CN115436899A - Method, device, equipment and storage medium for processing millimeter wave radar detection data - Google Patents
Method, device, equipment and storage medium for processing millimeter wave radar detection data Download PDFInfo
- Publication number
- CN115436899A CN115436899A CN202211062734.3A CN202211062734A CN115436899A CN 115436899 A CN115436899 A CN 115436899A CN 202211062734 A CN202211062734 A CN 202211062734A CN 115436899 A CN115436899 A CN 115436899A
- Authority
- CN
- China
- Prior art keywords
- region
- interest
- millimeter wave
- wave radar
- determining
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 286
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000012545 processing Methods 0.000 title claims abstract description 37
- 230000000007 visual effect Effects 0.000 claims abstract description 70
- 239000000523 sample Substances 0.000 claims description 26
- 238000004590 computer program Methods 0.000 claims description 17
- 238000003672 processing method Methods 0.000 claims description 6
- 238000004891 communication Methods 0.000 description 8
- 230000001788 irregular Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 238000005259 measurement Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses a method for processing millimeter wave radar detection data, which comprises the following steps: determining a first region of interest set corresponding to the first detection object and a second region of interest set corresponding to the second detection object according to the detection result of the millimeter wave radar on the first detection object and the detection result of the second detection object; determining a region of coincidence between the first set of regions of interest and the second set of regions of interest, and a longitudinal distance between the first set of regions of interest and the second set of regions of interest; determining whether the first detector and the second detector are the same according to the overlapping area and the longitudinal distance; determining a candidate region of interest set of the millimeter wave radar according to the determination result, the first region of interest set and the second region of interest set; and matching the candidate interesting region set with the visual information of the image acquisition equipment, and adjusting the candidate interesting region set according to a matching result to obtain a target interesting region set of the millimeter wave radar. The detection precision of the millimeter wave radar is improved.
Description
Technical Field
The embodiment of the invention relates to the field of computers, in particular to a method, a device, equipment and a storage medium for processing millimeter wave radar detection data.
Background
Along with the continuous development of intelligent driving technology, more and more vehicles are equipped with millimeter wave radars for increasing the perception of the vehicles to the surrounding environment, so that more perception information can be provided for drivers. For the millimeter wave radar, the accuracy of the longitudinal distance measurement of the target is needless to say, but for the transverse position of the target, due to the different relative position relationship between the millimeter wave radar and the detection target, the problem that the measurement of the transverse position of the object to be detected by the millimeter wave radar is inaccurate can occur, and the running safety of the vehicle is damaged. Therefore, how to improve the accuracy of the millimeter wave radar in measuring the transverse position of the detected object so as to improve the detection precision of the millimeter wave radar is a problem to be solved.
Disclosure of Invention
The invention provides a method, a device, equipment and a storage medium for processing detection data of a millimeter wave radar, which can improve the accuracy of the millimeter wave radar in measuring the transverse position of a detected object, thereby improving the detection precision of the millimeter wave radar.
According to an aspect of the present invention, there is provided a method for processing millimeter wave radar detection data, including:
determining a first region of interest set corresponding to a first detection object and a second region of interest set corresponding to a second detection object according to a detection result of a millimeter wave radar on the first detection object and a detection result of the second detection object;
determining a region of coincidence between the first set of regions of interest and the second set of regions of interest, and a longitudinal distance between the first set of regions of interest and the second set of regions of interest;
determining whether the first probe and the second probe are the same according to the overlap region and the longitudinal distance;
determining a candidate region of interest set of the millimeter wave radar according to the determination result, the first region of interest set and the second region of interest set;
and matching the candidate interesting region set with the visual information of the image acquisition equipment, and adjusting the candidate interesting region set according to a matching result to obtain a target interesting region set of the millimeter wave radar.
According to another aspect of the present invention, there is provided a processing apparatus of millimeter wave radar detection data, the apparatus including:
the region-of-interest set determining module is used for determining a first region-of-interest set corresponding to a first detection object and a second region-of-interest set corresponding to a second detection object according to a detection result of the millimeter wave radar on the first detection object and a detection result of the second detection object;
a region of coincidence determination module to determine a region of coincidence between the first set of regions of interest and the second set of regions of interest, and a longitudinal distance between the first set of regions of interest and the second set of regions of interest;
a detector determining module for determining whether the first detector and the second detector are the same according to the overlap region and the longitudinal distance;
a candidate region set determining module, configured to determine a candidate region set of interest of the millimeter wave radar according to the determination result, the first region set of interest, and the second region set of interest;
and the target area set determining module is used for matching the candidate interesting area set with the visual information of the image acquisition equipment, and adjusting the candidate interesting area set according to a matching result to obtain the target interesting area set of the millimeter wave radar.
According to another aspect of the present invention, there is provided an electronic apparatus including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the method of processing millimeter wave radar probe data according to any one of the embodiments of the present invention.
According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the processing method of millimeter wave radar detection data according to any one of the embodiments of the present invention when executed.
According to the technical scheme of the embodiment of the invention, a first interested area set corresponding to a first detection object and a second interested area set corresponding to a second detection object are determined according to the detection result of a millimeter wave radar on the first detection object and the detection result of the second detection object; determining a region of coincidence between the first set of regions of interest and the second set of regions of interest, and a longitudinal distance between the first set of regions of interest and the second set of regions of interest; determining whether the first detection object and the second detection object are the same or not according to the overlapping area and the longitudinal distance, and determining a candidate interest area set of the millimeter wave radar according to the determination result, the first interest area set and the second interest area set; and matching the candidate interesting region set with the visual information of the image acquisition equipment, and adjusting the candidate interesting region set according to a matching result to obtain a target interesting region set of the millimeter wave radar. According to the scheme, under the condition that the millimeter wave radar detects two detection objects, the first region of interest set and the second region of interest set are obtained by obtaining detection results of the millimeter wave radar on the two detection objects; and determining whether two detected objects detected by the millimeter wave radar are the same detected object or not according to the overlapping area and the longitudinal distance between the first interested area set and the second interested area set, thereby determining the candidate interested area of the millimeter wave radar. And matching the candidate interesting region of the millimeter wave radar with the visual information to adjust the candidate interesting region and obtain a target interesting region set of the millimeter wave radar. The problem of because the millimeter wave radar is inaccurate to the lateral position measurement of surveyed object, the millimeter wave radar that leads to has the error to the position identification result of surveyed object, influences vehicle safety of traveling is solved. The accuracy of the millimeter wave radar in measuring the transverse position of the detected object is improved, the error recognition of the millimeter wave radar on the detected object is avoided, and the detection precision of the millimeter wave radar is improved.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present invention, nor do they necessarily limit the scope of the invention. Other features of the present invention will become apparent from the following description.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, 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 flowchart of a method for processing millimeter wave radar detection data according to an embodiment of the present invention;
fig. 2 is a flowchart of a method for processing millimeter wave radar detection data according to a second embodiment of the present invention;
fig. 3 is a flowchart of a method for processing millimeter wave radar detection data according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a device for processing millimeter wave radar detection data according to a fourth embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It is to be understood that the terms "first" and "second," and the like in the description and claims of the present invention and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Moreover, the terms "comprises," "comprising," and any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example one
Fig. 1 is a flowchart of a method for processing millimeter wave radar detection data according to an embodiment of the present invention, which is applicable to a case of processing detection data of a millimeter wave radar. The method may be performed by a processing device of millimeter wave radar detection data, which may be implemented in hardware and/or software, and which may be configured in an electronic device. As shown in fig. 1, the method includes:
s110, determining a first interested area set corresponding to the first detection object and a second interested area set corresponding to the second detection object according to the detection result of the millimeter wave radar on the first detection object and the detection result of the second detection object.
The millimeter wave radar is a radar operating in a millimeter wave band for detection. The first detection object and the second detection object refer to objects detected by the millimeter wave radar, for example, detection objects in front of the vehicle detected by the millimeter wave radar mounted on the vehicle, and the detection objects may be moving detection objects or stationary detection objects. The region of interest set ROI (region of interest) refers to a region to be processed, which is delineated from a processed image in a manner of a square, a circle, an ellipse, or an irregular polygon, in machine vision and image processing. The first region of interest set and the second region of interest set each contain at least two sub-regions of interest. The sub-region of interest is any region that needs to be processed and is delineated from the processed image by a square, a circle, an ellipse or an irregular polygon.
It should be noted that, because there is a certain error in the result of detecting the object to be detected by the millimeter wave radar in the transverse direction, in a case where there is only one object to be detected, the millimeter wave radar may erroneously recognize one object to be detected as two objects to obtain the detection results of the two objects to be detected.
Specifically, when the millimeter wave radar identifies two detection objects, a first interest area set corresponding to the first detection object is obtained according to a detection result of the millimeter wave radar on the first detection object; and acquiring a second interested area set corresponding to the second detection object according to the detection result of the millimeter wave radar on the second detection object. The first region of interest set may be obtained by determining boundary points of the first detecting object, delineating boundary regions corresponding to the boundary points of the first detecting object in a square frame, a circle, an ellipse, an irregular polygon, or the like, and integrating the boundary regions corresponding to the boundary points of the first detecting object to obtain the first region of interest set. The second region of interest set may be obtained by determining boundary points of the second detection object, delineating boundary regions corresponding to the boundary points of the second detection object in a square frame, a circle, an ellipse, an irregular polygon, or the like, and integrating the boundary regions corresponding to the boundary points of the second detection object to obtain the second region of interest set.
S120, determining a coincidence region between the first region of interest set and the second region of interest set and a longitudinal distance between the first region of interest set and the second region of interest set.
Wherein a longitudinal distance between the first set of regions of interest and the second set of regions of interest may be a longitudinal distance from a center point of the first region of interest to a center point of the second region of interest.
Specifically, let the first region of interest set be R1, and R1= { a1, b1, c1, d1}, and the second region of interest set be R2, and R2= { a2, b2, c2, d2}. Wherein a1, b1, c1 and d1 are sub-regions of interest contained in the first region of interest set, i.e. the first sub-region of interest; a2 And b2, c2 and d2 are the sub-regions of interest contained in the second set of regions of interest, i.e. the second sub-region of interest. And determining whether the first region of interest set and the second region of interest set have overlapping regions, if so, setting the overlapping regions as Rn, and Rn = (R1 = R2). And determining a longitudinal distance between the first set of regions of interest and the second set of regions of interest.
And S130, determining whether the first detection object and the second detection object are the same or not according to the overlapping area and the longitudinal distance.
Specifically, if the area of the overlapping area is greater than or equal to a preset area threshold and the longitudinal distance is less than or equal to a preset distance threshold, it is determined that the first detection object and the second detection object are the same detection object, that is, the first detection object and the second detection object are the same; if the area of the overlapping area is smaller than a preset area threshold value or the longitudinal distance is smaller than a preset distance threshold value, the first detection object and the second detection object are determined to be different detection objects, namely the first detection object and the second detection object are different. The area threshold and the distance threshold can be set according to actual needs.
Illustratively, it may also be determined whether the first and second probes are the same by the sub-steps of:
s1301, determining the overlapping area of the overlapping area and the overlapping time corresponding to the overlapping area.
The overlapping time corresponding to the overlapping area refers to the continuous time during which the overlapping area of the overlapping area remains unchanged.
Specifically, according to the detection result of the millimeter wave radar, the overlapping area of the first interested area set and the second interested area set is determined, and the overlapping time corresponding to the overlapping area is determined.
S1302, determining a minimum region of interest set according to the comparison result of the first region of interest set and the second region of interest set.
Wherein, the minimum region of interest set refers to the region of interest set with the smallest area in the first region of interest set and the second region of interest set.
Specifically, the area of the first region of interest set and the area of the second region of interest set are determined, the area of the first region of interest set and the area of the second region of interest set are compared, and the minimum region of interest set is determined according to the comparison result. For example, if the area of the first region of interest set is less than or equal to the area of the second region of interest set, the first region of interest set is taken as the minimum region of interest set; and if the area of the first region of interest set is larger than that of the second region of interest set, taking the second region of interest set as a minimum region of interest set.
And S1303, if the overlapping area of the overlapping area is greater than or equal to the minimum interested area set, the longitudinal distance is less than or equal to the distance threshold, and the overlapping time is greater than or equal to the time threshold, determining that the first detector and the second detector are the same.
Wherein, the time threshold can be set according to actual needs.
Specifically, if the overlapping area of the overlapping area is greater than or equal to the area of the minimum region of interest set, the longitudinal distance is less than or equal to the distance threshold, and the overlapping time is greater than or equal to the time threshold, it is determined that the first object and the second object are the same.
And S1304, if the coincidence area of the coincidence region is smaller than the minimum interested region set, the coincidence time is smaller than a time threshold value, or the longitudinal distance is larger than a distance threshold value, determining that the first detector is different from the second detector.
Specifically, if the overlapping area of the overlapping area is smaller than the area of the minimum region of interest set, the overlapping time is smaller than a time threshold, or the longitudinal distance is larger than a distance threshold, it is determined that the first detector and the second detector are different.
It can be understood that, according to the longitudinal distance between the first region of interest set and the second region of interest set, the overlapping area of the overlapping region, and the overlapping time corresponding to the overlapping region, whether the first detection object and the second detection object are the same or not is determined, and the detection accuracy of the millimeter wave radar on the transverse position of the detection object can be improved.
S140, determining a candidate region of interest set of the millimeter wave radar according to the determination result, the first region of interest set and the second region of interest set.
The candidate region-of-interest set refers to a region-of-interest set which is detected by the millimeter wave radar and may have errors.
Specifically, according to the determination result, the first region of interest set and the second region of interest set are processed, the sub-region of interest of the candidate region of interest set is selected from the sub-region of interest of the first region of interest set and the sub-region of interest of the second region of interest set, the sub-regions of interest of the candidate region of interest set are integrated, and the candidate region of interest set of the millimeter wave radar is determined.
Illustratively, if the determination results are the same, integrating the first region of interest set and the second region of interest set to determine a candidate region of interest set of the millimeter wave radar; and if the determination results are different, taking the first region of interest set and the second region of interest set as two candidate region of interest sets of the millimeter wave radar.
Specifically, if the determination results are the same, determining a sub-region of interest in the first region of interest set, that is, a first sub-region of interest; and determining a sub-region of interest in the second set of regions of interest, i.e. a second sub-region of interest. And taking the first interesting sub-region and the second interesting sub-region as interesting sub-regions in a candidate interesting region set, integrating the first interesting sub-region and the second interesting sub-region, and acquiring the candidate interesting region set.
If the determination results are different, taking the first region of interest set as a candidate region of interest set corresponding to the first detection object detected by the millimeter wave radar; and taking the second region of interest set as a candidate region of interest set corresponding to a second detection object detected by the millimeter wave radar.
And determining a candidate region-of-interest set of the millimeter wave radar according to the determination result of whether the first detection object and the second detection object are the same, the first region-of-interest set and the second region-of-interest set, thereby further improving the detection accuracy of the millimeter wave radar.
S150, matching the candidate interesting region set with the visual information of the image acquisition equipment, and adjusting the candidate interesting region set according to a matching result to obtain a target interesting region set of the millimeter wave radar.
The image capturing device refers to a device for capturing an image, and may be a camera, for example. The visual information is the image around the millimeter wave radar acquired by the image acquisition equipment.
Specifically, the visual information in the detection range of the millimeter wave radar is acquired by adopting the image acquisition equipment, and the visual information comprises the visual information of the first detection object and the visual information of the second detection object acquired by the image acquisition equipment. And taking the interested sub-regions in the candidate interested region set as candidate interested sub-regions, respectively matching each candidate interested sub-region with the visual information, and determining the region matched with the visual information in the candidate interested sub-regions as a target interested sub-region. And integrating the target interesting sub-regions and determining a target interesting region set of the millimeter wave radar.
According to the technical scheme provided by the embodiment, a first interested area set corresponding to a first detection object and a second interested area set corresponding to a second detection object are determined according to the detection result of the millimeter wave radar on the first detection object and the detection result of the second detection object; determining a region of coincidence between the first set of regions of interest and the second set of regions of interest, and a longitudinal distance between the first set of regions of interest and the second set of regions of interest; determining whether the first detection object and the second detection object are the same or not according to the overlapping area and the longitudinal distance, and determining a candidate region of interest set of the millimeter wave radar according to the determination result, the first region of interest set and the second region of interest set; and matching the candidate interesting area set with the visual information of the image acquisition equipment, and adjusting the candidate interesting area set according to a matching result to obtain a target interesting area set of the millimeter wave radar. According to the scheme, under the condition that the millimeter wave radar detects two detection objects, the first region of interest set and the second region of interest set are obtained by obtaining detection results of the millimeter wave radar on the two detection objects; and determining whether two detected objects detected by the millimeter wave radar are the same detected object according to the overlapping area and the longitudinal distance between the first region of interest set and the second region of interest set, thereby determining the candidate region of interest of the millimeter wave radar. And matching the candidate interesting region of the millimeter wave radar with the visual information to adjust the candidate interesting region and obtain a target interesting region set of the millimeter wave radar. The problem of because the millimeter wave radar is inaccurate to the lateral position measurement of surveyed object, the millimeter wave radar that leads to has the error to the position identification result of surveyed object, influences vehicle safety of traveling is solved. The accuracy of the millimeter wave radar in measuring the transverse position of the detected object is improved, the error recognition of the millimeter wave radar on the detected object is avoided, and the detection precision of the millimeter wave radar is improved.
Example two
Fig. 2 is a flowchart of a method for processing millimeter wave radar detection data according to a second embodiment of the present invention, which is optimized based on the above-mentioned second embodiment, and provides a preferred embodiment for determining a first region of interest set corresponding to a first detection object and a second region of interest set corresponding to a second detection object according to a detection result of a millimeter wave radar on the first detection object and a detection result of the second detection object. Specifically, as shown in fig. 2, the method includes:
s210, dividing the detection range of the millimeter wave radar according to the region dividing condition to obtain at least two dividing lines of the detection range.
The area division condition refers to a predefined mode for dividing the detection range of the millimeter wave radar, and can be set according to actual needs, or can be changed according to actual needs. The detection range of the millimeter-wave radar refers to a range of an area that can be detected by the millimeter-wave radar. For example, the maximum detection distance of the current millimeter wave radar is generally 200 meters, so that a circular area with a radius of 200 meters and the millimeter wave radar as a center of a circle can be set as the detection range of the millimeter wave radar. According to the area dividing conditions, the detection range of the millimeter wave radar is divided into a plurality of detection areas, and dividing lines among the detection areas are dividing lines of the detection range.
Specifically, the area dividing condition may be that the detection range of the millimeter wave radar is divided once every ten meters, that is, a dividing line of the detection range is made every ten meters. The length of the interval between the dividing lines of the detection range can be set according to actual needs.
It should be noted that, when the millimeter wave radar detects a nearby detection object, the region of interest corresponding to the detection object that can be acquired is large; and detecting a remote detection object, wherein the region of interest corresponding to the detection object which can be acquired is smaller. Therefore, the area division condition may be set such that n division lines of the detection range are set in accordance with the distance between the division line of the detection range and the millimeter wave radar, n being a positive integer greater than 1. The dividing line of the detection range closest to the millimeter wave radar is the first dividing line, and the dividing line of the detection range farthest from the millimeter wave radar is the nth dividing line. The distance relationship between the dividing lines of the two adjacent detection ranges may be: y = km. Wherein y is the distance between the dividing line of the mth detection range and the dividing line of the (m + 1) th detection range, m is more than or equal to 1 and is less than n, and m is an integer. k is a coefficient, and k >1.
S220, obtaining the detection result of the first detection object and the detection result of the second detection object on each dividing line.
Specifically, according to the dividing lines of the detection range, the detection result of the millimeter wave radar on the first detection object on each dividing line and the detection result of the millimeter wave radar on the second detection object on each dividing line are determined.
S230, according to the detection result of the first detection object on each division line, determining a first interested sub-region of the first detection object on each division line, integrating the first interested sub-regions, and determining a first interested region set corresponding to the first detection object.
Specifically, the position of the first detection object on each division line is determined according to the detection result of the first detection object on each division line detected by the millimeter wave radar, and the first interesting sub-region of the first detection object on each division line is outlined in a mode of a square frame, a circle, an ellipse or an irregular polygon and the like according to the position of the first detection object on each division line. By integrating the first sub-regions of interest of the first probe on each dividing line, a first set of regions of interest corresponding to the first probe can be determined.
S240, according to the detection result of the second detection object on each division line, determining a second interested sub-region of the second detection object on each division line, integrating the second interested sub-regions, and determining a second interested region set corresponding to the second detection object.
Specifically, the position of the second detection object on each division line is determined according to the detection result of the second detection object on each division line detected by the millimeter wave radar, and the second interesting sub-region of the second detection object on each division line is outlined in a mode of a square frame, a circle, an ellipse or an irregular polygon and the like according to the position of the second detection object on each division line. And integrating the second interested sub-regions of the second detection object on each dividing line to determine a second interested region set corresponding to the second detection object.
S250, determining a coincidence region between the first region of interest set and the second region of interest set and a longitudinal distance between the first region of interest set and the second region of interest set.
And S260, determining whether the first detection object and the second detection object are the same or not according to the overlapping area and the longitudinal distance.
S270, determining a candidate interested area set of the millimeter wave radar according to the determination result, the first interested area set and the second interested area set.
S280, matching the candidate interesting region set with the visual information of the image acquisition equipment, and adjusting the candidate interesting region set according to a matching result to obtain a target interesting region set of the millimeter wave radar.
According to the technical scheme of the embodiment, the detection range of the millimeter wave radar is divided according to the region dividing condition, and at least two dividing lines of the detection range are obtained; determining a first interesting sub-region of the first detection object on each dividing line, which is detected by the millimeter wave radar, according to the detection result of the millimeter wave radar on the first detection object; determining a second interesting subarea of the second detection object detected by the millimeter wave radar on each dividing line according to the detection result of the millimeter wave radar on the second detection object; determining a first region of interest set from the first sub-region of interest; determining a second region of interest set according to the second sub-region of interest; determining whether a first detection object and a second detection object detected by the millimeter wave radar are the same or not according to the overlapping area and the longitudinal distance of the first region of interest set and the second region of interest set; determining a candidate region of interest set of the millimeter wave radar according to the determination result, the first region of interest set and the second region of interest set; and adjusting the candidate interesting region set according to the visual information of the image acquisition equipment, and determining a target interesting region set of the millimeter wave radar. The scheme provides an optional mode for determining the first region of interest set corresponding to the first detection object and the second region of interest set corresponding to the second detection object, the acquisition modes of the first region of interest set and the second region of interest set are normalized, the convenience for processing the first region of interest and the second region of interest is improved, and therefore the processing efficiency of millimeter wave radar detection data is improved.
EXAMPLE III
Fig. 3 is a flowchart of a method for processing millimeter wave radar detection data according to a third embodiment of the present invention, and this embodiment is optimized based on the foregoing embodiments, and provides a preferred embodiment for matching a candidate region of interest with visual information of an image acquisition device, and adjusting the candidate region of interest according to a matching result to obtain a target region of interest of a millimeter wave radar. Specifically, as shown in fig. 3, the method includes:
s310, determining a first interested area set corresponding to the first detection object and a second interested area set corresponding to the second detection object according to the detection result of the millimeter wave radar on the first detection object and the detection result of the second detection object.
S320, determining a coincidence region between the first region of interest set and the second region of interest set and a longitudinal distance between the first region of interest set and the second region of interest set.
And S330, determining whether the first detection object and the second detection object are the same or not according to the overlapping area and the longitudinal distance.
S340, determining a candidate region of interest set of the millimeter wave radar according to the determination result, the first region of interest set and the second region of interest set.
S350, matching each target interest sub-region in the target interest region set with the visual information of the image acquisition equipment through a normalized cross-correlation matching algorithm, and determining a first matching point of each target interest sub-region and the visual information.
Among them, the normalized cross-correlation matching algorithm is NCC (normalized cross correlation matching) algorithm. The NCC algorithm is a process of finding a corresponding position from a known template image into another large image. The template image is a preset small image, and the normalized cross-correlation matching algorithm is to search the template image in a large image and determine the position of the corresponding template image in the large image. In this embodiment, the known template image is a sub-region of interest of each target in the target region of interest set, and the large image is visual information of the image capturing device. The first matching point is the position point with the highest matching degree with the visual information in each target interest sub-area. The target sub-region of interest refers to a sub-region of interest contained in the target set of regions of interest.
Specifically, each target interesting sub-region in the target interesting region set is matched with the visual information of the image acquisition equipment through an NCC algorithm, a position point with the highest matching degree of each target interesting sub-region in the target interesting region set and the visual information is determined according to a matching result, and the position point with the highest matching degree of each target interesting sub-region in the target interesting region set and the visual information is used as a first matching point of each target interesting sub-region and the visual information.
Illustratively, the first matching point of each target sub-region of interest with visual information may be determined by the sub-steps of:
s3501, performing discrete processing on each target interest sub-region in the target interest region set, and determining candidate discrete points of each target interest sub-region.
The discrete processing is a training set preprocessing method for converting continuous numerical attributes into discrete numerical attributes.
Specifically, a discretization algorithm may be adopted to perform discretization on each target sub-region of interest in the target sub-region of interest set, and candidate discrete points of each target sub-region of interest in the target sub-region of interest set are obtained according to a discretization result.
And S3502, extracting image characteristic points of the visual information of the millimeter wave radar.
The image feature points refer to points with a sharp change in the image gray value or points with a large curvature on the image edge.
Specifically, a feature extraction algorithm is adopted to extract image feature points of the visual information of the millimeter wave radar.
S3503, matching the image characteristic points with the candidate discrete points of the target interest sub-regions through a normalized cross-correlation matching algorithm, determining target discrete points matched with the image characteristic points in the target interest sub-regions, and taking the target discrete points in the target interest sub-regions as first matching points of the target interest sub-regions and the visual information.
Specifically, the image feature points are matched with the candidate discrete points of each target interest sub-region through an NCC algorithm, the candidate discrete point with the highest matching degree with the image feature points in each target interest sub-region is determined, and the candidate discrete point with the highest matching degree with the image feature points in each target interest sub-region is used as the target discrete point matched with the image feature points in each target interest sub-region. And taking the target discrete point in each target interest sub-region as a first matching point of each target interest sub-region and the visual information.
It can be understood that the candidate discrete points of each target sub-region of interest are matched with the feature points of the visual information to determine the first matching points of each target sub-region of interest and the visual information, so that the acquisition accuracy of the first matching points can be ensured, and the acquisition efficiency of the first matching points can be improved.
S360, determining a first matching area of each target interest sub-area and the visual information according to the first matching point of each target interest sub-area.
The first matching area is an area where a first matching point is located and is delineated in a square frame, a circle, an ellipse or an irregular polygon, and the first matching area includes the first matching point.
For example, the first matching area may be a circular area obtained by rounding a circle with a predetermined radius around the first matching point. The specified radius can be set according to actual requirements.
And S370, matching the first matching area of each target interest sub-area with the visual information through a normalized cross-correlation matching algorithm, and determining a second matching point of the first matching area of each target interest sub-area and the visual information.
The second matching point is a position point with the highest matching degree between the first matching area of each target interest sub-area and the visual information.
Specifically, the first matching region of each target interest sub-region is matched with the visual information of the image acquisition device through an NCC algorithm, the position point with the highest matching degree of the first matching region of each target interest sub-region and the visual information is determined according to the matching result, and the position point with the highest matching degree of the first matching region of each target interest sub-region and the visual information is used as the second matching point of the first matching region of each target interest sub-region and the visual information.
And S380, determining second matching areas of the target sub-areas of interest and the visual information according to the first matching points of the target sub-areas of interest.
The second matching area is an area where a second matching point is located and is delineated by a square frame, a circle, an ellipse or an irregular polygon, and the second matching area includes the second matching point.
For example, the second matching area may be a circular area obtained by rounding the second matching point with a predetermined radius.
And S390, integrating the second matching areas of the target interest sub-areas to obtain a target interest area set of the millimeter wave radar.
Specifically, if the first detection object and the second detection object are the same, the second matching regions of the sub-regions of interest of the targets are integrated into one set, and a target region-of-interest set of the millimeter wave radar is obtained.
If the first detection object is different from the second detection object, integrating second matching areas of the target interest sub-areas in the first interest area set to obtain a target interest area set of the millimeter wave radar corresponding to the first detection object; and integrating second matching regions of the interested sub-regions of the targets in the second interested region set to obtain the interested region set of the targets of the millimeter wave radar corresponding to the second detection object.
According to the technical scheme of the embodiment, after a candidate interest area set of the millimeter wave radar is determined, a first matching point of visual information of each target interest sub-area in the target interest area set and image acquisition equipment is determined through a normalized cross-correlation matching algorithm, and a first matching area is determined according to the first matching point; and matching the first matching area in the interested sub-area of each target with the visual information according to a normalized cross-correlation matching algorithm, determining a second matching point, determining a second matching area according to the second matching point, and determining a target interested area set of the millimeter wave radar according to the second matching area. According to the scheme, the candidate region-of-interest set of the millimeter wave radar is adjusted through the normalized cross-correlation matching algorithm and the visual information acquired by the image acquisition equipment, so that the target region-of-interest set of the millimeter wave radar is acquired, the accuracy of the acquired target region-of-interest set of the millimeter wave radar is improved, and the detection precision of the millimeter wave radar is further improved.
Example four
Fig. 4 is a schematic structural diagram of a device for processing millimeter wave radar detection data according to a fourth embodiment of the present invention. The present embodiment is applicable to the case of processing probe data of a millimeter wave radar. As shown in fig. 4, the processing device of millimeter wave radar detection data includes: a region of interest set determination module 410, a coincidence region determination module 420, a probe determination module 430, a candidate region set determination module 440, and a target region set determination module 450.
The region-of-interest set determining module 410 is configured to determine, according to a detection result of the millimeter wave radar on the first detection object and a detection result of the second detection object, a first region-of-interest set corresponding to the first detection object and a second region-of-interest set corresponding to the second detection object;
a region of coincidence determination module 420 for determining a region of coincidence between the first set of regions of interest and the second set of regions of interest, and a longitudinal distance between the first set of regions of interest and the second set of regions of interest;
a probe determination module 430 for determining whether the first probe and the second probe are the same based on the overlap region and the longitudinal distance;
a candidate region set determining module 440, configured to determine a candidate region set of interest of the millimeter wave radar according to the determination result, the first region set of interest, and the second region set of interest;
and a target region set determining module 450, configured to match the candidate region of interest set with the visual information of the image acquisition device, and adjust the candidate region of interest set according to a matching result, so as to obtain a target region of interest set of the millimeter wave radar.
According to the technical scheme provided by the embodiment, a first interested area set corresponding to a first detection object and a second interested area set corresponding to a second detection object are determined according to the detection result of the millimeter wave radar on the first detection object and the detection result of the second detection object; determining a region of coincidence between the first set of regions of interest and the second set of regions of interest, and a longitudinal distance between the first set of regions of interest and the second set of regions of interest; determining whether the first detection object and the second detection object are the same or not according to the overlapping area and the longitudinal distance, and determining a candidate interest area set of the millimeter wave radar according to the determination result, the first interest area set and the second interest area set; and matching the candidate interesting area set with the visual information of the image acquisition equipment, and adjusting the candidate interesting area set according to a matching result to obtain a target interesting area set of the millimeter wave radar. According to the scheme, under the condition that the millimeter wave radar detects two detection objects, the first region of interest set and the second region of interest set are obtained by obtaining detection results of the millimeter wave radar on the two detection objects; and determining whether two detected objects detected by the millimeter wave radar are the same detected object according to the overlapping area and the longitudinal distance between the first region of interest set and the second region of interest set, thereby determining the candidate region of interest of the millimeter wave radar. And matching the candidate interesting region of the millimeter wave radar with the visual information to adjust the candidate interesting region and obtain a target interesting region set of the millimeter wave radar. The problem of because the millimeter wave radar is inaccurate to the lateral position measurement of surveyed object, the millimeter wave radar has the error to the position identification result of surveyed object, influences the vehicle safety of traveling is solved. The accuracy of the millimeter wave radar in measuring the transverse position of the detected object is improved, the error recognition of the millimeter wave radar on the detected object is avoided, and the detection precision of the millimeter wave radar is improved.
Illustratively, the region of interest set determining module 410 includes:
the detection range dividing unit is used for dividing the detection range of the millimeter wave radar according to the region dividing condition to obtain at least two dividing lines of the detection range;
a detection result acquisition unit configured to acquire a detection result of the first detection object and a detection result of the second detection object on each dividing line;
a first region set determining unit, configured to determine a first region of interest of the first object on each division line according to a detection result of the first object on each division line, integrate the first region of interest, and determine a first region set corresponding to the first object;
and the second region set determining unit is used for determining a second interested sub-region of the second detection object on each division line according to the detection result of the second detection object on each division line, integrating the second interested sub-region and determining a second interested region set corresponding to the second detection object.
Illustratively, the probe determination module 430 is specifically configured to:
determining the overlapping area of the overlapping area and the corresponding overlapping time of the overlapping area;
determining a minimum region of interest set according to the comparison result of the first region of interest set and the second region of interest set;
if the coincidence area of the coincidence region is larger than or equal to the minimum interested region set, the longitudinal distance is smaller than or equal to the distance threshold value, and the coincidence time is larger than or equal to the time threshold value, determining that the first detection object and the second detection object are the same;
and if the coincidence area of the coincidence region is smaller than the minimum interested region set, the coincidence time is smaller than a time threshold value, or the longitudinal distance is larger than a distance threshold value, the first detection object and the second detection object are determined to be different.
Illustratively, the candidate region set determining module 440 is specifically configured to:
if the determination result is the same, integrating the first region of interest set and the second region of interest set, and determining a candidate region of interest set of the millimeter wave radar;
and if the determination results are different, taking the first region of interest set and the second region of interest set as two candidate region of interest sets of the millimeter wave radar.
Illustratively, the target area set determination module 450 includes:
the first matching point determining unit is used for matching each target interesting subregion in the target interesting region set with the visual information of the image acquisition equipment through a normalized cross-correlation matching algorithm, and determining a first matching point of each target interesting subregion and the visual information;
the first matching region determining unit is used for determining a first matching region between each target interest sub-region and the visual information according to the first matching point of each target interest sub-region;
the second matching point determining unit is used for matching the first matching area of each target interest sub-area with the visual information through a normalized cross-correlation matching algorithm to determine a second matching point of the first matching area of each target interest sub-area and the visual information;
the second matching area determining unit is used for determining a second matching area between each target interest sub-area and the visual information according to the first matching point of each target interest sub-area;
and the target area set determining unit is used for integrating the second matching areas of the target interesting sub-areas to obtain a target interesting area set of the millimeter wave radar.
Exemplarily, the first matching point determining unit is specifically configured to:
performing discrete processing on each target interest sub-region in the target interest region set to determine candidate discrete points of each target interest sub-region;
extracting image characteristic points of visual information of the millimeter wave radar;
and matching the image characteristic points with the candidate discrete points of the target interest sub-regions by a normalized cross-correlation matching algorithm, determining the target discrete points matched with the image characteristic points in the target interest sub-regions, and taking the target discrete points in the target interest sub-regions as first matching points of the target interest sub-regions and the visual information.
The processing device for millimeter wave radar detection data provided by the embodiment can be applied to the processing method for millimeter wave radar detection data provided by any embodiment, and has corresponding functions and beneficial effects.
EXAMPLE five
FIG. 5 illustrates a schematic diagram of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 5, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data necessary for the operation of the electronic apparatus 10 may also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
A number of components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, or the like; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The processor 11 executes the respective methods and processes described above, such as the processing method of millimeter wave radar detection data.
In some embodiments, the method of processing millimeter wave radar probe data may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the processing method of millimeter wave radar probe data described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured by any other suitable means (e.g., by means of firmware) to perform the processing method of the millimeter wave radar detection data.
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solution of the present invention can be achieved.
The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A processing method of millimeter wave radar detection data is characterized by comprising the following steps:
determining a first region of interest set corresponding to a first detection object and a second region of interest set corresponding to a second detection object according to a detection result of a millimeter wave radar on the first detection object and a detection result of the second detection object;
determining a region of coincidence between the first set of regions of interest and the second set of regions of interest, and a longitudinal distance between the first set of regions of interest and the second set of regions of interest;
determining whether the first probe and the second probe are the same according to the overlap region and the longitudinal distance;
determining a candidate region of interest set of the millimeter wave radar according to the determination result, the first region of interest set and the second region of interest set;
and matching the candidate interesting region set with the visual information of the image acquisition equipment, and adjusting the candidate interesting region set according to a matching result to obtain a target interesting region set of the millimeter wave radar.
2. The method of claim 1, wherein determining a first set of regions of interest corresponding to a first probe and a second set of regions of interest corresponding to a second probe according to a detection result of the first probe and a detection result of the second probe by the millimeter wave radar comprises:
dividing the detection range of the millimeter wave radar according to the region dividing condition to obtain at least two dividing lines of the detection range;
acquiring the detection result of the first detection object and the detection result of the second detection object on each dividing line;
determining a first interesting sub-region of the first detection object on each division line according to the detection result of the first detection object on each division line, integrating the first interesting sub-region, and determining a first interesting region set corresponding to the first detection object;
and according to the detection result of the second detection object on each division line, determining a second interested sub-region of the second detection object on each division line, integrating the second interested sub-regions, and determining a second interested region set corresponding to the second detection object.
3. The method of claim 1, wherein determining whether the first probe and the second probe are the same based on the overlap region and the longitudinal distance comprises:
determining the overlapping area of the overlapping area and the corresponding overlapping time of the overlapping area;
determining a minimum region of interest set according to the comparison result of the first region of interest set and the second region of interest set;
if the coincidence area of the coincidence region is larger than or equal to the minimum region of interest set, the longitudinal distance is smaller than or equal to a distance threshold value, and the coincidence time is larger than or equal to a time threshold value, determining that the first detector and the second detector are the same;
and if the coincidence area of the coincidence region is smaller than the minimum interested region set, the coincidence time is smaller than a time threshold value, or the longitudinal distance is larger than a distance threshold value, determining that the first detector and the second detector are different.
4. The method of claim 1, wherein determining the candidate set of regions of interest for the millimeter wave radar based on the determination, the first set of regions of interest, and the second set of regions of interest comprises:
if the determination result is the same, integrating the first region of interest set and the second region of interest set, and determining a candidate region of interest set of the millimeter wave radar;
and if the determination results are different, taking the first region of interest set and the second region of interest set as two candidate region of interest sets of the millimeter wave radar.
5. The method according to claim 1, wherein matching the candidate region of interest set with visual information of an image acquisition device, and adjusting the candidate region of interest set according to a matching result to obtain a target region of interest set of the millimeter wave radar comprises:
matching each target interest sub-region in the target interest region set with visual information of image acquisition equipment through a normalized cross-correlation matching algorithm, and determining a first matching point of each target interest sub-region and the visual information;
determining a first matching area of each target sub-area of interest and the visual information according to the first matching point of each target sub-area of interest;
matching the first matching area of each target interest sub-area with the visual information through a normalized cross-correlation matching algorithm, and determining a second matching point of the first matching area of each target interest sub-area and the visual information;
determining a second matching area of each target interest sub-area and the visual information according to the first matching point of each target interest sub-area;
and integrating the second matching regions of the target interest sub-regions to obtain a target interest region set of the millimeter wave radar.
6. The method of claim 5, wherein determining a first matching point of each target sub-region of interest to visual information of an image acquisition device by matching each target sub-region of interest in the set of target sub-regions of interest to the visual information by a normalized cross-correlation matching algorithm comprises:
performing discrete processing on each target interest sub-region in the target interest region set to determine candidate discrete points of each target interest sub-region;
extracting image characteristic points of visual information of the millimeter wave radar;
and matching the image characteristic points with candidate discrete points of each target interest sub-region through a normalized cross-correlation matching algorithm, determining target discrete points matched with the image characteristic points in each target interest sub-region, and taking the target discrete points in each target interest sub-region as first matching points of each target interest sub-region and the visual information.
7. A processing apparatus of millimeter wave radar detection data, characterized by comprising:
the region-of-interest set determining module is used for determining a first region-of-interest set corresponding to a first detection object and a second region-of-interest set corresponding to a second detection object according to a detection result of the millimeter wave radar on the first detection object and a detection result of the second detection object;
a region of coincidence determination module to determine a region of coincidence between the first set of regions of interest and the second set of regions of interest, and a longitudinal distance between the first set of regions of interest and the second set of regions of interest;
a probe determination module for determining whether the first probe and the second probe are the same based on the overlap region and the longitudinal distance;
a candidate region set determining module, configured to determine a candidate region set of interest of the millimeter wave radar according to the determination result, the first region set of interest, and the second region set of interest;
and the target area set determining module is used for matching the candidate interesting area set with the visual information of the image acquisition equipment, and adjusting the candidate interesting area set according to a matching result to obtain the target interesting area set of the millimeter wave radar.
8. The apparatus of claim 7, wherein the region of interest set determination module comprises:
the detection range dividing unit is used for dividing the detection range of the millimeter wave radar according to the region dividing condition to obtain at least two dividing lines of the detection range;
a detection result acquisition unit configured to acquire a detection result of the first detection object and a detection result of the second detection object on each dividing line;
a first region set determining unit, configured to determine, according to a detection result of a first object on each division line, a first region of interest of the first object on each division line, integrate the first region of interest, and determine a first region set corresponding to the first object;
and the second region set determining unit is used for determining a second interested sub-region of the second detection object on each division line according to the detection result of the second detection object on each division line, integrating the second interested sub-region and determining a second interested region set corresponding to the second detection object.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the method of processing millimeter wave radar detection data of any one of claims 1 to 6.
10. A computer-readable storage medium storing computer instructions for causing a processor to implement the method of processing millimeter wave radar probe data according to any one of claims 1 to 6 when executed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211062734.3A CN115436899B (en) | 2022-08-31 | 2022-08-31 | Millimeter wave radar detection data processing method, device, equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211062734.3A CN115436899B (en) | 2022-08-31 | 2022-08-31 | Millimeter wave radar detection data processing method, device, equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115436899A true CN115436899A (en) | 2022-12-06 |
CN115436899B CN115436899B (en) | 2024-09-17 |
Family
ID=84245367
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211062734.3A Active CN115436899B (en) | 2022-08-31 | 2022-08-31 | Millimeter wave radar detection data processing method, device, equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115436899B (en) |
Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105353363A (en) * | 2015-11-25 | 2016-02-24 | 四川九洲空管科技有限责任公司 | Method for improving the target resolution by means of time diversity and frequency diversity |
WO2018021444A1 (en) * | 2016-07-29 | 2018-02-01 | 株式会社デンソー | Object detection apparatus |
CN107923978A (en) * | 2016-03-15 | 2018-04-17 | 欧姆龙株式会社 | Article detection device, object detecting method and program |
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 |
CN110794397A (en) * | 2019-10-18 | 2020-02-14 | 北京全路通信信号研究设计院集团有限公司 | Target detection method and system based on camera and radar |
CN111145152A (en) * | 2019-12-24 | 2020-05-12 | 上海联影智能医疗科技有限公司 | Image detection method, computer device, and storage medium |
CN111178119A (en) * | 2018-11-13 | 2020-05-19 | 北京市商汤科技开发有限公司 | Intersection state detection method and device, electronic equipment and vehicle |
CN113156421A (en) * | 2021-04-07 | 2021-07-23 | 南京邮电大学 | Obstacle detection method based on information fusion of millimeter wave radar and camera |
CN113850102A (en) * | 2020-06-28 | 2021-12-28 | 哈尔滨工业大学(威海) | Vehicle-mounted vision detection method and system based on millimeter wave radar assistance |
WO2022012158A1 (en) * | 2020-07-17 | 2022-01-20 | 华为技术有限公司 | Target determination method and target determination device |
CN113989755A (en) * | 2021-10-22 | 2022-01-28 | 智道网联科技(北京)有限公司 | Method, apparatus and computer readable storage medium for identifying an object |
WO2022096343A1 (en) * | 2020-11-05 | 2022-05-12 | Gestigon Gmbh | Method and apparatus for distinguishing different configuration states of an object based on an image representation of the object |
WO2022104096A1 (en) * | 2020-11-12 | 2022-05-19 | The Regents Of The University Of California | Multi radar object detection |
CN114842445A (en) * | 2022-04-12 | 2022-08-02 | 中国第一汽车股份有限公司 | Target detection method, device, equipment and medium based on multi-path fusion |
-
2022
- 2022-08-31 CN CN202211062734.3A patent/CN115436899B/en active Active
Patent Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105353363A (en) * | 2015-11-25 | 2016-02-24 | 四川九洲空管科技有限责任公司 | Method for improving the target resolution by means of time diversity and frequency diversity |
CN107923978A (en) * | 2016-03-15 | 2018-04-17 | 欧姆龙株式会社 | Article detection device, object detecting method and program |
WO2018021444A1 (en) * | 2016-07-29 | 2018-02-01 | 株式会社デンソー | Object detection apparatus |
CN111178119A (en) * | 2018-11-13 | 2020-05-19 | 北京市商汤科技开发有限公司 | Intersection state detection method and device, electronic equipment and vehicle |
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 |
CN110794397A (en) * | 2019-10-18 | 2020-02-14 | 北京全路通信信号研究设计院集团有限公司 | Target detection method and system based on camera and radar |
CN111145152A (en) * | 2019-12-24 | 2020-05-12 | 上海联影智能医疗科技有限公司 | Image detection method, computer device, and storage medium |
CN113850102A (en) * | 2020-06-28 | 2021-12-28 | 哈尔滨工业大学(威海) | Vehicle-mounted vision detection method and system based on millimeter wave radar assistance |
WO2022012158A1 (en) * | 2020-07-17 | 2022-01-20 | 华为技术有限公司 | Target determination method and target determination device |
WO2022096343A1 (en) * | 2020-11-05 | 2022-05-12 | Gestigon Gmbh | Method and apparatus for distinguishing different configuration states of an object based on an image representation of the object |
WO2022104096A1 (en) * | 2020-11-12 | 2022-05-19 | The Regents Of The University Of California | Multi radar object detection |
CN113156421A (en) * | 2021-04-07 | 2021-07-23 | 南京邮电大学 | Obstacle detection method based on information fusion of millimeter wave radar and camera |
CN113989755A (en) * | 2021-10-22 | 2022-01-28 | 智道网联科技(北京)有限公司 | Method, apparatus and computer readable storage medium for identifying an object |
CN114842445A (en) * | 2022-04-12 | 2022-08-02 | 中国第一汽车股份有限公司 | Target detection method, device, equipment and medium based on multi-path fusion |
Non-Patent Citations (2)
Title |
---|
靳延伟: "基于图像和雷达数据融合的列车前方障碍物检测算法研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑》, 15 February 2022 (2022-02-15), pages 1 - 82 * |
黄云华: "融合摄像头和毫米波雷达的障碍物检测算法研究及应用", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》, 15 April 2021 (2021-04-15), pages 1 - 70 * |
Also Published As
Publication number | Publication date |
---|---|
CN115436899B (en) | 2024-09-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114842445A (en) | Target detection method, device, equipment and medium based on multi-path fusion | |
CN112508128A (en) | Training sample construction method, counting method, device, electronic equipment and medium | |
CN115861959A (en) | Lane line identification method and device, electronic equipment and storage medium | |
CN113177980B (en) | Target object speed determining method and device for automatic driving and electronic equipment | |
CN114882470A (en) | Vehicle-mounted anti-collision early warning method and device, computer equipment and storage medium | |
CN112990170A (en) | Phased array radar target identification method and system, electronic device and medium | |
CN115436899B (en) | Millimeter wave radar detection data processing method, device, equipment and storage medium | |
CN116299291A (en) | Radar target identification method, device, equipment and storage medium | |
CN114581890B (en) | Method and device for determining lane line, electronic equipment and storage medium | |
CN115546597A (en) | Sensor fusion method, device, equipment and storage medium | |
CN113984072B (en) | Vehicle positioning method, device, equipment, storage medium and automatic driving vehicle | |
CN116008938A (en) | Target detection method, device, equipment and medium based on radar | |
CN115830268A (en) | Data acquisition method and device for optimizing perception algorithm and storage medium | |
CN114419068A (en) | Medical image segmentation method, device, equipment and storage medium | |
CN113936158A (en) | Label matching method and device | |
CN115857502B (en) | Driving control method and electronic device | |
CN114694138B (en) | Road surface detection method, device and equipment applied to intelligent driving | |
CN117368879B (en) | Radar diagram generation method and device, terminal equipment and readable storage medium | |
CN114037865B (en) | Image processing method, apparatus, device, storage medium, and program product | |
CN117392631B (en) | Road boundary extraction method and device, electronic equipment and storage medium | |
CN114926447B (en) | Method for training a model, method and device for detecting a target | |
CN115424441B (en) | Road curve optimization method, device, equipment and medium based on microwave radar | |
CN116778232B (en) | SAR image vertical stripe detection method, device, equipment and storage medium | |
CN117349063A (en) | Method, device, equipment and storage medium for determining detection performance of detector | |
CN115032615A (en) | Laser radar calibration point determining method, device, equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |