehicle running paths are obtained at any time, and the ground state is determined.
6. The system for assessing the ground state of an automatic driving automobile according to claim 5, further comprising a light adjustment module, wherein the light adjustment module is used for obtaining light rays when the image is obtained, and specifically comprises obtaining illumination intensity information of an area where the automobile is driven, and determining the light adjustment when the image is obtained according to the illumination intensity information.
7. The autonomous vehicle ground state assessment system of claim 5, wherein the ground state acquisition module obtains ground state characteristics in the vehicle travel path at any one of the ground state acquisition modules, and wherein determining the ground state comprises inputting the ground state characteristics in the vehicle travel path at any one of the ground state acquisition modules into a convolutional neural network model, and determining the ground state.
8. The ground state assessment system of an automatic driving automobile according to claim 7, further comprising a convolutional neural network model building module, wherein the convolutional neural network model building module is used for building a convolutional neural network model, and specifically comprises the steps of collecting image information data of a test vehicle in the running process of the test vehicle on different grounds to form a training database; and constructing a convolutional neural network by using the training database, and training the constructed convolutional neural network according to a back propagation algorithm to form a convolutional neural network model based on ground state assessment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911162569.7A CN111091066B (en) | 2019-11-25 | 2019-11-25 | Automatic driving automobile ground state assessment method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911162569.7A CN111091066B (en) | 2019-11-25 | 2019-11-25 | Automatic driving automobile ground state assessment method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111091066A CN111091066A (en) | 2020-05-01 |
| CN111091066B true CN111091066B (en) | 2023-09-22 |
Family
ID=70393513
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911162569.7A Active CN111091066B (en) | 2019-11-25 | 2019-11-25 | Automatic driving automobile ground state assessment method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111091066B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004191276A (en) * | 2002-12-13 | 2004-07-08 | Koito Ind Ltd | Apparatus for distinguishing road-surface state |
| CN105185160A (en) * | 2015-10-09 | 2015-12-23 | 卢庆港 | Pavement detection system and detection method |
| CN107247054A (en) * | 2017-04-20 | 2017-10-13 | 浙江工业职业技术学院 | A kind of retainer positive and negative image discriminating method based on bi-chromatic illumination |
| CN107392087A (en) * | 2017-05-27 | 2017-11-24 | 华勤通讯技术有限公司 | A kind of image processing method and device |
| CN108009522A (en) * | 2017-12-21 | 2018-05-08 | 海信集团有限公司 | A kind of Approach for road detection, device and terminal |
| CN108121325A (en) * | 2017-11-17 | 2018-06-05 | 南京视莱尔汽车电子有限公司 | A kind of autonomous driving vehicle state of ground assessment method |
| CN108375377A (en) * | 2017-01-31 | 2018-08-07 | 索尼公司 | Device and method for determining vehicle position in orbit |
| CN108513674A (en) * | 2018-03-26 | 2018-09-07 | 深圳市锐明技术股份有限公司 | A kind of detection alarm method, storage medium and the server of Chinese herbaceous peony accumulated snow and icing |
| CN109389095A (en) * | 2018-10-24 | 2019-02-26 | 中车株洲电力机车研究所有限公司 | A kind of pavement strip image-recognizing method and training method |
| CN109447164A (en) * | 2018-11-01 | 2019-03-08 | 厦门大学 | A kind of motor behavior method for classifying modes, system and device |
| CN109669451A (en) * | 2017-10-16 | 2019-04-23 | 株式会社万都 | Autonomous driving holding equipment and method |
| CN110874921A (en) * | 2018-08-31 | 2020-03-10 | 百度在线网络技术（北京）有限公司 | Intelligent road side unit and information processing method thereof |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8953838B2 (en) * | 2009-06-24 | 2015-02-10 | Here Global B.V. | Detecting ground geographic features in images based on invariant components |
| JP5892129B2 (en) * | 2013-08-29 | 2016-03-23 | 株式会社デンソー | Road shape recognition method, road shape recognition device, program, and recording medium |
| CN108985158A (en) * | 2018-06-08 | 2018-12-11 | 汉腾汽车有限公司 | A kind of road identification system and method |
| CN110162040B (en) * | 2019-05-10 | 2022-06-17 | 重庆大学 | Low-speed automatic driving trolley control method and system based on deep learning |
-
2019
- 2019-11-25 CN CN201911162569.7A patent/CN111091066B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004191276A (en) * | 2002-12-13 | 2004-07-08 | Koito Ind Ltd | Apparatus for distinguishing road-surface state |
| CN105185160A (en) * | 2015-10-09 | 2015-12-23 | 卢庆港 | Pavement detection system and detection method |
| CN108375377A (en) * | 2017-01-31 | 2018-08-07 | 索尼公司 | Device and method for determining vehicle position in orbit |
| CN107247054A (en) * | 2017-04-20 | 2017-10-13 | 浙江工业职业技术学院 | A kind of retainer positive and negative image discriminating method based on bi-chromatic illumination |
| CN107392087A (en) * | 2017-05-27 | 2017-11-24 | 华勤通讯技术有限公司 | A kind of image processing method and device |
| CN109669451A (en) * | 2017-10-16 | 2019-04-23 | 株式会社万都 | Autonomous driving holding equipment and method |
| CN108121325A (en) * | 2017-11-17 | 2018-06-05 | 南京视莱尔汽车电子有限公司 | A kind of autonomous driving vehicle state of ground assessment method |
| CN108009522A (en) * | 2017-12-21 | 2018-05-08 | 海信集团有限公司 | A kind of Approach for road detection, device and terminal |
| CN108513674A (en) * | 2018-03-26 | 2018-09-07 | 深圳市锐明技术股份有限公司 | A kind of detection alarm method, storage medium and the server of Chinese herbaceous peony accumulated snow and icing |
| CN110874921A (en) * | 2018-08-31 | 2020-03-10 | 百度在线网络技术（北京）有限公司 | Intelligent road side unit and information processing method thereof |
| CN109389095A (en) * | 2018-10-24 | 2019-02-26 | 中车株洲电力机车研究所有限公司 | A kind of pavement strip image-recognizing method and training method |
| CN109447164A (en) * | 2018-11-01 | 2019-03-08 | 厦门大学 | A kind of motor behavior method for classifying modes, system and device |
Non-Patent Citations (2)
| Title |
|---|
| Road Detection Based on Illuminant Invariance;Jose M.Alvarez等;IEEETRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS;第12卷(第1期);184-193 * |
| 基于卷积神经网络的路表病害识别与测量;沙爱民等;《中国公路学报》;20180115;第31卷(第01期);1-10 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111091066A (en) | 2020-05-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102373456B1 (en) | Learning method and learning device, and testing method and testing device for detecting parking spaces by using point regression results and relationship between points to thereby provide an auto-parking system | |
| CN108073170B (en) | Automated collaborative driving control for autonomous vehicles | |
| US11042758B2 (en) | Vehicle image generation | |
| US10467482B2 (en) | Method and arrangement for assessing the roadway surface being driven on by a vehicle | |
| CN109815300B (en) | Vehicle positioning method | |
| US20180150976A1 (en) | Method for automatically establishing extrinsic parameters of a camera of a vehicle | |
| CN106934378B (en) | Automobile high beam identification system and method based on video deep learning | |
| US20220101053A1 (en) | Neural network image processing | |
| CN111666805A (en) | Category tagging system for autonomous driving | |
| CN112660128B (en) | Apparatus for determining lane change path of autonomous vehicle and method thereof | |
| US11521375B2 (en) | Method and system for improved object marking in sensor data | |
| CN112198899A (en) | Road detection method, equipment and storage medium based on unmanned aerial vehicle | |
| DE102022102189A1 (en) | Multimodal segmentation mesh for improved semantic labeling in map generation | |
| US11270164B1 (en) | Vehicle neural network | |
| CN110765224A (en) | Processing method of electronic map, vehicle vision repositioning method and vehicle-mounted equipment | |
| CN109003286A (en) | Lane segmentation method based on deep learning and laser radar | |
| CN212009589U (en) | Video identification driving vehicle track acquisition device based on deep learning | |
| JP7444148B2 (en) | Information processing device, information processing method, program | |
| CN116634638A (en) | Light control strategy generation method, light control method and related device | |
| CN110588499A (en) | Machine vision-based headlamp adaptive control system and method | |
| DE102022100413A1 (en) | OBJECT DETECTION USING RADAR AND LIDAR COMBINATION | |
| CN111091066B (en) | Automatic driving automobile ground state assessment method and system | |
| DE102021132199A1 (en) | Determining object mobility parameters using an object sequence | |
| CN112509321A (en) | Unmanned aerial vehicle-based driving control method and system for urban complex traffic situation and readable storage medium | |
| CN116729042A (en) | Improved YOLOX-NANO model and automobile electric control suspension control method based on model |
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 |