CN115236641A - Detection method and device for radar obstruction, computer equipment, chip and terminal - Google Patents

Detection method and device for radar obstruction, computer equipment, chip and terminal Download PDF

Info

Publication number
CN115236641A
CN115236641A CN202210662153.7A CN202210662153A CN115236641A CN 115236641 A CN115236641 A CN 115236641A CN 202210662153 A CN202210662153 A CN 202210662153A CN 115236641 A CN115236641 A CN 115236641A
Authority
CN
China
Prior art keywords
point cloud
radar
cloud frame
real
time
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
Application number
CN202210662153.7A
Other languages
Chinese (zh)
Inventor
游昌斌
郭翔宇
鲁锦程
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Qingdao Vehicle Intelligence Pioneers Inc
Original Assignee
Qingdao Vehicle Intelligence Pioneers Inc
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Qingdao Vehicle Intelligence Pioneers Inc filed Critical Qingdao Vehicle Intelligence Pioneers Inc
Priority to CN202210662153.7A priority Critical patent/CN115236641A/en
Publication of CN115236641A publication Critical patent/CN115236641A/en
Pending legal-status Critical Current

Links

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
    • 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
    • G01S7/497—Means for monitoring or calibrating
    • 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

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)
  • Radar Systems Or Details Thereof (AREA)

Abstract

The invention discloses a method and a device for detecting radar shielding objects, computer equipment, a chip and a terminal, relates to the technical field of detection, and mainly aims to solve the problem of detection efficiency of the radar shielding objects of vehicles in the conventional mining area. The method mainly comprises the following steps: acquiring real-time point cloud frames acquired by different types of radars; determining a target point cloud frame corresponding to the real-time point cloud frame based on a time threshold; counting the total number of point cloud frames and the number of abnormal point cloud frames between the real-time point cloud frame and the target point cloud frame; and if the ratio of the number of the abnormal point cloud frames to the total number of the point cloud frames is greater than the ratio threshold of the number of the abnormal frames, determining that the radar is shielded, and realizing the detection of the radar shielding object.

Description

Detection method and device for radar obstruction, computer equipment, chip and terminal
Technical Field
The invention relates to the technical field of detection, in particular to a method and a device for detecting a radar obstruction, computer equipment, a chip and a terminal.
Background
In the field of autonomous driving, lidar is one of the important sensors in autonomous driving sensing systems to sense the surrounding environment. Because the radar lens is exposed in the external environment for a long time, objects such as dust and particles can be adhered to the mirror surface of the radar lens, laser reflection and receiving of the radar are affected, the distance of the surrounding environment cannot be accurately detected, and therefore the sensing system for automatic driving is affected. Especially to the more abominable mining area environment, intelligent vehicle more need to have the shelter to the radar and detect to reduce vehicle and staff's occurence of failure.
At present, current detection to radar shelter is usually based on artifical cleanness, perhaps installs dirty sensor, when reacing dirty threshold value, triggers cleaning device, but, artifical cleanness has increased manpower and materials, and can't be timely effectual clears away the shelter, and adds special hardware equipment and can the greatly increased equipment cost, and equipment structure is comparatively complicated, can't satisfy the effective clean demand of vehicle radar in the mining area to the detection efficiency of radar shelter has been reduced.
Disclosure of Invention
In view of this, the present invention provides a method and an apparatus for detecting radar shelters, a storage medium, and a computer device, and mainly aims to solve the problem of detection efficiency of radar shelters for vehicles in an existing mine.
According to an aspect of the present invention, there is provided a method of detecting a radar obstruction, including:
s1: acquiring real-time point cloud frames acquired by different types of radars;
s2: determining a target point cloud frame corresponding to the real-time point cloud frame based on a time threshold;
s3: counting the total number of the point cloud frames and the number of abnormal point cloud frames between the real-time point cloud frame and the target point cloud frame;
s4: and if the ratio of the number of the abnormal point cloud frames to the total number of the point cloud frames is greater than the ratio threshold of the number of the abnormal frames, determining that the radar is shielded.
Further, prior to the determining a target point cloud frame corresponding to the real-time point cloud frame based on a time threshold, the method further comprises:
acquiring normal point number in real-time point cloud frames collected by different types of radars and a normal point number ratio threshold corresponding to the different types of radars;
if the ratio of the number of normal points in the real-time point cloud frame to the total number of the points is greater than the normal point number ratio threshold, determining the state identifier of the real-time point cloud frame as a normal point cloud frame;
if the ratio of the number of normal points to the total number of points in the real-time point cloud frame is less than or equal to the normal point number ratio threshold, determining the state identifier of the real-time point cloud frame as an abnormal point cloud frame;
and storing the time stamps and the state identifications of the real-time point cloud frames in a target container according to the time sequence of obtaining the real-time point cloud frames, wherein one point cloud frame corresponds to one time stamp and one state identification.
Further, the determining a target point cloud frame corresponding to the real-time point cloud frame based on a time threshold comprises:
inquiring a target time stamp corresponding to the end point of the time threshold in the target container by taking the time stamp of the real-time point cloud frame as a starting point and the time threshold as an inquiry length;
and determining the point cloud frame corresponding to the target timestamp as a target point cloud frame.
Further, the counting the total number of the point cloud frames and the number of the abnormal point cloud frames between the real-time point cloud frame and the target point cloud frame comprises:
in the target container, counting the total number of point cloud frames between the real-time point cloud frame and the target point cloud frame based on the number of timestamps or the number of state identifications;
and counting the number of the abnormal point cloud frames between the real-time point cloud frame and the target point cloud frame based on the number of the abnormal state identifications.
Further, the obtaining the normal point number ratio threshold corresponding to the different types of radars includes:
acquiring a test point cloud frame of a radar of any type under a first preset occlusion degree value and a second preset occlusion degree value, wherein the first preset occlusion degree value is smaller than the second preset occlusion degree value;
identifying abnormal points in the test point cloud frame, counting the number of the abnormal points in the test point cloud frame, taking the difference value between the total number of the points in the test point cloud frame and the number of the abnormal points as the number of the normal points of the test point cloud frame, and taking the ratio of the number of the normal points to the total number of the points as the normal point number ratio threshold value under the corresponding preset occlusion degree value;
and taking the middle value between the normal point number ratio threshold value under the first preset shielding degree value and the normal point number ratio threshold value under the second preset shielding degree value as the normal point number ratio threshold value corresponding to any type of radar.
Further, the method further comprises:
setting a capacity parameter threshold of the target container, wherein the capacity parameter threshold comprises a time capacity parameter threshold or a frame number capacity parameter threshold;
updating the target container when the capacity of the target container reaches a corresponding capacity parameter threshold.
Further, before determining the target point cloud frame corresponding to the real-time point cloud frame based on a time threshold, the method further comprises:
setting a radar with an autonomous occlusion detection function as a specified type radar;
identifying and acquiring a radar type of the real-time point cloud frame through the real-time point cloud frame;
when the type of the radar is identified to be the designated type of radar, acquiring a fault code of the designated type of radar, and if the fault code indicates that the designated type of radar is in a non-shielding state, judging that the designated type of radar is in the non-shielding state;
and if the fault code indicates that the radar of the specified type is in the shielding state, repeating the steps S2-S4 to judge whether the radar of the specified type is shielded.
Further, after determining that the radar is occluded, the method further includes:
outputting shielding fault warning information to a control safety subsystem so that the control safety subsystem controls the vehicle provided with the radar to perform speed reduction processing and informs a security officer to perform clearing processing; or controlling the safety subsystem to start the corresponding automatic cleaning device.
According to another aspect of the present invention, there is provided a radar blocking object detection apparatus, including:
the acquisition module is used for acquiring real-time point cloud frames acquired by different types of radars;
a first determining module for determining a target point cloud frame corresponding to the real-time point cloud frame based on a time threshold;
the counting module is used for counting the total number of the point cloud frames and the number of abnormal point cloud frames between the real-time point cloud frame and the target point cloud frame;
and the second determining module is used for determining that the radar is shielded if the ratio of the number of the abnormal point cloud frames to the total number of the point cloud frames is greater than the ratio threshold of the number of the abnormal frames.
Further, the apparatus further comprises: a third determining module, a storing module,
the acquisition module is also used for acquiring the normal point number in the real-time point cloud frames acquired by different types of radars and the normal point number ratio threshold corresponding to the different types of radars;
the third determining module is configured to determine the status identifier of the real-time point cloud frame as a normal point cloud frame if the ratio of the number of normal points in the real-time point cloud frame to the total number of points is greater than the normal point number ratio threshold; if the ratio of the number of normal points to the total number of points in the real-time point cloud frame is less than or equal to the normal point number ratio threshold, determining the state identifier of the real-time point cloud frame as an abnormal point cloud frame;
the storage module is used for storing the time stamps and the state identifications of the real-time point cloud frames in a target container according to the time sequence of obtaining the real-time point cloud frames, wherein one point cloud frame corresponds to one time stamp and one state identification.
Further, the first determining module is specifically configured to query, in the target container, a target timestamp corresponding to an end point of the time threshold, with a timestamp of the real-time point cloud frame as a starting point and the time threshold as a query length; and determining the point cloud frame corresponding to the target timestamp as a target point cloud frame.
Further, the counting module is specifically configured to count, in the target container, a total number of point cloud frames between the real-time point cloud frame and the target point cloud frame based on the number of timestamps or the number of status identifiers; and counting the number of the abnormal point cloud frames between the real-time point cloud frame and the target point cloud frame based on the number of the abnormal state identifications.
Further, the obtaining module comprises:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring a test point cloud frame of a radar of any type under a first preset occlusion degree value and a second preset occlusion degree value, and the first preset occlusion degree value is smaller than the second preset occlusion degree value;
the statistical unit is used for identifying abnormal points in the test point cloud frame, counting the number of the abnormal points in the test point cloud frame, taking the difference value between the total number of the points in the test point cloud frame and the number of the abnormal points as the number of the normal points of the test point cloud frame, and taking the ratio of the number of the normal points to the total number of the points as the normal point number ratio threshold value under the corresponding preset occlusion degree value;
and the determining unit is used for taking a middle value between the normal point number ratio threshold value under the first preset shielding degree value and the normal point number ratio threshold value under the second preset shielding degree value as the normal point number ratio threshold value corresponding to any type of radar.
Further, the apparatus further comprises:
the setting module is used for setting a capacity parameter threshold of the target container, wherein the capacity parameter threshold comprises a time capacity parameter threshold or a frame number capacity parameter threshold;
and the updating module is used for updating the target container when the capacity of the target container reaches the corresponding capacity parameter threshold value.
Further, the apparatus further comprises:
the setting module is also used for setting the radar with the autonomous shielding detection function as a specified type radar;
the acquisition module is also used for identifying and acquiring the radar type of the real-time point cloud frame through the real-time point cloud frame;
when the type of the radar is identified to be the designated type of radar, acquiring a fault code of the designated type of radar, and if the fault code indicates that the designated type of radar is in a non-shielding state, judging that the designated type of radar is in the non-shielding state; and if the fault code indicates that the radar of the specified type is in the shielding state, repeating the steps S2-S4 to judge whether the radar of the specified type is shielded.
Further, the apparatus further comprises:
the output module is used for outputting shielding fault warning information to the control safety subsystem so that the control safety subsystem controls the vehicle provided with the radar to perform speed reduction processing and informs a security officer to perform clearing processing; or controlling the safety subsystem to start the corresponding automatic cleaning device.
According to an aspect of the invention, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of the method of detecting a radar obstruction as described above.
According to an aspect of the invention, there is provided a computer apparatus comprising a memory, a processor and a computer program stored on the memory and executable on the processor; the processor, when executing the computer program, performs the steps of the method for detecting radar obstruction described above.
According to an aspect of the invention, there is provided a chip comprising at least one processor and a communication interface, the communication interface being coupled to the at least one processor, the at least one processor being configured to execute a computer program or instructions to implement the method of detecting a radar obstruction as described above.
According to an aspect of the invention, there is provided a terminal comprising a detection apparatus for a radar obstruction as described above.
By the technical scheme, the technical scheme provided by the embodiment of the invention at least has the following advantages:
the invention provides a method and a device for detecting radar shelters, a medium and computer equipment.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a flow chart of a method for detecting radar obstruction according to an embodiment of the present invention;
FIG. 2 is a flow chart of another method for detecting radar obstruction provided by embodiments of the present invention;
FIG. 3 is a schematic diagram of a timestamp and status identification storage data chain according to an embodiment of the present invention;
FIG. 4 is a flow chart of a method for detecting radar obstruction according to an embodiment of the present invention;
FIG. 5 is a block diagram of an apparatus for detecting radar obstruction according to an embodiment of the present invention;
FIG. 6 is a schematic structural diagram of a computer-readable storage medium according to an embodiment of the present invention;
FIG. 7 is a schematic structural diagram of a computer device according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of a chip according to an embodiment of the present invention;
fig. 9 is a schematic structural diagram of a terminal according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description.
The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.
Techniques, methods, and apparatus known to one of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.
Embodiments of the invention are operational with numerous other general purpose or special purpose computing system environments or configurations. Examples of well known computing systems, environments, and/or configurations that may be suitable for use with the computer system/server include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, hand-held or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network pcs, minicomputer systems, mainframe computer systems, distributed cloud computing environments that include any of the above, and the like.
The computer system/server may be described in the general context of computer system-executable instructions, such as program modules, being executed by a computer system. Generally, program modules may include routines, programs, objects, components, logic, data structures, etc. that perform particular tasks or implement particular abstract data types. The computer system/server may be practiced in distributed cloud computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed cloud computing environment, program modules may be located in both local and remote computer system storage media including memory storage devices.
Example one
The embodiment of the invention provides a method for detecting a radar shelter, which comprises the following steps of:
101. and acquiring real-time point cloud frames acquired by different types of radars.
As a current execution end, the method for detecting a radar blocking object provided in the embodiment of the present invention may be applied to a control end of an unmanned vehicle or a service end of the unmanned vehicle, such as a vehicle control end of the unmanned vehicle, or a remote service end of the unmanned vehicle, so as to detect a radar installed on the unmanned vehicle. When the radars of different radar types are scanned by the real-time radar, point cloud data with a frame as a unit, namely a real-time point cloud frame, is generated, the real-time point cloud frame comprises a plurality of point data, and each point has a three-dimensional coordinate so as to represent a radar scanning result.
102. Determining a target point cloud frame corresponding to the real-time point cloud frame based on a time threshold.
The real-time point cloud frame is obtained by performing real-time radar scanning at the current moment, so that when the current execution end detects the generation message of the real-time point cloud frame, the target point cloud frame corresponding to the real-time point cloud frame can be determined based on the time threshold, namely the target point cloud frame corresponding to the real-time point cloud frame is searched according to the duration of the time threshold. Specifically, when different radar types are scanned, point cloud frames with different radar line numbers can be obtained by scanning for one second, so that the obtained point cloud frames can be stored according to the corresponding relation of time in historical radar scanning time, and a target point cloud frame corresponding to the real-time point cloud frame is determined based on a time threshold. For example, if the time threshold is 5 seconds, forward search is performed for 5 seconds at the time point of the real-time point cloud frame obtained by radar scanning at the current time, and the point cloud frame corresponding to the time before 5 seconds is determined as the target point cloud frame.
It should be noted that, the time threshold of 5 seconds is only an exemplary illustration, and the time threshold may be set according to an actual application scenario, for example, it may be set to 1 second, 3 seconds, 6 seconds, 8 seconds, 10 seconds, and the like, and the specific setting of the time threshold is not further limited in the present invention.
103. And counting the total number of the point cloud frames between the real-time point cloud frame and the target point cloud frame and the number of abnormal point cloud frames.
In the embodiment of the invention, the real-time point cloud frame is the point cloud frame obtained at the current moment, and the target point cloud frame is the point cloud frame which is searched according with the time threshold according to the current moment, so that a plurality of point cloud frames exist between the real-time point cloud frame and the target point cloud frame, and the total number of the point cloud frames and the number of corresponding abnormal point cloud frames can be counted. The total number of the point cloud frames is the total number including normal point cloud frames and abnormal point cloud frames, and therefore detection of the shielding object is determined according to the ratio of the number of the abnormal point cloud frames to the total number of the point cloud frames and the ratio threshold of the number of the abnormal frames. Specifically, the abnormal point cloud frame may be a point cloud frame artificially marked as an abnormal state identifier, or a point cloud frame judged to be marked as an abnormal state identifier based on point cloud data, and the embodiment of the present invention is not particularly limited.
It should be noted that, because radars of different radar types have scan lines with different line numbers, when determining whether the state of the point cloud frame is normal based on the point cloud data, the proportion of the number of normal points is also different, and therefore, the determination manner of the abnormal point cloud frames of different radar types is different, for example, the three-dimensional coordinates xyz of the abnormal point of one type of radar are all null (NAN), and the three-dimensional coordinates xyz of the abnormal point of another type of radar are all 0.
104. And if the ratio of the number of the abnormal point cloud frames to the total number of the point cloud frames is greater than the ratio threshold of the number of the abnormal frames, determining that the radar is shielded.
In the embodiment of the invention, when the ratio of the number of the abnormal point cloud frames to the total number of the point cloud frames is greater than the ratio threshold of the number of the abnormal frames, the radar lens is shielded. The proportion threshold of the number of abnormal frames may be preconfigured based on radar shielding requirements, and is preferably 50%, that is, when the number of abnormal point cloud frames is more than 50% of the total number of point cloud frames, it indicates that a radar is shielded, or a shielding object is attached to a radar lens. It should be noted that the percentage of abnormal frames corresponding to different types of radars may be the same or different, for example, the percentage of abnormal frames of the first type of radar is set to 50%, the percentage of abnormal frames of the second type of radar is set to 60%, and the percentage of abnormal frames of the third type of radar is set to 70%, in practical applications, the percentage of abnormal frames may be set according to characteristics of the different types of radars, and the percentage of abnormal frames is not further limited in the embodiment of the present invention. Of course, the number of abnormal frames of all types of radars may be set to 50%, 60%, 70%, 80%, etc. in proportion to the threshold.
In addition, in another embodiment of the present invention, as shown in fig. 2, after step S1 (acquiring real-time point cloud frames acquired by different types of radars), before step S2 (determining a target point cloud frame corresponding to the real-time point cloud frame based on a time threshold), the method further includes: the method comprises the following steps:
201. acquiring normal point number in real-time point cloud frames collected by different types of radars and a normal point number ratio threshold corresponding to the different types of radars;
202. if the ratio of the number of normal points in the real-time point cloud frame to the total number of the points is greater than the normal point number ratio threshold, determining the state identifier of the real-time point cloud frame as a normal point cloud frame;
203. if the ratio of the number of normal points to the total number of points in the real-time point cloud frame is less than or equal to the normal point number ratio threshold, determining the state identifier of the real-time point cloud frame as an abnormal point cloud frame;
204. and storing the time stamps and the state identifications of the real-time point cloud frames in a target container according to the time sequence of obtaining the real-time point cloud frames, wherein one point cloud frame corresponds to one time stamp and one state identification.
In order to ensure that a state identifier based on a point cloud frame between a real-time point cloud frame and a target point cloud frame is searched, and a timestamp is conveniently and accurately searched so as to accurately detect a shielding object, real-time point cloud frames corresponding to radar acquisition of different radar types are acquired, and the point cloud frames are composed of a plurality of points, so that the number of normal points acquired by the real-time point cloud frames acquired by different radar types can be acquired, and the normal point number corresponding to the different radar types accounts for a threshold value. Wherein, because different types of radars are when carrying out the radar scanning, the quantity of a point cloud frame mid point that generates is different, and the radar scan line number of different radar types is also different, in order to satisfy the detection demand of the shelter from thing of different radars, consequently, different types of radars can dispose in advance or dynamic generation is used for judging whether normal point count proportion threshold value of point cloud frame is normal to compare with the ratio of normal point count in the real-time point cloud frame and total number of points. The total number of the points is the total number of the points in the real-time point cloud frame, including the number of normal points and the number of abnormal points, and three-dimensional coordinate points of each point are contained in one frame of point cloud data obtained by scanning different radars, namely, a great amount of three-dimensional point data can be contained in one point cloud frame, so that the point cloud is formed. For example, 10000 three-dimensional points, i.e., three-dimensional data including 10000 points, are scanned in one point cloud frame. At this time, for a three-dimensional point in a real-time point cloud frame obtained by normal scanning of the radar, if three-dimensional coordinates x, y and z of the three-dimensional point all have corresponding specific scanning numerical values (non-0 or non-null), it is indicated that the three-dimensional point is a normal point, and if the three-dimensional coordinates x, y and z of the three-dimensional point are null or 0, it is indicated that the three-dimensional point is an abnormal point, so that the total number of normal points and abnormal points, the normal number of points and the abnormal number of points in the real-time point cloud frame can be determined based on the specific scanning numerical values of the three-dimensional point, and the ratio based on the number of the normal points and the total number of points is compared with the ratio threshold of the number of the normal points. If the ratio of the number of normal points in the real-time point cloud frame to the total number of the points is greater than the normal point number ratio threshold, then most of the points in the real-time point cloud frame are normal points, and therefore the state identifier of the real-time point cloud frame is determined to be a normal point cloud frame; if the ratio of the number of normal points in the real-time point cloud frame to the total number of the points is smaller than or equal to the normal point number ratio threshold, most of the points in the real-time point cloud frame are abnormal points, and therefore the state identifier of the real-time point cloud frame is determined to be the abnormal point cloud frame. In addition, in the embodiment of the invention, the radar types can be distinguished based on different radar manufacturers and also can be distinguished based on different radar lines, for example, the normal point number ratio thresholds corresponding to the fast-tening RS-bpearl radar, the osuster radar and the hijiang Livox radar are all different, preferably, the normal point number ratio threshold of the osuster radar is set to be 0.2, the normal point number ratio threshold of the fast-tening RS-bpearl radar is set to be 0.78, and the normal point number ratio threshold of the hijiang Livox radar is 0.5.
It should be noted that, in order to accurately find the target point cloud frame corresponding to the real-time point cloud frame based on the time threshold, when the corresponding real-time point cloud frame at different current time is determined, the abnormal point cloud frame or the normal point cloud frame is stored in the target container according to the time sequence of obtaining the real-time point cloud frame, and the time stamp and the status identifier of the real-time point cloud frame are stored in the target container. When the point cloud frames are stored in the target container, scanning time of each point cloud frame is stored as a time stamp while the point cloud frames are stored, and meanwhile, the state identifications of the point cloud frames are stored together. In addition, the TimeStamp and the corresponding state identifier of the point cloud frame stored in the target container may be stored based on a data chain form as shown in fig. 3, timeStamp _ n is a TimeStamp, status _ n is a state identifier of the point cloud frame (current real-time point cloud frame), and the target container may be a database or a storage unit with a preset storage amount.
In another embodiment of the present invention, for further definition and illustration, the step of determining a target point cloud frame corresponding to the real-time point cloud frame based on a time threshold comprises: inquiring a target time stamp corresponding to the end point of the time threshold in the target container by taking the time stamp of the real-time point cloud frame as a starting point and the time threshold as an inquiry length; and determining the point cloud frame corresponding to the target timestamp as a target point cloud frame.
The time stamps corresponding to the real-time point cloud frames at different current moments and the state identifications corresponding to the time stamps are stored in the target container, so that when the corresponding target point cloud frames are determined, specifically, the target time stamps corresponding to the end points of the time thresholds are inquired from the target container by taking the time stamps of the real-time point cloud frames as the starting points of searching and taking the time thresholds as the inquiry lengths, at the moment, the point cloud frames corresponding to the target time stamps are the target point cloud frames, and therefore the point cloud frames corresponding to the target time stamps are determined to be the target point cloud frames. <xnotran> , TimeStamp _ n , 5 , 5 TimeStamp _0, TimeStamp _0 TimeStamp _ n , TimeStamp _0 TimeStamp _ n . </xnotran>
It should be noted that, because the target container stores different timestamps and state identifiers of corresponding point cloud frames in a time sequence, when a time threshold is used as a query length for searching, and when the data storage space in the target container can just store all the timestamps and state identifiers in a time range corresponding to the time threshold, the timestamp of the first frame in the target container can be used as the target timestamp. When the data storage space in the target container may store the timestamp and the state identifier in the time range corresponding to the time threshold, the non-first-frame timestamp in the target container may be used as the target timestamp, for example, the non-first-frame timestamp may be a third-frame timestamp, a tenth-frame timestamp, and the like, and is determined only according to the data storage space of the target container.
In another embodiment of the present invention, for further definition and explanation, the steps further comprise: setting a capacity parameter threshold of the target container, wherein the capacity parameter threshold comprises a time capacity parameter threshold or a frame number capacity parameter threshold; updating the target container when the capacity of the target container reaches a corresponding capacity parameter threshold.
Since the data storage space of the target container may be greater than or equal to the data space storing the timestamp and the state identifier corresponding to the time threshold, in order to ensure that the total number of the point cloud frames in the target container is not changed for statistics, the threshold of the capacity parameter of the target container may be set in advance. The capacity parameter threshold includes a time capacity parameter threshold or a frame number capacity parameter threshold to limit the storage amount of point cloud frames and the storage amount of timestamps in the target container. When the capacity of the target container reaches the corresponding capacity parameter threshold, the target container is updated, and at this time, the timestamp and the state identifier of the most recent moment (the first frame) can be deleted to add the timestamp for storing the most recent moment (the current real-time point cloud frame),State identification to ensure the total number n of point cloud frames in the target container t And is not changed. Specifically, if the most previous time (the first frame) is an abnormal point cloud frame, the number n of the corresponding abnormal point cloud frames is n a 1 would be decremented. If the latest moment (the current real-time point cloud frame) is an abnormal point cloud frame, the number n of the corresponding abnormal point cloud frames a Adding 1, if the latest moment (the current real-time point cloud frame) is a normal point cloud frame, determining the number n of corresponding abnormal point cloud frames a Invariant, based on the number n of anomalous point cloud frames a And the total number n of point cloud frames t Based on n a /n t And comparing the number of the abnormal frames with a threshold to determine whether the radar is blocked, which is not specifically limited in the embodiment of the present invention.
It should be noted that, because the data storage space of the target container may be set, if the time range between the first frame timestamp in the target container and the current time is smaller than the time threshold in the process of searching the target timestamp based on the time threshold, it is indicated that the state identifier and the number of timestamps stored in the target container do not meet the requirement of statistics, and therefore, the state identifier of the timestamp and the state identifier of the real-time point cloud frame at the next time are stored based on the radar scanning performed at the next time until the time range between the first frame timestamp and the current time is equal to the time threshold, and statistics may be performed.
For example, only the timestamp and the corresponding state identifier within the last 5 seconds are stored in the target container, the time threshold is configured to be 5 seconds, the vehicle is driven for 20 seconds, the radar scans the point cloud for 1 second to be 10 frames, and then the point cloud frame with 200 frames is obtained. At the initial moment, the target container begins storing timestamp frame1, and as time progresses, liu Xucun reaches timestamp frame50. All timestamps between frame1 and frame50 and state identification are in the target container. If frame1 is the first frame, and the time difference between frame50 and frame1 is 5 seconds, then the state identifier of the 50 frames is counted. When the state identifier corresponding to the timestamp frame51 needs to be stored, the target container is updated, that is, the timestamp frame1 is deleted, at this time, the target container stores frames 2 to frame51, the first frame is the timestamp frame2, and the same time is 5 seconds between the timestamp frames 2 to 51, so as to continue the statistics. Similarly, until the last frame is stored, at this time, the timestamps are from frame151 to frame200, the timestamp of the first frame in the target container is frame151, that is, the latest timestamp and state identifier of one frame are stored, and the timestamp and state identifier of the first frame are deleted, so that the target container can be kept storing the timestamps and state identifiers of 50 frames.
In another embodiment of the present invention, for further definition and illustration, the step of counting the total number of point cloud frames and the number of abnormal point cloud frames between the real-time point cloud frame and the target point cloud frame comprises:
in the target container, counting the total number of point cloud frames between the real-time point cloud frame and the target point cloud frame based on the number of timestamps or the number of state identifications;
and counting the number of the abnormal point cloud frames between the real-time point cloud frame and the target point cloud frame based on the number of the abnormal state identifications.
In order to accurately count the total amount of point cloud frames and the number of abnormal point cloud frames, specifically, in the target container, after the target point cloud frame is determined, the number of the point cloud frames is counted based on the number of timestamps between the target timestamp of the target point cloud frame and the current time, or the total amount of the point cloud frames is determined based on the number of the target point cloud frame and the identification state of the real-time point cloud frame at the current time. Meanwhile, the number of the abnormal point cloud frames in the target container can be directly counted based on the number of the abnormal state identifications, and the embodiment of the invention is not particularly limited.
In another embodiment of the present invention, for further definition and explanation, as shown in fig. 4, the steps further include:
301. acquiring a test point cloud frame of a radar of any type under a first preset occlusion degree value and a second preset occlusion degree value;
302. identifying abnormal points in the test point cloud frame, counting the number of the abnormal points in the test point cloud frame, taking the difference value between the total number of the points in the test point cloud frame and the number of the abnormal points as the number of the normal points of the test point cloud frame, and taking the ratio of the number of the normal points to the total number of the points as the normal point number ratio threshold value under the corresponding preset occlusion degree value;
303. and taking the middle value between the normal point number ratio threshold value under the first preset shielding degree value and the normal point number ratio threshold value under the second preset shielding degree value as the normal point number ratio threshold value corresponding to any type of radar.
Due to the fact that the line numbers of different types of radars are different, the number of the points in the obtained point cloud frame is different, in order to accurately judge the state of the point cloud frame, the point cloud frame can be configured based on a test mode besides manual direct configuration of a normal point number ratio threshold, and therefore detection accuracy of the shielding object is improved. Specifically, a test point cloud frame of a radar of any type of radar under a first preset shielding degree value and a second preset shielding degree value is obtained, and at the moment, the first preset shielding degree value and the second preset shielding degree value are respectively used for representing different degrees of shielding of a radar lens by a shielding object, and if the radar lens is slightly shielded and seriously shielded, the radar lens respectively corresponds to different shielding degree values. The acquired first preset shielding degree value and the second preset shielding degree value can be used as corresponding degree values for slight shielding and serious shielding based on shielding objects such as sludge and dirty water in front of the radar lens under a test scene, wherein the first preset shielding degree value is smaller than the second preset shielding degree value. In a test scene, for different shielding degrees, identifying abnormal points in a test point cloud frame acquired by any type of radar, counting the number of the abnormal points, and obtaining the number of normal points, namely, the difference is made between the total number of the points in the test point cloud frame and the number of the abnormal points, at the moment, taking the ratio of the obtained normal points to the total number of the points as a normal points ratio threshold value under the shielding degree, for example, representing the first preset shielding degree value as a slight shielding degree, and taking the normal points ratio threshold value corresponding to the acquired test point cloud frame as a normal points ratio threshold value corresponding to the slight shielding degree.
After the second preset occlusion degree value is obtained by the same method, at this time, in order to configure a normal point number ratio threshold for any type of radar, a middle value between the normal point number ratio threshold under the first preset occlusion degree value and the normal point number ratio threshold under the second preset occlusion degree value is used as the normal point number ratio threshold corresponding to any type of radar. For example, the radar of type a obtains the normal point number ratio threshold a under the first occlusion degree value representing slight occlusion under the test scene 2 The normal point number ratio threshold a under the second occlusion degree value representing serious occlusion 3 Is then based on a 2 And a 3 The middle value between them is used as the normal point number ratio threshold value of the radar of the type a. In addition, because the first preset shielding degree value representing slight shielding is smaller than the second preset shielding degree value representing serious shielding, and the shielding degree in the point cloud frame is more serious and the number of abnormal points is more, the number of normal points corresponding to the obtained first preset shielding degree value accounts for the threshold value a 2 Is greater than the normal point number ratio threshold a corresponding to the second preset shielding degree value 3 。
In another embodiment of the present invention, for further definition and illustration, before the step of determining the target point cloud frame corresponding to the real-time point cloud frame based on a time threshold, the method further comprises:
setting a radar with an autonomous occlusion detection function as a specified type radar;
identifying and acquiring the radar type of the real-time point cloud frame through the real-time point cloud frame;
when the type of the radar is identified to be the designated type of radar, acquiring a fault code of the designated type of radar, and if the fault code indicates that the designated type of radar is in a non-shielding state, judging that the designated type of radar is in the non-shielding state;
and if the fault code indicates that the radar of the specified type is in the shielding state, repeating the steps S2-S4 to judge whether the radar of the specified type is shielded.
Because some radars have the function of autonomous occlusion detection in different types of radars, for the radars, in order to further simplify the detection steps of the occlusion objects and improve the efficiency of the occlusion object detection so as to meet the validity of the radars of different radar types for detecting the occlusion objects, the radars with the function of autonomous occlusion detection are set as the specific type radars, for example, if the Livox in Xinjiang has the function of autonomous occlusion detection, the Livox in Xinjiang is set as the specific type radars. At this time, before executing step S2 in the embodiment of the present invention, the radar type of the collected real-time point cloud frame is identified based on the real-time point cloud frame, so as to determine whether the radar at this time is a radar with an autonomous occlusion detection function. The radar type is identified, and can be determined based on the message name, the message identifier and the like of the generated message of the acquired real-time point cloud frame, and the radar type includes but is not limited to Sagitar RS-bpearl, ouster and Livox in Xinjiang. When the type of the radar is identified to be the designated type of radar, the radar can automatically detect the shielding object, so that the fault code of the designated type of radar is obtained, and whether the radar is shielded or not is determined based on the fault code. In the embodiment of the invention, for the specified type radar, if the fault code indicates that the specified type radar is in a non-shielding state, the radar is not shielded, and because the specified type radar is identified in the non-shielding state accurately, the specified type radar is judged to be in the non-shielding state. However, when the fault code indicates that the specified type of radar is in a shielding state, in order to avoid misjudgment of shielding object detection caused by hardware design defects of the radar, light irradiation, scraping of glass on the surface of the radar, and the like, steps S2 to S4 in the embodiment of the invention are executed to judge whether the specified type of radar is shielded, so that the detection accuracy of the shielding object is improved.
In a specific application scenario, the specified radar type may be libox in large-ARUM, a fault code of the Lidar in large-ARUM is read in a subscription mode, and if the radar is determined to be in a non-shielding state, shielding object detection in the embodiment of the invention may not be executed. If the shielding state is determined based on the fault code, the steps S2-S4 in the embodiment of the invention are executed, so that the detection accuracy is improved based on the detection of the radar shielding object in the embodiment of the invention.
In another embodiment of the present invention, for further definition and explanation, after the step of determining that an obstruction is present in the radar, the method further comprises: outputting shielding fault warning information to a control safety subsystem to enable the control safety subsystem to control the vehicle provided with the radar to perform speed reduction processing and inform a security officer to perform clearing processing; or controlling the safety subsystem to start the corresponding automatic cleaning device.
In order to ensure that the detected shelters are cleared in time, after the shelters are determined to exist in the radar, shelters fault warning information is output to the control safety subsystem, so that the control safety subsystem can control the vehicle provided with the radar to perform speed reduction processing, and the vehicle is prevented from operating under the condition that the radar cannot be scanned clearly. Or controlling the safety subsystem to start a corresponding automatic cleaning device, where the control safety subsystem may be a subsystem with an automatic cleaning device installed on a vehicle, or may be a terminal for remotely controlling the automatic cleaning device installed on the vehicle, and the embodiment of the present invention is not particularly limited. In addition, while the blocking fault warning information is output, in order to ensure that the vehicle can run safely, a security officer can be informed to clear the blocking object so as to ensure the safety of the vehicle.
Compared with the prior art, the embodiment of the invention provides a method for detecting radar shelters, which comprises the steps of acquiring real-time point cloud frames acquired by different types of radars; determining a target point cloud frame corresponding to the real-time point cloud frame based on a time threshold; counting the total number of point cloud frames and the number of abnormal point cloud frames between the real-time point cloud frame and the target point cloud frame; and if the ratio of the number of the abnormal point cloud frames to the total number of the point cloud frames is greater than the ratio threshold of the number of the abnormal point cloud frames, determining that the radar is shielded, meeting the shielding object detection requirements of different radars, and reducing the material cost for installing shielding object detection hardware, so that the detection efficiency and accuracy of the radar shielding object are improved, and the effective cleaning requirement of the mining area vehicle radar is met.
Example two
Further, as an implementation of the method shown in fig. 1, an embodiment of the present invention provides a radar blocking object detection apparatus, as shown in fig. 5, the apparatus includes:
an obtaining module 41, configured to obtain real-time point cloud frames acquired by different types of radars;
a first determining module 42 for determining a target point cloud frame corresponding to the real-time point cloud frame based on a time threshold;
a counting module 43, configured to count the total number of point cloud frames and the number of abnormal point cloud frames between the real-time point cloud frame and the target point cloud frame;
a second determining module 44, configured to determine that the radar is blocked if a ratio of the number of abnormal point cloud frames to the total number of point cloud frames is greater than a ratio threshold of the number of abnormal frames.
Further, the apparatus further comprises: a third determining module, a storing module,
the obtaining module 41 is further configured to obtain normal point numbers in real-time point cloud frames collected by different types of radars, and a normal point number ratio threshold corresponding to the different types of radars;
the third determining module is configured to determine the status identifier of the real-time point cloud frame as a normal point cloud frame if the ratio of the number of normal points in the real-time point cloud frame to the total number of points is greater than the normal point number ratio threshold; if the ratio of the number of normal points to the total number of points in the real-time point cloud frame is less than or equal to the normal point number ratio threshold, determining the state identifier of the real-time point cloud frame as an abnormal point cloud frame;
the storage module is used for storing the time stamps and the state identifications of the real-time point cloud frames in a target container according to the time sequence of obtaining the real-time point cloud frames, wherein one point cloud frame corresponds to one time stamp and one state identification.
Further, the first determining module 42 is specifically configured to query, in the target container, a target timestamp corresponding to an end point of the time threshold, with a timestamp of the real-time point cloud frame as a starting point and the time threshold as a query length; and determining the point cloud frame corresponding to the target timestamp as a target point cloud frame.
Further, the counting module 43 is specifically configured to count, in the target container, a total number of point cloud frames between the real-time point cloud frame and the target point cloud frame based on the number of timestamps or the number of status identifiers; and counting the number of the abnormal point cloud frames between the real-time point cloud frame and the target point cloud frame based on the number of the abnormal state identifications.
Further, the obtaining module 41 includes:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring a test point cloud frame of a radar of any type under a first preset occlusion degree value and a second preset occlusion degree value, and the first preset occlusion degree value is smaller than the second preset occlusion degree value;
the statistical unit is used for identifying abnormal points in the test point cloud frame, counting the number of the abnormal points in the test point cloud frame, taking the difference value between the total number of the points in the test point cloud frame and the number of the abnormal points as the number of the normal points of the test point cloud frame, and taking the ratio of the number of the normal points to the total number of the points as the normal point number ratio threshold value under the corresponding preset occlusion degree value;
and the determining unit is used for taking a middle value between the normal point number ratio threshold value under the first preset shielding degree value and the normal point number ratio threshold value under the second preset shielding degree value as the normal point number ratio threshold value corresponding to any type of radar.
Further, the apparatus further comprises:
the setting module is used for setting a capacity parameter threshold of the target container, wherein the capacity parameter threshold comprises a time capacity parameter threshold or a frame number capacity parameter threshold;
and the updating module is used for updating the target container when the capacity of the target container reaches the corresponding capacity parameter threshold value.
Further, the apparatus further comprises:
the setting module is also used for setting the radar with the autonomous shielding detection function as a specified type radar;
the acquisition module is also used for identifying and acquiring the radar type of the real-time point cloud frame through the real-time point cloud frame;
when the type of the radar is identified to be the designated type of radar, acquiring a fault code of the designated type of radar, and if the fault code indicates that the designated type of radar is in a non-shielding state, judging that the designated type of radar is in the non-shielding state; and if the fault code indicates that the radar of the specified type is in the shielding state, repeating the steps S2-S4 to judge whether the radar of the specified type is shielded.
Further, the apparatus further comprises:
and the output module is used for outputting shielding fault warning information to the control safety subsystem so as to enable the control safety subsystem to control the vehicle provided with the radar to perform speed reduction processing and inform a security officer to perform clearing processing.
It should be noted that the structural composition, the function implementation, and the technical effect of the detection device for the radar blocking object correspond to the implementation steps of the detection method for the radar blocking object one to one, and the same contents are not repeated.
The embodiment of the invention provides a detection device of a radar shelter, compared with the prior art, the detection device of the radar shelter is characterized in that real-time point cloud frames acquired by different types of radars are obtained, a target point cloud frame corresponding to the real-time point cloud frames is determined based on a time threshold, the total number of the point cloud frames and the number of abnormal point cloud frames between the real-time point cloud frames and the target point cloud frames are counted, and if the ratio of the number of the abnormal point cloud frames to the total number of the point cloud frames is greater than the ratio threshold of the number of the abnormal point cloud frames, the radar is determined to be sheltered, the shelter detection requirements of different radars are met, the material cost of shelter detection hardware installation is reduced, the detection efficiency and accuracy of the radar shelter are improved, and the effective cleaning requirements of radar of vehicles in a mining area are met.
EXAMPLE III
Fig. 6 is a schematic structural diagram of a computer-readable storage medium according to an embodiment of the present invention, and as shown in fig. 6, a computer-readable storage medium 500 stores a computer program 510, and when the computer program 510 is executed by a processor, the computer program is used to implement the method for detecting a radar obstruction according to the first embodiment. In the first embodiment, a method for detecting a radar blocking object has been described in detail, and is not described herein again.
The methods described in the above embodiments may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. Computer-readable media 500 may include computer storage media and communication media, and may include any medium that can communicate a computer program from one place to another. A storage medium may be any target medium that can be accessed by a computer.
As one possible design, the computer-readable medium 500 may include a compact disk read-only memory (CD-ROM), RAM, ROM, EEPROM, or other optical disk storage; the computer readable medium may include a disk memory or other disk storage device. Also, any connecting line may also be properly termed a computer-readable medium. For example, if the software is transmitted from a website, server, or other remote source using a coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of medium. Disk and disc, as used herein, includes Compact Disc (CD), laser disc, optical disc, digital Versatile Disc (DVD), floppy disk and blu-ray disc where disks usually reproduce data magnetically, while discs reproduce data optically with lasers.
Example four
Fig. 7 is a schematic structural diagram of a computer device according to an embodiment of the present invention, and as shown in fig. 7, the computer device 600 includes a memory 610, a processor 620, and a computer program stored in the memory 610 and executable by the processor, where the processor 620 executes the computer program 640 to perform the steps of the method according to the present invention, so as to implement accurate detection of an obstruction on a radar lens. Note that the computer program 440 in this embodiment is the same as the computer program 310.
The memory 610 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a ROM. The memory 620 has a storage space 630 storing a computer program 640 for performing any of the method steps of the above-described method. The computer program 640 may be read from or written to one or more computer program products. These computer program products comprise a program code carrier such as a hard disk, a Compact Disc (CD), a memory card or a floppy disk. Such a computer program product is typically a computer readable storage medium such as described in fig. 6. The computer device may include a plurality of processors, each of which may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. A processor herein may refer to one or more devices, circuits, and/or processing cores for processing data (e.g., computer program instructions).
EXAMPLE five
Fig. 8 is a schematic structural diagram of a chip according to an embodiment of the present invention, and as shown in fig. 8, the chip 800 includes one or more than two (including two) processors 810 and a communication interface 830. The communication interface 830 is coupled to the at least one processor 810, and the at least one processor 810 is configured to execute a computer program or instructions to implement the method for detecting a radar obstruction as described in the above method embodiments.
Preferably, memory 840 stores the following elements: an executable module or a data structure, or a subset thereof, or an expanded set thereof.
In an embodiment of the invention, memory 840 may comprise both read-only memory and random access memory and provide instructions and data to processor 810. A portion of the memory 840 may also include non-volatile random access memory (NVRAM).
In an embodiment of the invention, memory 840, communication interface 830, and memory 840 are coupled together by bus system 820. The bus system 820 may include a power bus, a control bus, a status signal bus, and the like, in addition to a data bus. For ease of description, the various buses are identified in FIG. 8 as bus system 820.
The method described in the above embodiments of the present invention may be applied to the processor 810 or implemented by the processor 810. Processor 810 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 810. The processor 810 may be a general-purpose processor (e.g., a microprocessor or a conventional processor), a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an FPGA (field-programmable gate array) or other programmable logic device, discrete gate, transistor logic device, or discrete hardware component, and the processor 810 may implement or execute the methods, steps, and logic blocks disclosed in the embodiments of the present invention.
EXAMPLE six
Fig. 9 is a schematic structural diagram of a terminal according to an embodiment of the present invention, and as shown in fig. 9, the terminal 900 includes the apparatus 910 for detecting a radar obstruction.
The terminal 900 can execute the method described in the above embodiments through the radar obstruction detection apparatus 910. It can be understood that the implementation manner of the terminal 900 for controlling the device 910 for detecting a radar obstruction may be set according to an actual application scenario, and the embodiment of the present invention is not limited in particular.
The terminal 900 includes but is not limited to: the system comprises a server, a vehicle-mounted terminal, a vehicle-mounted controller, a vehicle-mounted module, a vehicle-mounted component, a vehicle-mounted chip, a vehicle-mounted unit, a vehicle-mounted radar or a vehicle-mounted camera and other sensors, wherein the vehicle can implement the method provided by the invention through the vehicle-mounted terminal, the vehicle-mounted controller, the vehicle-mounted module, the vehicle-mounted component, the vehicle-mounted chip, the vehicle-mounted unit, the vehicle-mounted radar or the camera.
The vehicle in the embodiment of the invention comprises a passenger vehicle and a commercial vehicle, and common vehicle types of the commercial vehicle comprise but are not limited to: pickup trucks, mini trucks, light trucks, mini passenger cars, self-unloading vehicles, trucks, tractors, trailers, utility vehicles, mining vehicles, and the like. Mining vehicles include, but are not limited to, mine trucks, wide body cars, articulated haulers, excavators, power shovels, dozers, and the like. The embodiment of the invention does not further limit the types of vehicles, and any vehicle type is within the protection scope of the embodiment of the invention.
It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and alternatively, they may be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different than that described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. A method of detecting a radar obstruction, comprising:
s1: acquiring real-time point cloud frames acquired by different types of radars;
s2: determining a target point cloud frame corresponding to the real-time point cloud frame based on a time threshold;
s3: counting the total number of point cloud frames and the number of abnormal point cloud frames between the real-time point cloud frame and the target point cloud frame;
s4: and if the ratio of the number of the abnormal point cloud frames to the total number of the point cloud frames is greater than the ratio threshold of the number of the abnormal frames, determining that the radar is shielded.
2. The method of claim 1, wherein prior to determining a target point cloud frame corresponding to the real-time point cloud frame based on a time threshold, the method further comprises:
acquiring normal point number in real-time point cloud frames collected by different types of radars and a normal point number ratio threshold corresponding to the different types of radars;
if the ratio of the number of normal points in the real-time point cloud frame to the total number of the points is greater than the normal point number ratio threshold, determining the state identifier of the real-time point cloud frame as a normal point cloud frame;
if the ratio of the number of normal points to the total number of points in the real-time point cloud frame is less than or equal to the normal point number ratio threshold, determining the state identifier of the real-time point cloud frame as an abnormal point cloud frame;
and storing the time stamps and the state identifications of the real-time point cloud frames in a target container according to the time sequence of obtaining the real-time point cloud frames, wherein one point cloud frame corresponds to one time stamp and one state identification.
3. The method of claim 2, wherein the determining a target point cloud frame corresponding to the real-time point cloud frame based on a temporal threshold comprises:
inquiring a target time stamp corresponding to the end point of the time threshold in the target container by taking the time stamp of the real-time point cloud frame as a starting point and the time threshold as an inquiry length;
and determining the point cloud frame corresponding to the target time stamp as a target point cloud frame.
4. The method of claim 3, wherein the counting the total number of point cloud frames and the number of abnormal point cloud frames between the real-time point cloud frame and the target point cloud frame comprises:
in the target container, counting the total number of point cloud frames between the real-time point cloud frame and the target point cloud frame based on the number of timestamps or the number of state identifications;
and counting the number of the abnormal point cloud frames between the real-time point cloud frame and the target point cloud frame based on the number of the abnormal state identifications.
5. The method according to claim 2, wherein the obtaining of the normal point count ratio threshold corresponding to the different types of radars comprises:
acquiring a test point cloud frame of a radar of any type under a first preset occlusion degree value and a second preset occlusion degree value, wherein the first preset occlusion degree value is smaller than the second preset occlusion degree value;
identifying abnormal points in the test point cloud frame, counting the number of the abnormal points in the test point cloud frame, taking the difference value between the total number of the points in the test point cloud frame and the number of the abnormal points as the number of the normal points of the test point cloud frame, and taking the ratio of the number of the normal points to the total number of the points as the normal point number ratio threshold value under the corresponding preset occlusion degree value;
and taking the middle value between the normal point number ratio threshold value under the first preset shielding degree value and the normal point number ratio threshold value under the second preset shielding degree value as the normal point number ratio threshold value corresponding to any type of radar.
6. The method of claim 2, further comprising:
setting a capacity parameter threshold of the target container, wherein the capacity parameter threshold comprises a time capacity parameter threshold or a frame number capacity parameter threshold;
updating the target container when the capacity of the target container reaches a corresponding capacity parameter threshold.
7. The method of any of claims 1-6, wherein prior to determining the target point cloud frame corresponding to the real-time point cloud frame based on a time threshold, the method further comprises:
setting a radar with an autonomous occlusion detection function as a specified type radar;
identifying and acquiring the radar type of the real-time point cloud frame through the real-time point cloud frame;
when the type of the radar is identified to be the designated type of radar, acquiring a fault code of the designated type of radar, and if the fault code indicates that the designated type of radar is in a non-shielding state, judging that the designated type of radar is in the non-shielding state;
and if the fault code indicates that the radar of the specified type is in the shielding state, repeating the steps S2-S4 to judge whether the radar of the specified type is shielded.
8. The method of claim 1, wherein upon determining that the radar is occluded, the method further comprises:
outputting shielding fault warning information to a control safety subsystem so that the control safety subsystem controls the vehicle provided with the radar to perform speed reduction processing and informs a security officer to perform clearing processing; or controlling the safety subsystem to start the corresponding automatic cleaning device.
9. A radar shelter detection apparatus, comprising:
the acquisition module is used for acquiring real-time point cloud frames acquired by different types of radars;
a first determining module for determining a target point cloud frame corresponding to the real-time point cloud frame based on a time threshold;
the counting module is used for counting the total number of the point cloud frames and the number of abnormal point cloud frames between the real-time point cloud frame and the target point cloud frame;
and the second determining module is used for determining that the radar is shielded if the ratio of the number of the abnormal point cloud frames to the total number of the point cloud frames is greater than an abnormal frame number ratio threshold.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 8.
CN202210662153.7A 2022-06-13 2022-06-13 Detection method and device for radar obstruction, computer equipment, chip and terminal Pending CN115236641A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210662153.7A CN115236641A (en) 2022-06-13 2022-06-13 Detection method and device for radar obstruction, computer equipment, chip and terminal

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210662153.7A CN115236641A (en) 2022-06-13 2022-06-13 Detection method and device for radar obstruction, computer equipment, chip and terminal

Publications (1)

Publication Number Publication Date
CN115236641A true CN115236641A (en) 2022-10-25

Family

ID=83668940

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210662153.7A Pending CN115236641A (en) 2022-06-13 2022-06-13 Detection method and device for radar obstruction, computer equipment, chip and terminal

Country Status (1)

Country Link
CN (1) CN115236641A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116047540A (en) * 2023-02-07 2023-05-02 湖南大学无锡智能控制研究院 Laser radar self-shielding judging method and device based on point cloud intensity information

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116047540A (en) * 2023-02-07 2023-05-02 湖南大学无锡智能控制研究院 Laser radar self-shielding judging method and device based on point cloud intensity information
CN116047540B (en) * 2023-02-07 2024-03-22 湖南大学无锡智能控制研究院 Laser radar self-shielding judging method and device based on point cloud intensity information

Similar Documents

Publication Publication Date Title
US11827228B2 (en) Road abnormality detection apparatus, road abnormality detection method and road abnormality detection program
CN107230329B (en) Fire detector calibration method, device and equipment
CN108859952B (en) Vehicle lane change early warning method and device and radar
CN115236641A (en) Detection method and device for radar obstruction, computer equipment, chip and terminal
CN110866544B (en) Sensor data fusion method and device and storage medium
CN104424804A (en) Intelligent speed-measuring method with single radar and multiple lanes and system thereof
EP4279950A1 (en) Fault diagnosis and handling method for vehicle-mounted laser radar, apparatus, medium and vehicle
CN113741388A (en) Safety diagnosis system and method based on automatic driving perception failure
CN110533921B (en) Triggering snapshot method and system for vehicle
CN112560546A (en) Throwing behavior detection method and device and storage medium
CN116047540B (en) Laser radar self-shielding judging method and device based on point cloud intensity information
CN110217244B (en) Shield door control method and device and radar
EP3859595A1 (en) Target tracking method and device
CN111832418A (en) Vehicle control method, device, vehicle and storage medium
CN116092251A (en) Surface mine area intrusion monitoring system and method
CN116386313A (en) Method and system for detecting vehicle information
CN115921084A (en) Control method, device, medium and electronic equipment for allowing dumping of crusher
CN110969058B (en) Fusion method and device for environment targets
US20050209765A1 (en) Method and device for transmitting measurement data via a can bus in an object detection system for motor vehicles
CN113706739A (en) Remote fault diagnosis processing method, platform and system
CN111143423A (en) Dynamic scene labeling data mining method and device and terminal
CN215728848U (en) Integrated intelligent sensor equipment of laser radar and camera and mobile equipment
CN115937770A (en) Garbage dumping behavior detection algorithm under outdoor scene
CN116310773A (en) Robot, obstacle detection method and related device
CN117970317A (en) Acquisition method of vision missed detection target, intelligent 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