CN115390026A - Method and device for identifying target object based on vehicle-mounted radar and storage medium - Google Patents
Method and device for identifying target object based on vehicle-mounted radar and storage medium Download PDFInfo
- Publication number
- CN115390026A CN115390026A CN202110573451.4A CN202110573451A CN115390026A CN 115390026 A CN115390026 A CN 115390026A CN 202110573451 A CN202110573451 A CN 202110573451A CN 115390026 A CN115390026 A CN 115390026A
- Authority
- CN
- China
- Prior art keywords
- target object
- vehicle
- condition
- buffer
- radar
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- 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
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S7/415—Identification of targets based on measurements of movement associated with the target
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
- G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The present disclosure provides a method, an apparatus, and a storage medium for recognizing a target object based on a vehicle-mounted radar, which can accurately recognize the target object to reduce a false alarm rate of a vehicle-assisted driving system. Specifically, the method comprises the following steps: receiving detection data of the vehicle-mounted radar in a preset space range; judging whether an object meeting a first condition exists in the preset space range or not according to the detection data; when an object meeting the first condition exists in the preset space range, further judging whether the position parameter of the object meets a second condition; and when the position parameter of the object meets the second condition, determining that the target object exists in the space outside the vehicle.
Description
Technical Field
The disclosure relates to the field of assistant driving, in particular to a method and a device for identifying a target object based on a vehicle-mounted radar and a storage medium.
Background
In the field of vehicle auxiliary driving, a vehicle-mounted millimeter wave radar emits millimeter waves outwards through an antenna, evaluates the physical environment around a vehicle body according to collected echo data to acquire environment parameters such as the direction and the moving direction of a measured object, the relative distance and the relative speed between a vehicle and the measured object and the like, and further tracks, identifies and classifies the measured object according to the acquired environment parameters to reduce the false alarm rate and the false alarm rate of a vehicle auxiliary driving system.
As a typical static category, the guardrail is exemplified, and in an actual scene, the extending direction of the road guardrail changes in real time along with the extending direction of the road, and necessary openings exist on the paving path of the guardrail. In a complex and changeable scene of a road, the inherent limitations of a radar and errors existing in the process of evaluating environmental parameters are considered, and the position state and the structural state of a measured object cannot be accurately judged only by means of detection points and track information of the measured object in a current frame, namely, a target object cannot be accurately identified, so that the false alarm rate of an auxiliary driving system is influenced.
Disclosure of Invention
The invention provides a method, a device and a storage medium for identifying a target object based on a vehicle-mounted radar, which are beneficial to reducing the false alarm rate of a vehicle auxiliary driving system.
In order to achieve the above object, the present disclosure provides a method for identifying a target object based on a vehicle-mounted radar, the method including: (S100): receiving detection data of the vehicle-mounted radar in a preset space range; (S200): judging whether an object meeting a first condition exists in the preset space range or not according to the detection data; (S300): when an object meeting the first condition exists in the preset space range, further judging whether the position parameter of the object meets a second condition; (S400): and when the position parameter of the object meets the second condition, determining that the target object exists in the space outside the vehicle.
Optionally, the (S100) comprises: and dividing the preset space range into at least two regions, and configuring a buffer with preset capacity for each region to store the position parameters of the objects meeting the first condition detected in the corresponding region.
In another aspect, the present disclosure provides an apparatus for identifying a target object based on a vehicle-mounted radar, the apparatus including: the device comprises a first processing unit, a first processing unit and a first processing unit. Wherein: the first processing unit is used for receiving detection data of the vehicle-mounted radar in a preset space range; the second processing unit is used for judging whether an object meeting a first condition exists in the preset space range or not according to the detection data; the third processing unit is used for further judging whether the position parameters of the objects meet a second condition or not when the objects meeting the first condition exist in the preset space range; and the fourth processing unit is used for determining that the target object exists in the space outside the vehicle when the position parameter of the object meets the second condition.
Optionally, the first processing unit is further configured to divide the preset spatial range into at least two regions, and configure a buffer with a preset capacity for each region, so as to store the position parameters of the object meeting the first condition detected in the corresponding region.
Exemplarily, the first condition in the above scheme means that the ground speed of the object is zero; and, the location parameter is a lateral distance between the object and the onboard radar; and, the target object is a road guardrail.
In yet another aspect, the present disclosure provides a computer-readable storage medium to store processor-executable instructions, the processor-executable instructions stored therein being capable, when executed, of causing a processor to implement a method of identifying a target object based on an onboard radar as described above.
Compared with the prior art, the method for identifying the target object based on the vehicle-mounted radar is beneficial to reducing the false alarm rate of the vehicle auxiliary driving system, and the target object is characterized in that: stationary with respect to the ground and whose structure is continuous in the direction of extension of the road, for example road fixtures such as guardrails. Specifically, the method provided by the disclosure considers the complex and changeable road scene, divides the detection range of the vehicle-mounted radar into a plurality of areas, and configures a buffer for each area to store the position parameters of a plurality of static objects in the corresponding area. And further, the position parameters of the objects stored in the caches of all the areas are taken as the basis, and whether the object meeting the characteristics of the target object exists in the detection range of the vehicle-mounted radar or not is comprehensively judged by combining a second condition.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic step diagram of a method for identifying a target object based on a vehicle-mounted radar according to an embodiment of the present disclosure.
Fig. 2 is a schematic diagram of the substeps of S100 in fig. 1.
Fig. 3 is a schematic diagram of region division of a detection range of a vehicle-mounted radar provided by an embodiment of the present disclosure.
Fig. 4 is a schematic region division diagram of a detection range of another vehicle-mounted radar provided in the embodiment of the present disclosure.
Fig. 5 is a schematic view of a driving environment provided by the embodiment of the present disclosure.
Fig. 6 is a schematic structural diagram of an apparatus for identifying a target object based on a vehicle-mounted radar according to an embodiment of the present disclosure.
Detailed Description
The technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure. Furthermore, it should be understood that the detailed description and specific examples, while indicating the present disclosure, are given by way of illustration and explanation only, and are not intended to limit the present disclosure. In the present disclosure, unless otherwise specified, use of the directional terms "upper" and "lower" generally refer to upper and lower, and specifically to the orientation of the drawing figures in the drawings, in the actual use or operating condition of the device; while "inner" and "outer" are with respect to the outline of the device.
In one aspect, to achieve the above object, the present disclosure provides a method for identifying a target object based on a vehicle-mounted radar, including the steps as shown in fig. 1:
s100: and receiving detection data of the vehicle-mounted radar in a preset space range.
In some embodiments of the present disclosure, the vehicle-mounted radar may be at least one of a millimeter wave radar, a laser radar, and a sonic radar.
In some embodiments of the present disclosure, a class of objects that are stationary relative to the ground and have a continuous structure is used as the target object to be identified by the present method. It will be appreciated that such objects are typically public facilities such as guard rails in the center of highways, acoustic barriers at the roadside, and the like. And after an object satisfying the characteristics of being static and having continuous structure is identified, the object is marked as the target object, the transverse distance between the target object and the vehicle-mounted radar is recorded, and the target object and the vehicle-mounted radar are classified and stored. In the subsequent vehicle driving process, if the assistant driving system identifies an object with the same characteristics as the target object, the object is not regarded as an obstacle, so that the false alarm rate of the assistant driving system is reduced, and the smoothness of the vehicle driving process is ensured.
Specifically, in some embodiments of the present disclosure, the S100 includes the sub-steps as shown in fig. 2:
s110: and acquiring detection data of a frame of vehicle-mounted radar in a preset space range at preset time intervals.
Specifically, the detection data corresponding to each frame includes the traces of dots in one-to-one correspondence with the objects detected in the frame.
In general, radars are installed at four corners of a vehicle body of an automobile, and, for example, referring to fig. 3, a radar installed at a rear left corner of the vehicle body can detect an object in a range to the left side of a traveling direction of the automobile, particularly, to the rear left of the vehicle. In this case, the preset spatial range refers to a range of a left side portion of the driving direction of the vehicle, and the size of the detection range is mainly determined according to the functional characteristics of the radar.
The radar scans objects within a preset spatial range of the vehicle once every fixed time. Electromagnetic waves (or sound waves and the like) sent by the radar are transmitted on the surface of an object, and the radar receives echo data to obtain detection data of one frame. The detection data of one frame comprises a plurality of reflection point data of electromagnetic waves reflected on the surfaces of various objects, and the reflection points corresponding to the same object can reflect the outline of the object. The method is characterized in that reflection points of the same object are summarized into a point trace by a clustering method to represent the position state of the object in the current frame. Each point track contained in the current frame and the corresponding point track in the past frame form a track for different objects, namely in one frame, one object corresponds to one point track, and the set of the corresponding point tracks of one object in a plurality of frames forms the track corresponding to the object.
Ideally, if a target object exists in the detection range corresponding to each frame, the driving assistance system automatically classifies the objects meeting the same characteristic into the same class when processing the data in each frame, and does not interfere with the normal running of the vehicle based on the objects.
However, the road is considered to be complicated and changeable scenes, such as guardrail openings, sound-absorbing board interruptions and the like. In these cases, the target object does not necessarily exist in the detection range corresponding to each frame. The system, when processing these frames, cannot accurately classify the objects in the detection range corresponding to the current frame, e.g. by treating the broken road barrier as an obstacle and alerting the vehicle driver through the vehicle's control center. This corresponds to an increase in the false alarm rate of the driver assistance system.
Thus, in some embodiments of the present disclosure, the S100 further comprises:
s120: the preset spatial range is divided into at least two regions.
S130: and configuring a buffer with a preset capacity for each area, wherein the buffer is used for storing the position parameters of the detected objects in the corresponding area.
For example, please refer to FIG. 3 for installationRadar at the rear left corner of the vehicle body is exemplified. Specifically, a plane coordinate system is established by taking the position of the left rear angle radar as an origin, and the right left of the vehicle body is the positive direction of the Y axis. Meanwhile, the detection range (preset spatial range) of the left rear corner radar is divided into three regions as shown in fig. 3: namely zone i Wherein i = [1,2,3]In particular, zone 1 Indicating area one, zone 2 Zone two, zone 3 Indicating zone three. The radar mounted on the left rear side of the vehicle body has a zone as a main coverage area 1 And zone 2 。
Moreover, each region is configured with a buffer (buffer) for storing the multi-frame detection results of the same region, that is: and analyzing multi-frame data aiming at the same area to store the transverse distances between the static objects in the area and the vehicle-mounted radar in a preset number so as to accurately judge whether the target object meeting the conditions exists in the detection range of the radar.
Specifically, taking the partitioning manner shown in fig. 3 as an example, the buffer corresponding to each region is: buffer i Wherein i = [1,2,3]Specifically, buffer 1 、buffer 2 、buffer 3 Respectively represent and zone 1 、zone 2 、zone 3 A corresponding buffer.
In some embodiments of the present disclosure, the S100 further includes:
s140: and initializing the buffer corresponding to each region.
Specifically, in an initial stage of identifying the target object, it is necessary to initialize the buffer of each region.
Illustratively, the buffers corresponding to each region are configured to have the same capacity. Wherein the capacity of the cache refers to the number of elements that can be stored therein. In some embodiments of the present disclosure, the buffer i Wherein the element stored is zone i The position parameter of the detected stationary object, i.e. the lateral distance between the stationary object and the vehicle-mounted radar, i.e. the coordinate value (Y) of the stationary object in the Y-axis direction i Wherein i = [1,2,3])。
For convenience of description, let buffer exemplarily i Has a capacity of 4, i.e. the buffer corresponding to each region can store 4 elements (y) i ). It should be noted that in other embodiments of the present disclosure, the capacity of the buffer of each region may not be completely the same, so as to cope with the difference of the detection accuracy of the radar in different regions or different partition modes. Exemplarily, for a zone 1 Buffer (buffer) of 1 ) In which 4 position parameters (y) can be stored 1 ) The position parameter (y) 1 ) Represents a zone 1 The lateral distance between the stationary object being detected and the vehicle radar. Similarly, for zone 2 Buffer (buffer) of 2 ) Wherein 4 y can be stored 2 (ii) a For buffer 3 Wherein 4 y can be stored 3 。
To distinguish between buffers i 4 position parameters (y) i ) Buffer will be written i The index of the position of each position parameter is recorded as: currentId, and currentId = [1,2,3,4]. Further, buffer i Occupied position (already stored y) i ) In the amount of size i Indicates and, for a buffer with a capacity of 4 i ，size i ＝[0,1,2,3,4]. Illustratively, if buffer 1 Has not yet stored the position parameter (y) 1 ) Then buffer at this time 1 Size =0 (or as size) i = 0); if buffer 1 Has stored therein 2 position parameters (y) 1 ) At this time, the size 1 ＝2。
In the initialization stage, the buffer is initialized i The above parameters of (1). Specifically, the buffer is cleared i The location parameter stored in (a). Accordingly, size i =0, representing the current buffer i In which the position parameter (y) of the object is not stored i ) (ii) a At the same time, order buffer i currentId =1, indicating that buffer is about to be in i Is written at the position of index 1 of (1) i 。
S200: and judging whether an object meeting the first condition exists in the preset space range or not according to the detection data.
Specifically, for the detection data of each frame, it is determined whether the object corresponding to each point track in the frame meets the first condition based on the flight path corresponding to each point track in the frame. And storing the position parameters of the object meeting the first condition into the buffer corresponding to the corresponding region.
In some embodiments of the present disclosure, the first condition is that the speed of the object corresponding to the track to the ground is zero, i.e., the detected object is stationary relative to the ground. The position parameter refers to the distance between an object and the vehicle-mounted radar.
For example, the ground speed of an object in the detection range may be determined from the track of the object. Specifically, the track data of the object corresponding to each point track in the current frame is updated according to the data of each point track in the current frame. And determining the ground speed of the object corresponding to each track according to the updated track data. And an object with zero ground speed is identified as a stationary object.
And further confirming the zone (zone) of the point trace of the static object in the current frame i ) To store the position parameters of the stationary object into a buffer (buffer) of the corresponding region i ) In (1). The position parameter includes a lateral distance between the corresponding object and the vehicle-mounted radar, that is, a coordinate value (Y) of the corresponding object in the Y-axis direction i )。
In some embodiments of the present disclosure, the probe data for the same frame, if buffer i Has been occupied, the slave index is 1 (currentId) i Location override storage of = 1).
S300: when an object meeting the first condition exists in the preset space range, whether the position parameter of the object meets a second condition is further judged.
Specifically, the location parameters stored in the buffer corresponding to each region are sorted according to a preset rule, so as to extract at least one location parameter from the buffer corresponding to each region. And judging whether the position parameter extracted from the buffer corresponding to each region meets a second condition.
Wherein the second condition is that: the position parameters of the preferred objects meeting the first condition and located in different areas and detected in a preset number of frames meet a first numerical relation, a second numerical relation or a third numerical relation.
For example, referring to fig. 3, taking the radar installed at the left rear corner of the vehicle body as an example, the position parameters of the object satisfying the first condition in the detection range corresponding to the current frame are stored in the buffer (buffer) of the corresponding area i ) In (1). And, the preset rule is: the position parameters of the objects stored in the buffer corresponding to each region are sorted according to a rule that the numerical values are from small to large, and the index of the position parameter with the smallest numerical value is 1 (currentId = 1). The location parameter of the preferred object may be a buffer (buffer) per buffer i ) The second smallest position parameter (currentId) of medium value i = 2), but is not limited thereto. Buffer will be used i The position parameters of the preferred object in (1) are extracted and judged from the buffer i The position parameter (y) extracted from i ) Whether the second condition is satisfied.
In some embodiments of the present disclosure, the second condition comprises: y is 2 Is a significant value, and, y 1 、y 2 、y 3 The first numerical relationship should be satisfied. At this time, the first numerical relationship is: | y 1 -y 2 |<Threshold and/or y 3 -y 2 |<A threshold value.
For the radar installed at the left rear corner of the vehicle body, the main coverage zone is considered 1 And zone 2 Two regions, in which case the first numerical relationship is: | y 1 -y 2 |<And (4) a threshold value.
For radar mounted at the front left corner of the vehicle body, the coverage of zone is considered 3 And zone 2 Two regions, in which case the first numerical relationship is: | y 3 -y 2 |<And (4) a threshold value.
For a radar mounted in the middle of the left side of the vehicle body, it is considered that it mainly covers the zone 1 、zone 2 And zone 3 Three regions, wherein the first numerical relationship is: | y 1 -y 2 | and | y 3 -y 2 The values of all are less than the threshold.
In this case, the valid value is understood to be a value that corresponds to the current detection environment, for example, the target object is a guardrail in the center of a road, and if the extracted position parameter is a value that is significantly larger than the width of the road, or if the extracted position parameter does not correspond to a reasonable distance range between the vehicle-mounted radar and the guardrail, for example, is too small or too large, the position parameter is an invalid value. If the position parameter conforms to a reasonable transverse distance range between the guardrail and the vehicle-mounted radar, the position parameter at the moment can be considered to be a valid value. Exemplarily, if the position parameter y 1 、y 2 、y 3 The corresponding objects are distributed on the zone 1 、zone 2 、zone 3 The threshold value may then be understood as an installation tolerance of the road barrier, in particular in the direction along the road extension.
In some embodiments of the present disclosure, the second condition further comprises: at y 2 Not significant values and/or y 1 、y 2 、y 3 In the case where the first numerical relationship is not satisfied, y 2 And a preset value satisfies a second numerical relationship. At this time, the second numerical relationship is: l preset value-y 2 |<And (4) a threshold value.
Specifically, at y 2 Not significant values and/or y 1 、y 2 、y 3 Does not satisfy y 1 -y 2 |<Threshold and/or y 3 -y 2 |<Under the condition of a threshold value, acquiring a preset value and judging y 2 (slave buffer) 2 The position parameter extracted in (1) and the preset value. If the absolute value of the difference between the two does not exceed a threshold, then y is considered to be at that time 2 Is a valid value, and can be considered as y 2 The corresponding object is a target object, and the transverse distance between the target object and the vehicle-mounted radar is y 2 . It should be noted that the preset value is determined according to the current environment of the automobile, and for example, if there is a guardrail on one side of the radar, the preset value is set to be slightly larger (or slightly smaller ) than the preset valueEqual) to the distance between the vehicle radar and the guardrail. Therefore, the preset value can also be understood as the distance between the intended guard rail (target object) and the vehicle-mounted radar. If y is judged 2 If the preset value is relatively close to the preset value, y can be considered to be 2 Is an effective value, and the corresponding object is a target object, namely a guardrail.
In some embodiments of the present disclosure, the second condition further comprises: at y 2 Not a significant value and/or y 1 、y 2 、y 3 Does not satisfy the first numerical relationship, and, y 2 In the case where the second numerical relationship is not satisfied, y 1 、y 2 、y 3 Satisfies a third numerical relationship with the preset value. At this time, the third numerical relationship is: y-preset value<A threshold value, wherein y is y 1 、y 2 、y 3 At least one of (a).
Specifically, at y 2 Not significant values and/or y 1 、y 2 、y 3 Does not satisfy y 1 -y 2 |<Threshold and/or y 3 -y 2 |<Threshold value, and | preset value-y 2 If y is judged to be equal to or greater than the threshold value 1 、y 2 、y 3 Satisfies a "y-preset value" with the preset value<The numerical relationship of the threshold value indicates y 1 、y 2 、y 3 At least one of the corresponding objects is located on a side of the intended guardrail adjacent the vehicle. Then, at this time, a target object may exist in the detection range of the vehicle-mounted radar, and the target object refers to the expected guardrail whose distance from the vehicle-mounted radar is approximate to the preset value.
S400: and when the position parameter of the object meets a second condition, determining that the target object exists in the space outside the vehicle.
Specifically, it is determined that the object corresponding to the position parameter satisfying the second condition is the target object.
Illustratively, y is extracted as described above 2 、y 1 And/or y 3 If the second condition is satisfied, the determination is made thaty 2 、y 1 And/or y 3 The respective corresponding objects are the same kind of object, and the object is the target object. Meanwhile, the transverse distance between the target object and the vehicle-mounted radar can be determined according to the buffer 2 In (d) the position parameter (y) of the preferred object 2 ) And (4) determining.
In some embodiments of the present disclosure, after the target object is determined, in order to ensure that the correct target object is identified, the location parameter of the identified target object needs to be verified based on a verification condition.
Wherein the verification condition is: and the position parameter of the target object and the position parameter of the object which does not meet the first condition in the preset space range meet a fourth numerical relation.
Specifically, in the case that the angle corresponding to the second region shown in fig. 3 is relatively narrow, since the object in the second region is relatively close to the vehicle-mounted radar, the probe wave emitted by the radar is equivalent to vertical incidence, and the probe wave has strong reflectivity on the surface of the object in the second region, the echo data of some objects in the first region and the third region may be masked.
In general, in order to solve this problem, the angular ranges corresponding to the first and third regions are appropriately increased. However, with the expansion of the detection space ranges of the first area and the third area, some objects arranged above the road may enter the detection range of the vehicle-mounted radar, for example: signboards, billboards, overpasses or tunnel roofs, etc., and the location parameters of these objects are stored into the buffer 1 And/or buffer 3 . Meanwhile, the position parameters of the manhole cover, the roadblock and the object such as the automobile which is mistakenly considered to be static on the road surface are also stored in the buffer 2 In (1).
If the aforementioned object is selected as the preferred object, and the respective position parameter (y) is due to contingency 2 ’、y 1 ' and/or y 3 ') exactly meets the aforementioned second condition, namely: y is 2 ' is a valid value, and, | y 1 ’-y 2 ' | and/or | y 2 ’-y 3 ' I is less than oneAnd (4) a threshold value. Then at this point the system will misinterpret the identification of the target object and will note the lateral distance between the "target object" and the on-board radar as y 2 '. However, the "target object" at this time does not conform to the feature of being in a stationary state and having a continuous structure, and in fact, y 2 ’、y 1 ' and/or y 3 The' corresponding objects may not form a continuous structure nor may they all be in a static state, but at a certain moment they form a line in space exactly approximately parallel to the road extension direction. At this time, it is considered that the vehicle driving support system has misrecognition.
Therefore, in order to further improve the accuracy of the vehicle assistant driving system in identifying the target object, in some embodiments of the disclosure, a zone four (zone) may be further included in the detection space range of the vehicle-mounted radar 4 ) Its corresponding buffer 4 ) For storing the position parameters (y) of the dynamic objects detected in zone four 4 '). And, pass through buffer 4 The location parameters of the preferred dynamic object in S300 to verify whether the target object is identified as correct.
Specifically, taking the radar installed in the middle of the left side of the vehicle body as an example, the detection range of the vehicle-mounted radar is divided into regions according to the manner shown in fig. 4. Each zone (zone) i ) With corresponding buffer i ) And, the angles (α) of the four regions i ) The ranges are in turn: 5 degree<α 1 <70°、80°<α 2 <100°、115°<α 3 <175°、60°<α 4 <120 °; wherein, i = [1,2,3,4]. Further, buffer 1 、buffer 2 、buffer 3 Respectively for storing zone 1 、zone 2 、zone 3 The position parameter of the detected static object; buffer 4 For storing the position parameters of the dynamic objects detected in zone four.
Acquiring the lateral distance (y) between the target object and the in-vehicle radar determined in S300 2 ') and from buffer 4 The position of the preferred object extracted fromParameter (y) 4 ') determine y 2 ' and y 4 ' whether a verification condition is satisfied therebetween. Specifically, at y 2 In the case of' being a valid value, the verification condition is: y is 4 ' and y 2 ' should satisfy "| y 4 ’-y 2 ' | ≧ threshold "is a fourth numerical relationship.
To assist the reader in better understanding the methods provided by the present disclosure, please refer to the driving environment illustrated in fig. 5. Specifically, one side of the road guardrail is provided with a first vehicle and at least one second vehicle which run side by side, and the space above the road is provided with guideboards which are arranged at intervals. And a vehicle-mounted radar is arranged in the middle of the left side of the vehicle I, and for the vehicle I, a correct target object is a guardrail.
In particular, y 4 ' corresponds to the lateral distance between the on-board radar of the first vehicle and the second vehicle if y of the target object is determined in S300 2 ' and y 4 ' the verification condition is satisfied, i.e. | y 4 ’-y 2 ' | ≧ threshold, the identified target object is considered correct. If y 4 ’-y 2 ’|<The threshold value indicates that the position of the identified target object is close to or even coincident with the position of a vehicle II which normally runs on the lane, namely y 2 The actual corresponding object may be a vehicle II, or may be a manhole cover, a roadblock and other objects arranged on the same lane road surface, and is not part of the guardrail. I.e. the target object identified at this time is erroneous.
In addition, in y 2 ' in the case of a valid value, | y 4 ’-y 2 When' | is equal to or greater than the threshold, there are two cases, one is y 2 The' corresponding object is located between the second vehicle and the first vehicle, but the object located between the two vehicles is hardly recognized in consideration of the inherent blind area of the radar and the actual distance between the first vehicle and the second vehicle in the actual scene. Another case is y 2 The corresponding object is located on the side of the second vehicle far away from the first vehicle, and may be a guardrail or an object close to the guardrail, and may also be an object between the guardrail and the second vehicle. However, the guard rail and the vehicle in the actual scene are consideredThe actual distance between the second vehicle and the guardrail can be equal to the object close to the guardrail. Furthermore, the object close to the guardrail may also be the guardrail itself, taking into account installation errors of the guardrail and necessary alterations of the angle of the guardrail laying path. Thus, at y 2 ' is a valid value and y 4 ’-y 2 If the value of' | is equal to or greater than the threshold value, it can be considered that the correct target object, that is, the guard rail, is recognized.
If the position parameter of the identified target object does not meet the verification condition, namely the identified target object is wrong, clearing the buffer of the wrong target object 2 Position parameter (y) of 2 '). Specifically, let buffer 2 The position parameter with the maximum median value is stored at the position corresponding to the wrong target object in a covering mode and guarantees buffer 2 If the stored location parameters are continuous, the location parameter with the largest value is cleared (the location index is larger) to reduce the buffer 2 Repetition rate of the medium position parameter. At the same time, the buffer is processed in the same manner 4 The position parameter of the dynamic object is stored in the database to ensure that the verification condition can follow the buffer 2 And updating in time. If necessary, the buffer can be cleared in the same manner 1 And/or buffer 3 In and y 2 ' together constituting y of the erroneous target object 1 ' and/or y 3 ’。
In some embodiments of the present disclosure, after the verification step is completed, in order to update the buffer in time i The position parameter stored in the buffer memory can be aged and cleaned according to a preset period, wherein i = [1,2,3,4 =, and the position parameter in the buffer memory corresponding to each region can be aged and cleaned]。
Specifically, the period may be a frame period, and one period contains a fixed number of frames. Every time the frame with the number corresponding to the frame period is obtained, the buffer corresponding to each area is aged and cleaned once to update the buffer i The location parameter stored in (a). In the next frame period, the second frame within the corresponding detection range of each frame is satisfiedThe position parameter of the object of a condition can be continuously stored in the buffer i In (1).
Illustratively, to maintain buffer i The stored location parameters are continuous, each time only for buffer i And respectively carrying out aging and clearing on the position parameter with the minimum median value and the maximum median value. Note that, at this time, buffer i The stored position parameters are sorted according to a preset rule, and the position parameter with the minimum value is in the buffer in general i The index in (1). Specifically, first, the buffer is judged i Whether or not it is empty, i.e. size i Whether greater than 0. At size i >In the case of 0, the buffer is cleared i The position parameter with the maximum numerical value is judged again, and the buffer at the moment is judged again i Whether it is empty. Further, at size i >In the case of 0, the position parameter with the largest value at this time is overwritten and stored at the position of the position parameter with the smallest value, and one position parameter with the largest value is cleared again (the position index is larger) to reduce the buffer i Repetition rate of the medium position parameter. It will be appreciated that in a cleaning cycle (or aging cycle), the original buffer is removed i At least one position parameter with larger value in buffer i Under the condition of non-null, the position parameter with the second largest numerical value is used for aging the position parameter with the first smallest numerical value so as to ensure the buffer after cleaning i Continuity of the medium position parameter.
The embodiment of the disclosure provides a method for identifying a target object based on a vehicle-mounted radar, wherein the target object is characterized in that: stationary with respect to the ground and whose structure is continuous in the direction of extension of the roadway, such as a road fixture like a guardrail. Compared with the prior art, the method provided by the disclosure considers the complex and changeable scenes of the road, divides the detection range of the vehicle-mounted radar into a plurality of areas, and configures a buffer for each area to store the position parameters of a plurality of static objects in the corresponding area. And further, the position parameters of the objects stored in the buffer of each area are taken as the basis, and the second condition and the verification condition are integrated to judge whether the target object meeting the characteristics exists in the detection range of the vehicle-mounted radar. By adopting the method provided by the disclosure, the target object can be accurately identified, and particularly, for road public facilities such as guardrails and the like, although the target object has structural loss in a small range, such as guardrail openings and the like, in the running process of the vehicle, the target object can be judged to be integrally continuous in the extending direction of the road by the method provided by the disclosure, so that the auxiliary driving system of the vehicle can not regard the guardrail with the fixed opening detected by the vehicle-mounted radar as an obstacle and further give a warning to a driver through a control center of the vehicle. Namely, the method provided by the disclosure is beneficial to reducing the false alarm rate of the vehicle auxiliary driving system.
On the other hand, to achieve the above object, the present disclosure provides an apparatus for identifying a target object based on a vehicle-mounted radar, as shown in fig. 6, where the apparatus 6 includes: a first processing unit 61, a first processing unit 62, a first processing unit 63, a first processing unit 64.
Wherein: the first processing unit 61 is configured to receive detection data of the vehicle-mounted radar within a preset spatial range; the second processing unit 62 is configured to determine whether an object meeting a first condition exists in the preset spatial range according to the detection data; the third processing unit 63 is configured to further determine whether the position parameter of the object satisfies a second condition when the object satisfying the first condition exists in the preset spatial range; the fourth processing unit 64 is configured to determine that the target object exists in the space outside the vehicle when the position parameter of the object satisfies the second condition.
In some embodiments of the present disclosure, the first condition is: the object has zero ground speed; the second condition is: the position parameters of the preferred objects meeting the first condition and located in different areas and detected in a preset number of frames meet a first numerical relation, a second numerical relation or a third numerical relation. The target object is characterized in that: stationary with respect to the ground and whose structure is continuous in the direction of extension of the road, for example road fixtures such as guardrails.
In some embodiments of the present disclosure, the first processing unit 61 obtains a frame of detection data of the vehicle-mounted radar in the preset spatial range every preset time, where the detection data corresponding to each frame includes a point trace corresponding to an object detected by the current frame one to one.
In some embodiments of the present disclosure, for each frame of the detection data, the second processing unit 62 determines whether the object corresponding to each trace in the frame satisfies the first condition based on the flight path corresponding to each trace in the frame.
In some embodiments of the present disclosure, the first processing unit 61 is further configured to divide the preset spatial range into at least two regions; configuring a buffer with a preset capacity for each zone to store the position parameters of the detected objects associated with the corresponding zone; and initializing the buffer corresponding to each region.
In some embodiments of the present disclosure, in a case that an object corresponding to at least one trace in the current frame satisfies the first condition, the second processing unit 62 is further configured to store the position parameter of the object satisfying the first condition into a buffer corresponding to the corresponding region.
In some embodiments of the present disclosure, the third processing unit 63 is configured to sort the location parameters stored in the buffer corresponding to each of the regions according to a preset rule, and extract at least one location parameter from the buffer corresponding to each of the regions respectively; and, judge whether the position parameter extracted from the buffer corresponding to each said area meets the said second condition.
In some embodiments of the present disclosure, in a case that the location parameter extracted from the buffer corresponding to each of the regions satisfies the second condition, the fourth processing unit 64 is configured to determine that the object corresponding to the location parameter satisfying the second condition is the target object.
In some embodiments of the present disclosure, after the target object is determined, in order to ensure that the correct target object is identified, the fourth processing unit 64 is further configured to verify the location parameter of the identified target object based on a verification condition. Wherein the verification condition is: and the position parameter of the target object and the position parameter of the object which does not meet the first condition in the preset space range meet a fourth numerical relation.
After some embodiments of the present disclosure, in order to update the location parameters stored in the buffers corresponding to the respective regions in time, the location parameters in the buffers corresponding to the respective regions may be cleaned and aged according to a preset period.
Other aspects of the apparatus for identifying a target object based on a vehicle-mounted radar provided in the present disclosure are the same as or similar to the method for identifying a target object based on a vehicle-mounted radar described above (for example, expressions and meanings of the first numerical relationship, the second numerical relationship, the third numerical relationship, and the fourth numerical relationship are the same as or similar to those described above in conjunction with the embodiment of the method for identifying a target object based on a vehicle-mounted radar), and are not repeated herein.
The present disclosure also provides a computer-readable storage medium to store processor-executable instructions that, when executed, can cause a processor to implement any of the above-described methods of identifying a target object based on an onboard radar.
It will be understood by those skilled in the art that all or part of the flow of the above embodiments of the method for identifying a target object based on a vehicle-mounted radar can be implemented by hardware and/or software related to computer program instructions. The computer program may be stored in a non-volatile computer readable storage medium, and when executed, may perform the processes of the above method embodiments. Any reference to memory, storage, databases or other media used in the embodiments provided herein may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), enhanced SDRAM (ESDRAM), rambus (Rambus) direct RAM (RDRAM), direct bused dynamic RAM (DRDRAM), and bused dynamic RAM (RDRAM).
The embodiment of the disclosure provides a method, a device and a storage medium for identifying a target object based on a vehicle-mounted radar, wherein the target object is characterized in that: stationary with respect to the ground and whose structure is continuous in the direction of extension of the road, for example road fixtures such as guardrails. By adopting the method and the device, the target object can be accurately identified, and the false alarm rate of the vehicle auxiliary driving system is favorably reduced. In particular, for road public facilities such as guardrails, although a target object has structural defects, such as guardrail openings and the like, in a small range during the running process of a vehicle, the method and the device provided by the disclosure can judge that the target object is wholly continuous in the extending direction of the road, so that an assistant driving system of the vehicle does not regard the guardrail with the fixed opening detected by a vehicle-mounted radar as an obstacle and further give unnecessary warning to a driver through a control center of the vehicle.
The method, the device and the storage medium for identifying the target object based on the vehicle-mounted radar provided by the embodiment of the disclosure are described in detail, a specific example is applied in the description to explain the principle and the implementation of the disclosure, and the description of the embodiment is only used for helping to understand the method and the core idea of the disclosure; meanwhile, for those skilled in the art, according to the idea of the present disclosure, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present description should not be construed as a limitation to the present disclosure.
Claims (27)
1. A method for identifying a target object based on a vehicle-mounted radar, the method comprising:
(S100): receiving detection data of the vehicle-mounted radar in a preset space range;
(S200): judging whether an object meeting a first condition exists in the preset space range or not according to the detection data;
(S300): when an object meeting the first condition exists in the preset space range, further judging whether the position parameter of the object meets a second condition;
(S400): and when the position parameter of the object meets the second condition, determining that the target object exists in the space outside the vehicle.
2. The method for identifying a target object based on an on-vehicle radar according to claim 1, wherein the (S100) comprises:
and acquiring detection data of one frame of the vehicle-mounted radar in the preset space range at preset time intervals, wherein the detection data corresponding to each frame comprises point traces which are in one-to-one correspondence with the objects detected by the frame.
3. The method for identifying a target object based on a vehicle-mounted radar according to claim 2, wherein the (S200) comprises:
and determining whether the object corresponding to each point track in the frame meets the first condition or not based on the flight path corresponding to each point track in the frame aiming at the detection data of each frame.
4. The method for identifying a target object based on a vehicle radar according to claim 3, wherein the (S100) comprises:
the preset spatial range is divided into at least two regions.
5. The method for identifying a target object based on an on-vehicle radar according to claim 4, wherein the (S100) comprises: and configuring a buffer with preset capacity for each area, wherein the buffer is used for storing the position parameters of the detected objects in the corresponding area.
6. The method for identifying a target object based on an onboard radar as claimed in claim 5, wherein in case that the object corresponding to at least one point trace in the current frame satisfies the first condition, the (S200) comprises:
and storing the position parameters of the objects meeting the first condition into a buffer corresponding to the corresponding region.
7. The method for identifying a target object based on an on-vehicle radar according to claim 6, wherein the (S300) comprises:
sequencing the position parameters stored in the buffer corresponding to each region according to a preset rule and extracting at least one position parameter from the buffer corresponding to each region;
and judging whether the position parameters extracted from the buffer corresponding to each region meet the second condition or not.
8. The method for identifying a target object based on a vehicle-mounted radar according to claim 7, wherein in the case where the position parameter extracted from the buffer corresponding to each of the regions satisfies the second condition, the (S400) comprises:
determining that the object corresponding to the position parameter meeting the second condition is the target object;
and cleaning the position parameters in the buffer corresponding to each region according to a preset period.
9. The method for identifying a target object based on an on-vehicle radar according to claim 8, wherein after said determining that the object corresponding to the location parameter satisfying the second condition is the target object, said (S400) further comprises: and verifying the position parameters of the target object based on a verification condition.
10. The method for identifying a target object based on an on-vehicle radar according to claim 1, wherein the first condition is: the object has zero ground speed.
11. The method for identifying a target object based on the on-board radar of claim 4, wherein the second condition is: the position parameters of the preferred objects meeting the first condition and located in different areas and detected in a preset number of frames meet the first numerical relation, or the second numerical relation, or the third numerical relation.
12. The method for identifying a target object based on an onboard radar according to claim 9, wherein the verification condition is: and the position parameter of the target object and the position parameter of the object which does not meet the first condition in the preset space range meet a fourth numerical relation.
13. The method of claim 1, wherein the location parameter is a lateral distance between the object and the in-vehicle radar.
14. The method for identifying the target object based on the vehicle-mounted radar according to claim 1, wherein the target object is a road guardrail.
15. An apparatus for recognizing a target object based on a vehicle-mounted radar, the apparatus comprising:
the first processing unit is used for receiving detection data of the vehicle-mounted radar in a preset space range;
the second processing unit is used for judging whether an object meeting a first condition exists in the preset space range or not according to the detection data;
the third processing unit is used for further judging whether the position parameters of the objects meet a second condition or not when the objects meeting the first condition exist in the preset space range;
and the fourth processing unit is used for determining that the target object exists in the space outside the vehicle when the position parameter of the object meets the second condition.
16. The apparatus according to claim 15, wherein the first processing unit obtains a frame of detection data of the vehicle-mounted radar within the preset spatial range at preset time intervals, wherein the detection data corresponding to each frame comprises a one-to-one trace of points corresponding to the detected object of the frame.
17. The apparatus according to claim 16, wherein for each frame of the detection data, the second processing unit determines whether the object corresponding to each track in the frame satisfies the first condition based on the track corresponding to each track in the frame.
18. The vehicle-mounted radar-based target object identifying device of claim 17, wherein the first processing unit is further configured to divide the preset spatial range into at least two regions.
19. The apparatus for identifying a target object based on an on-board radar of claim 18, wherein the first processing unit is further configured to configure a buffer with a preset capacity for each of the regions; the buffer is used for storing the position parameters of the detected objects in the corresponding area.
20. The apparatus of claim 19, wherein in a case that an object corresponding to at least one point trace in the current frame satisfies the first condition, the second processing unit is further configured to store the position parameter of the object satisfying the first condition into a buffer corresponding to the corresponding region.
21. The vehicle-mounted radar-based target object identifying device according to claim 20, wherein the third processing unit is configured to sort the location parameters stored in the buffer corresponding to each of the regions according to a preset rule and extract at least one location parameter from the buffer corresponding to each of the regions; and judging whether the position parameter extracted from the buffer corresponding to each region meets the second condition.
22. The vehicle-mounted radar-based target object identifying device according to claim 21, wherein in a case where the position parameter extracted from the buffer corresponding to each of the regions satisfies the second condition, the fourth processing unit is configured to determine that an object corresponding to the position parameter satisfying the second condition is the target object; and cleaning the position parameters in the buffer corresponding to each region according to a preset period.
23. The vehicle-mounted radar-based target object identifying device of claim 22, wherein the fourth processing unit is further configured to verify the location parameter of the target object based on a verification condition.
24. The vehicle radar-based target object identification device of claim 15, wherein the first condition is: the object has zero ground speed.
25. The vehicle radar-based target object identification device of claim 18, wherein the second condition is: the position parameters of the preferred objects meeting the first condition and located in different areas and detected in a preset number of frames meet a first numerical relation, a second numerical relation or a third numerical relation.
26. The apparatus for identifying a target object based on a vehicle-mounted radar according to claim 23, wherein the verification condition is: and the position parameter of the target object and the position parameter of the object which does not meet the first condition in the preset space range meet a fourth numerical relation.
27. A computer-readable storage medium to store processor-executable instructions stored therein, which when executed, are capable of causing a processor to implement the method of identifying a target object based on vehicle radar of any one of claims 1-14.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110573451.4A CN115390026A (en) | 2021-05-25 | 2021-05-25 | Method and device for identifying target object based on vehicle-mounted radar and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110573451.4A CN115390026A (en) | 2021-05-25 | 2021-05-25 | Method and device for identifying target object based on vehicle-mounted radar and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115390026A true CN115390026A (en) | 2022-11-25 |
Family
ID=84114027
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110573451.4A Pending CN115390026A (en) | 2021-05-25 | 2021-05-25 | Method and device for identifying target object based on vehicle-mounted radar and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115390026A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117250595A (en) * | 2023-11-20 | 2023-12-19 | 长沙莫之比智能科技有限公司 | False alarm suppression method for vehicle-mounted millimeter wave radar metal well lid target |
-
2021
- 2021-05-25 CN CN202110573451.4A patent/CN115390026A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117250595A (en) * | 2023-11-20 | 2023-12-19 | 长沙莫之比智能科技有限公司 | False alarm suppression method for vehicle-mounted millimeter wave radar metal well lid target |
| CN117250595B (en) * | 2023-11-20 | 2024-01-12 | 长沙莫之比智能科技有限公司 | False alarm suppression method for vehicle-mounted millimeter wave radar metal well lid target |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109254289B (en) | Detection method and detection equipment for road guardrail | |
| US10761201B2 (en) | Object detection device and recording medium | |
| JP4981808B2 (en) | Vehicle start control method and driver support system based on sensor | |
| KR101104609B1 (en) | Method and System for Recognizing Target Parking Location | |
| JP3427809B2 (en) | Vehicle road shape recognition method and apparatus, recording medium | |
| US7545956B2 (en) | Single camera system and method for range and lateral position measurement of a preceding vehicle | |
| US10132919B2 (en) | Object detecting device, radar device, and object detection method | |
| US20090292468A1 (en) | Collision avoidance method and system using stereo vision and radar sensor fusion | |
| JP4086298B2 (en) | Object detection method and apparatus | |
| CN106168667B (en) | Vehicle-mounted radar system with image reflection detection | |
| US10488517B2 (en) | Method and apparatus for recognizing vehicles using laser beam scanning | |
| KR102588008B1 (en) | Method and control unit for detecting entering or exiting vehicles | |
| CN111796286B (en) | Brake grade evaluation method and device, vehicle and storage medium | |
| CN111742235B (en) | Method and system for identifying an empty parking space suitable for a vehicle | |
| CN110940980B (en) | Mirror image target removing method based on vehicle-mounted angle radar | |
| JPH10239436A (en) | Detector for vehicle-to-vehicle distance | |
| JP2016148547A (en) | Detection device | |
| JPH10221451A (en) | Radar equipment for vehicle | |
| CN114093165A (en) | Roadside laser radar-based vehicle-pedestrian conflict automatic identification method | |
| JP2012198730A (en) | Recognition method and device of road shape for vehicle, and recording medium | |
| CN115390026A (en) | Method and device for identifying target object based on vehicle-mounted radar and storage medium | |
| JP5402983B2 (en) | Vehicular road shape recognition method and apparatus, and recording medium | |
| KR101891725B1 (en) | Method for producing virtual lane based on short-range radar sensor | |
| Garcia et al. | Determination of minimum horizontal curve radius for safe stopping sight distance of vehicles overpassing truck platoons | |
| US20220196829A1 (en) | Radar Reference Map Generation |
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 |