CN112348000A - Obstacle recognition method, device, system and storage medium - Google Patents
Obstacle recognition method, device, system and storage medium Download PDFInfo
- Publication number
- CN112348000A CN112348000A CN202110016671.7A CN202110016671A CN112348000A CN 112348000 A CN112348000 A CN 112348000A CN 202110016671 A CN202110016671 A CN 202110016671A CN 112348000 A CN112348000 A CN 112348000A
- Authority
- CN
- China
- Prior art keywords
- detection
- area
- clustering
- overlapped
- 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
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The application relates to a method, a device, a system and a storage medium for identifying obstacles, belonging to the technical field of image processing, wherein the method comprises the following steps: acquiring a plurality of groups of point cloud data in a preset region of interest; carrying out region division on each group of point cloud data in the preset region of interest in an effective detection range to obtain a plurality of mutually overlapped detection regions; carrying out Euclidean clustering on the point clouds in the detection areas to obtain clustering results in the detection areas; and fusing the clustering results in each detection area to obtain an obstacle identification result. The problem that the target barrier cannot be accurately identified by the existing barrier identification algorithm can be solved.
Description
Technical Field
The application relates to an obstacle identification method, an obstacle identification device, an obstacle identification system and a storage medium, and belongs to the technical field of image processing.
Background
The unmanned vehicle is a novel intelligent vehicle, and is characterized in that each part of the vehicle is accurately controlled, calculated and analyzed through a control device (namely, a vehicle-mounted intelligent brain), and finally different devices in the unmanned vehicle are respectively controlled by sending instructions to an Electronic Control Unit (ECU), so that the full-automatic operation of the vehicle is realized, and the purpose of unmanned driving of the vehicle is achieved. The unmanned vehicle is provided with an obstacle avoidance system, and the obstacle is detected and identified, so that the unmanned vehicle can effectively avoid the obstacle to run.
In the prior art, for detecting an obstacle, the obstacle is scanned by a laser radar to obtain point cloud data of the obstacle, and the target position of the obstacle is detected by a Euclidean clustering method. The point cloud data obtained by laser radar sampling has the characteristics of dense point cloud at a near position and sparse point cloud at a far position. The principle of Euclidean clustering is that neighbor searching is carried out through KDTree to obtain k points nearest to the current point, and if the distance between the searched points and the current point is smaller than a set threshold value, the points are classified into the same class.
However, due to the characteristic that the point cloud is close and far, when the point cloud data is clustered, if the clustering threshold is set to be too small, objects at a distance cannot be clustered into the same class; if the clustering threshold is set too large, multiple nearby objects can be clustered into one object, and even if different clustering thresholds are set for different distances to perform segmented clustering, the problem that multiple cross-region targets are clustered can be caused.
Disclosure of Invention
The application provides a method, a device, a system and a storage medium for identifying obstacles, which can solve the problem that the existing obstacle identification algorithm can not accurately identify target obstacles.
The application provides the following technical scheme:
in a first aspect of embodiments of the present application, a method for identifying an obstacle is provided, where the method includes:
acquiring a plurality of groups of point cloud data in a preset detection range;
performing area division on each group of point cloud data in the preset detection range in the corresponding detection range to obtain a plurality of overlapped detection areas;
carrying out Euclidean clustering on the point clouds in the detection areas to obtain clustering results in the detection areas;
and fusing the clustering results in each detection area to obtain an obstacle identification result.
In a second aspect of the embodiments of the present application, there is provided an obstacle recognition apparatus for an autonomous vehicle, the apparatus including:
the data acquisition module is used for acquiring a plurality of groups of point cloud data in a preset detection range;
the region dividing module is used for performing region division on each group of point cloud data in the preset detection range in the corresponding detection range to obtain a plurality of overlapped detection regions;
the cluster analysis module is used for carrying out Euclidean clustering on the point clouds in the detection areas to obtain clustering results in the detection areas;
and the identification module is used for fusing the clustering results in each detection area to obtain an obstacle identification result.
In a third aspect of the embodiments of the present application, there is provided an obstacle identification system, where the system includes a processor and a memory, where the memory stores a computer program, and the computer program is loaded and executed by the processor to implement the obstacle identification method according to the first aspect of the embodiments of the present application.
In a fourth aspect of the embodiments of the present application, a computer-readable storage medium is provided, in which a computer program is stored, and the computer program, when being executed by a processor, is configured to implement the obstacle identification method according to embodiment 1 of the present application.
The beneficial effect of this application lies in: according to the embodiment of the application, by dividing the overlapped detection areas, the clustered target profiles in each detection area are finally fused according to the overlapped area sizes, the problem that the distance threshold values of the near and far positions cannot be unified due to global clustering is solved, the problem that the segmented clustering cross-area targets are split is also solved, a better clustering effect is achieved, and the target obstacles are accurately identified.
The foregoing description is only an overview of the technical solutions of the present application, and in order to make the technical solutions of the present application more clear and clear, and to implement the technical solutions according to the content of the description, the following detailed description is made with reference to the preferred embodiments of the present application and the accompanying drawings.
Drawings
Fig. 1 is a schematic structural diagram of an obstacle recognition system according to an embodiment of the present application;
fig. 2 is a flowchart of an obstacle identification method according to an embodiment of the present application;
FIG. 3 is a schematic diagram of region partitioning provided by an embodiment of the present application;
FIG. 4 is a schematic illustration of detection zones at different distance locations as provided by one embodiment of the present application;
FIG. 5 is a schematic diagram of a clustering result provided by an embodiment of the present application;
fig. 6 is a block diagram of an obstacle identification device according to an embodiment of the present application;
fig. 7 is a block diagram of an obstacle identification system provided in an embodiment of the present application.
Detailed Description
The following detailed description of embodiments of the present application will be described in conjunction with the accompanying drawings and examples. The following examples are intended to illustrate the present application but are not intended to limit the scope of the present application.
Fig. 1 is a network architecture diagram of an obstacle detection system provided in an embodiment of the present application, which may be installed in an unmanned vehicle for obstacle detection. In the driving process of the unmanned vehicle, an obstacle recognition system is required to be arranged to detect whether an obstacle exists in front of the driving direction of the vehicle or not so as to avoid the obstacle in time.
As shown in fig. 1, the obstacle detection system according to the embodiment of the present application includes: laser radar 1 and obstacle detection equipment 2, laser radar scanner establishes network connection with obstacle detection equipment 2, obstacle detection equipment 2 can be vehicle-mounted computer.
The working process of the obstacle detection system shown in fig. 1 in the embodiment of the present application is as follows:
after the unmanned vehicle starts the obstacle detection function, the laser radar 1 starts to work and emits laser to scan obstacles;
when the laser radar 1 scans the obstacle, outputting point cloud data to the obstacle detection equipment 2;
the obstacle detection equipment 2 acquires a plurality of groups of point cloud data in a preset detection range;
the obstacle detection equipment 2 performs area division on each group of point cloud data in the preset detection range to obtain a plurality of mutually overlapped detection areas;
the obstacle detection equipment 2 performs Euclidean clustering on the point clouds in the detection areas to obtain clustering results in the detection areas;
and the obstacle detection equipment 2 fuses the clustering results in each detection area to obtain an obstacle identification result.
Fig. 2 is a flowchart of an obstacle identification method according to an embodiment of the present application, where the present application is applied to the obstacle detection system shown in fig. 1, and an execution subject of each step is an example of an obstacle detection device in the system. The method at least comprises the following steps:
s201, acquiring a plurality of groups of point cloud data in a preset detection range;
in this embodiment, a plurality of laser beams are emitted through the laser radar, and if an obstacle is encountered, the laser beams are reflected by the obstacle, and a set of points reflected by the surface of the obstacle is a point cloud, where each point in the point cloud includes a three-dimensional coordinate (a position relative to the laser radar) of the point and a laser reflection intensity. Therefore, the position and distance of the obstacle can be detected according to the acquired point cloud data.
The detection range is a region of interest set in advance, that is, a region is selected from the entire data block, which is a focus of attention for data analysis.
S202, carrying out region division on each group of point cloud data in the detection range to obtain a plurality of mutually overlapped detection regions;
and dividing the distance area of each group of point cloud data in the detection range in a longitudinal direction according to a preset distance section in an area overlapping mode to obtain a plurality of overlapped detection areas, wherein the same point can be classified into different detection areas.
Referring to fig. 3, the X direction is a longitudinal direction, the detection range of the distance in the X direction is 0-50 meters, and the detection range is divided into 4 overlapped detection areas, that is: as can be seen from FIG. 3, the 4 detection regions overlap each other, with the distance region of 0-20 m being set as detection region 1, the distance region of 10-30 m being set as detection region 2, the distance region of 20-40 m being set as detection region 3, and the distance region of 30-50 m being set as detection region 4.
And S203, carrying out Euclidean clustering on the point clouds in the detection areas to obtain clustering results of the detection areas.
Specifically, before the euclidean clustering is performed in the present embodiment, different clustering thresholds are first set according to detection regions at different distance positions.
As shown in fig. 4, for example, three target regions (S1, S2, S3) detected in one detection range are respectively located at different distance positions within the detection range, the closer the target regions are, the closer their inner point sets are to each other, and the farther the target regions are, the farther their inner point sets are, see fig. 4, the closest the inner point sets of S1 are to each other, and the farthest the inner point sets of S3 are from each other. And in the detection area where S3 is located, the set clustering threshold is the largest, and S2 is the second, and S1 is the smallest.
According to the embodiment of the application, different clustering threshold values are set for the detection areas at different distance positions, a multi-thread mode is adopted for simultaneous clustering, and a plurality of detection areas are clustered simultaneously in a multi-thread mode, so that the efficiency is improved.
And S204, fusing the clustering results of each detection area to obtain an obstacle identification result.
Specifically, the embodiment of the present application fuses the clustering results in each detection area to obtain an obstacle identification result, and the method includes:
performing polygon fitting on each clustering result to obtain a target profile in each detection area;
calculating the area of the mutually overlapped region between the target contours;
and if the area of the mutually overlapped areas is larger than a preset value, merging the point clouds in the two overlapped target outlines, and performing polygon fitting again to obtain an obstacle identification result.
Referring to fig. 5, the conventional segmentation method may cause the problem that the targets across the interval are clustered into 2 targets, such as the real target P in the left image is detected as target P1 in the area 1 and is detected as target P2 in the area 2.
And if the real target P of the right image is detected as a target P1 in the area 1, a target P2 in the area 2 and a target P3 in the area 3, then the area of the overlapped area between the targets is calculated, if the area is larger than a preset value, point clouds in two overlapped polygons are merged, polygon fitting is carried out again, finally a real target frame is obtained through fusion, and an obstacle identification result is output.
To sum up, this application embodiment is through dividing overlap type detection area, and the target profile of clustering in every detection area is finally fused according to the area size that overlaps each other, has both solved global clustering and has leaded to the unable unified problem of near and distance threshold value in a distance, has also solved the problem that the regional target was split across in segmentation clustering, reaches better clustering effect.
Fig. 6 is a block diagram of an obstacle identification device according to an embodiment of the present application, and the present embodiment takes an example of an obstacle detection device applied to the obstacle detection system shown in fig. 1 as an illustration. The device at least comprises the following modules:
the data acquisition module is used for acquiring a plurality of groups of point cloud data in a preset detection range;
the region dividing module is used for performing region division on each group of point cloud data in the preset detection range to obtain a plurality of overlapped detection regions;
the cluster analysis module is used for carrying out Euclidean clustering on the point clouds in the detection areas to obtain clustering results in the detection areas;
and the identification module is used for fusing the clustering results in each detection area to obtain an obstacle identification result.
Further, the area dividing module performs area division in the corresponding detection range to obtain a plurality of overlapped detection areas, including:
and in the corresponding detection range, dividing the distance area in a region overlapping mode according to a preset distance section along the longitudinal direction to obtain a plurality of overlapped detection areas.
Further, the identification module includes:
the fitting unit is used for performing polygon fitting on each clustering result to obtain a target contour in each detection area;
the calculating unit is used for calculating the area of the region where the target contours are overlapped;
and the judging unit is used for merging the point clouds in the two overlapped target outlines and carrying out polygon fitting again to obtain an obstacle identification result if the area of the mutually overlapped areas is larger than a preset value.
The details of the obstacle identification device of the present embodiment refer to the method embodiments described above.
It should be noted that: in the obstacle recognition device provided in the above embodiment, when performing obstacle recognition, only the division of the above functional modules is taken as an example, and in practical applications, the above function allocation may be completed by different functional modules according to needs, that is, the internal structure of the obstacle recognition device is divided into different functional modules to complete all or part of the above described functions. In addition, the obstacle identification device provided by the above embodiment and the obstacle identification method embodiment belong to the same concept, and the specific implementation process thereof is described in the method embodiment and is not described herein again.
Fig. 7 is a block diagram of an obstacle identification system, which may be a tablet computer, a laptop computer, a desktop computer, or a server, according to an embodiment of the present application. The obstacle identification system includes at least a processor and a memory.
The processor may include one or more processing cores, such as: 4 core processors, 6 core processors, etc. The processor may be implemented in at least one hardware form of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), and a PLA (Programmable Logic Array). The processor may also include a main processor and a coprocessor, where the main processor is a processor for Processing data in an awake state, and is also called a Central Processing Unit (CPU); a coprocessor is a low power processor for processing data in a standby state. In some embodiments, the processor may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content that the display screen needs to display. In some embodiments, the processor may further include an AI (Artificial Intelligence) processor for processing computing operations related to machine learning.
The memory may include one or more computer-readable storage media, which may be non-transitory. The memory may also include high speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In some embodiments, a non-transitory computer-readable storage medium in a memory is used to store at least one instruction for execution by a processor to implement the obstacle identification method provided by method embodiments herein.
In some embodiments, the obstacle identification system may further include: a peripheral interface and at least one peripheral. The processor, memory and peripheral interface may be connected by bus or signal lines. Each peripheral may be connected to the peripheral interface via a bus, signal line, or circuit board. Illustratively, peripheral devices include, but are not limited to: radio frequency circuit, touch display screen, audio circuit, power supply, etc.
Of course, the obstacle identification system may also include fewer or more components, which is not limited by the embodiment.
Optionally, the present application further provides a computer readable storage medium, in which a program is stored, and the program is loaded and executed by a processor to implement the steps of the obstacle identification method of the above method embodiment.
Optionally, the present application further provides a computer product, which includes a computer-readable storage medium, in which a program is stored, and the program is loaded and executed by a processor to implement the steps of the obstacle identification method of the above-mentioned method embodiment.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. An obstacle identification method, characterized in that the method comprises:
acquiring a plurality of groups of point cloud data in a preset detection range;
carrying out region division on each group of point cloud data in the preset detection range to obtain a plurality of overlapped detection regions;
carrying out Euclidean clustering on the point clouds in the detection areas to obtain clustering results in the detection areas;
and fusing the clustering results in each detection area to obtain an obstacle identification result.
2. The method according to claim 1, wherein the performing area division on each group of point cloud data within the preset detection range to obtain a plurality of overlapped detection areas comprises:
and in the corresponding detection range, dividing the distance area in a region overlapping mode according to a preset distance section along the longitudinal direction to obtain a plurality of overlapped detection areas.
3. The method of claim 1, wherein the Euclidean clustering of the point clouds in each of the detection regions comprises:
and performing European clustering on the point clouds in the detection areas simultaneously by adopting multithreading.
4. The method of claim 2, wherein prior to the euclidean clustering of the point clouds in each of the detection regions, further comprising:
and setting different clustering threshold values for the detection areas according to the distance position of the detection areas.
5. The method according to claim 1, wherein the fusing the clustering results in each detection area to obtain an obstacle identification result comprises:
performing polygon fitting on each clustering result to obtain a target profile in each detection area;
calculating the area of the mutually overlapped region between the target contours;
and if the area of the mutually overlapped areas is larger than a preset value, merging the point clouds in the two overlapped target outlines, and performing polygon fitting again to finally obtain an obstacle identification result.
6. An obstacle recognition apparatus, characterized in that the apparatus comprises:
the data acquisition module is used for acquiring a plurality of groups of point cloud data in a preset detection range;
the region dividing module is used for performing region division on each group of point cloud data in the preset detection range to obtain a plurality of overlapped detection regions;
the cluster analysis module is used for carrying out Euclidean clustering on the point clouds in the detection areas to obtain clustering results in the detection areas;
and the identification module is used for fusing the clustering results in each detection area to obtain an obstacle identification result.
7. The apparatus of claim 6, wherein the area dividing module performs area division in the corresponding detection range to obtain a plurality of overlapped detection areas, and the area dividing module comprises:
and in the corresponding detection range, dividing the distance area in a region overlapping mode according to a preset distance section along the longitudinal direction to obtain a plurality of overlapped detection areas.
8. The apparatus of claim 6, wherein the identification module comprises:
the fitting unit is used for performing polygon fitting on each clustering result to obtain a target contour in each detection area;
the calculating unit is used for calculating the area of the region where the target contours are overlapped;
and the judging unit is used for merging the point clouds in the two overlapped target outlines and carrying out polygon fitting again if the area of the mutually overlapped areas is larger than a preset value, so as to finally obtain an obstacle identification result.
9. An obstacle identification system, the system comprising a processor and a memory, the memory having stored therein a computer program, characterized in that the computer program is loaded and executed by the processor to implement the obstacle identification method according to any one of claims 1 to 5.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, is adapted to carry out the obstacle identification method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110016671.7A CN112348000A (en) | 2021-01-07 | 2021-01-07 | Obstacle recognition method, device, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110016671.7A CN112348000A (en) | 2021-01-07 | 2021-01-07 | Obstacle recognition method, device, system and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112348000A true CN112348000A (en) | 2021-02-09 |
Family
ID=74427996
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110016671.7A Pending CN112348000A (en) | 2021-01-07 | 2021-01-07 | Obstacle recognition method, device, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112348000A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113030896A (en) * | 2021-03-10 | 2021-06-25 | 森思泰克河北科技有限公司 | Radar target clustering method and device and electronic equipment |
| CN115308771A (en) * | 2022-10-12 | 2022-11-08 | 深圳市速腾聚创科技有限公司 | Obstacle detection method and apparatus, medium, and electronic device |
| CN115792945A (en) * | 2023-01-30 | 2023-03-14 | 智道网联科技(北京)有限公司 | Floating obstacle detection method and device, electronic equipment and storage medium |
| WO2023179207A1 (en) * | 2022-03-22 | 2023-09-28 | 追觅创新科技(苏州)有限公司 | Map processing method and apparatus, cleaning device, storage medium, and electronic apparatus |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180129888A1 (en) * | 2016-11-04 | 2018-05-10 | X Development Llc | Intuitive occluded object indicator |
| CN108152831A (en) * | 2017-12-06 | 2018-06-12 | 中国农业大学 | A kind of laser radar obstacle recognition method and system |
| CN111079596A (en) * | 2019-12-05 | 2020-04-28 | 国家海洋环境监测中心 | System and method for identifying typical marine artificial target of high-resolution remote sensing image |
| CN111160302A (en) * | 2019-12-31 | 2020-05-15 | 深圳一清创新科技有限公司 | Obstacle information identification method and device based on automatic driving environment |
-
2021
- 2021-01-07 CN CN202110016671.7A patent/CN112348000A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180129888A1 (en) * | 2016-11-04 | 2018-05-10 | X Development Llc | Intuitive occluded object indicator |
| CN108152831A (en) * | 2017-12-06 | 2018-06-12 | 中国农业大学 | A kind of laser radar obstacle recognition method and system |
| CN111079596A (en) * | 2019-12-05 | 2020-04-28 | 国家海洋环境监测中心 | System and method for identifying typical marine artificial target of high-resolution remote sensing image |
| CN111160302A (en) * | 2019-12-31 | 2020-05-15 | 深圳一清创新科技有限公司 | Obstacle information identification method and device based on automatic driving environment |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113030896A (en) * | 2021-03-10 | 2021-06-25 | 森思泰克河北科技有限公司 | Radar target clustering method and device and electronic equipment |
| WO2023179207A1 (en) * | 2022-03-22 | 2023-09-28 | 追觅创新科技(苏州)有限公司 | Map processing method and apparatus, cleaning device, storage medium, and electronic apparatus |
| CN115308771A (en) * | 2022-10-12 | 2022-11-08 | 深圳市速腾聚创科技有限公司 | Obstacle detection method and apparatus, medium, and electronic device |
| CN115308771B (en) * | 2022-10-12 | 2023-03-14 | 深圳市速腾聚创科技有限公司 | Obstacle detection method and apparatus, medium, and electronic device |
| CN115792945A (en) * | 2023-01-30 | 2023-03-14 | 智道网联科技(北京)有限公司 | Floating obstacle detection method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11709058B2 (en) | Path planning method and device and mobile device | |
| Zermas et al. | Fast segmentation of 3d point clouds: A paradigm on lidar data for autonomous vehicle applications | |
| CN112348000A (en) | Obstacle recognition method, device, system and storage medium | |
| US10366310B2 (en) | Enhanced camera object detection for automated vehicles | |
| WO2021072696A1 (en) | Target detection and tracking method and system, and movable platform, camera and medium | |
| CN116129376A (en) | Road edge detection method and device | |
| CN108509820B (en) | Obstacle segmentation method and device, computer equipment and readable medium | |
| CN111598034A (en) | Obstacle detection method, obstacle detection device and storage medium | |
| WO2022099530A1 (en) | Motion segmentation method and apparatus for point cloud data, computer device and storage medium | |
| JP2016148547A (en) | Detection device | |
| CN112505652B (en) | Target detection method, device and storage medium | |
| CN111913177A (en) | Method and device for detecting target object and storage medium | |
| CN111308500A (en) | Obstacle sensing method and device based on single-line laser radar and computer terminal | |
| CN114882701B (en) | Parking space detection method and device, electronic equipment and machine readable storage medium | |
| KR20200087354A (en) | Data labeling apparatus and method for autonomous driving control | |
| CN114384492B (en) | Point cloud processing method and device for laser radar and storage medium | |
| CN114460598A (en) | Target identification method, device, equipment and storage medium | |
| CN115147333A (en) | Target detection method and device | |
| WO2022226831A1 (en) | Method and apparatus for detecting category-undefined obstacle, and computer device | |
| KR20220169727A (en) | Apparatus and method for tracking object using LiDAR sensor, and recording medium for recording program performing the method | |
| CN117291840A (en) | Point cloud noise filtering method, device, medium and equipment of patrol robot | |
| CN111912418A (en) | Method, device and medium for deleting obstacles in non-driving area of mobile carrier | |
| Morales Rosales et al. | On-road obstacle detection video system for traffic accident prevention | |
| CN113313629B (en) | Automatic intersection identification method and system and model storage method and system thereof | |
| CN113611112B (en) | Target association method, device, equipment and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210209 |