CN112162275A - Target object identification method, device, equipment and storage medium - Google Patents
Target object identification method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112162275A CN112162275A CN202011057323.6A CN202011057323A CN112162275A CN 112162275 A CN112162275 A CN 112162275A CN 202011057323 A CN202011057323 A CN 202011057323A CN 112162275 A CN112162275 A CN 112162275A
- Authority
- CN
- China
- Prior art keywords
- information
- target object
- target
- object information
- distance
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 230000003068 static effect Effects 0.000 claims abstract description 57
- 230000004927 fusion Effects 0.000 claims abstract description 21
- 238000001914 filtration Methods 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 2
- 238000001514 detection method Methods 0.000 abstract description 7
- 238000004891 communication Methods 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 230000001133 acceleration Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- 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
- G01S13/86—Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
- G01S13/867—Combination of radar systems with cameras
-
- 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
- G01S7/411—Identification of targets based on measurements of radar reflectivity
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to the technical field of automatic driving, and discloses a target object identification method, a device, equipment and a storage medium, wherein the method comprises the following steps: when a target identification instruction is acquired, acquiring initial target information, extracting preset distance information of the initial target information, identifying the initial target information according to the preset distance information to obtain target information, extracting target static object information and target non-static object information in the target information, and performing information fusion on the target static object information and the target non-static object information to obtain fused target information. The initial target object information is identified to obtain target object information, and then the target object information is extracted and fused, so that the problem that a front static target and a pedestrian not close to the vehicle and moving transversely are mistakenly identified as dangerous targets when the radar detection range is wide is solved, and the accuracy of target object identification is improved.
Description
Technical Field
The invention relates to the technical field of automatic driving, in particular to a target object identification method, a target object identification device, target object identification equipment and a storage medium.
Background
The automatic driving technology is a high-grade performance of intelligent driving, is vigorously developed at home and abroad, and needs to rely on sensors such as radar and the like to detect and identify surrounding target objects and feed the surrounding target objects back to a decision-making system for judgment, therefore, the next driving behavior is determined, the loaded automatic driving sample car is provided, the sensing system adopts a millimeter wave radar and a camera, the scanning angle in front of the radar is large, the detection of static targets such as trees in front can be brought into the target range, the false rate of the detection of the front targets is too high, and when pedestrian targets exist in front, the method has the advantages that pedestrians who do not move transversely close to the vehicle can be detected, judgment of a decision system is affected, accurate target identification is particularly important, and the target object is identified and detected generally according to the output principle of a sensor, data fusion processing and other methods, but identification errors are prone to occurring.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
The invention mainly aims to provide a target object identification method, a target object identification device, target object identification equipment and a storage medium, and aims to solve the problem that when the radar detection range is wide, a front static target and a pedestrian moving transversely and not close to a vehicle are identified as dangerous targets by mistake.
In order to achieve the above object, the present invention provides a target object recognition method, including the steps of:
when a target object identification instruction is obtained, obtaining initial target object information;
extracting preset distance information of the initial target object information;
identifying the initial target object information according to the preset distance information to obtain target object information;
and extracting target static object information and target non-static object information in the target object information, and performing information fusion on the target static object information and the target non-static object information to obtain fused target object information.
Preferably, the extracting preset distance information of the initial target object information includes:
acquiring target vehicle information of a target vehicle;
extracting the transverse distance and the longitudinal distance between an initial target object corresponding to the initial target object information and a target vehicle corresponding to the target vehicle information;
and taking the transverse distance and the longitudinal distance as the preset distance information.
Preferably, the identifying the initial target object information according to the preset distance information to obtain target object information includes:
judging whether the longitudinal distance is larger than a preset longitudinal distance or not;
if the longitudinal distance is greater than the preset longitudinal distance, judging whether the transverse distance is within a preset first transverse distance range;
and if the transverse distance is within the first transverse distance range, taking the initial target object information as target object information.
Preferably, after the determining whether the longitudinal distance is greater than a preset longitudinal distance, the method further includes:
if the longitudinal distance is smaller than or equal to the preset longitudinal distance, judging whether the transverse distance is within a preset second transverse distance range;
and if the transverse distance is within a second transverse distance range, taking the initial target object information as target object information.
Preferably, the identifying the initial target object information according to the preset distance information to obtain target object information includes:
judging whether the transverse distance is within a preset transverse distance range or not;
if the transverse distance is within a preset transverse distance range, acquiring the current running speed of the initial target object information, and judging whether the current running speed is greater than a preset running speed or not;
and if the running speed is greater than the preset running speed, taking the initial target object information as target object information.
Preferably, before the determining whether the lateral distance is within a preset lateral distance range, the method further includes:
acquiring the driving direction of the initial target object information;
and if the driving direction moves towards the transverse direction of the target vehicle, executing the step of judging whether the transverse distance is within a preset transverse distance range.
Preferably, before the obtaining of the initial target object information when the target object identification instruction is obtained, the method further includes:
acquiring original target object information acquired by a radar and a camera;
analyzing the original target object information to obtain original environment information and original target object parameter information;
and filtering the original environment information and the original target object parameter information to obtain initial target object information.
In order to achieve the above object, the present invention also provides an object recognition apparatus, including:
the acquisition module is used for acquiring initial target object information when a target object identification instruction is acquired;
the extraction module is used for extracting preset distance information of the initial target object information;
the identification module is used for identifying the initial target object information according to the preset distance information to obtain target object information;
and the fusion module is used for extracting the target static object information and the target non-static object information in the target object information, and performing information fusion on the target static object information and the target non-static object information to obtain fused target object information.
Further, to achieve the above object, the present invention also provides an object identifying apparatus including: a memory, a processor and an object recognition program stored on the memory and executable on the processor, the object recognition program being configured with steps implementing the object recognition method as described above.
Furthermore, to achieve the above object, the present invention also proposes a storage medium having stored thereon an object recognition program which, when executed by a processor, implements the steps of the object recognition method as described above.
According to the target object identification method, when a target object identification instruction is obtained, initial target object information is obtained, preset distance information of the initial target object information is extracted, the initial target object information is identified according to the preset distance information to obtain target object information, target static object information and target non-static object information in the target object information are extracted, and the target static object information and the target non-static object information are subjected to information fusion to obtain fused target object information. The initial target object information is identified to obtain target object information, and then the target object information is extracted and fused, so that the problem that a front static target and a pedestrian not close to the vehicle and moving transversely are mistakenly identified as dangerous targets when the radar detection range is wide is solved, and the accuracy of target object identification is improved.
Drawings
FIG. 1 is a schematic diagram of a target object recognition device in a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart illustrating a first embodiment of a target object recognition method according to the present invention;
FIG. 3 is a schematic overall flowchart of a first embodiment of a target object recognition method according to the present invention;
FIG. 4 is a flowchart illustrating a second embodiment of a target object recognition method according to the present invention;
FIG. 5 is a schematic diagram of the transverse distance and the longitudinal distance of the second embodiment of the object recognition method of the present invention;
FIG. 6 is a flowchart illustrating a method for identifying an object according to a third embodiment of the present invention;
fig. 7 is a functional block diagram of the object recognition apparatus according to the first embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a target object recognition device in a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the object recognition apparatus may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may comprise a Display screen (Display), an input unit such as keys, and the optional user interface 1003 may also comprise a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The Memory 1005 may be a Random Access Memory (RAM) Memory or a non-volatile Memory (e.g., a magnetic disk Memory). The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the device configuration shown in fig. 1 does not constitute a limitation of the object recognition device, and may include more or fewer components than those shown, or some components in combination, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a storage medium, may include therein an operating system, a network communication module, a user interface module, and an object recognition program.
In the object identifying apparatus shown in fig. 1, the network interface 1004 is mainly used for connecting an external network and performing data communication with other network apparatuses; the user interface 1003 is mainly used for connecting to a user equipment and performing data communication with the user equipment; the apparatus of the present invention calls the object recognition program stored in the memory 1005 through the processor 1001 and executes the object recognition method provided by the embodiment of the present invention.
Based on the hardware structure, the embodiment of the target object identification method is provided.
Referring to fig. 2, fig. 2 is a flowchart illustrating a first embodiment of the object recognition method according to the present invention.
In a first embodiment, the target identification method includes the steps of:
in step S10, when the target recognition instruction is acquired, initial target information is acquired.
It should be noted that the executing subject in this embodiment may be the target object identification method device, and may also be other devices that can implement the same or similar functions.
It should be understood that fig. 3 is a schematic overall flow chart of the present embodiment, and includes: the method comprises a sensing layer, a protocol analysis layer, a message filtering layer, a target tracking layer and a fusion layer, wherein a target tracking layer judgment method of a model is modified on the basis of considering longitudinal speed in the previous period in the figure 3, and a transverse speed criterion condition of the model is added, so that the interference of static targets such as trees existing on the roadside and the like on radar environment perception can be effectively eliminated, and the aim of improving the accuracy of target object identification is fulfilled.
It can be understood that, with continued reference to fig. 3, the target identification instruction may be an instruction for detecting and identifying a surrounding target object by the sensing layer, when the target identification instruction is obtained, initial target object information is obtained, original target object information acquired by the radar and the camera needs to be obtained before the initial target object information is obtained, the original target object information is analyzed to obtain original environment information and original target object parameter information, and the original environment information and the original target object parameter information are subjected to target object filtering to obtain the initial target object information.
It should be understood that the radar and camera may be millimeter wave radar and mobiley machine vision, and the embodiment is not limited thereto.
It can be understood that the millimeter wave radar is used for detecting original target objects and their motion state parameters and measuring target object fusion Communication (RCS), the machine vision camera is used for identifying traffic static marks such as lane lines and the like, and at the same time, assists in detecting original target objects and their motion state parameters, first, the millimeter wave radar and the machine vision camera acquire original target objects to obtain original target object information, the original target object information is transmitted through CNA bus, in a protocol analysis layer, original environment information and original target object parameter information are obtained through millimeter wave radar information analysis and camera CNA protocol analysis, the original environment information includes information such as roads, vehicles, pedestrians, road signs and the like, the original target object parameter information includes information such as distance, absorptivity, speed, acceleration and the like of the original target objects, wherein the obtained original target object parameter information is analyzed by taking the lane lines in the original environment information as reference objects, in the information filtering layer, the initial target object information can be obtained by filtering false alarm targets from the original environment information and the original target object parameter information in the information filtering layer.
And step S20, extracting preset distance information of the initial target object information.
It should be noted that, target vehicle information of a target vehicle is acquired, a transverse distance and a longitudinal distance between an initial target object corresponding to the initial target object information and the target vehicle corresponding to the target vehicle information are extracted, and the transverse distance and the longitudinal distance are used as the preset distance information.
It can be understood that the lateral distance and the longitudinal distance of the initial target object relative to the target vehicle are extracted with the target vehicle radar as a center point.
And step S30, identifying the initial target object information according to the preset distance information to obtain target object information.
It should be understood that the preset distance information includes a transverse distance and a longitudinal distance, when the longitudinal distance is judged to be greater than the preset longitudinal distance, the transverse distance is limited to be within a first transverse distance range, and then the initial target object information identified within the range can be used as the target object information, when the longitudinal distance is further judged to be less than or equal to the preset longitudinal distance, the transverse distance is limited to be within a second transverse distance range, and then the initial target object information identified within the range can be used as the target object information, and when the transverse distance is judged again to be within the preset transverse distance range, and the current driving speed is greater than the preset driving speed, and then the initial target object information identified within the range can be used as the target object information.
It is to be understood that the first lateral distance range and the second lateral distance range may be a sum of lateral distance values that are bilaterally symmetric about a center line of the millimeter wave radar of the target vehicle, and the first lateral distance range, the second lateral distance range, and the preset running speed may be values that can be set by a person skilled in the art according to specific situations, which is not limited by the embodiment.
And step S40, extracting target static object information and target non-static object information in the target object information, and performing information fusion on the target static object information and the target non-static object information to obtain fused target object information.
In the fusion layer, target static object information and target non-static object information are extracted from the target object information, and the extracted target static object information and target non-static object information are fused by weighted fusion of ARS radar and mobiley information, so that fused target object information can be obtained.
In this embodiment, when a target identification instruction is obtained, initial target information is obtained, preset distance information of the initial target information is extracted, the initial target information is identified according to the preset distance information to obtain target information, target static object information and target non-static object information in the target information are extracted, and the target static object information and the target non-static object information are subjected to information fusion to obtain fused target information. The initial target object information is identified to obtain target object information, and then the target object information is extracted and fused, so that the problem that a front static target and a pedestrian not close to the vehicle and moving transversely are mistakenly identified as dangerous targets when the radar detection range is wide is solved, and the accuracy of target object identification is improved.
In an embodiment, as shown in fig. 4, a second embodiment of the object identification method according to the present invention is provided based on the first embodiment, and the step S20 includes:
in step S201, target vehicle information of a target vehicle is acquired.
It is understood that the target vehicle information includes information such as position information and speed information of the target vehicle, and thus, information such as position information and speed information corresponding to the target vehicle is acquired.
Step S202, extracting the transverse distance and the longitudinal distance between the initial target object corresponding to the initial target object information and the target vehicle corresponding to the target vehicle information.
It should be noted that, according to the position information and the speed information corresponding to the target vehicle, the relative speed information between the initial target object corresponding to the initial target object information and the target vehicle corresponding to the target vehicle information is extracted by the radar, and the distance information, that is, the transverse distance and the longitudinal distance, between the initial target object corresponding to the initial target object information and the target vehicle corresponding to the target vehicle information is obtained by performing integral calculation according to the relative speed information.
It is understood that, for example, fig. 5 is a schematic diagram of the lateral distance and the longitudinal distance in the present embodiment, taking the millimeter wave radar of the target vehicle as a coordinate center point, and if the initial target object is on the right side of the target vehicle and the coordinate point of the initial target object is (a, b), the corresponding positional relationship between the initial target object and the target vehicle is a lateral distance and b is a longitudinal distance.
Step S203, using the horizontal distance and the vertical distance as the preset distance information.
It is understood that the preset distance information includes a lateral distance and a longitudinal distance between the initial target object with respect to the target vehicle.
In this embodiment, the target vehicle information of the target vehicle is acquired, and the transverse distance and the longitudinal distance included in the preset distance information between the initial target object corresponding to the initial target object information and the target vehicle corresponding to the target vehicle information are determined, so that the accuracy of target object identification is further improved.
In an embodiment, as shown in fig. 6, a third embodiment of the object identifying method according to the present invention is provided based on the first embodiment or the second embodiment, and in this embodiment, the step S30 includes:
step S301, judging whether the longitudinal distance is larger than a preset longitudinal distance.
It should be understood that the preset longitudinal distance may be a value that can be set by a person skilled in the art according to specific situations, and the present embodiment is not limited thereto, and the present embodiment may be described by using the preset longitudinal distance as 20 meters.
Step S302, if the longitudinal distance is greater than the preset longitudinal distance, determining whether the transverse distance is within a preset first transverse distance range.
It is understood that, by determining if the longitudinal distance is greater than 20 meters, it is further determined whether the lateral distance is within the preset first lateral distance range.
Step S303, if the lateral distance is within the first lateral distance range, using the initial target object information as target object information.
If the lateral distance is within the first lateral distance range, the initial object information may be regarded as the object information, and if the lateral distance is not within the first lateral distance range, the initial object information may not be regarded as the object information, and for example, if the lateral distance of the initial object information is 1 meter and the first lateral distance is 4 meters, that is, if the lateral distance of 1 meter is within 2 meters of the lateral distance value about the center line of the target vehicle, the initial object information may be regarded as the object information by determining that 1 meter is within 2 meters of the lateral distance value about the center line of the target vehicle. Assuming that the lateral distance of the initial target object information is 3 meters and the first lateral distance is 4 meters, that is, it is determined whether the lateral distance of 3 meters is within 2 meters of the lateral distance value of the left and right sides with the target vehicle as the center line, and by determining that 3 meters is not within 2 meters of the lateral distance value of the left and right sides, the initial target object information may not be the target object information.
Further, after step S301, the method further includes:
and if the longitudinal distance is smaller than or equal to the preset longitudinal distance, judging whether the transverse distance is within a preset second transverse distance range.
It can be understood that, by judging whether the longitudinal distance is less than or equal to 20 meters, whether the transverse distance is within the preset two transverse distance ranges is further judged.
And if the transverse distance is within a second transverse distance range, taking the initial target object information as target object information.
If the lateral distance is within the second lateral distance range, the initial object information may be regarded as the object information, and if the lateral distance is not within the second lateral distance range, the initial object information may not be regarded as the object information, and for example, if the lateral distance of the initial object information is 1 meter and the second lateral distance is 2.4 meters, that is, if the lateral distance 1 meter is within the left-right lateral distance value of 1.2 meters with the target vehicle as the center line, the initial object information may be regarded as the object information by determining that the lateral distance 1 meter is within the left-right lateral distance value of 1.2 meters. Assuming that the lateral distance of the initial target object information is 2 meters and the second lateral distance is 1.2 meters, that is, it is determined whether the lateral distance 2 meters is within 1.2 meters of the lateral distance value between the left and right sides with the target vehicle as the center line, and by determining that the lateral distance 2 meters is not within 1.2 meters of the lateral distance value between the left and right sides, the initial target object information may not be the target object information.
Further, step S30 includes:
and judging whether the transverse distance is within a preset transverse distance range.
It should be noted that, before determining whether the lateral distance is within the preset lateral distance range, the driving direction of the initial target object information needs to be acquired, and if the driving direction moves toward the lateral direction of the target vehicle, the step of determining whether the lateral distance is within the preset lateral distance range is performed.
It should be understood that the driving direction of the initial object information is acquired, if the driving direction is toward the lateral direction of the target vehicle, the step of determining whether the lateral distance is within the preset lateral distance range may be performed, and if the driving direction is not toward the lateral direction of the target vehicle, the initial object information in this case may not be used as the object information.
It should be noted that the preset transverse distance range may be a sum of transverse distance values that are bilaterally symmetric about a center line of a millimeter wave radar of a target vehicle, and the preset longitudinal distance may be a value that can be set by a person skilled in the art according to specific situations, which is not limited in this embodiment, and this embodiment may be exemplified by the preset transverse distance being 8 meters.
And if the transverse distance is within a preset transverse distance range, acquiring the current running speed of the initial target object information, and judging whether the current running speed is greater than a preset running speed.
It can be understood that, if the lateral distance is within 8 meters, that is, if the lateral distance is within 4 meters of the lateral distance value about the center line of the target vehicle, by acquiring the current running speed of the initial target object information, it is further determined whether the current running speed is greater than the preset running speed.
And if the running speed is greater than the preset running speed, taking the initial target object information as target object information.
It should be noted that, it is previously determined that the current driving direction of the acquired initial target object information moves in the lateral direction of the target vehicle, and when the current driving direction moves in the lateral direction of the target vehicle and the lateral distance is within the preset lateral distance range, it is determined that the initial target object information is used as the target object information if the driving speed is greater than the preset driving speed, and if the driving speed is less than or equal to the preset driving speed, the initial target object information may not be used as the target object information. For example, in a case where the current traveling direction is a direction moving in a lateral direction of the target vehicle and the lateral distance is within a preset lateral distance range, assuming that the preset traveling speed is 1m/s, if the traveling speed of the initial target object information is 2m/s, the initial target object information is regarded as the target object information by determining that the traveling speed is greater than the preset traveling speed, and if the traveling speed of the initial target object information is 0.5m/s, the initial target object information may not be regarded as the target object information by determining that the traveling speed is less than the preset traveling speed.
In this embodiment, the transverse distance and the longitudinal distance of the preset distance information are determined, the transverse distance and the longitudinal distance are further identified, whether the initial target object information can be used as the target object information is judged, then, when the driving direction information and the speed information of the initial target object information are obtained, the transverse distance and the speed information are identified, and whether the initial target object information can be used as the target object information is judged again, so that the accuracy of target object identification is further improved.
Furthermore, an embodiment of the present invention further provides a storage medium, in which an object identification program is stored, and the object identification program, when executed by a processor, implements the steps of the object identification method as described above.
Since the storage medium adopts all technical solutions of all the embodiments, at least all the beneficial effects brought by the technical solutions of the embodiments are achieved, and no further description is given here.
In addition, referring to fig. 7, an embodiment of the present invention further provides an object recognition apparatus, where the object recognition apparatus includes:
the obtaining module 10 is configured to obtain initial target object information when the target object identification instruction is obtained.
It can be understood that the target identification instruction may be an instruction for detecting and identifying a surrounding target in the sensing layer, when the target identification instruction is obtained, initial target information is obtained, original target information acquired by the radar and the camera is needed to be obtained before the initial target information is obtained, the original target information is analyzed to obtain original environment information and original target parameter information, and the original environment information and the original target parameter information are subjected to target filtering to obtain the initial target information.
It should be understood that the radar and camera may be millimeter wave radar and mobiley machine vision, and the embodiment is not limited thereto.
It can be understood that the millimeter wave radar is used for detecting original target objects and their motion state parameters and measuring target object fusion Communication (RCS), the machine vision camera is used for identifying traffic static marks such as lane lines and the like, and at the same time, assists in detecting original target objects and their motion state parameters, first, the millimeter wave radar and the machine vision camera acquire original target objects to obtain original target object information, the original target object information is transmitted through CNA bus, in a protocol analysis layer, original environment information and original target object parameter information are obtained through millimeter wave radar information analysis and camera CNA protocol analysis, the original environment information includes information such as roads, vehicles, pedestrians, road signs and the like, the original target object parameter information includes information such as distance, absorptivity, speed, acceleration and the like of the original target objects, wherein the obtained original target object parameter information is analyzed by taking the lane lines in the original environment information as reference objects, in the information filtering layer, the initial target object information can be obtained by filtering false alarm targets from the original environment information and the original target object parameter information in the information filtering layer.
And an extracting module 20, configured to extract preset distance information of the initial target object information.
It should be noted that, target vehicle information of a target vehicle is acquired, a transverse distance and a longitudinal distance between an initial target object corresponding to the initial target object information and the target vehicle corresponding to the target vehicle information are extracted, and the transverse distance and the longitudinal distance are used as the preset distance information.
It can be understood that the lateral distance and the longitudinal distance of the initial target object relative to the target vehicle are extracted with the target vehicle radar as a center point.
And the identification module 30 is configured to identify the initial target object information according to the preset distance information to obtain target object information.
It should be understood that the preset distance information includes a transverse distance and a longitudinal distance, when the longitudinal distance is judged to be greater than the preset longitudinal distance, the transverse distance is limited to be within a first transverse distance range, and then the initial target object information identified within the range can be used as the target object information, when the longitudinal distance is further judged to be less than or equal to the preset longitudinal distance, the transverse distance is limited to be within a second transverse distance range, and then the initial target object information identified within the range can be used as the target object information, and when the transverse distance is judged again to be within the preset transverse distance range, and the current driving speed is greater than the preset driving speed, and then the initial target object information identified within the range can be used as the target object information.
It is to be understood that the first lateral distance range and the second lateral distance range may be a sum of lateral distance values that are bilaterally symmetric about a center line of the millimeter wave radar of the target vehicle, and the first lateral distance range, the second lateral distance range, and the preset running speed may be values that can be set by a person skilled in the art according to specific situations, which is not limited by the embodiment.
And the fusion module 40 is configured to extract the target static object information and the target non-static object information in the target object information, and perform information fusion on the target static object information and the target non-static object information to obtain fused target object information.
In the fusion layer, the target information is obtained, the target static object information and the target non-static object information need to be extracted from the target information, and the extracted target static object information and the extracted target non-static object information are subjected to information fusion through weighted fusion of the ARS radar and the mobiley information, so that the fused target information can be obtained.
In this embodiment, when a target identification instruction is obtained, initial target information is obtained, preset distance information of the initial target information is extracted, the initial target information is identified according to the preset distance information to obtain target information, target static object information and target non-static object information in the target information are extracted, and the target static object information and the target non-static object information are subjected to information fusion to obtain fused target information. The initial target object information is identified to obtain target object information, and then the target object information is extracted and fused, so that the problem that a front static target and a pedestrian not close to the vehicle and moving transversely are mistakenly identified as dangerous targets when the radar detection range is wide is solved, and the accuracy of target object identification is improved.
In an embodiment, the obtaining module 10 is further configured to obtain original target object information collected by a radar and a camera; analyzing the original target object information to obtain original environment information and original target object parameter information; and filtering the original environment information and the original target object parameter information to obtain initial target object information.
In an embodiment, the extracting module 20 is further configured to obtain target vehicle information of a target vehicle; extracting the transverse distance and the longitudinal distance between an initial target object corresponding to the initial target object information and a target vehicle corresponding to the target vehicle information; and taking the transverse distance and the longitudinal distance as the preset distance information.
In an embodiment, the identification module 30 is further configured to determine whether the longitudinal distance is greater than a preset longitudinal distance; if the longitudinal distance is greater than the preset longitudinal distance, judging whether the transverse distance is within a preset first transverse distance range; and if the transverse distance is within the first transverse distance range, taking the initial target object information as target object information.
In an embodiment, the identifying module 30 is further configured to determine whether the transverse distance is within a preset second transverse distance range if the longitudinal distance is less than or equal to the preset longitudinal distance; and if the transverse distance is within a second transverse distance range, taking the initial target object information as target object information.
In an embodiment, the identifying module 40 is further configured to determine whether the lateral distance is within a preset lateral distance range; if the transverse distance is within a preset transverse distance range, acquiring the current running speed of the initial target object information, and judging whether the current running speed is greater than a preset running speed or not; and if the running speed is greater than the preset running speed, taking the initial target object information as target object information.
In an embodiment, the obtaining module 10 is further configured to obtain a driving direction of the initial target object information; and if the driving direction moves towards the transverse direction of the target vehicle, executing the step of judging whether the transverse distance is within a preset transverse distance range.
For other embodiments or specific implementation methods of the target object identification device according to the present invention, reference may be made to the above method embodiments, and details are not described herein again.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in an estimator readable storage medium (such as ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling an intelligent object recognition device (such as a mobile phone, an estimator, an object recognition device, an air conditioner, or an object recognition device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. An object recognition method, characterized by comprising the steps of:
when a target object identification instruction is obtained, obtaining initial target object information;
extracting preset distance information of the initial target object information;
identifying the initial target object information according to the preset distance information to obtain target object information;
and extracting target static object information and target non-static object information in the target object information, and performing information fusion on the target static object information and the target non-static object information to obtain fused target object information.
2. The method for identifying an object according to claim 1, wherein the extracting the preset distance information of the initial object information comprises:
acquiring target vehicle information of a target vehicle;
extracting the transverse distance and the longitudinal distance between an initial target object corresponding to the initial target object information and a target vehicle corresponding to the target vehicle information;
and taking the transverse distance and the longitudinal distance as the preset distance information.
3. The method for identifying the target object according to claim 2, wherein the identifying the initial target object information according to the preset distance information to obtain the target object information comprises:
judging whether the longitudinal distance is larger than a preset longitudinal distance or not;
if the longitudinal distance is greater than the preset longitudinal distance, judging whether the transverse distance is within a preset first transverse distance range;
and if the transverse distance is within the first transverse distance range, taking the initial target object information as target object information.
4. The method for identifying an object according to claim 3, wherein after determining whether the longitudinal distance is greater than a preset longitudinal distance, the method further comprises:
if the longitudinal distance is smaller than or equal to the preset longitudinal distance, judging whether the transverse distance is within a preset second transverse distance range;
and if the transverse distance is within a second transverse distance range, taking the initial target object information as target object information.
5. The method for identifying the target object according to claim 2, wherein the identifying the initial target object information according to the preset distance information to obtain the target object information comprises:
judging whether the transverse distance is within a preset transverse distance range or not;
if the transverse distance is within a preset transverse distance range, acquiring the current running speed of the initial target object information, and judging whether the current running speed is greater than a preset running speed or not;
and if the running speed is greater than the preset running speed, taking the initial target object information as target object information.
6. The method for identifying an object according to claim 5, wherein before determining whether the lateral distance is within a preset lateral distance range, the method further comprises:
acquiring the driving direction of the initial target object information;
and if the driving direction moves towards the transverse direction of the target vehicle, executing the step of judging whether the transverse distance is within a preset transverse distance range.
7. The object identification method according to any one of claims 1 to 6, wherein before acquiring the initial object information when the object identification instruction is acquired, further comprising:
acquiring original target object information acquired by a radar and a camera;
analyzing the original target object information to obtain original environment information and original target object parameter information;
and filtering the original environment information and the original target object parameter information to obtain initial target object information.
8. An object recognition apparatus, characterized in that the object recognition apparatus comprises:
the acquisition module is used for acquiring initial target object information when a target object identification instruction is acquired;
the extraction module is used for extracting preset distance information of the initial target object information;
the identification module is used for identifying the initial target object information according to the preset distance information to obtain target object information;
and the fusion module is used for extracting the target static object information and the target non-static object information in the target object information, and performing information fusion on the target static object information and the target non-static object information to obtain fused target object information.
9. An object recognition apparatus, characterized in that the object recognition apparatus comprises: memory, a processor and an object identification program stored on the memory and executable on the processor, the object identification program being configured with steps to implement an object identification method according to any of claims 1 to 7.
10. A storage medium having stored thereon an object recognition program which, when executed by a processor, implements the steps of the object recognition method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011057323.6A CN112162275B (en) | 2020-09-29 | 2020-09-29 | Target object identification method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011057323.6A CN112162275B (en) | 2020-09-29 | 2020-09-29 | Target object identification method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112162275A true CN112162275A (en) | 2021-01-01 |
| CN112162275B CN112162275B (en) | 2024-05-14 |
Family
ID=73860804
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011057323.6A Active CN112162275B (en) | 2020-09-29 | 2020-09-29 | Target object identification method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112162275B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011053139A (en) * | 2009-09-03 | 2011-03-17 | Toyota Motor Corp | Object detection device |
| JP2012089114A (en) * | 2010-09-24 | 2012-05-10 | Toyota Motor Corp | Obstacle recognition device |
| JP2016223812A (en) * | 2015-05-27 | 2016-12-28 | 株式会社デンソー | Vehicle control device and vehicle control method |
| CN109885056A (en) * | 2019-03-07 | 2019-06-14 | 格陆博科技有限公司 | A kind of more scene selection methods merged based on monocular cam and millimetre-wave radar |
| CN109901156A (en) * | 2019-01-25 | 2019-06-18 | 中国汽车技术研究中心有限公司 | A kind of subject fusion method and apparatus of vehicle millimetre-wave radar and camera |
| CN110095770A (en) * | 2019-04-26 | 2019-08-06 | 东风柳州汽车有限公司 | The detection method of vehicle-surroundings object |
| WO2019154029A1 (en) * | 2018-02-12 | 2019-08-15 | 北京宝沃汽车有限公司 | Method for searching for target object, and apparatus and storage medium |
| CN110275168A (en) * | 2019-07-09 | 2019-09-24 | 厦门金龙联合汽车工业有限公司 | A kind of multi-targets recognition and anti-collision early warning method and system |
| CN111505624A (en) * | 2020-04-30 | 2020-08-07 | 中国汽车工程研究院股份有限公司 | Environment sensing method based on machine vision and millimeter wave radar data fusion |
-
2020
- 2020-09-29 CN CN202011057323.6A patent/CN112162275B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011053139A (en) * | 2009-09-03 | 2011-03-17 | Toyota Motor Corp | Object detection device |
| JP2012089114A (en) * | 2010-09-24 | 2012-05-10 | Toyota Motor Corp | Obstacle recognition device |
| JP2016223812A (en) * | 2015-05-27 | 2016-12-28 | 株式会社デンソー | Vehicle control device and vehicle control method |
| WO2019154029A1 (en) * | 2018-02-12 | 2019-08-15 | 北京宝沃汽车有限公司 | Method for searching for target object, and apparatus and storage medium |
| CN109901156A (en) * | 2019-01-25 | 2019-06-18 | 中国汽车技术研究中心有限公司 | A kind of subject fusion method and apparatus of vehicle millimetre-wave radar and camera |
| CN109885056A (en) * | 2019-03-07 | 2019-06-14 | 格陆博科技有限公司 | A kind of more scene selection methods merged based on monocular cam and millimetre-wave radar |
| CN110095770A (en) * | 2019-04-26 | 2019-08-06 | 东风柳州汽车有限公司 | The detection method of vehicle-surroundings object |
| CN110275168A (en) * | 2019-07-09 | 2019-09-24 | 厦门金龙联合汽车工业有限公司 | A kind of multi-targets recognition and anti-collision early warning method and system |
| CN111505624A (en) * | 2020-04-30 | 2020-08-07 | 中国汽车工程研究院股份有限公司 | Environment sensing method based on machine vision and millimeter wave radar data fusion |
Non-Patent Citations (1)
| Title |
|---|
| 张海鸣 等: "非结构化环境下无人驾驶车辆跟驰方法", 《北京理工大学学报》, vol. 39, no. 11, pages 1126 - 1132 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112162275B (en) | 2024-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5939357B2 (en) | Moving track prediction apparatus and moving track prediction method | |
| US20150298621A1 (en) | Object detection apparatus and driving assistance apparatus | |
| KR101446546B1 (en) | Display system of vehicle information based on the position | |
| JP4171501B2 (en) | Vehicle periphery monitoring device | |
| CN109270524B (en) | Unmanned-vehicle-based multi-data fusion obstacle detection device and detection method thereof | |
| CN112014845A (en) | Vehicle obstacle positioning method, device, equipment and storage medium | |
| CN111553605A (en) | Vehicle lane change risk assessment method, device, equipment and storage medium | |
| CN110341621B (en) | Obstacle detection method and device | |
| CN112562406B (en) | Method and device for identifying off-line driving | |
| CN111144330A (en) | Deep learning-based lane line detection method, device and equipment | |
| CN113593301A (en) | Method for pre-judging vehicle clogging, vehicle, and computer-readable storage medium | |
| CN114037972A (en) | Target detection method, device, equipment and readable storage medium | |
| KR101687094B1 (en) | Apparatus for recognizing traffic sign and method thereof | |
| CN113433548B (en) | Data monitoring method, device, equipment and storage medium | |
| KR20160081190A (en) | Method and recording medium for pedestrian recognition using camera | |
| CN114475593A (en) | Travel track prediction method, vehicle, and computer-readable storage medium | |
| WO2024098992A1 (en) | Vehicle reversing detection method and apparatus | |
| CN113313182A (en) | Target identification method and terminal based on radar and video fusion | |
| JP2007212418A (en) | On-vehicle radar device | |
| CN113257036A (en) | Vehicle collision early warning method, device, equipment and storage medium | |
| CN112162275B (en) | Target object identification method, device, equipment and storage medium | |
| CN115757628A (en) | Vehicle collision detection method, device, equipment and medium | |
| CN112346046B (en) | Single-target tracking method and system based on vehicle-mounted millimeter wave radar | |
| CN113050063A (en) | Obstacle detection method, device and equipment based on laser sensor and storage medium | |
| CN114596706A (en) | Detection method and device of roadside sensing system, electronic equipment and roadside equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |