CN111582173A - Automatic driving method and system - Google Patents
Automatic driving method and system Download PDFInfo
- Publication number
- CN111582173A CN111582173A CN202010384728.4A CN202010384728A CN111582173A CN 111582173 A CN111582173 A CN 111582173A CN 202010384728 A CN202010384728 A CN 202010384728A CN 111582173 A CN111582173 A CN 111582173A
- Authority
- CN
- China
- Prior art keywords
- type
- defect
- area
- image information
- obstacle
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Abstract
The application discloses a method and a system for automatic driving, wherein the method comprises the following steps: acquiring an actual area corresponding to a defect area to be identified; identifying the actual area; when the identification result of the actual area is a non-known obstacle, determining the type of the non-known obstacle; and if the type of the unknown obstacle is an avoidance type, indicating the vehicle to carry out avoidance running on the unknown obstacle. The situation that the vehicle cannot effectively avoid the obstacle when an unconventional object cannot be identified is avoided, and the safety of the vehicle in the driving process is improved.
Description
Technical Field
The present application relates to the field of automatic driving technologies, and in particular, to a method and a system for automatic driving.
Background
The road obstacle detection technology is beneficial to the detection of obstacles on the road surface by the vehicle, so that the vehicle can avoid the detected obstacles and avoid collision.
In practical application, the road obstacle detection technology can only detect a standardized object, such as: trees, vehicles, people, etc., but are unable to detect irregular objects such as: and garbage blown up by wind.
In the prior art, a road obstacle detection technology is applied, and after a conventional object is detected, a vehicle can be effectively avoided. For an unconventional object, the object cannot be accurately identified, so that misjudgment may occur, the vehicle cannot be effectively avoided, and the safety of the vehicle in the driving process is reduced.
Disclosure of Invention
In order to solve the technical problem, the application provides an automatic driving method and system. The misjudgment condition occurring when the object fails is avoided, and the safety of the vehicle in the driving process is improved.
The embodiment of the application discloses the following technical scheme:
in a first aspect, the present application provides a method of autonomous driving, comprising:
acquiring an actual area corresponding to a defect area to be identified;
identifying the actual area;
when the identification result of the actual area is a non-known obstacle, determining the type of the non-known obstacle;
and if the type of the unknown obstacle is an avoidance type, indicating the vehicle to carry out avoidance running on the unknown obstacle.
As a possible implementation, after determining the type of the unknown obstacle, the method further includes:
and if the type of the unknown obstacle is a non-evasive type, indicating that the vehicle normally runs.
As a possible implementation manner, before the acquiring an actual region corresponding to a defect region to be identified, the method further includes:
acquiring front image information of the vehicle;
determining defect image information of the defect area to be identified according to the front image information;
the acquiring of the actual region corresponding to the defect region to be identified includes:
and determining an actual area corresponding to the defect area to be identified according to the defect image information.
As one possible implementation, the determining the type of the unknown obstacle includes:
determining the type of the unknown obstacle by inputting the defect image information into a type recognition model;
the type recognition model is obtained based on training samples and type training corresponding to the training samples, the training samples comprise historical defect image information, and the historical defect image information is obtained for a historical time period.
As a possible implementation manner, the determining, according to the front image information, defect image information of the defect region to be identified includes:
determining defect image information corresponding to a defect area to be identified in a drivable area according to the front image information; the travelable area is an area corresponding to the road ahead in the image.
As a possible implementation, after identifying the actual region, the method further includes:
and when the identification result of the actual area is a non-obstacle, indicating that the vehicle runs in a decelerating way.
In a first aspect, the present application provides a system for autonomous driving, comprising: the device comprises an area acquisition module, an identification module, a type determination module and a processing module;
the area acquisition module is used for acquiring an actual area corresponding to the defect area to be identified;
the identification module is used for identifying the actual area;
the type determining module is used for determining the type of the unknown obstacle when the identification result of the actual area is the unknown obstacle;
and the processing module is used for indicating the vehicle to carry out evasive running on the unknown obstacle if the type of the unknown obstacle is an evasive type.
As a possible implementation manner, the processing module is further configured to instruct the vehicle to normally run if the type of the unknown obstacle is a non-avoidance type.
As a possible implementation, an image acquisition module;
the image acquisition module is used for acquiring front image information of the vehicle; determining defect image information of the defect area to be identified according to the front image information;
the area obtaining module is specifically configured to determine an actual area corresponding to the defect area to be identified according to the defect image information.
As a possible implementation manner, the type determining module is specifically configured to determine the type of the unknown obstacle by inputting the defect image information into a type recognition model; the type recognition model is obtained based on training samples and type training corresponding to the training samples, the training samples comprise historical defect image information, and the historical defect image information is obtained for a historical time period.
As a possible implementation manner, the image obtaining module is specifically configured to determine, according to the front image information, defect image information corresponding to a defect area to be identified in a drivable area; the travelable area is an area corresponding to the road ahead in the image.
As a possible embodiment, the processing module is further configured to instruct the vehicle to run at a reduced speed when the identification result of the actual area is a non-obstacle.
According to the technical scheme, the method has the following advantages:
the invention provides an automatic driving method and system, wherein the method comprises the following steps: acquiring an actual area corresponding to a defect area to be identified; identifying the actual area; when the identification result of the actual area is a non-known obstacle, determining the type of the non-known obstacle; and if the type of the unknown obstacle is an avoidance type, indicating the vehicle to carry out avoidance running on the unknown obstacle. The situation that the vehicle cannot effectively avoid the obstacle when an unconventional object cannot be identified is avoided, and the safety of the vehicle in the driving process is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic diagram of an autonomous vehicle provided in an embodiment of the present application;
FIG. 2 is a flow chart of a method for automatic driving provided by an embodiment of the present application;
fig. 3 is a schematic diagram of an automatic driving system according to an embodiment of the present disclosure.
Detailed Description
In the prior art, for an unconventional object, the road obstacle detection technology cannot identify what the object is, and further misjudgment may occur. For example, when an object that cannot be detected is an animal suddenly rushing into the road surface, the vehicle should inevitably detect the object, but since it cannot detect what the object is, it is misjudged that the object is not an obstacle, and the vehicle may collide with the animal suddenly rushing into the road surface, thereby causing a safety accident and reducing safety during the driving of the vehicle.
In order to solve the above problems, the present application provides a method and system for automatic driving.
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Embodiments of the present application are described below in a specific context.
Referring to fig. 1, the figure is a schematic diagram of automatic vehicle driving provided in an embodiment of the present application.
As shown, the vehicle a is in an automatic low-speed running state on the unstructured road 2. In the figure, a dashed line region 1 is front actual information corresponding to the front image information. In fig. 3, the region outside the unstructured road is shown. In the figure 4 is the travelable area. In the figures 5 and 6 are the actual areas corresponding to the defect areas to be identified.
The unstructured roads refer to roads with low structuralization degrees, such as city non-arterial roads, rural streets and the like.
In the application, the vehicle can effectively identify the defect area 5 to be identified in the image, so that the condition that the barrier cannot be identified is avoided; in addition, the vehicle can also effectively identify the defect area 6 to be identified in the map, so that the influence of animals suddenly rushing into the road surface on the driving safety of the vehicle is avoided.
The following describes the technical solution of the embodiment of the present application in detail with reference to the above scenario.
The first embodiment is as follows:
the first embodiment of the present application provides an automatic driving method, which is described in detail below with reference to the accompanying drawings.
Referring to fig. 2, the figure is a flowchart of an automatic driving method according to an embodiment of the present application.
The automatic driving method comprises the following steps:
step 201: and acquiring an actual area corresponding to the defect area to be identified.
Referring to fig. 1, fig. 5 and 6 are actual regions corresponding to defect regions to be identified. The area to be identified is obtained through an image identification technology. Specifically, the defect region to be identified may be obtained by:
s1: acquiring front image information of a vehicle through image acquisition equipment; the front image information is a virtual image corresponding to the front actual information 1.
S2: and performing image processing on the front image information by an image segmentation processing technology to determine a defect area to be identified in the front image information.
And after the defect area to be identified is obtained, determining defect image information corresponding to the defect area to be identified. The defect image information may be obtained by cropping an image corresponding to the defect region to be identified. Further, in conjunction with the defect image information, the actual area corresponding to the defect area to be identified is determined, as shown at 5 and 6 in fig. 1.
After the actual area corresponding to the defect area to be identified is obtained, the actual area corresponding to the defect area to be identified can be processed in the following two processing modes.
The first method comprises the following steps: and judging whether the actual area corresponding to the defect area to be identified is positioned on the drivable area 4.
And eliminating the actual area corresponding to the defect area to be identified on the no-driving area 4. That is, the influence of factors other than the unstructured road 2 on the automatic driving of the vehicle when the vehicle is normally running is not taken into consideration. Therefore, the number of the actual areas corresponding to the defect areas to be identified which are identified at the same time is reduced, and the identification efficiency is further improved. A
And the second method comprises the following steps: and judging whether the actual area corresponding to the defect area to be identified is located in the drivable area or not.
And processing the acquired actual regions corresponding to all the defect regions to be identified to avoid the condition of missing processing or identification, thereby improving the comprehensiveness of identification of the actual regions corresponding to the defect regions to be identified and further improving the safety of the vehicle.
Step 202: and identifying the actual area.
As a possible implementation manner, after the actual region corresponding to the defect region to be identified is determined by the image identification technology, the actual region is further identified by the laser radar technology or the millimeter wave radar technology. Thereby judging whether the actual area corresponding to the defect area to be identified has the obstacle.
It can be understood that whether an obstacle exists in the actual region corresponding to the defect region to be identified is judged in a mode of combining the image and the radar, and therefore the accuracy of judgment is improved.
Step 203: when the identification result of the actual area is a non-known obstacle, determining the type of the non-known obstacle.
After the actual region corresponding to the defect region to be recognized is preliminarily recognized by the image recognition technology and the radar technology, it cannot be determined what obstacle causes the actual region corresponding to the defect region to be recognized, that is, the obstacle is an unknown obstacle.
Thus, in order to ensure the safety of the vehicle traveling, it is also necessary to determine the type of the unknown obstacle.
The type of the unknown obstacle comprises a non-avoidance type and an avoidance type, and the vehicle is controlled to enter different running states according to different types of the unknown obstacle.
Determining the type of the unknown obstacle may be performed by establishing a big data analysis model, analyzing the type of the unknown obstacle, and describing in detail how to establish the big data analysis model and obtaining the type of the unknown obstacle according to the big data analysis model.
As a possible embodiment, the type of the unknown obstacle is determined by inputting the defect image information into a type recognition model; the type recognition model is obtained based on training samples and type training corresponding to the training samples, the training samples comprise historical defect image information, and the historical defect image information is obtained for a historical time period.
The historical defect image information and the type of the unknown obstacle corresponding to the historical defect image information are used. The similar historical defect image information is continuously corrected, so that the accuracy of the type recognition model in recognition is improved.
In addition, the similar historical defective image information may be classified, and it may be determined what object the obstacle corresponding to the classified historical defective image information is specifically. In other words, this step may convert the unknown obstacles into known obstacles, thereby reducing the number of unknown obstacles and increasing the number of known obstacles. The burden of the obstacle recognition model is reduced.
Step 204: and if the type of the unknown obstacle is an avoidance type, indicating the vehicle to carry out avoidance running on the unknown obstacle.
When the unknown obstacle is of an avoidance type, it is explained that the unknown obstacle affects safe traveling of the vehicle. Thus, the vehicle needs to be instructed to avoid the unknown obstacle, so as to avoid a safety accident.
In some embodiments, after determining the type of the unknown obstacle, the method further comprises: and if the type of the unknown obstacle is a non-evasive type, indicating that the vehicle normally runs.
When the type of the unknown obstacle is a non-avoidance type, namely the vehicle can normally run, and the obstacle does not need to be avoided. For example, due to weather, a wind suddenly blows and blows up paper scrap on the ground, causing the location covered by paper scrap to be a defect area to be identified. However, the paper sheet is not recognized through the radar technology, and the vehicle is indicated to normally run after the paper sheet is determined to be of the non-avoidance type through the type analysis model.
In some embodiments, the determining the defect image information of the defect region to be identified according to the front image information includes: determining defect image information corresponding to a defect area to be identified in a drivable area according to the front image information; the travelable area is an area corresponding to the road ahead in the image.
After identifying the actual region, the method further comprises: and when the identification result of the actual area is a non-obstacle, indicating that the vehicle runs in a decelerating way.
It should be noted that some defective areas to be identified may be caused by depressions in the road surface, rather than by obstacles. Therefore, it is only necessary to identify whether or not there is a defective region to be identified in the travelable region, and if the defective region to be identified is a non-obstacle, it is considered that the defective region to be identified is caused by a depression of the road surface. Therefore, the vehicle is indicated to run at a reduced speed, the phenomenon that the vehicle jolts due to the road surface is avoided, and the driving experience is further improved.
Compared with the prior art, the method has the advantages that:
the invention provides an automatic driving method, which comprises the following steps: acquiring an actual area corresponding to a defect area to be identified; identifying the actual area; when the identification result of the actual area is a non-known obstacle, determining the type of the non-known obstacle; and if the type of the unknown obstacle is an avoidance type, indicating the vehicle to carry out avoidance running on the unknown obstacle. The situation that the vehicle cannot effectively avoid the obstacle when an unconventional object cannot be identified is avoided, and the safety of the vehicle in the driving process is improved.
Example two:
the first embodiment of the present application provides an automatic driving method, which is described in detail below with reference to the accompanying drawings.
Referring to fig. 3, the figure is a schematic diagram of an automatic driving system according to an embodiment of the present application.
The system for automatic driving comprises: an area acquisition module 301, a recognition module 302, a type determination module 303, and a processing module 304.
The area obtaining module 301 is configured to obtain an actual area corresponding to a defect area to be identified.
The identification module 302 is configured to identify the actual area.
The type determining module 303 is configured to determine a type of the unknown obstacle when the identification result of the actual area is the unknown obstacle.
The processing module 304 is configured to instruct the vehicle to perform avoidance driving on the unknown obstacle if the type of the unknown obstacle is an avoidance type.
As a possible implementation manner, the processing module 304 is further configured to instruct the vehicle to normally run if the type of the unknown obstacle is a non-avoidance type.
As a possible implementation, the system further comprises: an image acquisition module 305.
The image obtaining module 305 is configured to obtain front image information of the vehicle; and determining the defect image information of the defect area to be identified according to the front image information. The region obtaining module 301 is specifically configured to determine, according to the defect image information, an actual region corresponding to the defect region to be identified.
As a possible implementation manner, the type determining module 303 is specifically configured to determine the type of the unknown obstacle by inputting the defect image information into a type identification model; the type recognition model is obtained based on training samples and type training corresponding to the training samples, the training samples comprise historical defect image information, and the historical defect image information is obtained for a historical time period.
As a possible implementation manner, the image obtaining module 305 is specifically configured to determine, according to the front image information, defect image information corresponding to a defect area to be identified in a travelable area; the travelable area is an area corresponding to the road ahead in the image.
As a possible implementation, the processing module 304 is further configured to instruct the vehicle to run at a reduced speed when the identification result of the actual area is a non-obstacle.
Compared with the prior art, the method has the advantages that:
the invention provides an automatic driving system, which comprises: the device comprises an area acquisition module, an identification module, a type determination module and a processing module; the area acquisition module is used for acquiring an actual area corresponding to the defect area to be identified; the identification module is used for identifying the actual area; the type determining module is used for determining the type of the unknown obstacle when the identification result of the actual area is the unknown obstacle; and the processing module is used for indicating the vehicle to carry out evasive running on the unknown obstacle if the type of the unknown obstacle is an evasive type. The situation that the vehicle cannot effectively avoid the obstacle when an unconventional object cannot be identified is avoided, and the safety of the vehicle in the driving process is improved.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, they are described in a relatively simple manner, and reference may be made to some descriptions of method embodiments for relevant points. The above-described system embodiments are merely illustrative, and the units and modules described as separate components may or may not be physically separate. In addition, some or all of the units and modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
It should be understood that in the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" for describing an association relationship of associated objects, indicating that there may be three relationships, e.g., "a and/or B" may indicate: only A, only B and both A and B are present, wherein A and B may be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of single item(s) or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.
The foregoing is merely a preferred embodiment of the present application and is not intended to limit the present application in any way. Although the present application has been described with reference to the preferred embodiments, it is not intended to limit the present application. Those skilled in the art can now make numerous possible variations and modifications to the disclosed embodiments, or modify equivalent embodiments, using the methods and techniques disclosed above, without departing from the scope of the claimed embodiments. Therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present application still fall within the protection scope of the technical solution of the present application without departing from the content of the technical solution of the present application.
Claims (12)
1. A method of autonomous driving, comprising:
acquiring an actual area corresponding to a defect area to be identified;
identifying the actual area;
when the identification result of the actual area is a non-known obstacle, determining the type of the non-known obstacle;
and if the type of the unknown obstacle is an avoidance type, indicating the vehicle to carry out avoidance running on the unknown obstacle.
2. The method of claim 1, wherein after determining the type of the unknown obstacle, the method further comprises:
and if the type of the unknown obstacle is a non-evasive type, indicating that the vehicle normally runs.
3. The method according to claim 2, wherein before the obtaining of the actual region corresponding to the defect region to be identified, the method further comprises:
acquiring front image information of the vehicle;
determining defect image information of the defect area to be identified according to the front image information;
the acquiring of the actual region corresponding to the defect region to be identified includes:
and determining an actual area corresponding to the defect area to be identified according to the defect image information.
4. The method of claim 3, wherein the determining the type of the unknown obstacle comprises:
determining the type of the unknown obstacle by inputting the defect image information into a type recognition model;
the type recognition model is obtained based on training samples and type training corresponding to the training samples, the training samples comprise historical defect image information, and the historical defect image information is obtained for a historical time period.
5. The method according to claim 3, wherein the determining defect image information of the defect region to be identified from the front image information comprises:
determining defect image information corresponding to a defect area to be identified in a drivable area according to the front image information; the travelable area is an area corresponding to the road ahead in the image.
6. The method of claim 5, wherein after identifying the actual region, the method further comprises:
and when the identification result of the actual area is a non-obstacle, indicating that the vehicle runs in a decelerating way.
7. An autonomous driving system, comprising: the device comprises an area acquisition module, an identification module, a type determination module and a processing module;
the area acquisition module is used for acquiring an actual area corresponding to the defect area to be identified;
the identification module is used for identifying the actual area;
the type determining module is used for determining the type of the unknown obstacle when the identification result of the actual area is the unknown obstacle;
and the processing module is used for indicating the vehicle to carry out evasive running on the unknown obstacle if the type of the unknown obstacle is an evasive type.
8. The system of claim 7, wherein the processing module is further configured to indicate that the vehicle is traveling normally if the type of the unknown obstacle is a non-avoidance type.
9. The system of claim 8, further comprising: an image acquisition module;
the image acquisition module is used for acquiring front image information of the vehicle; determining defect image information of the defect area to be identified according to the front image information;
the area obtaining module is specifically configured to determine an actual area corresponding to the defect area to be identified according to the defect image information.
10. The system according to claim 9, wherein the type determination module is specifically configured to determine the type of the unknown obstacle by inputting the defect image information into a type recognition model; the type recognition model is obtained based on training samples and type training corresponding to the training samples, the training samples comprise historical defect image information, and the historical defect image information is obtained for a historical time period.
11. The system according to claim 9, wherein the image acquisition module is specifically configured to determine, according to the front image information, defect image information corresponding to a defect region to be identified in the drivable region; the travelable area is an area corresponding to the road ahead in the image.
12. The system of claim 11, wherein the processing module is further configured to instruct the vehicle to run at a reduced speed when the identification result of the actual area is a non-obstacle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010384728.4A CN111582173A (en) | 2020-05-08 | 2020-05-08 | Automatic driving method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010384728.4A CN111582173A (en) | 2020-05-08 | 2020-05-08 | Automatic driving method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111582173A true CN111582173A (en) | 2020-08-25 |
Family
ID=72124798
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010384728.4A Pending CN111582173A (en) | 2020-05-08 | 2020-05-08 | Automatic driving method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111582173A (en) |
Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1214656A (en) * | 1996-02-27 | 1999-04-21 | 航空工业有限公司 | Obstacle detection system |
| CN101549683A (en) * | 2009-04-23 | 2009-10-07 | 上海交通大学 | Vehicle intelligent method for automatically identifying road pit or obstruction |
| CN101881615A (en) * | 2010-05-28 | 2010-11-10 | 清华大学 | Method for detecting visual barrier for driving safety |
| CN102265310A (en) * | 2008-10-28 | 2011-11-30 | 俄勒冈健康科学大学 | Method and apparatus for visual field monitoring |
| CN104508726A (en) * | 2012-07-27 | 2015-04-08 | 日产自动车株式会社 | Three-dimensional object detection device, and three-dimensional object detection method |
| CN205186141U (en) * | 2015-12-03 | 2016-04-27 | 成都九十度工业产品设计有限公司 | Car intelligence cruise control system |
| CN106597471A (en) * | 2016-11-08 | 2017-04-26 | 上海禾赛光电科技有限公司 | Vehicle with automatic detection function of transparent barrier and work method thereof |
| CN107571819A (en) * | 2016-07-05 | 2018-01-12 | 奥迪股份公司 | Drive assist system, method and vehicle |
| CN107817798A (en) * | 2017-10-30 | 2018-03-20 | 洛阳中科龙网创新科技有限公司 | A kind of farm machinery barrier-avoiding method based on deep learning system |
| CN108099957A (en) * | 2017-12-14 | 2018-06-01 | 西北铁道电子股份有限公司 | A kind of locomotive shunting method and system based on detection of obstacles with identification |
| CN109291922A (en) * | 2018-09-30 | 2019-02-01 | 东风汽车集团有限公司 | A kind of automatic identification small obstacle and the driving assistance system braked and control method |
| CN109598187A (en) * | 2018-10-15 | 2019-04-09 | 西北铁道电子股份有限公司 | Obstacle recognition method, differentiating obstacle and railcar servomechanism |
| CN109635868A (en) * | 2018-12-10 | 2019-04-16 | 百度在线网络技术（北京）有限公司 | Determination method, apparatus, electronic equipment and the storage medium of barrier classification |
| CN109766851A (en) * | 2019-01-15 | 2019-05-17 | 珠海格力电器股份有限公司 | Determination method and device, the Car reversion image-forming equipment of barrier |
| CN110121740A (en) * | 2017-01-06 | 2019-08-13 | 极光飞行科学公司 | Collision avoidance system and method for unmanned vehicle |
| CN110231825A (en) * | 2019-06-21 | 2019-09-13 | 中国神华能源股份有限公司 | Vehicular intelligent cruising inspection system and method |
| CN110347145A (en) * | 2018-04-03 | 2019-10-18 | 百度（美国）有限责任公司 | Perception for automatic driving vehicle assists |
| CN110412986A (en) * | 2019-08-19 | 2019-11-05 | 中车株洲电力机车有限公司 | A kind of vehicle barrier detection method and system |
| CN110428092A (en) * | 2019-07-15 | 2019-11-08 | 南京邮电大学 | Multi-information fusion method and device, storage medium and terminal |
| CN110696826A (en) * | 2019-10-09 | 2020-01-17 | 北京百度网讯科技有限公司 | Method and device for controlling a vehicle |
-
2020
- 2020-05-08 CN CN202010384728.4A patent/CN111582173A/en active Pending
Patent Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1214656A (en) * | 1996-02-27 | 1999-04-21 | 航空工业有限公司 | Obstacle detection system |
| CN102265310A (en) * | 2008-10-28 | 2011-11-30 | 俄勒冈健康科学大学 | Method and apparatus for visual field monitoring |
| CN101549683A (en) * | 2009-04-23 | 2009-10-07 | 上海交通大学 | Vehicle intelligent method for automatically identifying road pit or obstruction |
| CN101881615A (en) * | 2010-05-28 | 2010-11-10 | 清华大学 | Method for detecting visual barrier for driving safety |
| CN104508726A (en) * | 2012-07-27 | 2015-04-08 | 日产自动车株式会社 | Three-dimensional object detection device, and three-dimensional object detection method |
| CN205186141U (en) * | 2015-12-03 | 2016-04-27 | 成都九十度工业产品设计有限公司 | Car intelligence cruise control system |
| CN107571819A (en) * | 2016-07-05 | 2018-01-12 | 奥迪股份公司 | Drive assist system, method and vehicle |
| CN106597471A (en) * | 2016-11-08 | 2017-04-26 | 上海禾赛光电科技有限公司 | Vehicle with automatic detection function of transparent barrier and work method thereof |
| CN110121740A (en) * | 2017-01-06 | 2019-08-13 | 极光飞行科学公司 | Collision avoidance system and method for unmanned vehicle |
| CN107817798A (en) * | 2017-10-30 | 2018-03-20 | 洛阳中科龙网创新科技有限公司 | A kind of farm machinery barrier-avoiding method based on deep learning system |
| CN108099957A (en) * | 2017-12-14 | 2018-06-01 | 西北铁道电子股份有限公司 | A kind of locomotive shunting method and system based on detection of obstacles with identification |
| CN110347145A (en) * | 2018-04-03 | 2019-10-18 | 百度（美国）有限责任公司 | Perception for automatic driving vehicle assists |
| CN109291922A (en) * | 2018-09-30 | 2019-02-01 | 东风汽车集团有限公司 | A kind of automatic identification small obstacle and the driving assistance system braked and control method |
| CN109598187A (en) * | 2018-10-15 | 2019-04-09 | 西北铁道电子股份有限公司 | Obstacle recognition method, differentiating obstacle and railcar servomechanism |
| CN109635868A (en) * | 2018-12-10 | 2019-04-16 | 百度在线网络技术（北京）有限公司 | Determination method, apparatus, electronic equipment and the storage medium of barrier classification |
| CN109766851A (en) * | 2019-01-15 | 2019-05-17 | 珠海格力电器股份有限公司 | Determination method and device, the Car reversion image-forming equipment of barrier |
| CN110231825A (en) * | 2019-06-21 | 2019-09-13 | 中国神华能源股份有限公司 | Vehicular intelligent cruising inspection system and method |
| CN110428092A (en) * | 2019-07-15 | 2019-11-08 | 南京邮电大学 | Multi-information fusion method and device, storage medium and terminal |
| CN110412986A (en) * | 2019-08-19 | 2019-11-05 | 中车株洲电力机车有限公司 | A kind of vehicle barrier detection method and system |
| CN110696826A (en) * | 2019-10-09 | 2020-01-17 | 北京百度网讯科技有限公司 | Method and device for controlling a vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107346612B (en) | Vehicle anti-collision method and system based on Internet of vehicles | |
| Nienaber et al. | Detecting potholes using simple image processing techniques and real-world footage | |
| US20210350149A1 (en) | Lane detection method and apparatus,lane detection device,and movable platform | |
| CN111815959B (en) | Vehicle violation detection method and device and computer readable storage medium | |
| EP2570963A2 (en) | Systems, devices, and methods for recognizing objects as perceived from a vehicle | |
| US9842283B2 (en) | Target object detection system and a method for target object detection | |
| CN110458050B (en) | Vehicle cut-in detection method and device based on vehicle-mounted video | |
| CN112287910B (en) | Road abnormal area detection method, road abnormal area detection device, electronic equipment and storage medium | |
| CN112232314A (en) | Vehicle control method and device for target detection based on deep learning | |
| CN112793567A (en) | Driving assistance method and system based on road condition detection | |
| CN114743181A (en) | Road vehicle target detection method and system, electronic device and storage medium | |
| CN111967384A (en) | Vehicle information processing method, device, equipment and computer readable storage medium | |
| CN113740874A (en) | Road edge detection method, electronic equipment and vehicle | |
| CN115782905A (en) | Automatic driving vehicle driving safety degree quantification system | |
| CN113432615B (en) | Detection method and system based on multi-sensor fusion drivable area and vehicle | |
| CN114915646A (en) | Data grading uploading method and device for unmanned mine car | |
| CN111157994A (en) | Sensing algorithm of millimeter wave radar | |
| CN114445798A (en) | Urban road parking space identification method and system based on deep learning | |
| CN111145554B (en) | Scene positioning method and device based on automatic driving AEB | |
| CN111582173A (en) | Automatic driving method and system | |
| CN112346080A (en) | Self-adaptive obstacle avoidance method based on single-line laser radar | |
| KR102105007B1 (en) | Edge-cloud system for collecting and providing data of connected car | |
| WO2022267266A1 (en) | Vehicle control method based on visual recognition, and device | |
| CN113611008B (en) | Vehicle driving scene acquisition method, device, equipment and medium | |
| CN114446057A (en) | Accident high-incidence point identification early warning method and system based on intelligent network connection environment |
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 |