CN114545443A - Blind area identification method and device - Google Patents
Blind area identification method and device Download PDFInfo
- Publication number
- CN114545443A CN114545443A CN202210121510.9A CN202210121510A CN114545443A CN 114545443 A CN114545443 A CN 114545443A CN 202210121510 A CN202210121510 A CN 202210121510A CN 114545443 A CN114545443 A CN 114545443A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- point
- target point
- target
- cloud data
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 62
- 239000011159 matrix material Substances 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 16
- 238000013507 mapping Methods 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 15
- 238000010586 diagram Methods 0.000 description 14
- 230000006870 function Effects 0.000 description 12
- 230000006872 improvement Effects 0.000 description 9
- 238000012545 processing Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 229920001296 polysiloxane Polymers 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
- G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- 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
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
- G01S7/4802—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Electromagnetism (AREA)
- Traffic Control Systems (AREA)
Abstract
The specification discloses a blind area identification method and a blind area identification device. Firstly, target point cloud data acquired by unmanned equipment is acquired. Secondly, determining a region which takes the target point cloud point as an initial position and is far away from the unmanned equipment according to the direction of the unmanned equipment pointing to the target point cloud point as an extension region corresponding to the target point cloud point according to the scanning angle of the laser radar arranged on the unmanned equipment when the target point cloud point is detected aiming at each target point cloud point contained in the determined target point cloud data. And then, identifying a data acquisition blind area of an area where the unmanned equipment is located when acquiring the target point cloud data according to the extension area corresponding to each target point cloud point in the target point cloud data. The method can determine the data acquisition blind area of the area where the unmanned equipment is located when the unmanned equipment acquires the target point cloud data, and avoid collision between the unmanned equipment and other surrounding obstacles, so that the safety of the unmanned equipment in the driving process is improved.
Description
Technical Field
The specification relates to the field of unmanned driving, in particular to a blind area identification method and device.
Background
In practical applications, a situation that a part of the field of view of the unmanned aerial vehicle is blocked by an obstacle occurs during driving of the unmanned aerial vehicle, for example, a large field of view area is blocked by a large vehicle around the unmanned aerial vehicle during driving of the unmanned aerial vehicle, and when the unmanned aerial vehicle passes through the large vehicle, a pedestrian may suddenly appear from a blind field of view area, and there is a possibility of collision with the pedestrian. At present, the unmanned equipment cannot determine the visual field blind area of the unmanned equipment, so that the unmanned equipment collides with surrounding obstacles, and the safety of the unmanned equipment in the driving process is low.
Therefore, how to improve the safety of the unmanned equipment in the driving process is an urgent problem to be solved.
Disclosure of Invention
The present specification provides a blind area identification method and apparatus, which partially solve the above problems in the prior art.
The technical scheme adopted by the specification is as follows:
the present specification provides a blind area identification method, which is applied to the field of unmanned driving, and comprises the following steps:
acquiring target point cloud data acquired by unmanned equipment;
determining a region which takes the target point cloud point as an initial position and is far away from the unmanned equipment according to the direction of the unmanned equipment pointing to the target point cloud point as an extension region corresponding to the target point cloud point according to a scanning angle when the laser radar arranged on the unmanned equipment detects the target point cloud point aiming at each target point cloud point contained in the determined target point cloud data;
and identifying a data acquisition blind area of an area where the unmanned equipment acquires the target point cloud data according to the extension area corresponding to each target point cloud point in the target point cloud data.
Optionally, the acquiring target point cloud data acquired by the unmanned device includes:
acquiring initial point cloud data acquired by the unmanned equipment;
and identifying noise points from the initial point cloud data, and taking the initial point cloud data without the noise points as the target point cloud data.
Optionally, identifying noise from the initial point cloud data comprises:
and identifying point cloud points on the ground from the initial point cloud data according to the height value corresponding to each point cloud point in the initial point cloud data, wherein the point cloud points are used as the identified noise points.
Optionally, identifying noise from the initial point cloud data comprises:
aiming at each point cloud point contained in each initial point cloud data, judging whether the height value corresponding to the point cloud point falls into a preset height value range or not;
and if the height value corresponding to the point cloud point is determined not to fall into the height value range, determining the point cloud point as a noise point.
Optionally, identifying noise from the initial point cloud data comprises:
aiming at each point cloud point contained in each initial point cloud data, judging whether the height value corresponding to the point cloud point falls into a preset height value range or not;
if the height value corresponding to the point cloud point is determined to fall into the height value range, judging whether a point cloud point positioned below the point cloud point exists in the projection direction of the point cloud point;
and if the point cloud point positioned below the point cloud point does not exist in the projection direction of the point cloud point, determining the point cloud point as a noise point.
Optionally, determining each target point cloud point included in the target point cloud data includes:
respectively mapping point cloud data located at different circumferences in the target point cloud data to each row of a preset matrix to obtain a point cloud matrix, wherein different row coordinates in the point cloud matrix correspond to the point cloud data at different circumferences in the target point cloud data, and different column coordinates in the point cloud matrix correspond to different scanning angles of a laser radar arranged on the unmanned equipment when the target point cloud data are obtained through scanning;
and according to the point cloud matrix, each target point cloud point contained in the target point cloud data.
Optionally, determining that the target point cloud data includes target point cloud points includes:
and aiming at each scanning angle of the laser radar arranged on the unmanned equipment when the target point cloud data is obtained by scanning, determining a point cloud point which is positioned in the scanning angle and is closest to the unmanned equipment from the target point cloud data as a target point cloud point.
Optionally, determining, for each target point cloud point included in the determined target point cloud data, a region that is far away from the unmanned device in a direction in which the unmanned device points to the target point cloud point and is determined as an extended region corresponding to the target point cloud point by using the target point cloud point as an initial position according to a scanning angle at which the laser radar arranged on the unmanned device detects the target point cloud point, including:
and aiming at each target point cloud point, if the reference target point cloud point exists in the preset range of the target point cloud point, determining that the reference target point cloud point is taken as an initial position, and taking an area far away from the unmanned equipment according to the direction of the unmanned equipment pointing to the target point cloud point as an extension area corresponding to the target point cloud point, wherein the distance between the reference target point cloud point and the unmanned equipment is smaller than the distance between the target point cloud point and the unmanned equipment.
This specification provides a blind area recognition device, the device is applied to the unmanned driving field, includes:
the acquisition module is used for acquiring target point cloud data acquired by the unmanned equipment;
the area module is used for determining each target point cloud point contained in the determined target point cloud data, determining an area which takes the target point cloud point as an initial position according to a scanning angle when a laser radar arranged on the unmanned equipment detects the target point cloud point, and is far away from the unmanned equipment according to the direction of the unmanned equipment pointing to the target point cloud point, and taking the area as an extended area corresponding to the target point cloud point;
and the identification module is used for identifying a data acquisition blind area of an area where the unmanned equipment is located when acquiring the target point cloud data according to the extension area corresponding to each target point cloud point in the target point cloud data.
The present specification provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the above-described blind area identification method.
The present specification provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the above blind area identification method when executing the program.
The technical scheme adopted by the specification can achieve the following beneficial effects:
in the control method of the unmanned aerial vehicle provided in the present specification. Firstly, target point cloud data acquired by unmanned equipment is acquired. Secondly, determining a region which takes the target point cloud point as an initial position and is far away from the unmanned equipment according to the direction of the unmanned equipment pointing to the target point cloud point as an extension region corresponding to the target point cloud point according to the scanning angle of the laser radar arranged on the unmanned equipment when the target point cloud point is detected aiming at each target point cloud point contained in the determined target point cloud data. And then, identifying a data acquisition blind area of an area where the unmanned equipment is located when acquiring the target point cloud data according to the extension area corresponding to each target point cloud point in the target point cloud data.
According to the method, the data acquisition blind area of the area where the unmanned equipment acquires the target point cloud data can be determined according to the extension area corresponding to the target point cloud point at each scanning angle, so that the unmanned equipment is controlled, collision between the unmanned equipment and other surrounding obstacles is avoided, and safety of the unmanned equipment in the driving process is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the specification and are incorporated in and constitute a part of this specification, illustrate embodiments of the specification and together with the description serve to explain the specification and not to limit the specification in a non-limiting sense. In the drawings:
FIG. 1 is a schematic flow chart of a blind area identification method in the present specification;
FIG. 2 is a schematic diagram of a data acquisition dead zone provided in an embodiment of the present disclosure;
FIG. 3 is a schematic diagram of a blind area identification device provided herein;
fig. 4 is a schematic diagram of an electronic device corresponding to fig. 1 provided in the present specification.
Detailed Description
In order to make the objects, technical solutions and advantages of the present disclosure more clear, the technical solutions of the present disclosure will be clearly and completely described below with reference to the specific embodiments of the present disclosure and the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present disclosure, and not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present specification without making any creative effort belong to the protection scope of the present specification.
The technical solutions provided by the embodiments of the present description are described in detail below with reference to the accompanying drawings.
Fig. 1 is a schematic flow chart of a blind area identification method in this specification, including the following steps:
s100: and acquiring target point cloud data acquired by the unmanned equipment.
The main body of the unmanned aerial vehicle control method according to the present specification may be an unmanned aerial vehicle, or an electronic device such as a server mounted on the unmanned aerial vehicle, and for convenience of description, the unmanned aerial vehicle control method provided in the present specification will be described below with reference to only the unmanned aerial vehicle as the main body of the unmanned aerial vehicle.
In the embodiment of the specification, the unmanned device can acquire the initial point cloud data acquired by the unmanned device. The initial point cloud data mentioned here may refer to unprocessed point cloud data acquired by a laser radar provided on the unmanned device.
Specifically, target point cloud data acquired by the unmanned equipment through the laser radar comprises a plurality of circumferences of point cloud data, each circumference of point cloud data comprises a plurality of point cloud points, the number of the point cloud points is determined by the resolution, and each point cloud point comprises coordinates (x, y, z) corresponding to a laser radar coordinate system and point cloud point intensity. For example, if the laser radar is a 64-line physical rotation type scanning laser radar (64 lines means that 64 laser transmitters are arranged on the laser radar), the laser radar can obtain point cloud data of 64 different circumferences, and the point cloud data of each circumference can be understood as being obtained after one laser transmitter scans for one circle. The resolution in each circle point cloud data is 0.2 degrees, namely 1800 point cloud points exist in each circle, and in one circle point cloud data, each point cloud point corresponds to one scanning angle.
In this embodiment, the unmanned aerial vehicle may process the acquired target point cloud data, and map point cloud data located at different circumferences in the target point cloud data to rows of a preset matrix respectively to obtain a point cloud matrix, where different row coordinates in the point cloud matrix correspond to point cloud data at different circumferences in the target point cloud data, and different column coordinates in the point cloud matrix correspond to different scanning angles of a laser radar arranged on the unmanned aerial vehicle when scanning to obtain the target point cloud data.
It is understood that point cloud points located on the same circumference are recorded in the same row in the point cloud matrix, and based on the point cloud matrix, a number of point cloud points corresponding to each scanning angle of the unmanned device can be determined. The specific formula for determining the column coordinates of the matrix is as follows:
L＝round((atan2(y，x)+π)/DegreeToRadians(d))
in the above formula, round () can be used to characterize the rounding function. atan2(y, x) can be used to characterize the arctangent function, converting coordinates to radians between (-pi, pi). Degreetotradians () may be used to characterize the conversion of angles to radians. d may be used to characterize the resolution of the point cloud data. As can be seen from the above formula, the drone may determine a number of point cloud points corresponding to each scan angle of the drone.
In practical application, point cloud points which can influence the unmanned equipment to determine the visual field blind area exist in the point cloud data acquired by the unmanned equipment, and based on the point cloud points, the unmanned equipment needs to remove the point cloud points from the acquired initial point cloud data so as to ensure that the unmanned equipment can determine the accurate visual field blind area.
In an embodiment of the present specification, the unmanned device may acquire initial point cloud data acquired by the unmanned device. And identifying noise points from the initial point cloud data, and taking the initial point cloud data without the noise points as target point cloud data.
In practical application, a large number of point cloud points in the point cloud data acquired by the unmanned equipment are obtained based on ground reflection, and the point cloud points on the ground are irrelevant to the determination of the view blind area of the unmanned equipment. Based on this, the unmanned device needs to remove each cloud point obtained based on ground reflection from the point cloud data.
In this specification, the unmanned aerial vehicle may identify, from the initial point cloud data, a point cloud point located on the ground as an identified noise point according to a height value corresponding to each point cloud point included in the initial point cloud data.
Specifically, the unmanned device can determine a height value corresponding to the ground around the unmanned device. And identifying point cloud points on the ground from the initial point cloud data according to the height value corresponding to the ground around the unmanned equipment, wherein the point cloud points are used as identified noise points.
For example, the unmanned device may calculate the cloud points of each point by using a RANdom SAmple Consensus (RANSAC) algorithm according to the height value corresponding to each cloud point in the initial point cloud data and the position of each cloud point, so as to determine the height value corresponding to the ground around the unmanned device. For another example, the unmanned device may obtain an elevation map, and determine a height value corresponding to the ground around the unmanned device through the elevation map. The present specification does not limit the method of determining the height value corresponding to the ground around the unmanned aerial device.
In practical application, in the driving process of the unmanned equipment, the too high obstacle cannot influence the driving of the unmanned equipment, and the too low obstacle cannot shield any target influencing the driving of the unmanned equipment, that is, only the cloud point with the height within the set range can influence the view blind area of the unmanned equipment. Based on this, the unmanned device needs to remove point cloud points whose height values do not meet the standard from the initial point cloud data.
In this specification, the unmanned aerial vehicle may determine, for each point cloud point included in each initial point cloud data, whether a height value corresponding to the point cloud point falls within a preset height value range. And if the height value corresponding to the point cloud point is determined not to fall into the height value range, determining the point cloud point as a noise point.
In practical applications, the unmanned aerial vehicle may encounter various suspended obstacles during driving, such as branches and leaves of a tree extending from the side of the lane to the lane, and billboards on poles of the side of the lane. This portion of the obstruction does not actually obstruct the field of view of the drone. Based on this, the server may remove the point cloud points reflected by the partially suspended obstacle from the initial point cloud data.
In this specification, the unmanned aerial vehicle may determine, for each point cloud point included in each initial point cloud data, whether a height value corresponding to the point cloud point falls within a preset height value range. Secondly, if the height value corresponding to the point cloud point is determined to fall into the height value range, whether a point cloud point located below the point cloud point exists in the projection direction of the point cloud point is judged. And finally, if the point cloud point positioned below the point cloud point does not exist in the projection direction of the point cloud point, determining the point cloud point as a noise point.
That is, if an obstacle is in a suspended state, a point cloud point does not necessarily exist below the position of the point cloud point reflected by the obstacle.
In this embodiment, the unmanned device has multiple methods to determine whether the point cloud point is a noise point, for example, for each scanning direction, the unmanned device may determine a height value corresponding to each cloud point in the scanning direction, and determine whether a point cloud point exists in the projection direction of the point cloud point, which is the same as the distance between the laser radar and is located below the point cloud point, based on the distance between each cloud point and the laser radar. And if the point cloud point which has the same distance with the laser radar and is positioned below the point cloud point does not exist in the projection direction of the point cloud point, determining the point cloud point as a noise point.
Of course, the unmanned aerial vehicle may remove at least one of point cloud points located on the ground, point cloud points that do not fall within the height value range, and point cloud points corresponding to a point cloud point that is not located below the point cloud point in the point cloud data in the projection direction of the point cloud point from the initial point cloud data, and determine the target point cloud data.
In this specification, the unmanned device to which the control method of the unmanned device provided in this specification is applied may be used to execute a delivery task in a delivery field, for example, a business scenario of delivery such as express delivery, logistics, and takeout using the unmanned device.
S102: and determining a region which takes the target point cloud point as an initial position and is far away from the unmanned equipment according to the direction of the unmanned equipment pointing to the target point cloud point as an extension region corresponding to the target point cloud point according to the scanning angle of the laser radar arranged on the unmanned equipment when the target point cloud point is detected aiming at each target point cloud point contained in the determined target point cloud data.
S104: and identifying a data acquisition blind area of an area where the unmanned equipment acquires the target point cloud data according to the extension area corresponding to each target point cloud point in the target point cloud data.
In practical application, the point cloud points in the initial point cloud data are obtained based on the reflection of the obstacle, and therefore, the positions of the point cloud points are the positions of the obstacle. That is, the drone cannot observe the field of view behind the location in the direction of the point cloud point at which the drone is pointed. Based on the method, the unmanned device can determine the visual field blind area corresponding to the area where the unmanned device is located.
In this embodiment, the unmanned device may determine, for each target point cloud point included in the determined target point cloud data, an area that is far from the unmanned device in a direction in which the unmanned device points at the target point cloud point, with the target point cloud point as an initial position, as an extended area corresponding to the target point cloud point, according to a scanning angle at which a laser radar arranged on the unmanned device detects the target point cloud point.
In practical application, the unmanned device acquires a plurality of point cloud points in the same scanning direction, and the distances from the point cloud points to the laser radar pairs may not be the same. For example, obstacles with different heights appear in one scanning direction of the unmanned device, and the distances from the point cloud point reflected by the different obstacles to the laser radar are different. In this case, an obstacle near the unmanned aerial vehicle during traveling may obstruct the view of the unmanned aerial vehicle in the scanning direction. Based on the distance between the point cloud point and the laser radar, the unmanned device can determine a target point cloud point in the scanning direction.
In this specification, the unmanned device may determine each scanning angle of the lidar arranged on the unmanned device when scanning to obtain target point cloud data. And aiming at each scanning angle, determining a point cloud point which is positioned in the scanning angle and is closest to the unmanned equipment from the target point cloud data to be used as a target point cloud point. The unmanned equipment can determine a plurality of target point cloud points from the target point cloud data based on the point cloud matrix, and because different column coordinates in the point cloud matrix correspond to different scanning angles, the distances between the point cloud points recorded in the same column and the unmanned equipment can be compared to determine the target point cloud points.
In practical application, the unmanned equipment divides the initial point cloud data into a plurality of finer scanning directions. For each scanning direction, the point cloud points in the adjacent scanning direction corresponding to the scanning direction influence the view blocked by the scanning direction. For example, if the surface of an obstacle is uneven, among several scanning directions directed to the obstacle, the scanning direction corresponding to the point cloud point closest to the unmanned aerial vehicle has actually affected the field of view of the unmanned aerial vehicle in other scanning directions near the scanning direction.
In this embodiment, for each target point cloud point, if it is determined that a reference target point cloud point exists within a preset range of the target point cloud point, the unmanned device may determine, using the reference target point cloud point as a starting position, an area away from the unmanned device in a direction in which the unmanned device points to the target point cloud point, as an extended area corresponding to the target point cloud point, where a distance between the reference target point cloud point and the unmanned device is smaller than a distance between the target point cloud point and the unmanned device.
That is to say, the unmanned device may select a reference target point cloud point closest to the lidar as the target point cloud point from the reference target point cloud points within the preset range. And taking the reference target cloud point as an initial position, and taking an area far away from the unmanned equipment according to the direction in which the unmanned equipment points to the target cloud point as an extension area corresponding to the target cloud point.
In this specification, the unmanned aerial vehicle may determine, according to an extended region corresponding to each target point cloud point in the target point cloud data, a data acquisition blind region of a region where the unmanned aerial vehicle acquires the target point cloud data. As shown in particular in fig. 2.
Fig. 2 is a schematic diagram of a method for determining a data acquisition dead zone according to an embodiment of the present disclosure.
In fig. 2, a cylinder may be used to characterize the obstacle, and lines around the cylinder may be used to characterize the extended area corresponding to the point cloud point reflected by the obstacle. And determining a data acquisition blind area of the area where the unmanned equipment is located according to the extension area corresponding to the cloud points of each point reflected by the barrier. As shown in fig. 2, the obstacle blocks the view range of the unmanned device, and the unmanned device can determine the position of the point cloud point from the point cloud points reflected by the obstacle. And taking the cloud point as an initial position, and taking an area far away from the unmanned equipment in the direction in which the unmanned equipment points to the cloud point as a data acquisition blind area of the area where the unmanned equipment acquires the point cloud data.
Specifically, the unmanned device can be divided into a plurality of squares according to a preset size in an area where the unmanned device is located. And for each square, if the square is an extended area corresponding to the target point cloud point, determining that the area where the square is located cannot be observed by the unmanned equipment. The unmanned equipment can determine the data acquisition blind area according to whether the unmanned equipment can observe the conditions of each square.
In the embodiment of the specification, the unmanned equipment can be controlled according to the data acquisition blind area. Specifically, the unmanned equipment can acquire a high-precision map of a region where the unmanned equipment is located and a position where the unmanned equipment is located, and determines the region where a data acquisition blind area of the unmanned equipment is located in the high-precision map according to the high-definition map. And aiming at each data acquisition blind area, controlling the unmanned equipment according to the information of the area where the data acquisition blind area is located and the distance between the position of the unmanned equipment and the data acquisition blind area.
For example, if the data acquisition blind area of the area where the unmanned device is located at the entrance and exit of the cell, the driving speed of the unmanned device is reduced when the unmanned device approaches the entrance and exit.
In the process, the data acquisition blind area of the area where the unmanned equipment acquires the target point cloud data can be determined according to the extension area corresponding to the target point cloud point at each scanning angle, so that the unmanned equipment is controlled, collision between the unmanned equipment and other surrounding obstacles is avoided, and safety of the unmanned equipment in the driving process is improved.
Based on the same idea, the blind area identification method provided in one or more embodiments of the present specification further provides a corresponding blind area identification device, as shown in fig. 3.
Fig. 3 is a schematic diagram of a blind area recognition device provided in this specification, where the device is applied to the field of unmanned driving, and the device includes:
the acquisition module 300 is configured to acquire target point cloud data acquired by the unmanned device;
a region module 302, configured to determine, for each target point cloud point included in the determined target point cloud data, a region that is far away from the unmanned device in a direction in which the unmanned device points at the target point cloud point, with the target point cloud point as an initial position according to a scanning angle at which a laser radar arranged on the unmanned device detects the target point cloud point, and serves as an extended region corresponding to the target point cloud point;
the identification module 304 is configured to identify a data acquisition blind area of an area where the unmanned equipment acquires the target point cloud data according to an extension area corresponding to each target point cloud point in the target point cloud data;
optionally, the obtaining module 300 is specifically configured to obtain initial point cloud data collected by the unmanned aerial vehicle, identify a noise point from the initial point cloud data, and use the initial point cloud data without the noise point as the target point cloud data.
Optionally, the obtaining module 300 is specifically configured to identify, according to a height value corresponding to each point cloud point included in the initial point cloud data, a point cloud point located on the ground from the initial point cloud data as the identified noise point.
Optionally, the obtaining module 300 is specifically configured to, for each point cloud point included in each initial point cloud data, determine whether a height value corresponding to the point cloud point falls within a preset height value range, and if it is determined that the height value corresponding to the point cloud point does not fall within the height value range, determine that the point cloud point is a noise point.
Optionally, the area module 302 is specifically configured to, for each point cloud point included in each initial point cloud data, determine whether a height value corresponding to the point cloud point falls within a preset height value range, determine whether a point cloud point located below the point cloud point exists in a projection direction of the point cloud point if it is determined that the height value corresponding to the point cloud point falls within the height value range, and determine that the point cloud point is a noise point if it is determined that the point cloud point located below the point cloud point does not exist in the projection direction of the point cloud point.
Optionally, the area module 302 is specifically configured to map point cloud data located at different circumferences in the target point cloud data to rows of a preset matrix respectively to obtain a point cloud matrix, where different row coordinates in the point cloud matrix correspond to point cloud data at different circumferences in the target point cloud data, and different column coordinates in the point cloud matrix correspond to different scanning angles of a laser radar arranged on the unmanned device when the target point cloud data is obtained by scanning; and according to the point cloud matrix, each target point cloud point contained in the target point cloud data.
Optionally, the area module 302 is specifically configured to, for each scanning angle of the target point cloud data obtained by scanning the laser radar set on the unmanned aerial vehicle, determine, from the target point cloud data, a point cloud point located within the scanning angle and closest to the unmanned aerial vehicle, as a target point cloud point.
Optionally, the area module 302 is specifically configured to, for each target point cloud point, determine, if it is determined that a reference target point cloud point exists within a preset range of the target point cloud point, that the reference target point cloud point is used as a starting position, and determine, as an extended area corresponding to the target point cloud point, an area away from the unmanned aerial vehicle in a direction in which the unmanned aerial vehicle points to the target point cloud point, where a distance between the reference target point cloud point and the unmanned aerial vehicle is smaller than a distance between the target point cloud point and the unmanned aerial vehicle.
The present specification also provides a computer-readable storage medium storing a computer program, which can be used to execute a blind area identification method provided in fig. 1 above.
The present specification also provides a schematic block diagram of an electronic device corresponding to fig. 1 shown in fig. 4. As shown in fig. 4, at the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include hardware required for other services. The processor reads a corresponding computer program from the non-volatile memory into the memory and then runs the computer program to implement the above-mentioned blind area identification method shown in fig. 1. Of course, besides the software implementation, the present specification does not exclude other implementations, such as logic devices or a combination of software and hardware, and the like, that is, the execution subject of the following processing flow is not limited to each logic unit, and may be hardware or logic devices.
It should be noted that all actions of acquiring signals, information or data in the present application are performed under the premise of complying with the corresponding data protection regulation policy of the country of the location and obtaining the authorization given by the owner of the corresponding device.
In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD) (e.g., a Field Programmable Gate Array (FPGA)) is an integrated circuit whose Logic functions are determined by a user programming the Device. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Hardware Description Language), traffic, pl (core universal Programming Language), HDCal (jhdware Description Language), lang, Lola, HDL, laspam, hardward Description Language (vhr Description Language), vhal (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry for implementing the logical method flows can be readily obtained by a mere need to program the method flows with some of the hardware description languages described above and into an integrated circuit.
The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer readable medium that stores computer readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and embedded microcontrollers, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functions of the various elements may be implemented in the same one or more software and/or hardware implementations of the present description.
As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The description has been presented with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the description. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
This description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
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 the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only an example of the present specification, and is not intended to limit the present specification. Various modifications and alterations to this description will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification should be included in the scope of the claims of the present specification.
Claims (11)
1. A blind area identification method is applied to the field of unmanned driving and comprises the following steps:
acquiring target point cloud data acquired by unmanned equipment;
determining a region which takes the target point cloud point as an initial position and is far away from the unmanned equipment according to the direction of the unmanned equipment pointing to the target point cloud point as an extension region corresponding to the target point cloud point according to a scanning angle when the laser radar arranged on the unmanned equipment detects the target point cloud point aiming at each target point cloud point contained in the determined target point cloud data;
and identifying a data acquisition blind area of an area where the unmanned equipment acquires the target point cloud data according to the extension area corresponding to each target point cloud point in the target point cloud data.
2. The method of claim 1, wherein obtaining target point cloud data acquired by an unmanned device comprises:
acquiring initial point cloud data acquired by the unmanned equipment;
and identifying noise points from the initial point cloud data, and taking the initial point cloud data without the noise points as the target point cloud data.
3. The method of claim 2, wherein identifying noise from the initial point cloud data comprises:
and identifying point cloud points on the ground from the initial point cloud data according to the height value corresponding to each point cloud point in the initial point cloud data, wherein the point cloud points are used as the identified noise points.
4. The method of claim 2, wherein identifying noise from the initial point cloud data comprises:
aiming at each point cloud point contained in each initial point cloud data, judging whether the height value corresponding to the point cloud point falls into a preset height value range or not;
and if the height value corresponding to the point cloud point is determined not to fall into the height value range, determining the point cloud point as a noise point.
5. The method of claim 2 or 4, wherein identifying noise from the initial point cloud data comprises:
aiming at each point cloud point contained in each initial point cloud data, judging whether the height value corresponding to the point cloud point falls into a preset height value range or not;
if the height value corresponding to the point cloud point is determined to fall into the height value range, judging whether a point cloud point positioned below the point cloud point exists in the projection direction of the point cloud point;
and if the point cloud point positioned below the point cloud point does not exist in the projection direction of the point cloud point, determining the point cloud point as a noise point.
6. The method of claim 1, wherein determining each target point cloud point contained in the target point cloud data comprises:
respectively mapping point cloud data located at different circumferences in the target point cloud data to each row of a preset matrix to obtain a point cloud matrix, wherein different row coordinates in the point cloud matrix correspond to the point cloud data at different circumferences in the target point cloud data, and different column coordinates in the point cloud matrix correspond to different scanning angles of a laser radar arranged on the unmanned equipment when the target point cloud data are obtained through scanning;
and according to the point cloud matrix, each target point cloud point contained in the target point cloud data.
7. The method of claim 1 or 6, wherein determining that the target point cloud data includes target point cloud points comprises:
and aiming at each scanning angle of the laser radar arranged on the unmanned equipment when the target point cloud data is obtained by scanning, determining a point cloud point which is positioned in the scanning angle and is closest to the unmanned equipment from the target point cloud data as a target point cloud point.
8. The method of claim 1, wherein for each target point cloud point included in the determined target point cloud data, determining, according to a scanning angle at which a lidar disposed on the unmanned device detects the target point cloud point, a region away from the unmanned device in a direction in which the unmanned device points to the target point cloud point, with the target point cloud point as a starting position, as an extended region corresponding to the target point cloud point, includes:
and aiming at each target point cloud point, if the reference target point cloud point exists in the preset range of the target point cloud point, determining that the reference target point cloud point is taken as an initial position, and taking an area far away from the unmanned equipment according to the direction of the unmanned equipment pointing to the target point cloud point as an extension area corresponding to the target point cloud point, wherein the distance between the reference target point cloud point and the unmanned equipment is smaller than the distance between the target point cloud point and the unmanned equipment.
9. A blind area recognition device, characterized in that the device is applied to the field of unmanned driving, includes:
the acquisition module is used for acquiring target point cloud data acquired by the unmanned equipment;
the area module is used for determining each target point cloud point contained in the determined target point cloud data, determining a region which takes the target point cloud point as an initial position according to a scanning angle when the laser radar arranged on the unmanned equipment detects the target point cloud point, and is far away from the unmanned equipment according to the direction of the unmanned equipment pointing to the target point cloud point, and taking the region as an extended region corresponding to the target point cloud point;
and the identification module is used for identifying a data acquisition blind area of an area where the unmanned equipment is located when acquiring the target point cloud data according to the extension area corresponding to each target point cloud point in the target point cloud data.
10. A computer-readable storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements the method of any of the preceding claims 1 to 8.
11. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of claims 1 to 8 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210121510.9A CN114545443A (en) | 2022-02-09 | 2022-02-09 | Blind area identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210121510.9A CN114545443A (en) | 2022-02-09 | 2022-02-09 | Blind area identification method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114545443A true CN114545443A (en) | 2022-05-27 |
Family
ID=81673432
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210121510.9A Withdrawn CN114545443A (en) | 2022-02-09 | 2022-02-09 | Blind area identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114545443A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170185089A1 (en) * | 2015-12-27 | 2017-06-29 | Toyota Motor Engineering & Manufacturing North America, Inc. | Detection of overhanging objects |
| US20190138823A1 (en) * | 2017-11-09 | 2019-05-09 | Here Global B.V. | Automatic occlusion detection in road network data |
| US20200158875A1 (en) * | 2018-11-15 | 2020-05-21 | Beijing Didi Infinity Technology And Development C O., Ltd. | Systems and methods for correcting a high-definition map based on detection of obstructing objects |
| CN112130165A (en) * | 2020-09-15 | 2020-12-25 | 北京三快在线科技有限公司 | Positioning method, positioning device, positioning medium and unmanned equipment |
| CN112558035A (en) * | 2019-09-24 | 2021-03-26 | 北京百度网讯科技有限公司 | Method and apparatus for estimating ground |
| CN112733813A (en) * | 2021-03-30 | 2021-04-30 | 北京三快在线科技有限公司 | Data noise reduction method and device |
| CN113753081A (en) * | 2019-01-15 | 2021-12-07 | 北京百度网讯科技有限公司 | Method and device for avoiding traffic participants in roadside blind areas of laser radar |
| CN113859228A (en) * | 2020-06-30 | 2021-12-31 | 上海商汤智能科技有限公司 | Vehicle control method and device, electronic equipment and storage medium |
| CN113866791A (en) * | 2020-06-30 | 2021-12-31 | 商汤集团有限公司 | Processing method and processing device for data collected by radar device |
-
2022
- 2022-02-09 CN CN202210121510.9A patent/CN114545443A/en not_active Withdrawn
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170185089A1 (en) * | 2015-12-27 | 2017-06-29 | Toyota Motor Engineering & Manufacturing North America, Inc. | Detection of overhanging objects |
| US20190138823A1 (en) * | 2017-11-09 | 2019-05-09 | Here Global B.V. | Automatic occlusion detection in road network data |
| US20200158875A1 (en) * | 2018-11-15 | 2020-05-21 | Beijing Didi Infinity Technology And Development C O., Ltd. | Systems and methods for correcting a high-definition map based on detection of obstructing objects |
| CN113753081A (en) * | 2019-01-15 | 2021-12-07 | 北京百度网讯科技有限公司 | Method and device for avoiding traffic participants in roadside blind areas of laser radar |
| CN112558035A (en) * | 2019-09-24 | 2021-03-26 | 北京百度网讯科技有限公司 | Method and apparatus for estimating ground |
| CN113859228A (en) * | 2020-06-30 | 2021-12-31 | 上海商汤智能科技有限公司 | Vehicle control method and device, electronic equipment and storage medium |
| CN113866791A (en) * | 2020-06-30 | 2021-12-31 | 商汤集团有限公司 | Processing method and processing device for data collected by radar device |
| CN112130165A (en) * | 2020-09-15 | 2020-12-25 | 北京三快在线科技有限公司 | Positioning method, positioning device, positioning medium and unmanned equipment |
| CN112733813A (en) * | 2021-03-30 | 2021-04-30 | 北京三快在线科技有限公司 | Data noise reduction method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11506769B2 (en) | Method and device for detecting precision of internal parameter of laser radar | |
| CN112733813B (en) | Data noise reduction method and device | |
| JP2020040654A (en) | Yaw-angle determination method, yaw-angle determination device, equipment, computer-readable storage medium | |
| CN110927742A (en) | Obstacle tracking method, device, equipment and storage medium | |
| CN111311709A (en) | Method and device for generating high-precision map | |
| CN107609510B (en) | Positioning method and device for lower set of quayside container crane | |
| CN111797711A (en) | Model training method and device | |
| CN111353417A (en) | Target detection method and device | |
| CN112418038A (en) | Human body detection method, human body detection device, electronic equipment and medium | |
| CN114077252B (en) | Robot collision obstacle distinguishing device and method | |
| CN113486775A (en) | Target tracking method, system, electronic equipment and storage medium | |
| CN112990099A (en) | Method and device for detecting lane line | |
| CN112462403A (en) | Positioning method, positioning device, storage medium and electronic equipment | |
| CN114545443A (en) | Blind area identification method and device | |
| CN114631124A (en) | Three-dimensional point cloud segmentation method and device and movable platform | |
| US20230367319A1 (en) | Intelligent obstacle avoidance method and apparatus based on binocular vision, and non-transitory computer-readable storage medium | |
| CN114332201A (en) | Model training and target detection method and device | |
| CN114623824A (en) | Method and device for determining barrier speed | |
| CN114495065A (en) | Target object identification method and device | |
| CN114549579A (en) | Target tracking method and device | |
| CN114299147A (en) | Positioning method, positioning device, storage medium and electronic equipment | |
| CN113887351A (en) | Obstacle detection method and obstacle detection device for unmanned driving | |
| CN114187355A (en) | Image calibration method and device | |
| CN112329547A (en) | Data processing method and device | |
| CN113205144B (en) | Model training method and 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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220527 |
|
| WW01 | Invention patent application withdrawn after publication |