CN112528710B - Road surface detection method and device, electronic equipment and storage medium - Google Patents
Road surface detection method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112528710B CN112528710B CN201910884186.4A CN201910884186A CN112528710B CN 112528710 B CN112528710 B CN 112528710B CN 201910884186 A CN201910884186 A CN 201910884186A CN 112528710 B CN112528710 B CN 112528710B
- Authority
- CN
- China
- Prior art keywords
- region
- vehicle
- area
- undulating
- data points
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 25
- 238000005096 rolling process Methods 0.000 claims abstract description 7
- 238000000034 method Methods 0.000 claims description 22
- 238000012545 processing Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 12
- 238000013135 deep learning Methods 0.000 claims description 9
- 238000013527 convolutional neural network Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 4
- 230000004044 response Effects 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 239000003897 fog Substances 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/91—Radar or analogous systems specially adapted for specific applications for traffic control
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Multimedia (AREA)
- Electromagnetism (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Traffic Control Systems (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention provides a pavement detection method, a pavement detection device, electronic equipment and a storage medium, wherein the pavement detection method comprises the following steps: s1: detecting road surface information of the advancing direction of the vehicle in real time through a radar arranged on the vehicle, obtaining data points, and constructing a three-dimensional model according to the data points; s2: judging whether a rolling area exists in a first area in the vehicle advancing direction according to the three-dimensional model; s3: and when the judgment result of the step S2 is yes and the undulating region enters a second region in the vehicle advancing direction, extracting data point information of the undulating region, identifying the undulating region through a preset algorithm, and marking the undulating region, wherein the distance from the first region to the vehicle is larger than the distance from the second region to the vehicle. After the scheme is adopted, the accuracy of road surface detection is improved, the missing report rate and the false report rate are reduced to a great extent, and sufficient time is reserved for vehicle response.
Description
Technical Field
The present invention relates to the field of vehicle technologies, and in particular, to a method and apparatus for detecting a road surface, an electronic device, and a storage medium.
Background
With the development of unmanned technologies, a road surface detection technology has emerged, which guides the running of an unmanned vehicle by detecting the condition of the road surface.
In the prior art, the road surface detection technology is mainly based on a laser radar, and road surface fluctuation information is obtained by analyzing the vertical height and the horizontal distance of a laser radar scanning point relative to the laser radar.
However, the laser radar is greatly affected by weather, and is easy to have the problems of false alarm, false alarm and untimely alarm, and meanwhile, the prior art only mentions that the road surface fluctuation condition is detected, but the road condition that a vehicle can pass through and the vehicle can not pass through is not marked, and a mechanism for pre-judging the road condition in front is not mentionedby not mentioning, so that sufficient time can not be reserved for vehicle response.
Therefore, there is a need to develop a method, apparatus, electronic device, and storage medium for road surface detection with high road surface detection accuracy, low false alarm rate and false alarm rate, and sufficient vehicle response time.
Disclosure of Invention
In order to overcome the technical defects, the invention aims to provide a pavement detection method, a device, electronic equipment and a storage medium, wherein the pavement detection method is high in pavement detection accuracy, low in missing report rate and false report rate and sufficient in vehicle response time.
The invention discloses a pavement detection method, which comprises the following steps:
s1: detecting road surface information of the advancing direction of the vehicle in real time through a radar arranged on the vehicle, obtaining data points, and constructing a three-dimensional model according to the data points;
s2: judging whether a rolling area exists in a first area in the vehicle advancing direction according to the three-dimensional model;
s3: and when the judgment result of the step S2 is yes and the undulating region enters a second region in the vehicle advancing direction, extracting data point information of the undulating region, identifying the undulating region through a preset algorithm, and marking the undulating region, wherein the distance from the first region to the vehicle is larger than the distance from the second region to the vehicle.
Preferably, the radar is a millimeter wave radar, and the data points include distance information and angle information.
Preferably, in said step S2,
judging whether a fluctuation area exists in the first area according to the distribution condition of the data points in the three-dimensional model of the first area.
Preferably, the undulating region is identified and marked by a predetermined algorithm, including,
analyzing and processing the extracted data point information of the undulating region through a preset deep learning algorithm, and outputting a marking result of the undulating region, wherein the marking result comprises a normal passing region, a speed-down passing region and an unviable region.
Preferably, the deep learning algorithm is obtained by training the convolutional neural network by inputting data point samples of the undulating region and corresponding labeling results.
Preferably, the step S3 further comprises,
s4: when the undulating region identified in the step S3 enters a third region in the vehicle advancing direction, extracting data point information of the undulating region, identifying the undulating region through a preset algorithm, and marking the undulating region, wherein the distance from the second region to the vehicle is greater than the distance from the third region to the vehicle;
and controlling the vehicle to run according to the marking result.
Preferably, the first region is a region in the range of 70-150 meters in front of the vehicle, the second region is a region in the range of 40-70 meters in front of the vehicle, and the third region is a region in the range of 0-40 meters in front of the vehicle.
The invention also discloses a road surface detection device, which comprises,
the modeling unit is used for detecting the pavement information of the advancing direction of the vehicle in real time through a radar installed on the vehicle, obtaining data points and constructing a three-dimensional model according to the data points;
the judging unit is used for judging whether a fluctuation area exists in a first area in the vehicle advancing direction according to the three-dimensional model;
and the identification marking unit is used for extracting data point information of the undulating region when the judging result of the judging unit is yes and the undulating region enters a second region in the vehicle advancing direction, identifying the undulating region through a preset algorithm and marking the undulating region, wherein the distance from the first region to the vehicle is larger than the distance from the second region to the vehicle.
The invention also discloses an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps of the method when executing the computer program.
The invention also discloses a computer readable storage medium having stored thereon a computer program which when executed by a processor realizes the steps of the above method.
After the technical scheme is adopted, compared with the prior art, the invention has the beneficial effects that:
1. the road conditions in front are pre-judged firstly through regional detection, then the road conditions are further identified and marked, the accuracy of road surface detection is improved, the rate of missing report and the rate of false report are reduced to a great extent, and sufficient time is reserved for vehicle response.
2. The millimeter wave radar is adopted to detect the road surface, so that the system cost is reduced to the greatest extent, and the influence of weather change on radar detection is reduced.
3. The vehicle can normally pass through the area, the vehicle needs to pass through the area at a reduced speed, and the vehicle can not pass through the area for marking, so that the comfort level of the vehicle in the running process is improved, the vehicle chassis is protected, and the running safety of the vehicle is improved.
Drawings
FIG. 1 is a flow chart of a method of road surface detection according to an embodiment of the invention;
FIG. 2 is a schematic illustration of a radar in a vehicle position according to an embodiment of the present invention;
fig. 3 is a schematic view of different regions in a forward direction of a vehicle according to an embodiment of the invention.
Reference numerals:
1-vehicle, 2-first radar, 3-second radar, 4-private CAN bus, 5-vehicle CAN bus, 6-first area, 7-second area, 8-third area
Detailed Description
Advantages of the invention are further illustrated in the following description, taken in conjunction with the accompanying drawings and detailed description.
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as detailed in the accompanying claims.
The terminology used in the present disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. As used in this disclosure and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.
It should be understood that although the terms first, second, third, etc. may be used in this disclosure to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present disclosure. The word "if" as used herein may be interpreted as "at … …" or "at … …" or "responsive to a determination", depending on the context.
In the description of the present invention, it should be understood that the terms "longitudinal," "transverse," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like indicate orientations or positional relationships based on the orientation or positional relationships shown in the drawings, merely to facilitate describing the present invention and simplify the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the present invention.
In the description of the present invention, unless otherwise specified and defined, it should be noted that the terms "mounted," "connected," and "coupled" are to be construed broadly, and may be, for example, mechanical or electrical, or may be in communication with each other between two elements, directly or indirectly through intermediaries, as would be understood by those skilled in the art, in view of the specific meaning of the terms described above.
In the following description, suffixes such as "module", "component", or "unit" for representing elements are used only for facilitating the description of the present invention, and are not of specific significance per se. Thus, "module" and "component" may be used in combination.
Referring to fig. 1, a flowchart of a method for detecting a road surface according to an embodiment of the present invention includes the following steps:
s1: and detecting the pavement information of the advancing direction of the vehicle in real time through a radar installed on the vehicle, obtaining data points, and constructing a three-dimensional model according to the data points.
The vehicle may be an automobile, preferably an unmanned automobile. The radar is installed on the vehicle and is used for detecting the road surface in the advancing direction of the vehicle. The number of the radars can be one or a plurality of. When the radar is one, it is preferably provided at an intermediate position in the front of the vehicle. Referring to fig. 2, in the present embodiment, the radars are two, a first radar 2 and a second radar 3 respectively provided on left and right sides of the front of the vehicle 1. The first radar 2 and the second radar 3 are millimeter wave radars, the millimeter wave has strong capability of penetrating fog, smoke and dust, and then compared with a laser radar, the millimeter wave radars have the characteristics of all weather (except for heavy rainy days) all day, are little affected by weather, and have low cost and good economical efficiency. The first radar 2 and the second radar 3 communicate with each other through a private CAN bus 4, and the second radar 3 (and/or the first radar 2) communicates with a central control system of the vehicle through a vehicle CAN bus 5. In other embodiments, the radar may also be a lidar.
In the present embodiment, a millimeter wave radar provided at the front of a vehicle transmits and receives radar waves to the road surface in the forward direction of the vehicle in real time through an antenna, and a large number of data points including distance information and angle information are obtained. The range information may be obtained by calculating the time of flight of the radar wave, multiplied by the speed of light, and divided by 2. The angle information can be obtained by calculating the phase difference of radar waves reflected by the same target received by parallel receiving antennas. Further, a three-dimensional model of the vehicle forward direction road surface can be constructed from the data points. Preferably, constructing the three-dimensional modeling is achieved mainly by means of the imaging function of the millimeter wave radar.
The radar installed on the vehicle continuously transmits and receives radar waves to obtain a large number of data points, the data points are continuously updated along with the running of the vehicle, and correspondingly, the three-dimensional model of the road surface in the running direction of the vehicle constructed according to the data points is also continuously updated.
Preferably, before the step S1, a step of radar self-checking is further included, where the step S1 and the subsequent steps are performed in the case that the radar self-checking has no fault.
S2: judging whether a rolling area exists in a first area in the vehicle advancing direction according to the three-dimensional model;
the first region is a region within a preset range in the vehicle advancing direction. Specifically, the radar may be divided into different areas according to the detection range of the radar in the vehicle forward direction. In some embodiments, two regions are divided in the vehicle forward direction, a first region being a region farther from the vehicle and a second region being a region nearer to the vehicle, the first region being a greater distance from the vehicle than the second region, preferably the first region being a region in the range of 60-150 meters from the vehicle in the vehicle forward direction and the first region being a region in the range of 0-60 meters from the vehicle in the vehicle forward direction. Referring to fig. 3, in the present embodiment, three regions are divided in the forward direction of the vehicle 1, the first region 6 is a region farther from the vehicle 1, the second region 7 is a region at a medium distance from the vehicle 1, the third region 8 is a region closer to the vehicle 1, the distance from the first region 7 to the vehicle 1 is greater than the distance from the second region 7 to the vehicle 1, the distance from the second region 7 to the vehicle 1 is greater than the distance from the third region 8 to the vehicle 1, preferably, the first region 6 is a region in the range of 70 to 150 m from the vehicle in the forward direction of the vehicle, the second region 7 is a region in the range of 40 to 70 m from the vehicle in the forward direction of the vehicle, and the third region 8 is a region in the range of 0 to 40 m from the vehicle in the forward direction of the vehicle.
Judging whether a fluctuation area exists in the first area according to the distribution condition of the data points in the three-dimensional model of the first area. The undulating region is a region that is raised and/or recessed relative to the road surface. Specifically, whether the undulating region exists or not can be judged by comparing the distribution condition of the data points in the three-dimensional model of the first region with the distribution condition of the data points of the standard horizontal road surface through a processing module of the millimeter wave radar or a processing module in the vehicle control system. When undulating regions are present, the distribution of the undulating region data points, such as the concentration of data points, is significantly different from a horizontal road surface. Further, the degree of protrusion or depression of the undulating region can be determined according to the distance information contained in the data points of the undulating region, and when the degree of protrusion or depression exceeds the preset range, the region is determined to be the undulating region. The processing module can be a single chip microcomputer. The data point distribution of a standard horizontal road surface can be pre-stored in the processing module.
S3: and when the judgment result of the step S2 is yes and the undulating region enters a second region in the vehicle advancing direction, extracting data point information of the undulating region, identifying the undulating region through a preset algorithm, and marking the undulating region, wherein the distance from the first region to the vehicle is larger than the distance from the second region to the vehicle. Preferably, the radar is a millimeter wave radar, and the data points include distance information and angle information.
When it is determined in step S2 that the undulating region exists in the first region, and when the undulating region enters the second region as the vehicle travels, extracting data point information of the undulating region in the second region, analyzing and processing the extracted data point information of the undulating region through a preset deep learning algorithm, and outputting a marking result of the undulating region, wherein the marking result comprises a normal traffic region, a deceleration traffic region and an unvented region. The deep learning algorithm is obtained by inputting a large number of data point samples of the fluctuation area and corresponding marking results into the convolutional neural network for training, the convolutional neural network is trained to obtain corresponding marking information according to the data point information by inputting a large number of data point samples of the fluctuation area and corresponding marking results into the convolutional neural network, and the corresponding deep learning algorithm and parameters are obtained by a large number of training. And according to the obtained deep learning algorithm, analyzing and processing the extracted data point information of the fluctuation region, and outputting a corresponding marking result. The normal passing area is an area with small fluctuation and small influence on the vehicle, and the vehicle can normally pass through without any treatment; the speed-reducing passing area is an area with small fluctuation and certain influence on the vehicle, and the vehicle can safely pass through the speed-reducing area; the non-passable area is an area where the vehicle is in danger of passing through and needs to be avoided because of large heave. Preferably, in step S3, the distribution of the data points in the three-dimensional model of the second region is compared with the distribution of the data points of the standard horizontal road surface, and whether or not there is a undulating region is determined, that is, whether or not there is another undulating region in addition to the undulating region determined in the first region is determined.
Because the second area is closer to the vehicle, the detection precision of the radar is higher, and the obtained data point information is more accurate, the identification marking of the undulating area in the second area through the preset algorithm can obtain more accurate results. Meanwhile, through regional division, the first region is judged in advance, and then the second region is identified with the mark, so that the rate of missing report and false report can be effectively reduced, and sufficient time is reserved for vehicle response.
In some embodiments, only two regions are divided in the vehicle forward direction, the first region being a region farther from the vehicle and the second region being a region closer to the vehicle. After the mark of the undulating region is obtained in the step S3, the vehicle is guided to run according to the mark information, namely, the vehicle is controlled to normally pass through the marked normal passing region, the vehicle is slowed down to pass through the marked slowing-down passing region, and the marked non-passable region is avoided.
In the present embodiment, three regions (the first region 6, the second region 7, and the third region 8) are divided in the forward direction of the vehicle 1, and in order to further improve the recognition accuracy, the following steps are further included in step S3:
s4: and when the undulating region identified in the step S3 enters a third region in the vehicle advancing direction, extracting data point information of the undulating region, identifying the undulating region through a preset algorithm, and marking the undulating region, wherein the distance from the second region to the vehicle is larger than the distance from the third region to the vehicle.
The undulating region identified in step S3 may refer to an undulating region determined in the first region, or may refer to an undulating region determined in the second region (i.e., an undulating region other than the undulating region in the first region). And extracting data point information of the undulating region in the third region, analyzing and processing the extracted data point information of the undulating region through a preset deep learning algorithm, and outputting a marking result of the undulating region, wherein the marking result comprises a normal passing region, a speed-down passing region and an unviable region. This step is similar to step S3 and will not be described again here.
And the identification mark is carried out on the undulating region in the third region, and the result of the identification mark of the second region is further calibrated, so that the detection accuracy is further improved. Further, according to the marking result in the step S4, the vehicle is guided to run, that is, the vehicle is controlled to normally pass through the marked normal traffic area, and the vehicle is slowed down to pass through the marked speed-down traffic area, so as to avoid the marked non-passable area. In this way, the comfort level of the vehicle in the running process is improved, the chassis of the vehicle is protected, and the running safety of the vehicle is improved.
The invention also discloses a road surface detection device, which comprises,
the modeling unit is used for detecting the pavement information of the advancing direction of the vehicle in real time through a radar installed on the vehicle, obtaining data points and constructing a three-dimensional model according to the data points;
the judging unit is used for judging whether a fluctuation area exists in a first area in the vehicle advancing direction according to the three-dimensional model;
and the identification marking unit is used for extracting data point information of the undulating region when the judging result of the judging unit is yes and the undulating region enters a second region in the vehicle advancing direction, identifying the undulating region through a preset algorithm and marking the undulating region, wherein the distance from the first region to the vehicle is larger than the distance from the second region to the vehicle.
Preferably, the device of the present invention further comprises:
and the identification mark calibration unit is used for extracting data point information of the undulating region when the undulating region identified in the second region enters a third region in the vehicle advancing direction, identifying the undulating region through a preset algorithm and marking the undulating region, wherein the distance from the second region to the vehicle is larger than the distance from the third region to the vehicle.
And the control unit is used for controlling the vehicle to run according to the marking result.
The invention also discloses an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps of the method when executing the computer program. The electronic device is preferably a vehicle-mounted computer.
The processor may include one or more processing cores. The processor uses various interfaces and lines to connect various portions of the overall intelligent terminal, and performs various functions of the electronic device and processes data by running or executing computer programs (including instructions, programs, code sets or instruction sets, etc.) stored in the memory, and invoking data stored in the memory. Alternatively, the processor may be implemented in hardware in at least one of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), programmable logic array (Programmable Logic Array, PLA). The processor may integrate one or a combination of several of a central processing unit (Central Processing Unit, CPU), an image processor (Graphics Processing Unit, GPU), and a modem etc. The CPU mainly processes an operating system, a user interface, an application program and the like, and the GPU is used for rendering and drawing contents required to be displayed on the screen.
The Memory may include random access Memory (Random Access Memory, RAM) or Read-Only Memory (rom). Optionally, the memory includes a non-transitory computer readable medium (non-transitory computer-readable storage medium). The memory may be used to store a computer program (including instructions, programs, code, sets of codes or instructions, etc.).
The invention also discloses a computer readable storage medium having stored thereon a computer program which when executed by a processor realizes the steps of the above method.
The computer readable storage medium may be various types of storage media, optionally non-transitory storage media. The computer readable storage medium may be selected from a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, etc. which may store the program code.
It should be noted that the embodiments of the present invention are preferred and not limited in any way, and any person skilled in the art may make use of the above-disclosed technical content to change or modify the same into equivalent effective embodiments without departing from the technical scope of the present invention, and any modification or equivalent change and modification of the above-described embodiments according to the technical substance of the present invention still falls within the scope of the technical scope of the present invention.
Claims (8)
1. A method of road surface detection comprising:
s1: detecting road surface information of the advancing direction of the vehicle in real time through a radar arranged on the vehicle, obtaining data points, and constructing a three-dimensional model according to the data points;
s2: judging whether a rolling area exists in a first area in the vehicle advancing direction according to the three-dimensional model;
s3: when the judgment result of the step S2 is yes and the undulating region enters a second region in the vehicle advancing direction, extracting data point information of the undulating region, identifying the undulating region through a preset algorithm, and marking the undulating region, wherein the distance from the first region to the vehicle is larger than the distance from the second region to the vehicle;
in step S3, comparing the distribution of the data points in the three-dimensional model of the second area with the distribution of the data points of the standard horizontal road surface, and judging whether there is a rolling area, that is, judging whether there is other rolling area except the rolling area judged in the first area; the step S3 may be followed by a further step,
s4: when the undulating region identified in the step S3 enters a third region in the vehicle advancing direction, extracting data point information of the undulating region, identifying the undulating region through a preset algorithm, and marking the undulating region, wherein the distance from the second region to the vehicle is greater than the distance from the third region to the vehicle; controlling the vehicle to run according to the marking result;
the radar is a millimeter wave radar, and the data points comprise distance information and angle information.
2. The method of claim 1, wherein,
in the step S2 of the process described above,
judging whether a fluctuation area exists in the first area according to the distribution condition of the data points in the three-dimensional model of the first area.
3. The method of claim 2, wherein,
identifying and marking the undulating region by a predetermined algorithm, including,
analyzing and processing the extracted data point information of the undulating region through a preset deep learning algorithm, and outputting a marking result of the undulating region, wherein the marking result comprises a normal passing region, a speed-down passing region and an unviable region.
4. The method of claim 3, wherein,
the deep learning algorithm is obtained by training a data point sample of a fluctuation area and a corresponding marking result input to the convolutional neural network.
5. The method of claim 1, wherein,
the first area is an area in the range of 70-150 meters in front of the vehicle, the second area is an area in the range of 40-70 meters in front of the vehicle, and the third area is an area in the range of 0-40 meters in front of the vehicle.
6. A road surface detection device is characterized by comprising,
the modeling unit is used for detecting the pavement information of the advancing direction of the vehicle in real time through a radar installed on the vehicle, obtaining data points and constructing a three-dimensional model according to the data points; the radar is a millimeter wave radar, and the data points comprise distance information and angle information;
the judging unit is used for judging whether a fluctuation area exists in a first area in the vehicle advancing direction according to the three-dimensional model; comparing the distribution condition of the data points in the three-dimensional model of the second area with the distribution condition of the data points of the standard horizontal pavement, judging whether a fluctuation area exists or not, namely judging whether other fluctuation areas exist besides the fluctuation area judged in the first area or not;
the identification marking unit is used for extracting data point information of the undulating region when the judging result of the judging unit is yes and the undulating region enters a second region in the vehicle advancing direction, identifying the undulating region through a preset algorithm and marking the undulating region, wherein the distance from the first region to the vehicle is larger than the distance from the second region to the vehicle; the method comprises the steps that when the recognized undulating region enters a third region in the vehicle advancing direction, data point information of the undulating region is extracted, the undulating region is recognized through a preset algorithm, and the undulating region is marked, wherein the distance from the second region to the vehicle is larger than the distance from the third region to the vehicle; and controlling the vehicle to run according to the marking result.
7. An electronic device comprising a memory and a processor, said memory storing a computer program, characterized in that,
the processor, when executing the computer program, implements the steps of the method of any one of claims 1 to 5.
8. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910884186.4A CN112528710B (en) | 2019-09-19 | 2019-09-19 | Road surface detection method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910884186.4A CN112528710B (en) | 2019-09-19 | 2019-09-19 | Road surface detection method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112528710A CN112528710A (en) | 2021-03-19 |
| CN112528710B true CN112528710B (en) | 2024-04-09 |
Family
ID=74975282
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910884186.4A Active CN112528710B (en) | 2019-09-19 | 2019-09-19 | Road surface detection method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112528710B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118587904B (en) * | 2024-08-05 | 2024-12-03 | 视缘(上海)交通科技有限公司 | Vehicle-road cooperation method, system, terminal and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB201321179D0 (en) * | 2013-12-02 | 2014-01-15 | Daimler Ag | Device and method to derive optimum speed of vehicle for comfortable ride |
| WO2018007079A1 (en) * | 2016-07-08 | 2018-01-11 | Jaguar Land Rover Limited | Improvements in vehicle speed control |
| CN108099897A (en) * | 2017-11-17 | 2018-06-01 | 浙江吉利汽车研究院有限公司 | Cruise control method, apparatus and system |
| CN108604415A (en) * | 2016-01-22 | 2018-09-28 | 日产自动车株式会社 | The determination method and decision maker of pedestrian |
| CN109615649A (en) * | 2018-10-31 | 2019-04-12 | 阿里巴巴集团控股有限公司 | A kind of image labeling method, apparatus and system |
| CN109826074A (en) * | 2019-02-22 | 2019-05-31 | 三一汽车制造有限公司 | The safety traffic method and road roller of road roller |
| CN110008941A (en) * | 2019-06-05 | 2019-07-12 | 长沙智能驾驶研究院有限公司 | Driving area detection method, device, computer equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10160447B2 (en) * | 2015-10-20 | 2018-12-25 | Ford Global Technologies, Llc | Systems and methods for abrupt road change assist and active suspension control |
-
2019
- 2019-09-19 CN CN201910884186.4A patent/CN112528710B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB201321179D0 (en) * | 2013-12-02 | 2014-01-15 | Daimler Ag | Device and method to derive optimum speed of vehicle for comfortable ride |
| CN108604415A (en) * | 2016-01-22 | 2018-09-28 | 日产自动车株式会社 | The determination method and decision maker of pedestrian |
| WO2018007079A1 (en) * | 2016-07-08 | 2018-01-11 | Jaguar Land Rover Limited | Improvements in vehicle speed control |
| CN108099897A (en) * | 2017-11-17 | 2018-06-01 | 浙江吉利汽车研究院有限公司 | Cruise control method, apparatus and system |
| CN109615649A (en) * | 2018-10-31 | 2019-04-12 | 阿里巴巴集团控股有限公司 | A kind of image labeling method, apparatus and system |
| CN109826074A (en) * | 2019-02-22 | 2019-05-31 | 三一汽车制造有限公司 | The safety traffic method and road roller of road roller |
| CN110008941A (en) * | 2019-06-05 | 2019-07-12 | 长沙智能驾驶研究院有限公司 | Driving area detection method, device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112528710A (en) | 2021-03-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109817021B (en) | Method and device for avoiding traffic participants in roadside blind areas of laser radar | |
| CN109254289B (en) | Detection method and detection equipment for road guardrail | |
| US10032085B2 (en) | Method and system to identify traffic lights by an autonomous vehicle | |
| JP7222879B2 (en) | Transportation hazard early warning methods, devices, equipment and media | |
| US8184159B2 (en) | Forward looking sensor system | |
| JP6166294B2 (en) | Automatic driving system, automatic driving method and computing device | |
| US20190087667A1 (en) | A device and a method for distinguishing between traversable and nontraversable objects | |
| CN109219760B (en) | Method for detecting at least one parking space for a vehicle | |
| JP2022024741A (en) | Vehicle control device and vehicle control method | |
| JP2016115334A (en) | Method and system for adaptive ray-based scene analysis of semantic traffic spaces, and vehicle equipped with such system | |
| US20150220795A1 (en) | Method and device for recognizing traffic signs for a vehicle | |
| CN111742235B (en) | Method and system for identifying an empty parking space suitable for a vehicle | |
| CN111284501B (en) | Device and method for managing running model based on object recognition, and vehicle running control device using the device | |
| CN111638520A (en) | Obstacle recognition method, obstacle recognition device, electronic device and storage medium | |
| US12228943B2 (en) | Object identification for autonomous road vehicles | |
| CN111508276A (en) | High-precision map-based V2X reverse overtaking early warning method, system and medium | |
| CN113787997B (en) | Emergency braking control method, electronic device, and storage medium | |
| CN110703770A (en) | Method and device for controlling automatic running of track inspection vehicle | |
| KR101687094B1 (en) | Apparatus for recognizing traffic sign and method thereof | |
| CN112528710B (en) | Road surface detection method and device, electronic equipment and storage medium | |
| CN111352111B (en) | Positioning and/or classifying objects | |
| KR102087046B1 (en) | Method and apparatus for providing information of a blind spot based on a lane using local dynamic map in autonomous vehicle | |
| CN115805865A (en) | Heavy-duty car blind area early warning method, device, equipment and storage medium | |
| KR20210114530A (en) | How to determine a confidence score for a target around a vehicle | |
| CN110095776B (en) | Method for determining the presence and/or the characteristics of an object and surrounding identification device |
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 |